diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..5bb54859f7bc94ad7743a289b0d927ac359fb421 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +checkpoint-117/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-234/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-351/tokenizer.json filter=lfs diff=lfs merge=lfs -text +checkpoint-468/tokenizer.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..7f08ec3391935fdcc17be94b76a36a6846ee827b --- /dev/null +++ b/README.md @@ -0,0 +1,149 @@ +--- +library_name: peft +tags: +- generated_from_trainer +datasets: +- Guilherme34/uncensor +base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B +model-index: +- name: outputs/out/DeepSeek-R1-Distill-Qwen-7B-Uncensored + results: [] +--- + + + +[Built with Axolotl](https://github.com/axolotl-ai-cloud/axolotl) +
See axolotl config + +axolotl version: `0.6.0` +```yaml +base_model: /cpool/DeepSeek-R1-Distill-Qwen-7B + +load_in_8bit: false +load_in_4bit: false +strict: false + +datasets: + - path: Guilherme34/uncensor + type: chat_template + chat_template: llama3 + field_messages: messages + message_field_role: role + message_field_content: content + roles: + system: + - system + user: + - user + assistant: + - assistant +dataset_prepared_path: last_run_prepared +val_set_size: 0.0 +output_dir: ./outputs/out/DeepSeek-R1-Distill-Qwen-7B-Uncensored +save_safetensors: true + +sequence_len: 4096 +sample_packing: false +pad_to_sequence_len: true + +adapter: lora +lora_model_dir: +lora_r: 32 +lora_alpha: 16 +lora_dropout: 0.05 +lora_target_linear: true +lora_fan_in_fan_out: + +gradient_accumulation_steps: 4 +micro_batch_size: 1 +num_epochs: 4 +optimizer: adamw_torch +lr_scheduler: cosine +learning_rate: 0.0002 + +train_on_inputs: false +group_by_length: false +bf16: true +tf32: true + +gradient_checkpointing: true +gradient_checkpointing_kwargs: + use_reentrant: true +logging_steps: 1 +flash_attention: true + +warmup_steps: 10 +evals_per_epoch: 1 +eval_table_size: 20 +eval_max_new_tokens: 128 +saves_per_epoch: 1 +save_total_limit: 20 +debug: +deepspeed: +weight_decay: 0.0 +fsdp: + - full_shard + - auto_wrap +fsdp_config: + fsdp_limit_all_gathers: true + fsdp_sync_module_states: true + fsdp_offload_params: true + fsdp_use_orig_params: false + fsdp_cpu_ram_efficient_loading: true + fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP + fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer + fsdp_state_dict_type: FULL_STATE_DICT + fsdp_sharding_strategy: FULL_SHARD +special_tokens: + +``` + +

+ +# outputs/out/DeepSeek-R1-Distill-Qwen-7B-Uncensored + +This model was trained from scratch on the Guilherme34/uncensor dataset. + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 0.0002 +- train_batch_size: 1 +- eval_batch_size: 1 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 2 +- gradient_accumulation_steps: 4 +- total_train_batch_size: 8 +- total_eval_batch_size: 2 +- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- lr_scheduler_warmup_steps: 10 +- num_epochs: 4 + +### Training results + + + +### Framework versions + +- PEFT 0.14.0 +- Transformers 4.47.1 +- Pytorch 2.5.1+cu124 +- Datasets 3.2.0 +- Tokenizers 0.21.0 diff --git a/adapter_config.json b/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..324e93a070435c3ef71b8e5c1a17321dfd9614f6 --- /dev/null +++ b/adapter_config.json @@ -0,0 +1,37 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/cpool/DeepSeek-R1-Distill-Qwen-7B", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": null, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_bias": false, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "up_proj", + "k_proj", + "down_proj", + "gate_proj", + "v_proj", + "o_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapter_model.safetensors b/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c57583fd85eef714567dc4268759c13dbdf0dc9b --- /dev/null +++ b/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76b45071fea0cc56ec629a56bd69f7af8a8df37bfed0de5e375d9b49525015b3 +size 2497283840 diff --git a/checkpoint-117/README.md b/checkpoint-117/README.md new file mode 100644 index 0000000000000000000000000000000000000000..a1856dcc51e1f1ee5a60850ea184165793425f6d --- /dev/null +++ b/checkpoint-117/README.md @@ -0,0 +1,202 @@ +--- +base_model: /cpool/DeepSeek-R1-Distill-Qwen-7B +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-117/adapter_config.json b/checkpoint-117/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..324e93a070435c3ef71b8e5c1a17321dfd9614f6 --- /dev/null +++ b/checkpoint-117/adapter_config.json @@ -0,0 +1,37 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/cpool/DeepSeek-R1-Distill-Qwen-7B", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": null, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_bias": false, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "up_proj", + "k_proj", + "down_proj", + "gate_proj", + "v_proj", + "o_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-117/adapter_model.safetensors b/checkpoint-117/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ceebc74e4a7cb60d7a118a15dd1f740b9f3794e1 --- /dev/null +++ b/checkpoint-117/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5249860a8d8ae91516f00665337067203028ce305712b40bef1b8258a4ed91a +size 2497283840 diff --git a/checkpoint-117/optimizer.bin b/checkpoint-117/optimizer.bin new file mode 100644 index 0000000000000000000000000000000000000000..6dd25f4b6a6cc4baf0f2ff699eb2df0f63e620c1 --- /dev/null +++ b/checkpoint-117/optimizer.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d13becf0ae5915b0ac5a4616c237c513a13e142c755b0f8db04fb153beead03d +size 646273514 diff --git a/checkpoint-117/pytorch_model_fsdp.bin b/checkpoint-117/pytorch_model_fsdp.bin new file mode 100644 index 0000000000000000000000000000000000000000..f9432667b1fe83952b5a266aaf8857f307009797 --- /dev/null +++ b/checkpoint-117/pytorch_model_fsdp.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dad05f82a4a75a98df03e4912dcde8adc4c6717d397af003f0006b1d2c2e95b +size 323107814 diff --git a/checkpoint-117/rng_state_0.pth b/checkpoint-117/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..2476641658b5efd08808a5f8af08d72090adeca3 --- /dev/null +++ b/checkpoint-117/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f54843c3190814def2c41d4be5521b99fcf637f808a0135c89d1ef0964f4f6dd +size 14512 diff --git a/checkpoint-117/rng_state_1.pth b/checkpoint-117/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..cd696d918abd92e31f0e4aea4cd4fcdbf7c817cc --- /dev/null +++ b/checkpoint-117/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d1187b590b65941d7f95bdeca758868a76aa6d8fa9b8824430cf9edfdae5df2 +size 14512 diff --git a/checkpoint-117/scheduler.pt b/checkpoint-117/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..a75c246e9ded45754dce91a2be5ed2c52b2fe23d --- /dev/null +++ b/checkpoint-117/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e6bb887f60ead14806ab781b36a2d2c6f0961c257f4780e647407683f4efc61 +size 1064 diff --git a/checkpoint-117/special_tokens_map.json b/checkpoint-117/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1 --- /dev/null +++ b/checkpoint-117/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-117/tokenizer.json b/checkpoint-117/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/checkpoint-117/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/checkpoint-117/tokenizer_config.json b/checkpoint-117/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b068ffca3220a746ba50cc69f850e544217e3a86 --- /dev/null +++ b/checkpoint-117/tokenizer_config.json @@ -0,0 +1,195 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": null, + "use_default_system_prompt": false +} diff --git a/checkpoint-117/trainer_state.json b/checkpoint-117/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..dc10963438ac21e7b8363dbf670d180e65f735e1 --- /dev/null +++ b/checkpoint-117/trainer_state.json @@ -0,0 +1,852 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 500, + "global_step": 117, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.008547008547008548, + "grad_norm": 0.15355850756168365, + "learning_rate": 2e-05, + "loss": 1.4892, + "step": 1 + }, + { + "epoch": 0.017094017094017096, + "grad_norm": 0.1224861666560173, + "learning_rate": 4e-05, + "loss": 1.1445, + "step": 2 + }, + { + "epoch": 0.02564102564102564, + "grad_norm": 0.1645984649658203, + "learning_rate": 6e-05, + "loss": 1.5538, + "step": 3 + }, + { + "epoch": 0.03418803418803419, + "grad_norm": 0.125856414437294, + "learning_rate": 8e-05, + "loss": 1.7634, + "step": 4 + }, + { + "epoch": 0.042735042735042736, + "grad_norm": 0.1726977378129959, + "learning_rate": 0.0001, + "loss": 1.4105, + "step": 5 + }, + { + "epoch": 0.05128205128205128, + "grad_norm": 0.18316921591758728, + "learning_rate": 0.00012, + "loss": 1.8364, + "step": 6 + }, + { + "epoch": 0.05982905982905983, + "grad_norm": 0.17618055641651154, + "learning_rate": 0.00014, + "loss": 1.3885, + "step": 7 + }, + { + "epoch": 0.06837606837606838, + "grad_norm": 0.17036275565624237, + "learning_rate": 0.00016, + "loss": 1.3574, + "step": 8 + }, + { + "epoch": 0.07692307692307693, + "grad_norm": 0.18832312524318695, + "learning_rate": 0.00018, + "loss": 1.2256, + "step": 9 + }, + { + "epoch": 0.08547008547008547, + "grad_norm": 0.22157786786556244, + "learning_rate": 0.0002, + "loss": 1.515, + "step": 10 + }, + { + "epoch": 0.09401709401709402, + "grad_norm": 0.21728643774986267, + "learning_rate": 0.0001999976474595967, + "loss": 1.4505, + "step": 11 + }, + { + "epoch": 0.10256410256410256, + "grad_norm": 0.16113220155239105, + "learning_rate": 0.00019999058994907564, + "loss": 1.132, + "step": 12 + }, + { + "epoch": 0.1111111111111111, + "grad_norm": 0.1798534393310547, + "learning_rate": 0.00019997882780049847, + "loss": 1.2355, + "step": 13 + }, + { + "epoch": 0.11965811965811966, + "grad_norm": 0.19335126876831055, + "learning_rate": 0.0001999623615672837, + "loss": 1.4485, + "step": 14 + }, + { + "epoch": 0.1282051282051282, + "grad_norm": 0.14973561465740204, + "learning_rate": 0.00019994119202418098, + "loss": 1.4852, + "step": 15 + }, + { + "epoch": 0.13675213675213677, + "grad_norm": 0.1763419359922409, + "learning_rate": 0.00019991532016723439, + "loss": 1.0831, + "step": 16 + }, + { + "epoch": 0.1452991452991453, + "grad_norm": 0.148220494389534, + "learning_rate": 0.00019988474721373568, + "loss": 1.5454, + "step": 17 + }, + { + "epoch": 0.15384615384615385, + "grad_norm": 0.1581086665391922, + "learning_rate": 0.00019984947460216707, + "loss": 0.9387, + "step": 18 + }, + { + "epoch": 0.1623931623931624, + "grad_norm": 0.1937003880739212, + "learning_rate": 0.00019980950399213344, + "loss": 1.1612, + "step": 19 + }, + { + "epoch": 0.17094017094017094, + "grad_norm": 0.15193545818328857, + "learning_rate": 0.00019976483726428422, + "loss": 0.9678, + "step": 20 + }, + { + "epoch": 0.1794871794871795, + "grad_norm": 0.17265811562538147, + "learning_rate": 0.0001997154765202251, + "loss": 1.0147, + "step": 21 + }, + { + "epoch": 0.18803418803418803, + "grad_norm": 0.16466519236564636, + "learning_rate": 0.00019966142408241901, + "loss": 1.1492, + "step": 22 + }, + { + "epoch": 0.19658119658119658, + "grad_norm": 0.17746295034885406, + "learning_rate": 0.00019960268249407675, + "loss": 1.2277, + "step": 23 + }, + { + "epoch": 0.20512820512820512, + "grad_norm": 0.1838495433330536, + "learning_rate": 0.00019953925451903756, + "loss": 1.1559, + "step": 24 + }, + { + "epoch": 0.21367521367521367, + "grad_norm": 0.1542479395866394, + "learning_rate": 0.0001994711431416389, + "loss": 1.855, + "step": 25 + }, + { + "epoch": 0.2222222222222222, + "grad_norm": 0.1788703054189682, + "learning_rate": 0.00019939835156657616, + "loss": 1.6273, + "step": 26 + }, + { + "epoch": 0.23076923076923078, + "grad_norm": 0.15661294758319855, + "learning_rate": 0.00019932088321875172, + "loss": 1.0783, + "step": 27 + }, + { + "epoch": 0.23931623931623933, + "grad_norm": 0.1869712620973587, + "learning_rate": 0.00019923874174311394, + "loss": 0.9181, + "step": 28 + }, + { + "epoch": 0.24786324786324787, + "grad_norm": 0.14521349966526031, + "learning_rate": 0.0001991519310044857, + "loss": 1.4428, + "step": 29 + }, + { + "epoch": 0.2564102564102564, + "grad_norm": 0.17194955050945282, + "learning_rate": 0.00019906045508738228, + "loss": 1.3213, + "step": 30 + }, + { + "epoch": 0.26495726495726496, + "grad_norm": 0.14739835262298584, + "learning_rate": 0.0001989643182958196, + "loss": 0.9933, + "step": 31 + }, + { + "epoch": 0.27350427350427353, + "grad_norm": 0.17825335264205933, + "learning_rate": 0.00019886352515311134, + "loss": 1.034, + "step": 32 + }, + { + "epoch": 0.28205128205128205, + "grad_norm": 0.16200387477874756, + "learning_rate": 0.0001987580804016563, + "loss": 1.3064, + "step": 33 + }, + { + "epoch": 0.2905982905982906, + "grad_norm": 0.170911967754364, + "learning_rate": 0.00019864798900271532, + "loss": 1.2321, + "step": 34 + }, + { + "epoch": 0.29914529914529914, + "grad_norm": 0.16599859297275543, + "learning_rate": 0.0001985332561361776, + "loss": 0.9447, + "step": 35 + }, + { + "epoch": 0.3076923076923077, + "grad_norm": 0.14686603844165802, + "learning_rate": 0.00019841388720031727, + "loss": 0.8823, + "step": 36 + }, + { + "epoch": 0.3162393162393162, + "grad_norm": 0.1870049089193344, + "learning_rate": 0.00019828988781153917, + "loss": 1.1041, + "step": 37 + }, + { + "epoch": 0.3247863247863248, + "grad_norm": 0.1619299054145813, + "learning_rate": 0.00019816126380411476, + "loss": 0.9918, + "step": 38 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 0.18731147050857544, + "learning_rate": 0.00019802802122990758, + "loss": 1.0642, + "step": 39 + }, + { + "epoch": 0.3418803418803419, + "grad_norm": 0.17905616760253906, + "learning_rate": 0.00019789016635808837, + "loss": 1.0877, + "step": 40 + }, + { + "epoch": 0.3504273504273504, + "grad_norm": 0.15318270027637482, + "learning_rate": 0.00019774770567484022, + "loss": 1.2165, + "step": 41 + }, + { + "epoch": 0.358974358974359, + "grad_norm": 0.14854711294174194, + "learning_rate": 0.00019760064588305345, + "loss": 0.9812, + "step": 42 + }, + { + "epoch": 0.36752136752136755, + "grad_norm": 0.15519340336322784, + "learning_rate": 0.00019744899390201006, + "loss": 0.9977, + "step": 43 + }, + { + "epoch": 0.37606837606837606, + "grad_norm": 0.1589617133140564, + "learning_rate": 0.0001972927568670583, + "loss": 1.4097, + "step": 44 + }, + { + "epoch": 0.38461538461538464, + "grad_norm": 0.17286093533039093, + "learning_rate": 0.00019713194212927696, + "loss": 1.1385, + "step": 45 + }, + { + "epoch": 0.39316239316239315, + "grad_norm": 0.19325074553489685, + "learning_rate": 0.00019696655725512933, + "loss": 0.9997, + "step": 46 + }, + { + "epoch": 0.4017094017094017, + "grad_norm": 0.18447531759738922, + "learning_rate": 0.00019679661002610743, + "loss": 1.0873, + "step": 47 + }, + { + "epoch": 0.41025641025641024, + "grad_norm": 0.16223366558551788, + "learning_rate": 0.00019662210843836574, + "loss": 0.99, + "step": 48 + }, + { + "epoch": 0.4188034188034188, + "grad_norm": 0.1919640749692917, + "learning_rate": 0.0001964430607023449, + "loss": 1.0171, + "step": 49 + }, + { + "epoch": 0.42735042735042733, + "grad_norm": 0.22606882452964783, + "learning_rate": 0.00019625947524238563, + "loss": 1.4172, + "step": 50 + }, + { + "epoch": 0.4358974358974359, + "grad_norm": 0.17758312821388245, + "learning_rate": 0.00019607136069633212, + "loss": 0.9964, + "step": 51 + }, + { + "epoch": 0.4444444444444444, + "grad_norm": 0.16785483062267303, + "learning_rate": 0.0001958787259151258, + "loss": 0.9883, + "step": 52 + }, + { + "epoch": 0.452991452991453, + "grad_norm": 0.19499914348125458, + "learning_rate": 0.00019568157996238884, + "loss": 1.0293, + "step": 53 + }, + { + "epoch": 0.46153846153846156, + "grad_norm": 0.15674076974391937, + "learning_rate": 0.0001954799321139975, + "loss": 1.3643, + "step": 54 + }, + { + "epoch": 0.4700854700854701, + "grad_norm": 0.16759538650512695, + "learning_rate": 0.00019527379185764612, + "loss": 0.8998, + "step": 55 + }, + { + "epoch": 0.47863247863247865, + "grad_norm": 0.20853222906589508, + "learning_rate": 0.00019506316889240027, + "loss": 1.4597, + "step": 56 + }, + { + "epoch": 0.48717948717948717, + "grad_norm": 0.18584011495113373, + "learning_rate": 0.00019484807312824067, + "loss": 0.8848, + "step": 57 + }, + { + "epoch": 0.49572649572649574, + "grad_norm": 0.24146708846092224, + "learning_rate": 0.0001946285146855968, + "loss": 1.0529, + "step": 58 + }, + { + "epoch": 0.5042735042735043, + "grad_norm": 0.20457321405410767, + "learning_rate": 0.0001944045038948709, + "loss": 0.9917, + "step": 59 + }, + { + "epoch": 0.5128205128205128, + "grad_norm": 0.21354275941848755, + "learning_rate": 0.00019417605129595157, + "loss": 0.9096, + "step": 60 + }, + { + "epoch": 0.5213675213675214, + "grad_norm": 0.2198089212179184, + "learning_rate": 0.0001939431676377183, + "loss": 0.9228, + "step": 61 + }, + { + "epoch": 0.5299145299145299, + "grad_norm": 0.18545866012573242, + "learning_rate": 0.0001937058638775353, + "loss": 0.8399, + "step": 62 + }, + { + "epoch": 0.5384615384615384, + "grad_norm": 0.1578792780637741, + "learning_rate": 0.00019346415118073632, + "loss": 1.6315, + "step": 63 + }, + { + "epoch": 0.5470085470085471, + "grad_norm": 0.23443493247032166, + "learning_rate": 0.00019321804092009906, + "loss": 1.0905, + "step": 64 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 0.20623010396957397, + "learning_rate": 0.00019296754467531014, + "loss": 0.9367, + "step": 65 + }, + { + "epoch": 0.5641025641025641, + "grad_norm": 0.24046015739440918, + "learning_rate": 0.00019271267423242024, + "loss": 0.9195, + "step": 66 + }, + { + "epoch": 0.5726495726495726, + "grad_norm": 0.22675752639770508, + "learning_rate": 0.00019245344158328972, + "loss": 1.1275, + "step": 67 + }, + { + "epoch": 0.5811965811965812, + "grad_norm": 0.22297680377960205, + "learning_rate": 0.0001921898589250242, + "loss": 0.9244, + "step": 68 + }, + { + "epoch": 0.5897435897435898, + "grad_norm": 0.21324071288108826, + "learning_rate": 0.0001919219386594007, + "loss": 0.9706, + "step": 69 + }, + { + "epoch": 0.5982905982905983, + "grad_norm": 0.21497191488742828, + "learning_rate": 0.00019164969339228422, + "loss": 1.0559, + "step": 70 + }, + { + "epoch": 0.6068376068376068, + "grad_norm": 0.2526251971721649, + "learning_rate": 0.00019137313593303463, + "loss": 1.0632, + "step": 71 + }, + { + "epoch": 0.6153846153846154, + "grad_norm": 0.19590331614017487, + "learning_rate": 0.00019109227929390378, + "loss": 1.8134, + "step": 72 + }, + { + "epoch": 0.6239316239316239, + "grad_norm": 0.21532683074474335, + "learning_rate": 0.00019080713668942356, + "loss": 0.9466, + "step": 73 + }, + { + "epoch": 0.6324786324786325, + "grad_norm": 0.2264883816242218, + "learning_rate": 0.00019051772153578389, + "loss": 0.8941, + "step": 74 + }, + { + "epoch": 0.6410256410256411, + "grad_norm": 0.22985824942588806, + "learning_rate": 0.00019022404745020163, + "loss": 0.8991, + "step": 75 + }, + { + "epoch": 0.6495726495726496, + "grad_norm": 0.19453634321689606, + "learning_rate": 0.00018992612825027976, + "loss": 0.9837, + "step": 76 + }, + { + "epoch": 0.6581196581196581, + "grad_norm": 0.2547195851802826, + "learning_rate": 0.0001896239779533575, + "loss": 1.1035, + "step": 77 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.20812910795211792, + "learning_rate": 0.00018931761077585035, + "loss": 0.8916, + "step": 78 + }, + { + "epoch": 0.6752136752136753, + "grad_norm": 0.2176084816455841, + "learning_rate": 0.00018900704113258165, + "loss": 0.8826, + "step": 79 + }, + { + "epoch": 0.6837606837606838, + "grad_norm": 0.2221064418554306, + "learning_rate": 0.00018869228363610404, + "loss": 0.9069, + "step": 80 + }, + { + "epoch": 0.6923076923076923, + "grad_norm": 0.2675364911556244, + "learning_rate": 0.00018837335309601213, + "loss": 1.035, + "step": 81 + }, + { + "epoch": 0.7008547008547008, + "grad_norm": 0.1994653195142746, + "learning_rate": 0.00018805026451824546, + "loss": 1.5854, + "step": 82 + }, + { + "epoch": 0.7094017094017094, + "grad_norm": 0.20346811413764954, + "learning_rate": 0.00018772303310438275, + "loss": 1.4788, + "step": 83 + }, + { + "epoch": 0.717948717948718, + "grad_norm": 0.22119802236557007, + "learning_rate": 0.00018739167425092644, + "loss": 1.4946, + "step": 84 + }, + { + "epoch": 0.7264957264957265, + "grad_norm": 0.2174052894115448, + "learning_rate": 0.00018705620354857833, + "loss": 0.8667, + "step": 85 + }, + { + "epoch": 0.7350427350427351, + "grad_norm": 0.2322807013988495, + "learning_rate": 0.00018671663678150607, + "loss": 0.861, + "step": 86 + }, + { + "epoch": 0.7435897435897436, + "grad_norm": 0.22151263058185577, + "learning_rate": 0.0001863729899266004, + "loss": 0.8966, + "step": 87 + }, + { + "epoch": 0.7521367521367521, + "grad_norm": 0.243766650557518, + "learning_rate": 0.0001860252791527236, + "loss": 1.2998, + "step": 88 + }, + { + "epoch": 0.7606837606837606, + "grad_norm": 0.19212521612644196, + "learning_rate": 0.00018567352081994852, + "loss": 1.5215, + "step": 89 + }, + { + "epoch": 0.7692307692307693, + "grad_norm": 0.20964723825454712, + "learning_rate": 0.00018531773147878895, + "loss": 1.4717, + "step": 90 + }, + { + "epoch": 0.7777777777777778, + "grad_norm": 0.24561531841754913, + "learning_rate": 0.0001849579278694209, + "loss": 0.9569, + "step": 91 + }, + { + "epoch": 0.7863247863247863, + "grad_norm": 0.23924781382083893, + "learning_rate": 0.00018459412692089494, + "loss": 0.9441, + "step": 92 + }, + { + "epoch": 0.7948717948717948, + "grad_norm": 0.2302614450454712, + "learning_rate": 0.0001842263457503397, + "loss": 0.8417, + "step": 93 + }, + { + "epoch": 0.8034188034188035, + "grad_norm": 0.24661926925182343, + "learning_rate": 0.00018385460166215638, + "loss": 1.1297, + "step": 94 + }, + { + "epoch": 0.811965811965812, + "grad_norm": 0.24925513565540314, + "learning_rate": 0.00018347891214720477, + "loss": 0.8999, + "step": 95 + }, + { + "epoch": 0.8205128205128205, + "grad_norm": 0.19934344291687012, + "learning_rate": 0.00018309929488198012, + "loss": 1.4818, + "step": 96 + }, + { + "epoch": 0.8290598290598291, + "grad_norm": 0.24845215678215027, + "learning_rate": 0.00018271576772778154, + "loss": 0.9454, + "step": 97 + }, + { + "epoch": 0.8376068376068376, + "grad_norm": 0.22845034301280975, + "learning_rate": 0.00018232834872987147, + "loss": 1.5063, + "step": 98 + }, + { + "epoch": 0.8461538461538461, + "grad_norm": 0.2563302516937256, + "learning_rate": 0.00018193705611662696, + "loss": 0.9946, + "step": 99 + }, + { + "epoch": 0.8547008547008547, + "grad_norm": 0.30030304193496704, + "learning_rate": 0.0001815419082986815, + "loss": 1.0936, + "step": 100 + }, + { + "epoch": 0.8632478632478633, + "grad_norm": 0.22599591314792633, + "learning_rate": 0.00018114292386805936, + "loss": 1.346, + "step": 101 + }, + { + "epoch": 0.8717948717948718, + "grad_norm": 0.20411820709705353, + "learning_rate": 0.00018074012159730032, + "loss": 1.5147, + "step": 102 + }, + { + "epoch": 0.8803418803418803, + "grad_norm": 0.20635190606117249, + "learning_rate": 0.00018033352043857675, + "loss": 1.1425, + "step": 103 + }, + { + "epoch": 0.8888888888888888, + "grad_norm": 0.22327086329460144, + "learning_rate": 0.00017992313952280172, + "loss": 1.4435, + "step": 104 + }, + { + "epoch": 0.8974358974358975, + "grad_norm": 0.2183496206998825, + "learning_rate": 0.00017950899815872892, + "loss": 1.5659, + "step": 105 + }, + { + "epoch": 0.905982905982906, + "grad_norm": 0.31636252999305725, + "learning_rate": 0.00017909111583204422, + "loss": 1.4703, + "step": 106 + }, + { + "epoch": 0.9145299145299145, + "grad_norm": 0.3305496275424957, + "learning_rate": 0.0001786695122044487, + "loss": 1.0904, + "step": 107 + }, + { + "epoch": 0.9230769230769231, + "grad_norm": 0.22857435047626495, + "learning_rate": 0.0001782442071127338, + "loss": 1.3801, + "step": 108 + }, + { + "epoch": 0.9316239316239316, + "grad_norm": 0.31968221068382263, + "learning_rate": 0.0001778152205678477, + "loss": 1.4907, + "step": 109 + }, + { + "epoch": 0.9401709401709402, + "grad_norm": 0.27950960397720337, + "learning_rate": 0.00017738257275395404, + "loss": 1.0864, + "step": 110 + }, + { + "epoch": 0.9487179487179487, + "grad_norm": 0.2740281820297241, + "learning_rate": 0.00017694628402748202, + "loss": 0.9241, + "step": 111 + }, + { + "epoch": 0.9572649572649573, + "grad_norm": 0.26951318979263306, + "learning_rate": 0.0001765063749161688, + "loss": 0.9894, + "step": 112 + }, + { + "epoch": 0.9658119658119658, + "grad_norm": 0.2811899781227112, + "learning_rate": 0.00017606286611809353, + "loss": 0.9659, + "step": 113 + }, + { + "epoch": 0.9743589743589743, + "grad_norm": 0.23854824900627136, + "learning_rate": 0.00017561577850070355, + "loss": 1.0623, + "step": 114 + }, + { + "epoch": 0.9829059829059829, + "grad_norm": 0.21959957480430603, + "learning_rate": 0.00017516513309983253, + "loss": 0.8671, + "step": 115 + }, + { + "epoch": 0.9914529914529915, + "grad_norm": 0.3096697926521301, + "learning_rate": 0.00017471095111871074, + "loss": 1.0756, + "step": 116 + }, + { + "epoch": 1.0, + "grad_norm": 0.23363932967185974, + "learning_rate": 0.0001742532539269674, + "loss": 0.8988, + "step": 117 + } + ], + "logging_steps": 1, + "max_steps": 468, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 117, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 7.59834818421719e+16, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-117/training_args.bin b/checkpoint-117/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..6aa0501cedc8c6a042abaac1eb0d2755310396ba --- /dev/null +++ b/checkpoint-117/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7fe3839cfcc5a93b060094e1030e134d680eeeb9bb2bdbde204831612dbb1c1 +size 6840 diff --git a/checkpoint-234/README.md b/checkpoint-234/README.md new file mode 100644 index 0000000000000000000000000000000000000000..a1856dcc51e1f1ee5a60850ea184165793425f6d --- /dev/null +++ b/checkpoint-234/README.md @@ -0,0 +1,202 @@ +--- +base_model: /cpool/DeepSeek-R1-Distill-Qwen-7B +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-234/adapter_config.json b/checkpoint-234/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..324e93a070435c3ef71b8e5c1a17321dfd9614f6 --- /dev/null +++ b/checkpoint-234/adapter_config.json @@ -0,0 +1,37 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/cpool/DeepSeek-R1-Distill-Qwen-7B", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": null, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_bias": false, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "up_proj", + "k_proj", + "down_proj", + "gate_proj", + "v_proj", + "o_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-234/adapter_model.safetensors b/checkpoint-234/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..970202e49013c43fbeff0cfe9fd9622b6e4ec572 --- /dev/null +++ b/checkpoint-234/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a90abdd25017e6a42e92545f4431155f49ef9491585602234ce83b559965fa5f +size 2497283840 diff --git a/checkpoint-234/optimizer.bin b/checkpoint-234/optimizer.bin new file mode 100644 index 0000000000000000000000000000000000000000..9b1c4ffca953fdfe5c1a6a0b780102e709154e09 --- /dev/null +++ b/checkpoint-234/optimizer.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35db9b65829b915e513f2e0ca419f89eed66fb6c43b6869481fc6eae9b37b7cb +size 646273514 diff --git a/checkpoint-234/pytorch_model_fsdp.bin b/checkpoint-234/pytorch_model_fsdp.bin new file mode 100644 index 0000000000000000000000000000000000000000..c03bef4e159433a213f638c5425fdea4edfe5fa8 --- /dev/null +++ b/checkpoint-234/pytorch_model_fsdp.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ce573db7745bffd04b572fe69db1fac46fd36914375d24c346666fbdb2c09bd +size 323107814 diff --git a/checkpoint-234/rng_state_0.pth b/checkpoint-234/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..d4e8b73ab2a466715c70d5455108e59d938f1da5 --- /dev/null +++ b/checkpoint-234/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58aff579f5c422c4cfa2f9521a13e0c8c5c09ae324f9b3862a1e6717b01af4bf +size 14512 diff --git a/checkpoint-234/rng_state_1.pth b/checkpoint-234/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..200c53191391330ee4c018f6314f757275b26892 --- /dev/null +++ b/checkpoint-234/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1096036849777c5ef501092cfe5a6743135a255015f15917bff932802d5326b +size 14512 diff --git a/checkpoint-234/scheduler.pt b/checkpoint-234/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..1a53d6ad19737393310a49f8c29253f205f4f816 --- /dev/null +++ b/checkpoint-234/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:997057b731bc65f59ea4d3bb39f1828f4d4670db8a01f052c60d232d4e8dfea7 +size 1064 diff --git a/checkpoint-234/special_tokens_map.json b/checkpoint-234/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1 --- /dev/null +++ b/checkpoint-234/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-234/tokenizer.json b/checkpoint-234/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/checkpoint-234/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/checkpoint-234/tokenizer_config.json b/checkpoint-234/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b068ffca3220a746ba50cc69f850e544217e3a86 --- /dev/null +++ b/checkpoint-234/tokenizer_config.json @@ -0,0 +1,195 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": null, + "use_default_system_prompt": false +} diff --git a/checkpoint-234/trainer_state.json b/checkpoint-234/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..66e886896c01616df9737b99d7eb066c4c321c86 --- /dev/null +++ b/checkpoint-234/trainer_state.json @@ -0,0 +1,1671 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.0, + "eval_steps": 500, + "global_step": 234, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.008547008547008548, + "grad_norm": 0.15355850756168365, + "learning_rate": 2e-05, + "loss": 1.4892, + "step": 1 + }, + { + "epoch": 0.017094017094017096, + "grad_norm": 0.1224861666560173, + "learning_rate": 4e-05, + "loss": 1.1445, + "step": 2 + }, + { + "epoch": 0.02564102564102564, + "grad_norm": 0.1645984649658203, + "learning_rate": 6e-05, + "loss": 1.5538, + "step": 3 + }, + { + "epoch": 0.03418803418803419, + "grad_norm": 0.125856414437294, + "learning_rate": 8e-05, + "loss": 1.7634, + "step": 4 + }, + { + "epoch": 0.042735042735042736, + "grad_norm": 0.1726977378129959, + "learning_rate": 0.0001, + "loss": 1.4105, + "step": 5 + }, + { + "epoch": 0.05128205128205128, + "grad_norm": 0.18316921591758728, + "learning_rate": 0.00012, + "loss": 1.8364, + "step": 6 + }, + { + "epoch": 0.05982905982905983, + "grad_norm": 0.17618055641651154, + "learning_rate": 0.00014, + "loss": 1.3885, + "step": 7 + }, + { + "epoch": 0.06837606837606838, + "grad_norm": 0.17036275565624237, + "learning_rate": 0.00016, + "loss": 1.3574, + "step": 8 + }, + { + "epoch": 0.07692307692307693, + "grad_norm": 0.18832312524318695, + "learning_rate": 0.00018, + "loss": 1.2256, + "step": 9 + }, + { + "epoch": 0.08547008547008547, + "grad_norm": 0.22157786786556244, + "learning_rate": 0.0002, + "loss": 1.515, + "step": 10 + }, + { + "epoch": 0.09401709401709402, + "grad_norm": 0.21728643774986267, + "learning_rate": 0.0001999976474595967, + "loss": 1.4505, + "step": 11 + }, + { + "epoch": 0.10256410256410256, + "grad_norm": 0.16113220155239105, + "learning_rate": 0.00019999058994907564, + "loss": 1.132, + "step": 12 + }, + { + "epoch": 0.1111111111111111, + "grad_norm": 0.1798534393310547, + "learning_rate": 0.00019997882780049847, + "loss": 1.2355, + "step": 13 + }, + { + "epoch": 0.11965811965811966, + "grad_norm": 0.19335126876831055, + "learning_rate": 0.0001999623615672837, + "loss": 1.4485, + "step": 14 + }, + { + "epoch": 0.1282051282051282, + "grad_norm": 0.14973561465740204, + "learning_rate": 0.00019994119202418098, + "loss": 1.4852, + "step": 15 + }, + { + "epoch": 0.13675213675213677, + "grad_norm": 0.1763419359922409, + "learning_rate": 0.00019991532016723439, + "loss": 1.0831, + "step": 16 + }, + { + "epoch": 0.1452991452991453, + "grad_norm": 0.148220494389534, + "learning_rate": 0.00019988474721373568, + "loss": 1.5454, + "step": 17 + }, + { + "epoch": 0.15384615384615385, + "grad_norm": 0.1581086665391922, + "learning_rate": 0.00019984947460216707, + "loss": 0.9387, + "step": 18 + }, + { + "epoch": 0.1623931623931624, + "grad_norm": 0.1937003880739212, + "learning_rate": 0.00019980950399213344, + "loss": 1.1612, + "step": 19 + }, + { + "epoch": 0.17094017094017094, + "grad_norm": 0.15193545818328857, + "learning_rate": 0.00019976483726428422, + "loss": 0.9678, + "step": 20 + }, + { + "epoch": 0.1794871794871795, + "grad_norm": 0.17265811562538147, + "learning_rate": 0.0001997154765202251, + "loss": 1.0147, + "step": 21 + }, + { + "epoch": 0.18803418803418803, + "grad_norm": 0.16466519236564636, + "learning_rate": 0.00019966142408241901, + "loss": 1.1492, + "step": 22 + }, + { + "epoch": 0.19658119658119658, + "grad_norm": 0.17746295034885406, + "learning_rate": 0.00019960268249407675, + "loss": 1.2277, + "step": 23 + }, + { + "epoch": 0.20512820512820512, + "grad_norm": 0.1838495433330536, + "learning_rate": 0.00019953925451903756, + "loss": 1.1559, + "step": 24 + }, + { + "epoch": 0.21367521367521367, + "grad_norm": 0.1542479395866394, + "learning_rate": 0.0001994711431416389, + "loss": 1.855, + "step": 25 + }, + { + "epoch": 0.2222222222222222, + "grad_norm": 0.1788703054189682, + "learning_rate": 0.00019939835156657616, + "loss": 1.6273, + "step": 26 + }, + { + "epoch": 0.23076923076923078, + "grad_norm": 0.15661294758319855, + "learning_rate": 0.00019932088321875172, + "loss": 1.0783, + "step": 27 + }, + { + "epoch": 0.23931623931623933, + "grad_norm": 0.1869712620973587, + "learning_rate": 0.00019923874174311394, + "loss": 0.9181, + "step": 28 + }, + { + "epoch": 0.24786324786324787, + "grad_norm": 0.14521349966526031, + "learning_rate": 0.0001991519310044857, + "loss": 1.4428, + "step": 29 + }, + { + "epoch": 0.2564102564102564, + "grad_norm": 0.17194955050945282, + "learning_rate": 0.00019906045508738228, + "loss": 1.3213, + "step": 30 + }, + { + "epoch": 0.26495726495726496, + "grad_norm": 0.14739835262298584, + "learning_rate": 0.0001989643182958196, + "loss": 0.9933, + "step": 31 + }, + { + "epoch": 0.27350427350427353, + "grad_norm": 0.17825335264205933, + "learning_rate": 0.00019886352515311134, + "loss": 1.034, + "step": 32 + }, + { + "epoch": 0.28205128205128205, + "grad_norm": 0.16200387477874756, + "learning_rate": 0.0001987580804016563, + "loss": 1.3064, + "step": 33 + }, + { + "epoch": 0.2905982905982906, + "grad_norm": 0.170911967754364, + "learning_rate": 0.00019864798900271532, + "loss": 1.2321, + "step": 34 + }, + { + "epoch": 0.29914529914529914, + "grad_norm": 0.16599859297275543, + "learning_rate": 0.0001985332561361776, + "loss": 0.9447, + "step": 35 + }, + { + "epoch": 0.3076923076923077, + "grad_norm": 0.14686603844165802, + "learning_rate": 0.00019841388720031727, + "loss": 0.8823, + "step": 36 + }, + { + "epoch": 0.3162393162393162, + "grad_norm": 0.1870049089193344, + "learning_rate": 0.00019828988781153917, + "loss": 1.1041, + "step": 37 + }, + { + "epoch": 0.3247863247863248, + "grad_norm": 0.1619299054145813, + "learning_rate": 0.00019816126380411476, + "loss": 0.9918, + "step": 38 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 0.18731147050857544, + "learning_rate": 0.00019802802122990758, + "loss": 1.0642, + "step": 39 + }, + { + "epoch": 0.3418803418803419, + "grad_norm": 0.17905616760253906, + "learning_rate": 0.00019789016635808837, + "loss": 1.0877, + "step": 40 + }, + { + "epoch": 0.3504273504273504, + "grad_norm": 0.15318270027637482, + "learning_rate": 0.00019774770567484022, + "loss": 1.2165, + "step": 41 + }, + { + "epoch": 0.358974358974359, + "grad_norm": 0.14854711294174194, + "learning_rate": 0.00019760064588305345, + "loss": 0.9812, + "step": 42 + }, + { + "epoch": 0.36752136752136755, + "grad_norm": 0.15519340336322784, + "learning_rate": 0.00019744899390201006, + "loss": 0.9977, + "step": 43 + }, + { + "epoch": 0.37606837606837606, + "grad_norm": 0.1589617133140564, + "learning_rate": 0.0001972927568670583, + "loss": 1.4097, + "step": 44 + }, + { + "epoch": 0.38461538461538464, + "grad_norm": 0.17286093533039093, + "learning_rate": 0.00019713194212927696, + "loss": 1.1385, + "step": 45 + }, + { + "epoch": 0.39316239316239315, + "grad_norm": 0.19325074553489685, + "learning_rate": 0.00019696655725512933, + "loss": 0.9997, + "step": 46 + }, + { + "epoch": 0.4017094017094017, + "grad_norm": 0.18447531759738922, + "learning_rate": 0.00019679661002610743, + "loss": 1.0873, + "step": 47 + }, + { + "epoch": 0.41025641025641024, + "grad_norm": 0.16223366558551788, + "learning_rate": 0.00019662210843836574, + "loss": 0.99, + "step": 48 + }, + { + "epoch": 0.4188034188034188, + "grad_norm": 0.1919640749692917, + "learning_rate": 0.0001964430607023449, + "loss": 1.0171, + "step": 49 + }, + { + "epoch": 0.42735042735042733, + "grad_norm": 0.22606882452964783, + "learning_rate": 0.00019625947524238563, + "loss": 1.4172, + "step": 50 + }, + { + "epoch": 0.4358974358974359, + "grad_norm": 0.17758312821388245, + "learning_rate": 0.00019607136069633212, + "loss": 0.9964, + "step": 51 + }, + { + "epoch": 0.4444444444444444, + "grad_norm": 0.16785483062267303, + "learning_rate": 0.0001958787259151258, + "loss": 0.9883, + "step": 52 + }, + { + "epoch": 0.452991452991453, + "grad_norm": 0.19499914348125458, + "learning_rate": 0.00019568157996238884, + "loss": 1.0293, + "step": 53 + }, + { + "epoch": 0.46153846153846156, + "grad_norm": 0.15674076974391937, + "learning_rate": 0.0001954799321139975, + "loss": 1.3643, + "step": 54 + }, + { + "epoch": 0.4700854700854701, + "grad_norm": 0.16759538650512695, + "learning_rate": 0.00019527379185764612, + "loss": 0.8998, + "step": 55 + }, + { + "epoch": 0.47863247863247865, + "grad_norm": 0.20853222906589508, + "learning_rate": 0.00019506316889240027, + "loss": 1.4597, + "step": 56 + }, + { + "epoch": 0.48717948717948717, + "grad_norm": 0.18584011495113373, + "learning_rate": 0.00019484807312824067, + "loss": 0.8848, + "step": 57 + }, + { + "epoch": 0.49572649572649574, + "grad_norm": 0.24146708846092224, + "learning_rate": 0.0001946285146855968, + "loss": 1.0529, + "step": 58 + }, + { + "epoch": 0.5042735042735043, + "grad_norm": 0.20457321405410767, + "learning_rate": 0.0001944045038948709, + "loss": 0.9917, + "step": 59 + }, + { + "epoch": 0.5128205128205128, + "grad_norm": 0.21354275941848755, + "learning_rate": 0.00019417605129595157, + "loss": 0.9096, + "step": 60 + }, + { + "epoch": 0.5213675213675214, + "grad_norm": 0.2198089212179184, + "learning_rate": 0.0001939431676377183, + "loss": 0.9228, + "step": 61 + }, + { + "epoch": 0.5299145299145299, + "grad_norm": 0.18545866012573242, + "learning_rate": 0.0001937058638775353, + "loss": 0.8399, + "step": 62 + }, + { + "epoch": 0.5384615384615384, + "grad_norm": 0.1578792780637741, + "learning_rate": 0.00019346415118073632, + "loss": 1.6315, + "step": 63 + }, + { + "epoch": 0.5470085470085471, + "grad_norm": 0.23443493247032166, + "learning_rate": 0.00019321804092009906, + "loss": 1.0905, + "step": 64 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 0.20623010396957397, + "learning_rate": 0.00019296754467531014, + "loss": 0.9367, + "step": 65 + }, + { + "epoch": 0.5641025641025641, + "grad_norm": 0.24046015739440918, + "learning_rate": 0.00019271267423242024, + "loss": 0.9195, + "step": 66 + }, + { + "epoch": 0.5726495726495726, + "grad_norm": 0.22675752639770508, + "learning_rate": 0.00019245344158328972, + "loss": 1.1275, + "step": 67 + }, + { + "epoch": 0.5811965811965812, + "grad_norm": 0.22297680377960205, + "learning_rate": 0.0001921898589250242, + "loss": 0.9244, + "step": 68 + }, + { + "epoch": 0.5897435897435898, + "grad_norm": 0.21324071288108826, + "learning_rate": 0.0001919219386594007, + "loss": 0.9706, + "step": 69 + }, + { + "epoch": 0.5982905982905983, + "grad_norm": 0.21497191488742828, + "learning_rate": 0.00019164969339228422, + "loss": 1.0559, + "step": 70 + }, + { + "epoch": 0.6068376068376068, + "grad_norm": 0.2526251971721649, + "learning_rate": 0.00019137313593303463, + "loss": 1.0632, + "step": 71 + }, + { + "epoch": 0.6153846153846154, + "grad_norm": 0.19590331614017487, + "learning_rate": 0.00019109227929390378, + "loss": 1.8134, + "step": 72 + }, + { + "epoch": 0.6239316239316239, + "grad_norm": 0.21532683074474335, + "learning_rate": 0.00019080713668942356, + "loss": 0.9466, + "step": 73 + }, + { + "epoch": 0.6324786324786325, + "grad_norm": 0.2264883816242218, + "learning_rate": 0.00019051772153578389, + "loss": 0.8941, + "step": 74 + }, + { + "epoch": 0.6410256410256411, + "grad_norm": 0.22985824942588806, + "learning_rate": 0.00019022404745020163, + "loss": 0.8991, + "step": 75 + }, + { + "epoch": 0.6495726495726496, + "grad_norm": 0.19453634321689606, + "learning_rate": 0.00018992612825027976, + "loss": 0.9837, + "step": 76 + }, + { + "epoch": 0.6581196581196581, + "grad_norm": 0.2547195851802826, + "learning_rate": 0.0001896239779533575, + "loss": 1.1035, + "step": 77 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.20812910795211792, + "learning_rate": 0.00018931761077585035, + "loss": 0.8916, + "step": 78 + }, + { + "epoch": 0.6752136752136753, + "grad_norm": 0.2176084816455841, + "learning_rate": 0.00018900704113258165, + "loss": 0.8826, + "step": 79 + }, + { + "epoch": 0.6837606837606838, + "grad_norm": 0.2221064418554306, + "learning_rate": 0.00018869228363610404, + "loss": 0.9069, + "step": 80 + }, + { + "epoch": 0.6923076923076923, + "grad_norm": 0.2675364911556244, + "learning_rate": 0.00018837335309601213, + "loss": 1.035, + "step": 81 + }, + { + "epoch": 0.7008547008547008, + "grad_norm": 0.1994653195142746, + "learning_rate": 0.00018805026451824546, + "loss": 1.5854, + "step": 82 + }, + { + "epoch": 0.7094017094017094, + "grad_norm": 0.20346811413764954, + "learning_rate": 0.00018772303310438275, + "loss": 1.4788, + "step": 83 + }, + { + "epoch": 0.717948717948718, + "grad_norm": 0.22119802236557007, + "learning_rate": 0.00018739167425092644, + "loss": 1.4946, + "step": 84 + }, + { + "epoch": 0.7264957264957265, + "grad_norm": 0.2174052894115448, + "learning_rate": 0.00018705620354857833, + "loss": 0.8667, + "step": 85 + }, + { + "epoch": 0.7350427350427351, + "grad_norm": 0.2322807013988495, + "learning_rate": 0.00018671663678150607, + "loss": 0.861, + "step": 86 + }, + { + "epoch": 0.7435897435897436, + "grad_norm": 0.22151263058185577, + "learning_rate": 0.0001863729899266004, + "loss": 0.8966, + "step": 87 + }, + { + "epoch": 0.7521367521367521, + "grad_norm": 0.243766650557518, + "learning_rate": 0.0001860252791527236, + "loss": 1.2998, + "step": 88 + }, + { + "epoch": 0.7606837606837606, + "grad_norm": 0.19212521612644196, + "learning_rate": 0.00018567352081994852, + "loss": 1.5215, + "step": 89 + }, + { + "epoch": 0.7692307692307693, + "grad_norm": 0.20964723825454712, + "learning_rate": 0.00018531773147878895, + "loss": 1.4717, + "step": 90 + }, + { + "epoch": 0.7777777777777778, + "grad_norm": 0.24561531841754913, + "learning_rate": 0.0001849579278694209, + "loss": 0.9569, + "step": 91 + }, + { + "epoch": 0.7863247863247863, + "grad_norm": 0.23924781382083893, + "learning_rate": 0.00018459412692089494, + "loss": 0.9441, + "step": 92 + }, + { + "epoch": 0.7948717948717948, + "grad_norm": 0.2302614450454712, + "learning_rate": 0.0001842263457503397, + "loss": 0.8417, + "step": 93 + }, + { + "epoch": 0.8034188034188035, + "grad_norm": 0.24661926925182343, + "learning_rate": 0.00018385460166215638, + "loss": 1.1297, + "step": 94 + }, + { + "epoch": 0.811965811965812, + "grad_norm": 0.24925513565540314, + "learning_rate": 0.00018347891214720477, + "loss": 0.8999, + "step": 95 + }, + { + "epoch": 0.8205128205128205, + "grad_norm": 0.19934344291687012, + "learning_rate": 0.00018309929488198012, + "loss": 1.4818, + "step": 96 + }, + { + "epoch": 0.8290598290598291, + "grad_norm": 0.24845215678215027, + "learning_rate": 0.00018271576772778154, + "loss": 0.9454, + "step": 97 + }, + { + "epoch": 0.8376068376068376, + "grad_norm": 0.22845034301280975, + "learning_rate": 0.00018232834872987147, + "loss": 1.5063, + "step": 98 + }, + { + "epoch": 0.8461538461538461, + "grad_norm": 0.2563302516937256, + "learning_rate": 0.00018193705611662696, + "loss": 0.9946, + "step": 99 + }, + { + "epoch": 0.8547008547008547, + "grad_norm": 0.30030304193496704, + "learning_rate": 0.0001815419082986815, + "loss": 1.0936, + "step": 100 + }, + { + "epoch": 0.8632478632478633, + "grad_norm": 0.22599591314792633, + "learning_rate": 0.00018114292386805936, + "loss": 1.346, + "step": 101 + }, + { + "epoch": 0.8717948717948718, + "grad_norm": 0.20411820709705353, + "learning_rate": 0.00018074012159730032, + "loss": 1.5147, + "step": 102 + }, + { + "epoch": 0.8803418803418803, + "grad_norm": 0.20635190606117249, + "learning_rate": 0.00018033352043857675, + "loss": 1.1425, + "step": 103 + }, + { + "epoch": 0.8888888888888888, + "grad_norm": 0.22327086329460144, + "learning_rate": 0.00017992313952280172, + "loss": 1.4435, + "step": 104 + }, + { + "epoch": 0.8974358974358975, + "grad_norm": 0.2183496206998825, + "learning_rate": 0.00017950899815872892, + "loss": 1.5659, + "step": 105 + }, + { + "epoch": 0.905982905982906, + "grad_norm": 0.31636252999305725, + "learning_rate": 0.00017909111583204422, + "loss": 1.4703, + "step": 106 + }, + { + "epoch": 0.9145299145299145, + "grad_norm": 0.3305496275424957, + "learning_rate": 0.0001786695122044487, + "loss": 1.0904, + "step": 107 + }, + { + "epoch": 0.9230769230769231, + "grad_norm": 0.22857435047626495, + "learning_rate": 0.0001782442071127338, + "loss": 1.3801, + "step": 108 + }, + { + "epoch": 0.9316239316239316, + "grad_norm": 0.31968221068382263, + "learning_rate": 0.0001778152205678477, + "loss": 1.4907, + "step": 109 + }, + { + "epoch": 0.9401709401709402, + "grad_norm": 0.27950960397720337, + "learning_rate": 0.00017738257275395404, + "loss": 1.0864, + "step": 110 + }, + { + "epoch": 0.9487179487179487, + "grad_norm": 0.2740281820297241, + "learning_rate": 0.00017694628402748202, + "loss": 0.9241, + "step": 111 + }, + { + "epoch": 0.9572649572649573, + "grad_norm": 0.26951318979263306, + "learning_rate": 0.0001765063749161688, + "loss": 0.9894, + "step": 112 + }, + { + "epoch": 0.9658119658119658, + "grad_norm": 0.2811899781227112, + "learning_rate": 0.00017606286611809353, + "loss": 0.9659, + "step": 113 + }, + { + "epoch": 0.9743589743589743, + "grad_norm": 0.23854824900627136, + "learning_rate": 0.00017561577850070355, + "loss": 1.0623, + "step": 114 + }, + { + "epoch": 0.9829059829059829, + "grad_norm": 0.21959957480430603, + "learning_rate": 0.00017516513309983253, + "loss": 0.8671, + "step": 115 + }, + { + "epoch": 0.9914529914529915, + "grad_norm": 0.3096697926521301, + "learning_rate": 0.00017471095111871074, + "loss": 1.0756, + "step": 116 + }, + { + "epoch": 1.0, + "grad_norm": 0.23363932967185974, + "learning_rate": 0.0001742532539269674, + "loss": 0.8988, + "step": 117 + }, + { + "epoch": 1.0085470085470085, + "grad_norm": 0.23965218663215637, + "learning_rate": 0.00017379206305962526, + "loss": 0.7737, + "step": 118 + }, + { + "epoch": 1.017094017094017, + "grad_norm": 0.24553611874580383, + "learning_rate": 0.00017332740021608722, + "loss": 0.7793, + "step": 119 + }, + { + "epoch": 1.0256410256410255, + "grad_norm": 0.267673522233963, + "learning_rate": 0.00017285928725911562, + "loss": 0.8077, + "step": 120 + }, + { + "epoch": 1.0341880341880343, + "grad_norm": 0.3069080114364624, + "learning_rate": 0.00017238774621380337, + "loss": 0.8226, + "step": 121 + }, + { + "epoch": 1.0427350427350428, + "grad_norm": 0.26568329334259033, + "learning_rate": 0.00017191279926653761, + "loss": 1.5833, + "step": 122 + }, + { + "epoch": 1.0512820512820513, + "grad_norm": 0.2673753499984741, + "learning_rate": 0.00017143446876395602, + "loss": 1.3896, + "step": 123 + }, + { + "epoch": 1.0598290598290598, + "grad_norm": 0.23525093495845795, + "learning_rate": 0.00017095277721189528, + "loss": 1.3125, + "step": 124 + }, + { + "epoch": 1.0683760683760684, + "grad_norm": 0.3066873550415039, + "learning_rate": 0.00017046774727433222, + "loss": 0.8894, + "step": 125 + }, + { + "epoch": 1.0769230769230769, + "grad_norm": 0.27280548214912415, + "learning_rate": 0.00016997940177231722, + "loss": 0.7649, + "step": 126 + }, + { + "epoch": 1.0854700854700854, + "grad_norm": 0.23357781767845154, + "learning_rate": 0.00016948776368290084, + "loss": 1.4143, + "step": 127 + }, + { + "epoch": 1.0940170940170941, + "grad_norm": 0.2928774356842041, + "learning_rate": 0.00016899285613805246, + "loss": 0.6522, + "step": 128 + }, + { + "epoch": 1.1025641025641026, + "grad_norm": 0.33789336681365967, + "learning_rate": 0.00016849470242357196, + "loss": 0.7737, + "step": 129 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 0.3078365921974182, + "learning_rate": 0.00016799332597799413, + "loss": 0.8068, + "step": 130 + }, + { + "epoch": 1.1196581196581197, + "grad_norm": 0.3175398111343384, + "learning_rate": 0.00016748875039148593, + "loss": 1.223, + "step": 131 + }, + { + "epoch": 1.1282051282051282, + "grad_norm": 0.27531448006629944, + "learning_rate": 0.0001669809994047364, + "loss": 1.3081, + "step": 132 + }, + { + "epoch": 1.1367521367521367, + "grad_norm": 0.34105026721954346, + "learning_rate": 0.0001664700969078398, + "loss": 0.9031, + "step": 133 + }, + { + "epoch": 1.1452991452991452, + "grad_norm": 0.25465068221092224, + "learning_rate": 0.00016595606693917142, + "loss": 1.3237, + "step": 134 + }, + { + "epoch": 1.1538461538461537, + "grad_norm": 0.2841501533985138, + "learning_rate": 0.00016543893368425666, + "loss": 0.7393, + "step": 135 + }, + { + "epoch": 1.1623931623931625, + "grad_norm": 0.3230992257595062, + "learning_rate": 0.00016491872147463306, + "loss": 0.7437, + "step": 136 + }, + { + "epoch": 1.170940170940171, + "grad_norm": 0.25824740529060364, + "learning_rate": 0.00016439545478670543, + "loss": 1.883, + "step": 137 + }, + { + "epoch": 1.1794871794871795, + "grad_norm": 0.31415536999702454, + "learning_rate": 0.00016386915824059427, + "loss": 0.703, + "step": 138 + }, + { + "epoch": 1.188034188034188, + "grad_norm": 0.26885557174682617, + "learning_rate": 0.00016333985659897735, + "loss": 0.6592, + "step": 139 + }, + { + "epoch": 1.1965811965811965, + "grad_norm": 0.4018881618976593, + "learning_rate": 0.00016280757476592466, + "loss": 0.7733, + "step": 140 + }, + { + "epoch": 1.205128205128205, + "grad_norm": 0.3181138038635254, + "learning_rate": 0.0001622723377857265, + "loss": 0.7577, + "step": 141 + }, + { + "epoch": 1.2136752136752136, + "grad_norm": 0.2720906436443329, + "learning_rate": 0.00016173417084171536, + "loss": 1.3883, + "step": 142 + }, + { + "epoch": 1.2222222222222223, + "grad_norm": 0.34472835063934326, + "learning_rate": 0.00016119309925508078, + "loss": 0.7757, + "step": 143 + }, + { + "epoch": 1.2307692307692308, + "grad_norm": 0.40166720747947693, + "learning_rate": 0.0001606491484836782, + "loss": 0.79, + "step": 144 + }, + { + "epoch": 1.2393162393162394, + "grad_norm": 0.38203030824661255, + "learning_rate": 0.00016010234412083086, + "loss": 0.8184, + "step": 145 + }, + { + "epoch": 1.2478632478632479, + "grad_norm": 0.3825059235095978, + "learning_rate": 0.00015955271189412598, + "loss": 0.9065, + "step": 146 + }, + { + "epoch": 1.2564102564102564, + "grad_norm": 0.403533935546875, + "learning_rate": 0.00015900027766420393, + "loss": 0.7605, + "step": 147 + }, + { + "epoch": 1.264957264957265, + "grad_norm": 0.3657178282737732, + "learning_rate": 0.00015844506742354164, + "loss": 0.8265, + "step": 148 + }, + { + "epoch": 1.2735042735042734, + "grad_norm": 0.2825511693954468, + "learning_rate": 0.00015788710729522953, + "loss": 1.166, + "step": 149 + }, + { + "epoch": 1.282051282051282, + "grad_norm": 0.4000828266143799, + "learning_rate": 0.00015732642353174259, + "loss": 1.2792, + "step": 150 + }, + { + "epoch": 1.2905982905982907, + "grad_norm": 0.3135271668434143, + "learning_rate": 0.0001567630425137049, + "loss": 0.6227, + "step": 151 + }, + { + "epoch": 1.2991452991452992, + "grad_norm": 0.3828388452529907, + "learning_rate": 0.00015619699074864864, + "loss": 0.6989, + "step": 152 + }, + { + "epoch": 1.3076923076923077, + "grad_norm": 0.45689550042152405, + "learning_rate": 0.00015562829486976673, + "loss": 0.9088, + "step": 153 + }, + { + "epoch": 1.3162393162393162, + "grad_norm": 0.36523374915122986, + "learning_rate": 0.00015505698163465986, + "loss": 0.9859, + "step": 154 + }, + { + "epoch": 1.3247863247863247, + "grad_norm": 0.4206138551235199, + "learning_rate": 0.00015448307792407734, + "loss": 0.7771, + "step": 155 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.3400786817073822, + "learning_rate": 0.00015390661074065256, + "loss": 0.772, + "step": 156 + }, + { + "epoch": 1.341880341880342, + "grad_norm": 0.334692120552063, + "learning_rate": 0.00015332760720763232, + "loss": 1.3839, + "step": 157 + }, + { + "epoch": 1.3504273504273505, + "grad_norm": 0.4513654112815857, + "learning_rate": 0.00015274609456760073, + "loss": 0.8578, + "step": 158 + }, + { + "epoch": 1.358974358974359, + "grad_norm": 0.4215463399887085, + "learning_rate": 0.00015216210018119733, + "loss": 0.9154, + "step": 159 + }, + { + "epoch": 1.3675213675213675, + "grad_norm": 0.38081440329551697, + "learning_rate": 0.00015157565152583002, + "loss": 0.6723, + "step": 160 + }, + { + "epoch": 1.376068376068376, + "grad_norm": 0.38604873418807983, + "learning_rate": 0.0001509867761943818, + "loss": 0.9546, + "step": 161 + }, + { + "epoch": 1.3846153846153846, + "grad_norm": 0.39846640825271606, + "learning_rate": 0.00015039550189391298, + "loss": 0.7379, + "step": 162 + }, + { + "epoch": 1.393162393162393, + "grad_norm": 0.3619799315929413, + "learning_rate": 0.0001498018564443571, + "loss": 1.12, + "step": 163 + }, + { + "epoch": 1.4017094017094016, + "grad_norm": 0.4657539427280426, + "learning_rate": 0.0001492058677772123, + "loss": 1.0395, + "step": 164 + }, + { + "epoch": 1.4102564102564101, + "grad_norm": 0.3850860893726349, + "learning_rate": 0.000148607563934227, + "loss": 0.7949, + "step": 165 + }, + { + "epoch": 1.4188034188034189, + "grad_norm": 0.30473998188972473, + "learning_rate": 0.00014800697306608044, + "loss": 0.6285, + "step": 166 + }, + { + "epoch": 1.4273504273504274, + "grad_norm": 0.36891016364097595, + "learning_rate": 0.00014740412343105828, + "loss": 0.9947, + "step": 167 + }, + { + "epoch": 1.435897435897436, + "grad_norm": 0.3746401071548462, + "learning_rate": 0.00014679904339372302, + "loss": 0.7204, + "step": 168 + }, + { + "epoch": 1.4444444444444444, + "grad_norm": 0.4085482060909271, + "learning_rate": 0.00014619176142357935, + "loss": 0.7145, + "step": 169 + }, + { + "epoch": 1.452991452991453, + "grad_norm": 0.40742969512939453, + "learning_rate": 0.0001455823060937347, + "loss": 0.8273, + "step": 170 + }, + { + "epoch": 1.4615384615384617, + "grad_norm": 0.3882700502872467, + "learning_rate": 0.00014497070607955476, + "loss": 0.7025, + "step": 171 + }, + { + "epoch": 1.4700854700854702, + "grad_norm": 0.43999457359313965, + "learning_rate": 0.00014435699015731448, + "loss": 0.7473, + "step": 172 + }, + { + "epoch": 1.4786324786324787, + "grad_norm": 0.3841669261455536, + "learning_rate": 0.00014374118720284388, + "loss": 0.8794, + "step": 173 + }, + { + "epoch": 1.4871794871794872, + "grad_norm": 0.3169039189815521, + "learning_rate": 0.00014312332619016965, + "loss": 1.007, + "step": 174 + }, + { + "epoch": 1.4957264957264957, + "grad_norm": 0.44292953610420227, + "learning_rate": 0.0001425034361901516, + "loss": 0.846, + "step": 175 + }, + { + "epoch": 1.5042735042735043, + "grad_norm": 0.3945798873901367, + "learning_rate": 0.00014188154636911524, + "loss": 1.3956, + "step": 176 + }, + { + "epoch": 1.5128205128205128, + "grad_norm": 0.4760408103466034, + "learning_rate": 0.0001412576859874791, + "loss": 0.7811, + "step": 177 + }, + { + "epoch": 1.5213675213675213, + "grad_norm": 0.401869535446167, + "learning_rate": 0.00014063188439837832, + "loss": 0.6903, + "step": 178 + }, + { + "epoch": 1.5299145299145298, + "grad_norm": 0.3994334042072296, + "learning_rate": 0.0001400041710462833, + "loss": 0.688, + "step": 179 + }, + { + "epoch": 1.5384615384615383, + "grad_norm": 0.41962575912475586, + "learning_rate": 0.0001393745754656146, + "loss": 0.7697, + "step": 180 + }, + { + "epoch": 1.547008547008547, + "grad_norm": 0.36107930541038513, + "learning_rate": 0.00013874312727935292, + "loss": 0.715, + "step": 181 + }, + { + "epoch": 1.5555555555555556, + "grad_norm": 0.3828651010990143, + "learning_rate": 0.00013810985619764572, + "loss": 1.3298, + "step": 182 + }, + { + "epoch": 1.564102564102564, + "grad_norm": 0.3839617967605591, + "learning_rate": 0.00013747479201640914, + "loss": 0.6851, + "step": 183 + }, + { + "epoch": 1.5726495726495726, + "grad_norm": 0.4327555298805237, + "learning_rate": 0.00013683796461592604, + "loss": 0.7906, + "step": 184 + }, + { + "epoch": 1.5811965811965814, + "grad_norm": 0.3910170793533325, + "learning_rate": 0.00013619940395944027, + "loss": 0.7832, + "step": 185 + }, + { + "epoch": 1.5897435897435899, + "grad_norm": 0.4029540419578552, + "learning_rate": 0.00013555914009174663, + "loss": 0.7723, + "step": 186 + }, + { + "epoch": 1.5982905982905984, + "grad_norm": 0.3986589014530182, + "learning_rate": 0.00013491720313777756, + "loss": 1.1658, + "step": 187 + }, + { + "epoch": 1.606837606837607, + "grad_norm": 0.3962538242340088, + "learning_rate": 0.00013427362330118543, + "loss": 0.7481, + "step": 188 + }, + { + "epoch": 1.6153846153846154, + "grad_norm": 0.4297255277633667, + "learning_rate": 0.0001336284308629216, + "loss": 0.9531, + "step": 189 + }, + { + "epoch": 1.623931623931624, + "grad_norm": 0.3742808699607849, + "learning_rate": 0.00013298165617981172, + "loss": 0.9516, + "step": 190 + }, + { + "epoch": 1.6324786324786325, + "grad_norm": 0.44721004366874695, + "learning_rate": 0.00013233332968312715, + "loss": 1.075, + "step": 191 + }, + { + "epoch": 1.641025641025641, + "grad_norm": 0.41275331377983093, + "learning_rate": 0.0001316834818771535, + "loss": 0.8295, + "step": 192 + }, + { + "epoch": 1.6495726495726495, + "grad_norm": 0.46620428562164307, + "learning_rate": 0.00013103214333775521, + "loss": 0.8314, + "step": 193 + }, + { + "epoch": 1.658119658119658, + "grad_norm": 0.4467974901199341, + "learning_rate": 0.00013037934471093682, + "loss": 0.7321, + "step": 194 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.42806383967399597, + "learning_rate": 0.00012972511671140125, + "loss": 0.7144, + "step": 195 + }, + { + "epoch": 1.6752136752136753, + "grad_norm": 0.3721958100795746, + "learning_rate": 0.00012906949012110456, + "loss": 1.0117, + "step": 196 + }, + { + "epoch": 1.6837606837606838, + "grad_norm": 0.46833130717277527, + "learning_rate": 0.00012841249578780757, + "loss": 0.9599, + "step": 197 + }, + { + "epoch": 1.6923076923076923, + "grad_norm": 0.3547254502773285, + "learning_rate": 0.00012775416462362457, + "loss": 0.8255, + "step": 198 + }, + { + "epoch": 1.7008547008547008, + "grad_norm": 0.36470168828964233, + "learning_rate": 0.00012709452760356884, + "loss": 1.3796, + "step": 199 + }, + { + "epoch": 1.7094017094017095, + "grad_norm": 0.4088481068611145, + "learning_rate": 0.00012643361576409516, + "loss": 0.818, + "step": 200 + }, + { + "epoch": 1.717948717948718, + "grad_norm": 0.43268319964408875, + "learning_rate": 0.00012577146020163968, + "loss": 0.8157, + "step": 201 + }, + { + "epoch": 1.7264957264957266, + "grad_norm": 0.4660526216030121, + "learning_rate": 0.00012510809207115666, + "loss": 0.775, + "step": 202 + }, + { + "epoch": 1.735042735042735, + "grad_norm": 0.41217854619026184, + "learning_rate": 0.00012444354258465268, + "loss": 0.7172, + "step": 203 + }, + { + "epoch": 1.7435897435897436, + "grad_norm": 0.4177812933921814, + "learning_rate": 0.00012377784300971807, + "loss": 1.1308, + "step": 204 + }, + { + "epoch": 1.7521367521367521, + "grad_norm": 0.3943150043487549, + "learning_rate": 0.0001231110246680558, + "loss": 1.4001, + "step": 205 + }, + { + "epoch": 1.7606837606837606, + "grad_norm": 0.48257848620414734, + "learning_rate": 0.00012244311893400763, + "loss": 0.9118, + "step": 206 + }, + { + "epoch": 1.7692307692307692, + "grad_norm": 0.4754193127155304, + "learning_rate": 0.00012177415723307808, + "loss": 0.825, + "step": 207 + }, + { + "epoch": 1.7777777777777777, + "grad_norm": 0.3812815546989441, + "learning_rate": 0.00012110417104045575, + "loss": 0.6433, + "step": 208 + }, + { + "epoch": 1.7863247863247862, + "grad_norm": 0.3967946469783783, + "learning_rate": 0.00012043319187953241, + "loss": 0.8549, + "step": 209 + }, + { + "epoch": 1.7948717948717947, + "grad_norm": 0.4312019348144531, + "learning_rate": 0.00011976125132041974, + "loss": 0.8387, + "step": 210 + }, + { + "epoch": 1.8034188034188035, + "grad_norm": 0.4585026204586029, + "learning_rate": 0.00011908838097846404, + "loss": 0.9471, + "step": 211 + }, + { + "epoch": 1.811965811965812, + "grad_norm": 0.4149639904499054, + "learning_rate": 0.00011841461251275867, + "loss": 1.0415, + "step": 212 + }, + { + "epoch": 1.8205128205128205, + "grad_norm": 0.48069992661476135, + "learning_rate": 0.00011773997762465429, + "loss": 0.7534, + "step": 213 + }, + { + "epoch": 1.8290598290598292, + "grad_norm": 0.3820441961288452, + "learning_rate": 0.0001170645080562676, + "loss": 0.8292, + "step": 214 + }, + { + "epoch": 1.8376068376068377, + "grad_norm": 0.3951680660247803, + "learning_rate": 0.00011638823558898762, + "loss": 0.6923, + "step": 215 + }, + { + "epoch": 1.8461538461538463, + "grad_norm": 0.40777531266212463, + "learning_rate": 0.00011571119204198037, + "loss": 0.7335, + "step": 216 + }, + { + "epoch": 1.8547008547008548, + "grad_norm": 0.3792341649532318, + "learning_rate": 0.00011503340927069189, + "loss": 0.8608, + "step": 217 + }, + { + "epoch": 1.8632478632478633, + "grad_norm": 0.36157581210136414, + "learning_rate": 0.00011435491916534919, + "loss": 0.7314, + "step": 218 + }, + { + "epoch": 1.8717948717948718, + "grad_norm": 0.41833943128585815, + "learning_rate": 0.00011367575364946006, + "loss": 0.7662, + "step": 219 + }, + { + "epoch": 1.8803418803418803, + "grad_norm": 0.45951926708221436, + "learning_rate": 0.00011299594467831078, + "loss": 0.6988, + "step": 220 + }, + { + "epoch": 1.8888888888888888, + "grad_norm": 0.4588642120361328, + "learning_rate": 0.00011231552423746283, + "loss": 0.8544, + "step": 221 + }, + { + "epoch": 1.8974358974358974, + "grad_norm": 0.3614063560962677, + "learning_rate": 0.00011163452434124773, + "loss": 0.728, + "step": 222 + }, + { + "epoch": 1.9059829059829059, + "grad_norm": 0.4452153742313385, + "learning_rate": 0.00011095297703126093, + "loss": 0.7399, + "step": 223 + }, + { + "epoch": 1.9145299145299144, + "grad_norm": 0.42948612570762634, + "learning_rate": 0.00011027091437485404, + "loss": 0.9105, + "step": 224 + }, + { + "epoch": 1.9230769230769231, + "grad_norm": 0.37950897216796875, + "learning_rate": 0.00010958836846362621, + "loss": 0.9612, + "step": 225 + }, + { + "epoch": 1.9316239316239316, + "grad_norm": 0.4386560916900635, + "learning_rate": 0.00010890537141191417, + "loss": 0.683, + "step": 226 + }, + { + "epoch": 1.9401709401709402, + "grad_norm": 0.4166669547557831, + "learning_rate": 0.00010822195535528106, + "loss": 1.1851, + "step": 227 + }, + { + "epoch": 1.9487179487179487, + "grad_norm": 0.4029337465763092, + "learning_rate": 0.00010753815244900458, + "loss": 0.6721, + "step": 228 + }, + { + "epoch": 1.9572649572649574, + "grad_norm": 0.47789204120635986, + "learning_rate": 0.00010685399486656406, + "loss": 0.8654, + "step": 229 + }, + { + "epoch": 1.965811965811966, + "grad_norm": 0.4141186475753784, + "learning_rate": 0.00010616951479812658, + "loss": 0.7619, + "step": 230 + }, + { + "epoch": 1.9743589743589745, + "grad_norm": 0.4745655655860901, + "learning_rate": 0.00010548474444903247, + "loss": 0.698, + "step": 231 + }, + { + "epoch": 1.982905982905983, + "grad_norm": 0.4075687825679779, + "learning_rate": 0.00010479971603828, + "loss": 0.7387, + "step": 232 + }, + { + "epoch": 1.9914529914529915, + "grad_norm": 0.37726572155952454, + "learning_rate": 0.00010411446179700943, + "loss": 0.714, + "step": 233 + }, + { + "epoch": 2.0, + "grad_norm": 0.5989537239074707, + "learning_rate": 0.00010342901396698659, + "loss": 0.7816, + "step": 234 + } + ], + "logging_steps": 1, + "max_steps": 468, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 117, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.519669636843438e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-234/training_args.bin b/checkpoint-234/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..6aa0501cedc8c6a042abaac1eb0d2755310396ba --- /dev/null +++ b/checkpoint-234/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7fe3839cfcc5a93b060094e1030e134d680eeeb9bb2bdbde204831612dbb1c1 +size 6840 diff --git a/checkpoint-351/README.md b/checkpoint-351/README.md new file mode 100644 index 0000000000000000000000000000000000000000..a1856dcc51e1f1ee5a60850ea184165793425f6d --- /dev/null +++ b/checkpoint-351/README.md @@ -0,0 +1,202 @@ +--- +base_model: /cpool/DeepSeek-R1-Distill-Qwen-7B +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-351/adapter_config.json b/checkpoint-351/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..324e93a070435c3ef71b8e5c1a17321dfd9614f6 --- /dev/null +++ b/checkpoint-351/adapter_config.json @@ -0,0 +1,37 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/cpool/DeepSeek-R1-Distill-Qwen-7B", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": null, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_bias": false, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "up_proj", + "k_proj", + "down_proj", + "gate_proj", + "v_proj", + "o_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-351/adapter_model.safetensors b/checkpoint-351/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0eaf8a2b96bd04a1a2dc10d3ba310531cb39fd9b --- /dev/null +++ b/checkpoint-351/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1afd48c3ee699f8ae2782888c901f6069735b17549bb7c95b7a64a5a51b2e8f +size 2497283840 diff --git a/checkpoint-351/optimizer.bin b/checkpoint-351/optimizer.bin new file mode 100644 index 0000000000000000000000000000000000000000..70a3a2c8f65d67ed5de8aa4f6f457913b4ea54d5 --- /dev/null +++ b/checkpoint-351/optimizer.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2974a024832406f2aa24a8eb6a05e6432c8fb724e40e91dfa06bc435d8f33787 +size 646273514 diff --git a/checkpoint-351/pytorch_model_fsdp.bin b/checkpoint-351/pytorch_model_fsdp.bin new file mode 100644 index 0000000000000000000000000000000000000000..e0179aa49c594f1157626e6404c9ef4b7233698c --- /dev/null +++ b/checkpoint-351/pytorch_model_fsdp.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c86cbb8c3ee8ae812c4dfd68ca37b029fb18a06d361fa356076849d28faeadf +size 323107814 diff --git a/checkpoint-351/rng_state_0.pth b/checkpoint-351/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..8b5c060c1695fb4e720934f638c0cfc13fd011de --- /dev/null +++ b/checkpoint-351/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cb646fb0a7810041dc2ede17cfeee4863f8c3d042cb0e9b5af7526d6fd7a7b1 +size 14512 diff --git a/checkpoint-351/rng_state_1.pth b/checkpoint-351/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..198abdda2fdee6d66e986c5d207343dd2bad3343 --- /dev/null +++ b/checkpoint-351/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6ac6e96f74bd461ab986ebacd1e0b91ce7ac52c36d246c1857bc8dfa7551867 +size 14512 diff --git a/checkpoint-351/scheduler.pt b/checkpoint-351/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..70b686928b26f50d11d522f76ed91d8d21474a0a --- /dev/null +++ b/checkpoint-351/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:454dfa8bbb56ee568c79ad1c952ebecb5c624e8574cf9b37d1ca345031d56714 +size 1064 diff --git a/checkpoint-351/special_tokens_map.json b/checkpoint-351/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1 --- /dev/null +++ b/checkpoint-351/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-351/tokenizer.json b/checkpoint-351/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/checkpoint-351/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/checkpoint-351/tokenizer_config.json b/checkpoint-351/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b068ffca3220a746ba50cc69f850e544217e3a86 --- /dev/null +++ b/checkpoint-351/tokenizer_config.json @@ -0,0 +1,195 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": null, + "use_default_system_prompt": false +} diff --git a/checkpoint-351/trainer_state.json b/checkpoint-351/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..1477ce09cd45daf0549dad1aee9f0cd65b17f616 --- /dev/null +++ b/checkpoint-351/trainer_state.json @@ -0,0 +1,2490 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0, + "eval_steps": 500, + "global_step": 351, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.008547008547008548, + "grad_norm": 0.15355850756168365, + "learning_rate": 2e-05, + "loss": 1.4892, + "step": 1 + }, + { + "epoch": 0.017094017094017096, + "grad_norm": 0.1224861666560173, + "learning_rate": 4e-05, + "loss": 1.1445, + "step": 2 + }, + { + "epoch": 0.02564102564102564, + "grad_norm": 0.1645984649658203, + "learning_rate": 6e-05, + "loss": 1.5538, + "step": 3 + }, + { + "epoch": 0.03418803418803419, + "grad_norm": 0.125856414437294, + "learning_rate": 8e-05, + "loss": 1.7634, + "step": 4 + }, + { + "epoch": 0.042735042735042736, + "grad_norm": 0.1726977378129959, + "learning_rate": 0.0001, + "loss": 1.4105, + "step": 5 + }, + { + "epoch": 0.05128205128205128, + "grad_norm": 0.18316921591758728, + "learning_rate": 0.00012, + "loss": 1.8364, + "step": 6 + }, + { + "epoch": 0.05982905982905983, + "grad_norm": 0.17618055641651154, + "learning_rate": 0.00014, + "loss": 1.3885, + "step": 7 + }, + { + "epoch": 0.06837606837606838, + "grad_norm": 0.17036275565624237, + "learning_rate": 0.00016, + "loss": 1.3574, + "step": 8 + }, + { + "epoch": 0.07692307692307693, + "grad_norm": 0.18832312524318695, + "learning_rate": 0.00018, + "loss": 1.2256, + "step": 9 + }, + { + "epoch": 0.08547008547008547, + "grad_norm": 0.22157786786556244, + "learning_rate": 0.0002, + "loss": 1.515, + "step": 10 + }, + { + "epoch": 0.09401709401709402, + "grad_norm": 0.21728643774986267, + "learning_rate": 0.0001999976474595967, + "loss": 1.4505, + "step": 11 + }, + { + "epoch": 0.10256410256410256, + "grad_norm": 0.16113220155239105, + "learning_rate": 0.00019999058994907564, + "loss": 1.132, + "step": 12 + }, + { + "epoch": 0.1111111111111111, + "grad_norm": 0.1798534393310547, + "learning_rate": 0.00019997882780049847, + "loss": 1.2355, + "step": 13 + }, + { + "epoch": 0.11965811965811966, + "grad_norm": 0.19335126876831055, + "learning_rate": 0.0001999623615672837, + "loss": 1.4485, + "step": 14 + }, + { + "epoch": 0.1282051282051282, + "grad_norm": 0.14973561465740204, + "learning_rate": 0.00019994119202418098, + "loss": 1.4852, + "step": 15 + }, + { + "epoch": 0.13675213675213677, + "grad_norm": 0.1763419359922409, + "learning_rate": 0.00019991532016723439, + "loss": 1.0831, + "step": 16 + }, + { + "epoch": 0.1452991452991453, + "grad_norm": 0.148220494389534, + "learning_rate": 0.00019988474721373568, + "loss": 1.5454, + "step": 17 + }, + { + "epoch": 0.15384615384615385, + "grad_norm": 0.1581086665391922, + "learning_rate": 0.00019984947460216707, + "loss": 0.9387, + "step": 18 + }, + { + "epoch": 0.1623931623931624, + "grad_norm": 0.1937003880739212, + "learning_rate": 0.00019980950399213344, + "loss": 1.1612, + "step": 19 + }, + { + "epoch": 0.17094017094017094, + "grad_norm": 0.15193545818328857, + "learning_rate": 0.00019976483726428422, + "loss": 0.9678, + "step": 20 + }, + { + "epoch": 0.1794871794871795, + "grad_norm": 0.17265811562538147, + "learning_rate": 0.0001997154765202251, + "loss": 1.0147, + "step": 21 + }, + { + "epoch": 0.18803418803418803, + "grad_norm": 0.16466519236564636, + "learning_rate": 0.00019966142408241901, + "loss": 1.1492, + "step": 22 + }, + { + "epoch": 0.19658119658119658, + "grad_norm": 0.17746295034885406, + "learning_rate": 0.00019960268249407675, + "loss": 1.2277, + "step": 23 + }, + { + "epoch": 0.20512820512820512, + "grad_norm": 0.1838495433330536, + "learning_rate": 0.00019953925451903756, + "loss": 1.1559, + "step": 24 + }, + { + "epoch": 0.21367521367521367, + "grad_norm": 0.1542479395866394, + "learning_rate": 0.0001994711431416389, + "loss": 1.855, + "step": 25 + }, + { + "epoch": 0.2222222222222222, + "grad_norm": 0.1788703054189682, + "learning_rate": 0.00019939835156657616, + "loss": 1.6273, + "step": 26 + }, + { + "epoch": 0.23076923076923078, + "grad_norm": 0.15661294758319855, + "learning_rate": 0.00019932088321875172, + "loss": 1.0783, + "step": 27 + }, + { + "epoch": 0.23931623931623933, + "grad_norm": 0.1869712620973587, + "learning_rate": 0.00019923874174311394, + "loss": 0.9181, + "step": 28 + }, + { + "epoch": 0.24786324786324787, + "grad_norm": 0.14521349966526031, + "learning_rate": 0.0001991519310044857, + "loss": 1.4428, + "step": 29 + }, + { + "epoch": 0.2564102564102564, + "grad_norm": 0.17194955050945282, + "learning_rate": 0.00019906045508738228, + "loss": 1.3213, + "step": 30 + }, + { + "epoch": 0.26495726495726496, + "grad_norm": 0.14739835262298584, + "learning_rate": 0.0001989643182958196, + "loss": 0.9933, + "step": 31 + }, + { + "epoch": 0.27350427350427353, + "grad_norm": 0.17825335264205933, + "learning_rate": 0.00019886352515311134, + "loss": 1.034, + "step": 32 + }, + { + "epoch": 0.28205128205128205, + "grad_norm": 0.16200387477874756, + "learning_rate": 0.0001987580804016563, + "loss": 1.3064, + "step": 33 + }, + { + "epoch": 0.2905982905982906, + "grad_norm": 0.170911967754364, + "learning_rate": 0.00019864798900271532, + "loss": 1.2321, + "step": 34 + }, + { + "epoch": 0.29914529914529914, + "grad_norm": 0.16599859297275543, + "learning_rate": 0.0001985332561361776, + "loss": 0.9447, + "step": 35 + }, + { + "epoch": 0.3076923076923077, + "grad_norm": 0.14686603844165802, + "learning_rate": 0.00019841388720031727, + "loss": 0.8823, + "step": 36 + }, + { + "epoch": 0.3162393162393162, + "grad_norm": 0.1870049089193344, + "learning_rate": 0.00019828988781153917, + "loss": 1.1041, + "step": 37 + }, + { + "epoch": 0.3247863247863248, + "grad_norm": 0.1619299054145813, + "learning_rate": 0.00019816126380411476, + "loss": 0.9918, + "step": 38 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 0.18731147050857544, + "learning_rate": 0.00019802802122990758, + "loss": 1.0642, + "step": 39 + }, + { + "epoch": 0.3418803418803419, + "grad_norm": 0.17905616760253906, + "learning_rate": 0.00019789016635808837, + "loss": 1.0877, + "step": 40 + }, + { + "epoch": 0.3504273504273504, + "grad_norm": 0.15318270027637482, + "learning_rate": 0.00019774770567484022, + "loss": 1.2165, + "step": 41 + }, + { + "epoch": 0.358974358974359, + "grad_norm": 0.14854711294174194, + "learning_rate": 0.00019760064588305345, + "loss": 0.9812, + "step": 42 + }, + { + "epoch": 0.36752136752136755, + "grad_norm": 0.15519340336322784, + "learning_rate": 0.00019744899390201006, + "loss": 0.9977, + "step": 43 + }, + { + "epoch": 0.37606837606837606, + "grad_norm": 0.1589617133140564, + "learning_rate": 0.0001972927568670583, + "loss": 1.4097, + "step": 44 + }, + { + "epoch": 0.38461538461538464, + "grad_norm": 0.17286093533039093, + "learning_rate": 0.00019713194212927696, + "loss": 1.1385, + "step": 45 + }, + { + "epoch": 0.39316239316239315, + "grad_norm": 0.19325074553489685, + "learning_rate": 0.00019696655725512933, + "loss": 0.9997, + "step": 46 + }, + { + "epoch": 0.4017094017094017, + "grad_norm": 0.18447531759738922, + "learning_rate": 0.00019679661002610743, + "loss": 1.0873, + "step": 47 + }, + { + "epoch": 0.41025641025641024, + "grad_norm": 0.16223366558551788, + "learning_rate": 0.00019662210843836574, + "loss": 0.99, + "step": 48 + }, + { + "epoch": 0.4188034188034188, + "grad_norm": 0.1919640749692917, + "learning_rate": 0.0001964430607023449, + "loss": 1.0171, + "step": 49 + }, + { + "epoch": 0.42735042735042733, + "grad_norm": 0.22606882452964783, + "learning_rate": 0.00019625947524238563, + "loss": 1.4172, + "step": 50 + }, + { + "epoch": 0.4358974358974359, + "grad_norm": 0.17758312821388245, + "learning_rate": 0.00019607136069633212, + "loss": 0.9964, + "step": 51 + }, + { + "epoch": 0.4444444444444444, + "grad_norm": 0.16785483062267303, + "learning_rate": 0.0001958787259151258, + "loss": 0.9883, + "step": 52 + }, + { + "epoch": 0.452991452991453, + "grad_norm": 0.19499914348125458, + "learning_rate": 0.00019568157996238884, + "loss": 1.0293, + "step": 53 + }, + { + "epoch": 0.46153846153846156, + "grad_norm": 0.15674076974391937, + "learning_rate": 0.0001954799321139975, + "loss": 1.3643, + "step": 54 + }, + { + "epoch": 0.4700854700854701, + "grad_norm": 0.16759538650512695, + "learning_rate": 0.00019527379185764612, + "loss": 0.8998, + "step": 55 + }, + { + "epoch": 0.47863247863247865, + "grad_norm": 0.20853222906589508, + "learning_rate": 0.00019506316889240027, + "loss": 1.4597, + "step": 56 + }, + { + "epoch": 0.48717948717948717, + "grad_norm": 0.18584011495113373, + "learning_rate": 0.00019484807312824067, + "loss": 0.8848, + "step": 57 + }, + { + "epoch": 0.49572649572649574, + "grad_norm": 0.24146708846092224, + "learning_rate": 0.0001946285146855968, + "loss": 1.0529, + "step": 58 + }, + { + "epoch": 0.5042735042735043, + "grad_norm": 0.20457321405410767, + "learning_rate": 0.0001944045038948709, + "loss": 0.9917, + "step": 59 + }, + { + "epoch": 0.5128205128205128, + "grad_norm": 0.21354275941848755, + "learning_rate": 0.00019417605129595157, + "loss": 0.9096, + "step": 60 + }, + { + "epoch": 0.5213675213675214, + "grad_norm": 0.2198089212179184, + "learning_rate": 0.0001939431676377183, + "loss": 0.9228, + "step": 61 + }, + { + "epoch": 0.5299145299145299, + "grad_norm": 0.18545866012573242, + "learning_rate": 0.0001937058638775353, + "loss": 0.8399, + "step": 62 + }, + { + "epoch": 0.5384615384615384, + "grad_norm": 0.1578792780637741, + "learning_rate": 0.00019346415118073632, + "loss": 1.6315, + "step": 63 + }, + { + "epoch": 0.5470085470085471, + "grad_norm": 0.23443493247032166, + "learning_rate": 0.00019321804092009906, + "loss": 1.0905, + "step": 64 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 0.20623010396957397, + "learning_rate": 0.00019296754467531014, + "loss": 0.9367, + "step": 65 + }, + { + "epoch": 0.5641025641025641, + "grad_norm": 0.24046015739440918, + "learning_rate": 0.00019271267423242024, + "loss": 0.9195, + "step": 66 + }, + { + "epoch": 0.5726495726495726, + "grad_norm": 0.22675752639770508, + "learning_rate": 0.00019245344158328972, + "loss": 1.1275, + "step": 67 + }, + { + "epoch": 0.5811965811965812, + "grad_norm": 0.22297680377960205, + "learning_rate": 0.0001921898589250242, + "loss": 0.9244, + "step": 68 + }, + { + "epoch": 0.5897435897435898, + "grad_norm": 0.21324071288108826, + "learning_rate": 0.0001919219386594007, + "loss": 0.9706, + "step": 69 + }, + { + "epoch": 0.5982905982905983, + "grad_norm": 0.21497191488742828, + "learning_rate": 0.00019164969339228422, + "loss": 1.0559, + "step": 70 + }, + { + "epoch": 0.6068376068376068, + "grad_norm": 0.2526251971721649, + "learning_rate": 0.00019137313593303463, + "loss": 1.0632, + "step": 71 + }, + { + "epoch": 0.6153846153846154, + "grad_norm": 0.19590331614017487, + "learning_rate": 0.00019109227929390378, + "loss": 1.8134, + "step": 72 + }, + { + "epoch": 0.6239316239316239, + "grad_norm": 0.21532683074474335, + "learning_rate": 0.00019080713668942356, + "loss": 0.9466, + "step": 73 + }, + { + "epoch": 0.6324786324786325, + "grad_norm": 0.2264883816242218, + "learning_rate": 0.00019051772153578389, + "loss": 0.8941, + "step": 74 + }, + { + "epoch": 0.6410256410256411, + "grad_norm": 0.22985824942588806, + "learning_rate": 0.00019022404745020163, + "loss": 0.8991, + "step": 75 + }, + { + "epoch": 0.6495726495726496, + "grad_norm": 0.19453634321689606, + "learning_rate": 0.00018992612825027976, + "loss": 0.9837, + "step": 76 + }, + { + "epoch": 0.6581196581196581, + "grad_norm": 0.2547195851802826, + "learning_rate": 0.0001896239779533575, + "loss": 1.1035, + "step": 77 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.20812910795211792, + "learning_rate": 0.00018931761077585035, + "loss": 0.8916, + "step": 78 + }, + { + "epoch": 0.6752136752136753, + "grad_norm": 0.2176084816455841, + "learning_rate": 0.00018900704113258165, + "loss": 0.8826, + "step": 79 + }, + { + "epoch": 0.6837606837606838, + "grad_norm": 0.2221064418554306, + "learning_rate": 0.00018869228363610404, + "loss": 0.9069, + "step": 80 + }, + { + "epoch": 0.6923076923076923, + "grad_norm": 0.2675364911556244, + "learning_rate": 0.00018837335309601213, + "loss": 1.035, + "step": 81 + }, + { + "epoch": 0.7008547008547008, + "grad_norm": 0.1994653195142746, + "learning_rate": 0.00018805026451824546, + "loss": 1.5854, + "step": 82 + }, + { + "epoch": 0.7094017094017094, + "grad_norm": 0.20346811413764954, + "learning_rate": 0.00018772303310438275, + "loss": 1.4788, + "step": 83 + }, + { + "epoch": 0.717948717948718, + "grad_norm": 0.22119802236557007, + "learning_rate": 0.00018739167425092644, + "loss": 1.4946, + "step": 84 + }, + { + "epoch": 0.7264957264957265, + "grad_norm": 0.2174052894115448, + "learning_rate": 0.00018705620354857833, + "loss": 0.8667, + "step": 85 + }, + { + "epoch": 0.7350427350427351, + "grad_norm": 0.2322807013988495, + "learning_rate": 0.00018671663678150607, + "loss": 0.861, + "step": 86 + }, + { + "epoch": 0.7435897435897436, + "grad_norm": 0.22151263058185577, + "learning_rate": 0.0001863729899266004, + "loss": 0.8966, + "step": 87 + }, + { + "epoch": 0.7521367521367521, + "grad_norm": 0.243766650557518, + "learning_rate": 0.0001860252791527236, + "loss": 1.2998, + "step": 88 + }, + { + "epoch": 0.7606837606837606, + "grad_norm": 0.19212521612644196, + "learning_rate": 0.00018567352081994852, + "loss": 1.5215, + "step": 89 + }, + { + "epoch": 0.7692307692307693, + "grad_norm": 0.20964723825454712, + "learning_rate": 0.00018531773147878895, + "loss": 1.4717, + "step": 90 + }, + { + "epoch": 0.7777777777777778, + "grad_norm": 0.24561531841754913, + "learning_rate": 0.0001849579278694209, + "loss": 0.9569, + "step": 91 + }, + { + "epoch": 0.7863247863247863, + "grad_norm": 0.23924781382083893, + "learning_rate": 0.00018459412692089494, + "loss": 0.9441, + "step": 92 + }, + { + "epoch": 0.7948717948717948, + "grad_norm": 0.2302614450454712, + "learning_rate": 0.0001842263457503397, + "loss": 0.8417, + "step": 93 + }, + { + "epoch": 0.8034188034188035, + "grad_norm": 0.24661926925182343, + "learning_rate": 0.00018385460166215638, + "loss": 1.1297, + "step": 94 + }, + { + "epoch": 0.811965811965812, + "grad_norm": 0.24925513565540314, + "learning_rate": 0.00018347891214720477, + "loss": 0.8999, + "step": 95 + }, + { + "epoch": 0.8205128205128205, + "grad_norm": 0.19934344291687012, + "learning_rate": 0.00018309929488198012, + "loss": 1.4818, + "step": 96 + }, + { + "epoch": 0.8290598290598291, + "grad_norm": 0.24845215678215027, + "learning_rate": 0.00018271576772778154, + "loss": 0.9454, + "step": 97 + }, + { + "epoch": 0.8376068376068376, + "grad_norm": 0.22845034301280975, + "learning_rate": 0.00018232834872987147, + "loss": 1.5063, + "step": 98 + }, + { + "epoch": 0.8461538461538461, + "grad_norm": 0.2563302516937256, + "learning_rate": 0.00018193705611662696, + "loss": 0.9946, + "step": 99 + }, + { + "epoch": 0.8547008547008547, + "grad_norm": 0.30030304193496704, + "learning_rate": 0.0001815419082986815, + "loss": 1.0936, + "step": 100 + }, + { + "epoch": 0.8632478632478633, + "grad_norm": 0.22599591314792633, + "learning_rate": 0.00018114292386805936, + "loss": 1.346, + "step": 101 + }, + { + "epoch": 0.8717948717948718, + "grad_norm": 0.20411820709705353, + "learning_rate": 0.00018074012159730032, + "loss": 1.5147, + "step": 102 + }, + { + "epoch": 0.8803418803418803, + "grad_norm": 0.20635190606117249, + "learning_rate": 0.00018033352043857675, + "loss": 1.1425, + "step": 103 + }, + { + "epoch": 0.8888888888888888, + "grad_norm": 0.22327086329460144, + "learning_rate": 0.00017992313952280172, + "loss": 1.4435, + "step": 104 + }, + { + "epoch": 0.8974358974358975, + "grad_norm": 0.2183496206998825, + "learning_rate": 0.00017950899815872892, + "loss": 1.5659, + "step": 105 + }, + { + "epoch": 0.905982905982906, + "grad_norm": 0.31636252999305725, + "learning_rate": 0.00017909111583204422, + "loss": 1.4703, + "step": 106 + }, + { + "epoch": 0.9145299145299145, + "grad_norm": 0.3305496275424957, + "learning_rate": 0.0001786695122044487, + "loss": 1.0904, + "step": 107 + }, + { + "epoch": 0.9230769230769231, + "grad_norm": 0.22857435047626495, + "learning_rate": 0.0001782442071127338, + "loss": 1.3801, + "step": 108 + }, + { + "epoch": 0.9316239316239316, + "grad_norm": 0.31968221068382263, + "learning_rate": 0.0001778152205678477, + "loss": 1.4907, + "step": 109 + }, + { + "epoch": 0.9401709401709402, + "grad_norm": 0.27950960397720337, + "learning_rate": 0.00017738257275395404, + "loss": 1.0864, + "step": 110 + }, + { + "epoch": 0.9487179487179487, + "grad_norm": 0.2740281820297241, + "learning_rate": 0.00017694628402748202, + "loss": 0.9241, + "step": 111 + }, + { + "epoch": 0.9572649572649573, + "grad_norm": 0.26951318979263306, + "learning_rate": 0.0001765063749161688, + "loss": 0.9894, + "step": 112 + }, + { + "epoch": 0.9658119658119658, + "grad_norm": 0.2811899781227112, + "learning_rate": 0.00017606286611809353, + "loss": 0.9659, + "step": 113 + }, + { + "epoch": 0.9743589743589743, + "grad_norm": 0.23854824900627136, + "learning_rate": 0.00017561577850070355, + "loss": 1.0623, + "step": 114 + }, + { + "epoch": 0.9829059829059829, + "grad_norm": 0.21959957480430603, + "learning_rate": 0.00017516513309983253, + "loss": 0.8671, + "step": 115 + }, + { + "epoch": 0.9914529914529915, + "grad_norm": 0.3096697926521301, + "learning_rate": 0.00017471095111871074, + "loss": 1.0756, + "step": 116 + }, + { + "epoch": 1.0, + "grad_norm": 0.23363932967185974, + "learning_rate": 0.0001742532539269674, + "loss": 0.8988, + "step": 117 + }, + { + "epoch": 1.0085470085470085, + "grad_norm": 0.23965218663215637, + "learning_rate": 0.00017379206305962526, + "loss": 0.7737, + "step": 118 + }, + { + "epoch": 1.017094017094017, + "grad_norm": 0.24553611874580383, + "learning_rate": 0.00017332740021608722, + "loss": 0.7793, + "step": 119 + }, + { + "epoch": 1.0256410256410255, + "grad_norm": 0.267673522233963, + "learning_rate": 0.00017285928725911562, + "loss": 0.8077, + "step": 120 + }, + { + "epoch": 1.0341880341880343, + "grad_norm": 0.3069080114364624, + "learning_rate": 0.00017238774621380337, + "loss": 0.8226, + "step": 121 + }, + { + "epoch": 1.0427350427350428, + "grad_norm": 0.26568329334259033, + "learning_rate": 0.00017191279926653761, + "loss": 1.5833, + "step": 122 + }, + { + "epoch": 1.0512820512820513, + "grad_norm": 0.2673753499984741, + "learning_rate": 0.00017143446876395602, + "loss": 1.3896, + "step": 123 + }, + { + "epoch": 1.0598290598290598, + "grad_norm": 0.23525093495845795, + "learning_rate": 0.00017095277721189528, + "loss": 1.3125, + "step": 124 + }, + { + "epoch": 1.0683760683760684, + "grad_norm": 0.3066873550415039, + "learning_rate": 0.00017046774727433222, + "loss": 0.8894, + "step": 125 + }, + { + "epoch": 1.0769230769230769, + "grad_norm": 0.27280548214912415, + "learning_rate": 0.00016997940177231722, + "loss": 0.7649, + "step": 126 + }, + { + "epoch": 1.0854700854700854, + "grad_norm": 0.23357781767845154, + "learning_rate": 0.00016948776368290084, + "loss": 1.4143, + "step": 127 + }, + { + "epoch": 1.0940170940170941, + "grad_norm": 0.2928774356842041, + "learning_rate": 0.00016899285613805246, + "loss": 0.6522, + "step": 128 + }, + { + "epoch": 1.1025641025641026, + "grad_norm": 0.33789336681365967, + "learning_rate": 0.00016849470242357196, + "loss": 0.7737, + "step": 129 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 0.3078365921974182, + "learning_rate": 0.00016799332597799413, + "loss": 0.8068, + "step": 130 + }, + { + "epoch": 1.1196581196581197, + "grad_norm": 0.3175398111343384, + "learning_rate": 0.00016748875039148593, + "loss": 1.223, + "step": 131 + }, + { + "epoch": 1.1282051282051282, + "grad_norm": 0.27531448006629944, + "learning_rate": 0.0001669809994047364, + "loss": 1.3081, + "step": 132 + }, + { + "epoch": 1.1367521367521367, + "grad_norm": 0.34105026721954346, + "learning_rate": 0.0001664700969078398, + "loss": 0.9031, + "step": 133 + }, + { + "epoch": 1.1452991452991452, + "grad_norm": 0.25465068221092224, + "learning_rate": 0.00016595606693917142, + "loss": 1.3237, + "step": 134 + }, + { + "epoch": 1.1538461538461537, + "grad_norm": 0.2841501533985138, + "learning_rate": 0.00016543893368425666, + "loss": 0.7393, + "step": 135 + }, + { + "epoch": 1.1623931623931625, + "grad_norm": 0.3230992257595062, + "learning_rate": 0.00016491872147463306, + "loss": 0.7437, + "step": 136 + }, + { + "epoch": 1.170940170940171, + "grad_norm": 0.25824740529060364, + "learning_rate": 0.00016439545478670543, + "loss": 1.883, + "step": 137 + }, + { + "epoch": 1.1794871794871795, + "grad_norm": 0.31415536999702454, + "learning_rate": 0.00016386915824059427, + "loss": 0.703, + "step": 138 + }, + { + "epoch": 1.188034188034188, + "grad_norm": 0.26885557174682617, + "learning_rate": 0.00016333985659897735, + "loss": 0.6592, + "step": 139 + }, + { + "epoch": 1.1965811965811965, + "grad_norm": 0.4018881618976593, + "learning_rate": 0.00016280757476592466, + "loss": 0.7733, + "step": 140 + }, + { + "epoch": 1.205128205128205, + "grad_norm": 0.3181138038635254, + "learning_rate": 0.0001622723377857265, + "loss": 0.7577, + "step": 141 + }, + { + "epoch": 1.2136752136752136, + "grad_norm": 0.2720906436443329, + "learning_rate": 0.00016173417084171536, + "loss": 1.3883, + "step": 142 + }, + { + "epoch": 1.2222222222222223, + "grad_norm": 0.34472835063934326, + "learning_rate": 0.00016119309925508078, + "loss": 0.7757, + "step": 143 + }, + { + "epoch": 1.2307692307692308, + "grad_norm": 0.40166720747947693, + "learning_rate": 0.0001606491484836782, + "loss": 0.79, + "step": 144 + }, + { + "epoch": 1.2393162393162394, + "grad_norm": 0.38203030824661255, + "learning_rate": 0.00016010234412083086, + "loss": 0.8184, + "step": 145 + }, + { + "epoch": 1.2478632478632479, + "grad_norm": 0.3825059235095978, + "learning_rate": 0.00015955271189412598, + "loss": 0.9065, + "step": 146 + }, + { + "epoch": 1.2564102564102564, + "grad_norm": 0.403533935546875, + "learning_rate": 0.00015900027766420393, + "loss": 0.7605, + "step": 147 + }, + { + "epoch": 1.264957264957265, + "grad_norm": 0.3657178282737732, + "learning_rate": 0.00015844506742354164, + "loss": 0.8265, + "step": 148 + }, + { + "epoch": 1.2735042735042734, + "grad_norm": 0.2825511693954468, + "learning_rate": 0.00015788710729522953, + "loss": 1.166, + "step": 149 + }, + { + "epoch": 1.282051282051282, + "grad_norm": 0.4000828266143799, + "learning_rate": 0.00015732642353174259, + "loss": 1.2792, + "step": 150 + }, + { + "epoch": 1.2905982905982907, + "grad_norm": 0.3135271668434143, + "learning_rate": 0.0001567630425137049, + "loss": 0.6227, + "step": 151 + }, + { + "epoch": 1.2991452991452992, + "grad_norm": 0.3828388452529907, + "learning_rate": 0.00015619699074864864, + "loss": 0.6989, + "step": 152 + }, + { + "epoch": 1.3076923076923077, + "grad_norm": 0.45689550042152405, + "learning_rate": 0.00015562829486976673, + "loss": 0.9088, + "step": 153 + }, + { + "epoch": 1.3162393162393162, + "grad_norm": 0.36523374915122986, + "learning_rate": 0.00015505698163465986, + "loss": 0.9859, + "step": 154 + }, + { + "epoch": 1.3247863247863247, + "grad_norm": 0.4206138551235199, + "learning_rate": 0.00015448307792407734, + "loss": 0.7771, + "step": 155 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.3400786817073822, + "learning_rate": 0.00015390661074065256, + "loss": 0.772, + "step": 156 + }, + { + "epoch": 1.341880341880342, + "grad_norm": 0.334692120552063, + "learning_rate": 0.00015332760720763232, + "loss": 1.3839, + "step": 157 + }, + { + "epoch": 1.3504273504273505, + "grad_norm": 0.4513654112815857, + "learning_rate": 0.00015274609456760073, + "loss": 0.8578, + "step": 158 + }, + { + "epoch": 1.358974358974359, + "grad_norm": 0.4215463399887085, + "learning_rate": 0.00015216210018119733, + "loss": 0.9154, + "step": 159 + }, + { + "epoch": 1.3675213675213675, + "grad_norm": 0.38081440329551697, + "learning_rate": 0.00015157565152583002, + "loss": 0.6723, + "step": 160 + }, + { + "epoch": 1.376068376068376, + "grad_norm": 0.38604873418807983, + "learning_rate": 0.0001509867761943818, + "loss": 0.9546, + "step": 161 + }, + { + "epoch": 1.3846153846153846, + "grad_norm": 0.39846640825271606, + "learning_rate": 0.00015039550189391298, + "loss": 0.7379, + "step": 162 + }, + { + "epoch": 1.393162393162393, + "grad_norm": 0.3619799315929413, + "learning_rate": 0.0001498018564443571, + "loss": 1.12, + "step": 163 + }, + { + "epoch": 1.4017094017094016, + "grad_norm": 0.4657539427280426, + "learning_rate": 0.0001492058677772123, + "loss": 1.0395, + "step": 164 + }, + { + "epoch": 1.4102564102564101, + "grad_norm": 0.3850860893726349, + "learning_rate": 0.000148607563934227, + "loss": 0.7949, + "step": 165 + }, + { + "epoch": 1.4188034188034189, + "grad_norm": 0.30473998188972473, + "learning_rate": 0.00014800697306608044, + "loss": 0.6285, + "step": 166 + }, + { + "epoch": 1.4273504273504274, + "grad_norm": 0.36891016364097595, + "learning_rate": 0.00014740412343105828, + "loss": 0.9947, + "step": 167 + }, + { + "epoch": 1.435897435897436, + "grad_norm": 0.3746401071548462, + "learning_rate": 0.00014679904339372302, + "loss": 0.7204, + "step": 168 + }, + { + "epoch": 1.4444444444444444, + "grad_norm": 0.4085482060909271, + "learning_rate": 0.00014619176142357935, + "loss": 0.7145, + "step": 169 + }, + { + "epoch": 1.452991452991453, + "grad_norm": 0.40742969512939453, + "learning_rate": 0.0001455823060937347, + "loss": 0.8273, + "step": 170 + }, + { + "epoch": 1.4615384615384617, + "grad_norm": 0.3882700502872467, + "learning_rate": 0.00014497070607955476, + "loss": 0.7025, + "step": 171 + }, + { + "epoch": 1.4700854700854702, + "grad_norm": 0.43999457359313965, + "learning_rate": 0.00014435699015731448, + "loss": 0.7473, + "step": 172 + }, + { + "epoch": 1.4786324786324787, + "grad_norm": 0.3841669261455536, + "learning_rate": 0.00014374118720284388, + "loss": 0.8794, + "step": 173 + }, + { + "epoch": 1.4871794871794872, + "grad_norm": 0.3169039189815521, + "learning_rate": 0.00014312332619016965, + "loss": 1.007, + "step": 174 + }, + { + "epoch": 1.4957264957264957, + "grad_norm": 0.44292953610420227, + "learning_rate": 0.0001425034361901516, + "loss": 0.846, + "step": 175 + }, + { + "epoch": 1.5042735042735043, + "grad_norm": 0.3945798873901367, + "learning_rate": 0.00014188154636911524, + "loss": 1.3956, + "step": 176 + }, + { + "epoch": 1.5128205128205128, + "grad_norm": 0.4760408103466034, + "learning_rate": 0.0001412576859874791, + "loss": 0.7811, + "step": 177 + }, + { + "epoch": 1.5213675213675213, + "grad_norm": 0.401869535446167, + "learning_rate": 0.00014063188439837832, + "loss": 0.6903, + "step": 178 + }, + { + "epoch": 1.5299145299145298, + "grad_norm": 0.3994334042072296, + "learning_rate": 0.0001400041710462833, + "loss": 0.688, + "step": 179 + }, + { + "epoch": 1.5384615384615383, + "grad_norm": 0.41962575912475586, + "learning_rate": 0.0001393745754656146, + "loss": 0.7697, + "step": 180 + }, + { + "epoch": 1.547008547008547, + "grad_norm": 0.36107930541038513, + "learning_rate": 0.00013874312727935292, + "loss": 0.715, + "step": 181 + }, + { + "epoch": 1.5555555555555556, + "grad_norm": 0.3828651010990143, + "learning_rate": 0.00013810985619764572, + "loss": 1.3298, + "step": 182 + }, + { + "epoch": 1.564102564102564, + "grad_norm": 0.3839617967605591, + "learning_rate": 0.00013747479201640914, + "loss": 0.6851, + "step": 183 + }, + { + "epoch": 1.5726495726495726, + "grad_norm": 0.4327555298805237, + "learning_rate": 0.00013683796461592604, + "loss": 0.7906, + "step": 184 + }, + { + "epoch": 1.5811965811965814, + "grad_norm": 0.3910170793533325, + "learning_rate": 0.00013619940395944027, + "loss": 0.7832, + "step": 185 + }, + { + "epoch": 1.5897435897435899, + "grad_norm": 0.4029540419578552, + "learning_rate": 0.00013555914009174663, + "loss": 0.7723, + "step": 186 + }, + { + "epoch": 1.5982905982905984, + "grad_norm": 0.3986589014530182, + "learning_rate": 0.00013491720313777756, + "loss": 1.1658, + "step": 187 + }, + { + "epoch": 1.606837606837607, + "grad_norm": 0.3962538242340088, + "learning_rate": 0.00013427362330118543, + "loss": 0.7481, + "step": 188 + }, + { + "epoch": 1.6153846153846154, + "grad_norm": 0.4297255277633667, + "learning_rate": 0.0001336284308629216, + "loss": 0.9531, + "step": 189 + }, + { + "epoch": 1.623931623931624, + "grad_norm": 0.3742808699607849, + "learning_rate": 0.00013298165617981172, + "loss": 0.9516, + "step": 190 + }, + { + "epoch": 1.6324786324786325, + "grad_norm": 0.44721004366874695, + "learning_rate": 0.00013233332968312715, + "loss": 1.075, + "step": 191 + }, + { + "epoch": 1.641025641025641, + "grad_norm": 0.41275331377983093, + "learning_rate": 0.0001316834818771535, + "loss": 0.8295, + "step": 192 + }, + { + "epoch": 1.6495726495726495, + "grad_norm": 0.46620428562164307, + "learning_rate": 0.00013103214333775521, + "loss": 0.8314, + "step": 193 + }, + { + "epoch": 1.658119658119658, + "grad_norm": 0.4467974901199341, + "learning_rate": 0.00013037934471093682, + "loss": 0.7321, + "step": 194 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.42806383967399597, + "learning_rate": 0.00012972511671140125, + "loss": 0.7144, + "step": 195 + }, + { + "epoch": 1.6752136752136753, + "grad_norm": 0.3721958100795746, + "learning_rate": 0.00012906949012110456, + "loss": 1.0117, + "step": 196 + }, + { + "epoch": 1.6837606837606838, + "grad_norm": 0.46833130717277527, + "learning_rate": 0.00012841249578780757, + "loss": 0.9599, + "step": 197 + }, + { + "epoch": 1.6923076923076923, + "grad_norm": 0.3547254502773285, + "learning_rate": 0.00012775416462362457, + "loss": 0.8255, + "step": 198 + }, + { + "epoch": 1.7008547008547008, + "grad_norm": 0.36470168828964233, + "learning_rate": 0.00012709452760356884, + "loss": 1.3796, + "step": 199 + }, + { + "epoch": 1.7094017094017095, + "grad_norm": 0.4088481068611145, + "learning_rate": 0.00012643361576409516, + "loss": 0.818, + "step": 200 + }, + { + "epoch": 1.717948717948718, + "grad_norm": 0.43268319964408875, + "learning_rate": 0.00012577146020163968, + "loss": 0.8157, + "step": 201 + }, + { + "epoch": 1.7264957264957266, + "grad_norm": 0.4660526216030121, + "learning_rate": 0.00012510809207115666, + "loss": 0.775, + "step": 202 + }, + { + "epoch": 1.735042735042735, + "grad_norm": 0.41217854619026184, + "learning_rate": 0.00012444354258465268, + "loss": 0.7172, + "step": 203 + }, + { + "epoch": 1.7435897435897436, + "grad_norm": 0.4177812933921814, + "learning_rate": 0.00012377784300971807, + "loss": 1.1308, + "step": 204 + }, + { + "epoch": 1.7521367521367521, + "grad_norm": 0.3943150043487549, + "learning_rate": 0.0001231110246680558, + "loss": 1.4001, + "step": 205 + }, + { + "epoch": 1.7606837606837606, + "grad_norm": 0.48257848620414734, + "learning_rate": 0.00012244311893400763, + "loss": 0.9118, + "step": 206 + }, + { + "epoch": 1.7692307692307692, + "grad_norm": 0.4754193127155304, + "learning_rate": 0.00012177415723307808, + "loss": 0.825, + "step": 207 + }, + { + "epoch": 1.7777777777777777, + "grad_norm": 0.3812815546989441, + "learning_rate": 0.00012110417104045575, + "loss": 0.6433, + "step": 208 + }, + { + "epoch": 1.7863247863247862, + "grad_norm": 0.3967946469783783, + "learning_rate": 0.00012043319187953241, + "loss": 0.8549, + "step": 209 + }, + { + "epoch": 1.7948717948717947, + "grad_norm": 0.4312019348144531, + "learning_rate": 0.00011976125132041974, + "loss": 0.8387, + "step": 210 + }, + { + "epoch": 1.8034188034188035, + "grad_norm": 0.4585026204586029, + "learning_rate": 0.00011908838097846404, + "loss": 0.9471, + "step": 211 + }, + { + "epoch": 1.811965811965812, + "grad_norm": 0.4149639904499054, + "learning_rate": 0.00011841461251275867, + "loss": 1.0415, + "step": 212 + }, + { + "epoch": 1.8205128205128205, + "grad_norm": 0.48069992661476135, + "learning_rate": 0.00011773997762465429, + "loss": 0.7534, + "step": 213 + }, + { + "epoch": 1.8290598290598292, + "grad_norm": 0.3820441961288452, + "learning_rate": 0.0001170645080562676, + "loss": 0.8292, + "step": 214 + }, + { + "epoch": 1.8376068376068377, + "grad_norm": 0.3951680660247803, + "learning_rate": 0.00011638823558898762, + "loss": 0.6923, + "step": 215 + }, + { + "epoch": 1.8461538461538463, + "grad_norm": 0.40777531266212463, + "learning_rate": 0.00011571119204198037, + "loss": 0.7335, + "step": 216 + }, + { + "epoch": 1.8547008547008548, + "grad_norm": 0.3792341649532318, + "learning_rate": 0.00011503340927069189, + "loss": 0.8608, + "step": 217 + }, + { + "epoch": 1.8632478632478633, + "grad_norm": 0.36157581210136414, + "learning_rate": 0.00011435491916534919, + "loss": 0.7314, + "step": 218 + }, + { + "epoch": 1.8717948717948718, + "grad_norm": 0.41833943128585815, + "learning_rate": 0.00011367575364946006, + "loss": 0.7662, + "step": 219 + }, + { + "epoch": 1.8803418803418803, + "grad_norm": 0.45951926708221436, + "learning_rate": 0.00011299594467831078, + "loss": 0.6988, + "step": 220 + }, + { + "epoch": 1.8888888888888888, + "grad_norm": 0.4588642120361328, + "learning_rate": 0.00011231552423746283, + "loss": 0.8544, + "step": 221 + }, + { + "epoch": 1.8974358974358974, + "grad_norm": 0.3614063560962677, + "learning_rate": 0.00011163452434124773, + "loss": 0.728, + "step": 222 + }, + { + "epoch": 1.9059829059829059, + "grad_norm": 0.4452153742313385, + "learning_rate": 0.00011095297703126093, + "loss": 0.7399, + "step": 223 + }, + { + "epoch": 1.9145299145299144, + "grad_norm": 0.42948612570762634, + "learning_rate": 0.00011027091437485404, + "loss": 0.9105, + "step": 224 + }, + { + "epoch": 1.9230769230769231, + "grad_norm": 0.37950897216796875, + "learning_rate": 0.00010958836846362621, + "loss": 0.9612, + "step": 225 + }, + { + "epoch": 1.9316239316239316, + "grad_norm": 0.4386560916900635, + "learning_rate": 0.00010890537141191417, + "loss": 0.683, + "step": 226 + }, + { + "epoch": 1.9401709401709402, + "grad_norm": 0.4166669547557831, + "learning_rate": 0.00010822195535528106, + "loss": 1.1851, + "step": 227 + }, + { + "epoch": 1.9487179487179487, + "grad_norm": 0.4029337465763092, + "learning_rate": 0.00010753815244900458, + "loss": 0.6721, + "step": 228 + }, + { + "epoch": 1.9572649572649574, + "grad_norm": 0.47789204120635986, + "learning_rate": 0.00010685399486656406, + "loss": 0.8654, + "step": 229 + }, + { + "epoch": 1.965811965811966, + "grad_norm": 0.4141186475753784, + "learning_rate": 0.00010616951479812658, + "loss": 0.7619, + "step": 230 + }, + { + "epoch": 1.9743589743589745, + "grad_norm": 0.4745655655860901, + "learning_rate": 0.00010548474444903247, + "loss": 0.698, + "step": 231 + }, + { + "epoch": 1.982905982905983, + "grad_norm": 0.4075687825679779, + "learning_rate": 0.00010479971603828, + "loss": 0.7387, + "step": 232 + }, + { + "epoch": 1.9914529914529915, + "grad_norm": 0.37726572155952454, + "learning_rate": 0.00010411446179700943, + "loss": 0.714, + "step": 233 + }, + { + "epoch": 2.0, + "grad_norm": 0.5989537239074707, + "learning_rate": 0.00010342901396698659, + "loss": 0.7816, + "step": 234 + }, + { + "epoch": 2.0085470085470085, + "grad_norm": 0.3381822109222412, + "learning_rate": 0.00010274340479908568, + "loss": 0.443, + "step": 235 + }, + { + "epoch": 2.017094017094017, + "grad_norm": 0.375904381275177, + "learning_rate": 0.00010205766655177215, + "loss": 0.4966, + "step": 236 + }, + { + "epoch": 2.0256410256410255, + "grad_norm": 0.3564665615558624, + "learning_rate": 0.00010137183148958463, + "loss": 0.6866, + "step": 237 + }, + { + "epoch": 2.034188034188034, + "grad_norm": 0.4133633077144623, + "learning_rate": 0.00010068593188161697, + "loss": 0.5057, + "step": 238 + }, + { + "epoch": 2.0427350427350426, + "grad_norm": 0.4830314517021179, + "learning_rate": 0.0001, + "loss": 0.6148, + "step": 239 + }, + { + "epoch": 2.051282051282051, + "grad_norm": 0.4566143751144409, + "learning_rate": 9.931406811838308e-05, + "loss": 0.5323, + "step": 240 + }, + { + "epoch": 2.0598290598290596, + "grad_norm": 0.4714205265045166, + "learning_rate": 9.862816851041541e-05, + "loss": 0.4689, + "step": 241 + }, + { + "epoch": 2.0683760683760686, + "grad_norm": 0.4094763696193695, + "learning_rate": 9.79423334482279e-05, + "loss": 0.6019, + "step": 242 + }, + { + "epoch": 2.076923076923077, + "grad_norm": 0.5059089660644531, + "learning_rate": 9.725659520091433e-05, + "loss": 0.5675, + "step": 243 + }, + { + "epoch": 2.0854700854700856, + "grad_norm": 0.49986734986305237, + "learning_rate": 9.657098603301346e-05, + "loss": 0.6499, + "step": 244 + }, + { + "epoch": 2.094017094017094, + "grad_norm": 0.42914658784866333, + "learning_rate": 9.588553820299056e-05, + "loss": 0.513, + "step": 245 + }, + { + "epoch": 2.1025641025641026, + "grad_norm": 0.5760869979858398, + "learning_rate": 9.520028396172003e-05, + "loss": 0.8912, + "step": 246 + }, + { + "epoch": 2.111111111111111, + "grad_norm": 0.5276662707328796, + "learning_rate": 9.451525555096753e-05, + "loss": 0.5903, + "step": 247 + }, + { + "epoch": 2.1196581196581197, + "grad_norm": 0.5043647289276123, + "learning_rate": 9.383048520187344e-05, + "loss": 0.5089, + "step": 248 + }, + { + "epoch": 2.128205128205128, + "grad_norm": 0.522574782371521, + "learning_rate": 9.314600513343595e-05, + "loss": 0.5059, + "step": 249 + }, + { + "epoch": 2.1367521367521367, + "grad_norm": 0.48663464188575745, + "learning_rate": 9.246184755099545e-05, + "loss": 0.9519, + "step": 250 + }, + { + "epoch": 2.1452991452991452, + "grad_norm": 0.5056342482566833, + "learning_rate": 9.177804464471898e-05, + "loss": 1.1279, + "step": 251 + }, + { + "epoch": 2.1538461538461537, + "grad_norm": 0.5033504366874695, + "learning_rate": 9.109462858808586e-05, + "loss": 1.1843, + "step": 252 + }, + { + "epoch": 2.1623931623931623, + "grad_norm": 0.48481982946395874, + "learning_rate": 9.041163153637381e-05, + "loss": 0.5202, + "step": 253 + }, + { + "epoch": 2.1709401709401708, + "grad_norm": 0.5677529573440552, + "learning_rate": 8.972908562514598e-05, + "loss": 0.5685, + "step": 254 + }, + { + "epoch": 2.1794871794871793, + "grad_norm": 0.6009398102760315, + "learning_rate": 8.904702296873912e-05, + "loss": 0.6472, + "step": 255 + }, + { + "epoch": 2.1880341880341883, + "grad_norm": 0.5119011998176575, + "learning_rate": 8.836547565875227e-05, + "loss": 0.501, + "step": 256 + }, + { + "epoch": 2.1965811965811968, + "grad_norm": 0.44192251563072205, + "learning_rate": 8.76844757625372e-05, + "loss": 1.1073, + "step": 257 + }, + { + "epoch": 2.2051282051282053, + "grad_norm": 0.5733199715614319, + "learning_rate": 8.70040553216892e-05, + "loss": 0.5188, + "step": 258 + }, + { + "epoch": 2.213675213675214, + "grad_norm": 0.5789536237716675, + "learning_rate": 8.632424635053997e-05, + "loss": 0.719, + "step": 259 + }, + { + "epoch": 2.2222222222222223, + "grad_norm": 0.4420778453350067, + "learning_rate": 8.564508083465079e-05, + "loss": 0.4935, + "step": 260 + }, + { + "epoch": 2.230769230769231, + "grad_norm": 0.4915638267993927, + "learning_rate": 8.496659072930813e-05, + "loss": 0.5342, + "step": 261 + }, + { + "epoch": 2.2393162393162394, + "grad_norm": 0.4589202404022217, + "learning_rate": 8.428880795801965e-05, + "loss": 0.4839, + "step": 262 + }, + { + "epoch": 2.247863247863248, + "grad_norm": 0.5273900628089905, + "learning_rate": 8.36117644110124e-05, + "loss": 0.8426, + "step": 263 + }, + { + "epoch": 2.2564102564102564, + "grad_norm": 0.5588923096656799, + "learning_rate": 8.293549194373243e-05, + "loss": 0.5051, + "step": 264 + }, + { + "epoch": 2.264957264957265, + "grad_norm": 0.4949032664299011, + "learning_rate": 8.226002237534572e-05, + "loss": 0.4751, + "step": 265 + }, + { + "epoch": 2.2735042735042734, + "grad_norm": 0.6772957444190979, + "learning_rate": 8.158538748724139e-05, + "loss": 0.9695, + "step": 266 + }, + { + "epoch": 2.282051282051282, + "grad_norm": 0.5875369906425476, + "learning_rate": 8.091161902153595e-05, + "loss": 0.5566, + "step": 267 + }, + { + "epoch": 2.2905982905982905, + "grad_norm": 0.4558923840522766, + "learning_rate": 8.023874867958027e-05, + "loss": 0.8852, + "step": 268 + }, + { + "epoch": 2.299145299145299, + "grad_norm": 0.5420984625816345, + "learning_rate": 7.95668081204676e-05, + "loss": 0.8007, + "step": 269 + }, + { + "epoch": 2.3076923076923075, + "grad_norm": 0.5497881770133972, + "learning_rate": 7.889582895954427e-05, + "loss": 0.5261, + "step": 270 + }, + { + "epoch": 2.316239316239316, + "grad_norm": 0.5697259306907654, + "learning_rate": 7.822584276692191e-05, + "loss": 0.4692, + "step": 271 + }, + { + "epoch": 2.324786324786325, + "grad_norm": 0.5963535904884338, + "learning_rate": 7.755688106599241e-05, + "loss": 0.5553, + "step": 272 + }, + { + "epoch": 2.3333333333333335, + "grad_norm": 0.5704771280288696, + "learning_rate": 7.688897533194424e-05, + "loss": 0.6445, + "step": 273 + }, + { + "epoch": 2.341880341880342, + "grad_norm": 0.6348976492881775, + "learning_rate": 7.622215699028196e-05, + "loss": 0.5257, + "step": 274 + }, + { + "epoch": 2.3504273504273505, + "grad_norm": 0.4737604260444641, + "learning_rate": 7.555645741534736e-05, + "loss": 0.4532, + "step": 275 + }, + { + "epoch": 2.358974358974359, + "grad_norm": 0.6055320501327515, + "learning_rate": 7.489190792884338e-05, + "loss": 1.0912, + "step": 276 + }, + { + "epoch": 2.3675213675213675, + "grad_norm": 0.6330887079238892, + "learning_rate": 7.422853979836034e-05, + "loss": 0.8996, + "step": 277 + }, + { + "epoch": 2.376068376068376, + "grad_norm": 0.5483549237251282, + "learning_rate": 7.356638423590485e-05, + "loss": 0.6033, + "step": 278 + }, + { + "epoch": 2.3846153846153846, + "grad_norm": 0.5688058733940125, + "learning_rate": 7.290547239643117e-05, + "loss": 0.5904, + "step": 279 + }, + { + "epoch": 2.393162393162393, + "grad_norm": 0.49569448828697205, + "learning_rate": 7.224583537637544e-05, + "loss": 0.6198, + "step": 280 + }, + { + "epoch": 2.4017094017094016, + "grad_norm": 0.5610498189926147, + "learning_rate": 7.158750421219244e-05, + "loss": 1.2213, + "step": 281 + }, + { + "epoch": 2.41025641025641, + "grad_norm": 0.5684900283813477, + "learning_rate": 7.093050987889547e-05, + "loss": 0.5249, + "step": 282 + }, + { + "epoch": 2.4188034188034186, + "grad_norm": 0.5226355195045471, + "learning_rate": 7.027488328859876e-05, + "loss": 0.4525, + "step": 283 + }, + { + "epoch": 2.427350427350427, + "grad_norm": 0.4944767653942108, + "learning_rate": 6.96206552890632e-05, + "loss": 0.5517, + "step": 284 + }, + { + "epoch": 2.435897435897436, + "grad_norm": 0.5820432305335999, + "learning_rate": 6.896785666224481e-05, + "loss": 0.5575, + "step": 285 + }, + { + "epoch": 2.4444444444444446, + "grad_norm": 0.6503978967666626, + "learning_rate": 6.831651812284652e-05, + "loss": 0.5344, + "step": 286 + }, + { + "epoch": 2.452991452991453, + "grad_norm": 0.5511913299560547, + "learning_rate": 6.766667031687286e-05, + "loss": 0.6221, + "step": 287 + }, + { + "epoch": 2.4615384615384617, + "grad_norm": 0.5843252539634705, + "learning_rate": 6.701834382018832e-05, + "loss": 0.5421, + "step": 288 + }, + { + "epoch": 2.47008547008547, + "grad_norm": 0.5561351180076599, + "learning_rate": 6.637156913707839e-05, + "loss": 0.4725, + "step": 289 + }, + { + "epoch": 2.4786324786324787, + "grad_norm": 0.5449361205101013, + "learning_rate": 6.572637669881458e-05, + "loss": 0.5561, + "step": 290 + }, + { + "epoch": 2.4871794871794872, + "grad_norm": 0.5354922413825989, + "learning_rate": 6.508279686222243e-05, + "loss": 1.0458, + "step": 291 + }, + { + "epoch": 2.4957264957264957, + "grad_norm": 0.6082772612571716, + "learning_rate": 6.444085990825338e-05, + "loss": 0.6117, + "step": 292 + }, + { + "epoch": 2.5042735042735043, + "grad_norm": 0.5007249712944031, + "learning_rate": 6.380059604055974e-05, + "loss": 0.4964, + "step": 293 + }, + { + "epoch": 2.5128205128205128, + "grad_norm": 0.728626549243927, + "learning_rate": 6.316203538407397e-05, + "loss": 0.7009, + "step": 294 + }, + { + "epoch": 2.5213675213675213, + "grad_norm": 0.5644152760505676, + "learning_rate": 6.252520798359092e-05, + "loss": 0.5498, + "step": 295 + }, + { + "epoch": 2.52991452991453, + "grad_norm": 0.5440083742141724, + "learning_rate": 6.18901438023543e-05, + "loss": 0.4946, + "step": 296 + }, + { + "epoch": 2.5384615384615383, + "grad_norm": 0.5415129661560059, + "learning_rate": 6.125687272064713e-05, + "loss": 0.5534, + "step": 297 + }, + { + "epoch": 2.547008547008547, + "grad_norm": 0.457343727350235, + "learning_rate": 6.0625424534385425e-05, + "loss": 0.6737, + "step": 298 + }, + { + "epoch": 2.5555555555555554, + "grad_norm": 0.6592293977737427, + "learning_rate": 5.9995828953716695e-05, + "loss": 0.64, + "step": 299 + }, + { + "epoch": 2.564102564102564, + "grad_norm": 0.591465413570404, + "learning_rate": 5.936811560162169e-05, + "loss": 0.5807, + "step": 300 + }, + { + "epoch": 2.5726495726495724, + "grad_norm": 0.5375930666923523, + "learning_rate": 5.87423140125209e-05, + "loss": 0.4945, + "step": 301 + }, + { + "epoch": 2.5811965811965814, + "grad_norm": 0.5260182619094849, + "learning_rate": 5.811845363088477e-05, + "loss": 0.4258, + "step": 302 + }, + { + "epoch": 2.58974358974359, + "grad_norm": 0.6136443614959717, + "learning_rate": 5.749656380984844e-05, + "loss": 0.5744, + "step": 303 + }, + { + "epoch": 2.5982905982905984, + "grad_norm": 0.6215261220932007, + "learning_rate": 5.687667380983037e-05, + "loss": 0.4933, + "step": 304 + }, + { + "epoch": 2.606837606837607, + "grad_norm": 0.5154852867126465, + "learning_rate": 5.625881279715615e-05, + "loss": 0.4296, + "step": 305 + }, + { + "epoch": 2.6153846153846154, + "grad_norm": 0.5293765664100647, + "learning_rate": 5.5643009842685554e-05, + "loss": 1.0884, + "step": 306 + }, + { + "epoch": 2.623931623931624, + "grad_norm": 0.5633432269096375, + "learning_rate": 5.502929392044528e-05, + "loss": 0.5541, + "step": 307 + }, + { + "epoch": 2.6324786324786325, + "grad_norm": 0.590496301651001, + "learning_rate": 5.4417693906265365e-05, + "loss": 0.4662, + "step": 308 + }, + { + "epoch": 2.641025641025641, + "grad_norm": 0.6000109910964966, + "learning_rate": 5.380823857642069e-05, + "loss": 0.5581, + "step": 309 + }, + { + "epoch": 2.6495726495726495, + "grad_norm": 0.5975021719932556, + "learning_rate": 5.3200956606277006e-05, + "loss": 0.861, + "step": 310 + }, + { + "epoch": 2.658119658119658, + "grad_norm": 0.5424284934997559, + "learning_rate": 5.259587656894174e-05, + "loss": 0.5272, + "step": 311 + }, + { + "epoch": 2.6666666666666665, + "grad_norm": 0.6322450041770935, + "learning_rate": 5.199302693391959e-05, + "loss": 0.6545, + "step": 312 + }, + { + "epoch": 2.6752136752136755, + "grad_norm": 0.9423356652259827, + "learning_rate": 5.139243606577302e-05, + "loss": 0.8078, + "step": 313 + }, + { + "epoch": 2.683760683760684, + "grad_norm": 0.6575957536697388, + "learning_rate": 5.0794132222787707e-05, + "loss": 0.5547, + "step": 314 + }, + { + "epoch": 2.6923076923076925, + "grad_norm": 0.6143584251403809, + "learning_rate": 5.019814355564292e-05, + "loss": 0.5707, + "step": 315 + }, + { + "epoch": 2.700854700854701, + "grad_norm": 0.5541775822639465, + "learning_rate": 4.960449810608705e-05, + "loss": 0.7209, + "step": 316 + }, + { + "epoch": 2.7094017094017095, + "grad_norm": 0.5190094113349915, + "learning_rate": 4.90132238056182e-05, + "loss": 0.5075, + "step": 317 + }, + { + "epoch": 2.717948717948718, + "grad_norm": 0.5351387858390808, + "learning_rate": 4.8424348474170014e-05, + "loss": 1.1994, + "step": 318 + }, + { + "epoch": 2.7264957264957266, + "grad_norm": 0.64601731300354, + "learning_rate": 4.783789981880267e-05, + "loss": 0.5779, + "step": 319 + }, + { + "epoch": 2.735042735042735, + "grad_norm": 0.46943098306655884, + "learning_rate": 4.725390543239929e-05, + "loss": 0.4131, + "step": 320 + }, + { + "epoch": 2.7435897435897436, + "grad_norm": 0.5379695296287537, + "learning_rate": 4.667239279236768e-05, + "loss": 0.6601, + "step": 321 + }, + { + "epoch": 2.752136752136752, + "grad_norm": 0.599001407623291, + "learning_rate": 4.609338925934743e-05, + "loss": 0.5375, + "step": 322 + }, + { + "epoch": 2.7606837606837606, + "grad_norm": 0.5188902616500854, + "learning_rate": 4.551692207592265e-05, + "loss": 0.9628, + "step": 323 + }, + { + "epoch": 2.769230769230769, + "grad_norm": 0.5495883226394653, + "learning_rate": 4.494301836534016e-05, + "loss": 0.5334, + "step": 324 + }, + { + "epoch": 2.7777777777777777, + "grad_norm": 0.6632270216941833, + "learning_rate": 4.4371705130233275e-05, + "loss": 0.5572, + "step": 325 + }, + { + "epoch": 2.786324786324786, + "grad_norm": 0.5476614236831665, + "learning_rate": 4.380300925135138e-05, + "loss": 0.4915, + "step": 326 + }, + { + "epoch": 2.7948717948717947, + "grad_norm": 0.5509811043739319, + "learning_rate": 4.3236957486295115e-05, + "loss": 1.2116, + "step": 327 + }, + { + "epoch": 2.8034188034188032, + "grad_norm": 0.4459514617919922, + "learning_rate": 4.267357646825746e-05, + "loss": 1.3973, + "step": 328 + }, + { + "epoch": 2.8119658119658117, + "grad_norm": 0.5664827823638916, + "learning_rate": 4.211289270477047e-05, + "loss": 0.5076, + "step": 329 + }, + { + "epoch": 2.8205128205128203, + "grad_norm": 0.5930613875389099, + "learning_rate": 4.1554932576458415e-05, + "loss": 0.5522, + "step": 330 + }, + { + "epoch": 2.8290598290598292, + "grad_norm": 0.5950198769569397, + "learning_rate": 4.0999722335796075e-05, + "loss": 1.1402, + "step": 331 + }, + { + "epoch": 2.8376068376068377, + "grad_norm": 0.5899688601493835, + "learning_rate": 4.044728810587406e-05, + "loss": 0.5293, + "step": 332 + }, + { + "epoch": 2.8461538461538463, + "grad_norm": 0.6274430751800537, + "learning_rate": 3.989765587916914e-05, + "loss": 0.4995, + "step": 333 + }, + { + "epoch": 2.8547008547008548, + "grad_norm": 0.5911152958869934, + "learning_rate": 3.935085151632185e-05, + "loss": 0.6738, + "step": 334 + }, + { + "epoch": 2.8632478632478633, + "grad_norm": 0.5615319013595581, + "learning_rate": 3.8806900744919205e-05, + "loss": 0.3968, + "step": 335 + }, + { + "epoch": 2.871794871794872, + "grad_norm": 0.5533549189567566, + "learning_rate": 3.826582915828468e-05, + "loss": 0.6669, + "step": 336 + }, + { + "epoch": 2.8803418803418803, + "grad_norm": 0.5834083557128906, + "learning_rate": 3.7727662214273495e-05, + "loss": 0.4875, + "step": 337 + }, + { + "epoch": 2.888888888888889, + "grad_norm": 0.4788981080055237, + "learning_rate": 3.719242523407539e-05, + "loss": 0.454, + "step": 338 + }, + { + "epoch": 2.8974358974358974, + "grad_norm": 0.49913716316223145, + "learning_rate": 3.666014340102268e-05, + "loss": 1.0155, + "step": 339 + }, + { + "epoch": 2.905982905982906, + "grad_norm": 0.5248069763183594, + "learning_rate": 3.613084175940578e-05, + "loss": 0.986, + "step": 340 + }, + { + "epoch": 2.9145299145299144, + "grad_norm": 0.5040814280509949, + "learning_rate": 3.5604545213294616e-05, + "loss": 0.9928, + "step": 341 + }, + { + "epoch": 2.9230769230769234, + "grad_norm": 0.538275420665741, + "learning_rate": 3.508127852536698e-05, + "loss": 0.8618, + "step": 342 + }, + { + "epoch": 2.931623931623932, + "grad_norm": 0.676364541053772, + "learning_rate": 3.456106631574336e-05, + "loss": 0.6912, + "step": 343 + }, + { + "epoch": 2.9401709401709404, + "grad_norm": 0.5177461504936218, + "learning_rate": 3.4043933060828605e-05, + "loss": 0.5507, + "step": 344 + }, + { + "epoch": 2.948717948717949, + "grad_norm": 0.5291532278060913, + "learning_rate": 3.352990309216022e-05, + "loss": 1.0143, + "step": 345 + }, + { + "epoch": 2.9572649572649574, + "grad_norm": 0.7094171047210693, + "learning_rate": 3.3019000595263574e-05, + "loss": 0.5838, + "step": 346 + }, + { + "epoch": 2.965811965811966, + "grad_norm": 0.5676212906837463, + "learning_rate": 3.251124960851408e-05, + "loss": 0.4447, + "step": 347 + }, + { + "epoch": 2.9743589743589745, + "grad_norm": 0.6674243211746216, + "learning_rate": 3.200667402200586e-05, + "loss": 0.6201, + "step": 348 + }, + { + "epoch": 2.982905982905983, + "grad_norm": 0.6357935070991516, + "learning_rate": 3.1505297576428075e-05, + "loss": 0.4907, + "step": 349 + }, + { + "epoch": 2.9914529914529915, + "grad_norm": 0.5493906736373901, + "learning_rate": 3.100714386194757e-05, + "loss": 0.5175, + "step": 350 + }, + { + "epoch": 3.0, + "grad_norm": 0.5719403028488159, + "learning_rate": 3.0512236317099175e-05, + "loss": 0.4602, + "step": 351 + } + ], + "logging_steps": 1, + "max_steps": 468, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 117, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.279504455265157e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-351/training_args.bin b/checkpoint-351/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..6aa0501cedc8c6a042abaac1eb0d2755310396ba --- /dev/null +++ b/checkpoint-351/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7fe3839cfcc5a93b060094e1030e134d680eeeb9bb2bdbde204831612dbb1c1 +size 6840 diff --git a/checkpoint-468/README.md b/checkpoint-468/README.md new file mode 100644 index 0000000000000000000000000000000000000000..a1856dcc51e1f1ee5a60850ea184165793425f6d --- /dev/null +++ b/checkpoint-468/README.md @@ -0,0 +1,202 @@ +--- +base_model: /cpool/DeepSeek-R1-Distill-Qwen-7B +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.14.0 \ No newline at end of file diff --git a/checkpoint-468/adapter_config.json b/checkpoint-468/adapter_config.json new file mode 100644 index 0000000000000000000000000000000000000000..324e93a070435c3ef71b8e5c1a17321dfd9614f6 --- /dev/null +++ b/checkpoint-468/adapter_config.json @@ -0,0 +1,37 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/cpool/DeepSeek-R1-Distill-Qwen-7B", + "bias": "none", + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": null, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 16, + "lora_bias": false, + "lora_dropout": 0.05, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 32, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "up_proj", + "k_proj", + "down_proj", + "gate_proj", + "v_proj", + "o_proj", + "q_proj" + ], + "task_type": "CAUSAL_LM", + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-468/adapter_model.safetensors b/checkpoint-468/adapter_model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c57583fd85eef714567dc4268759c13dbdf0dc9b --- /dev/null +++ b/checkpoint-468/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76b45071fea0cc56ec629a56bd69f7af8a8df37bfed0de5e375d9b49525015b3 +size 2497283840 diff --git a/checkpoint-468/optimizer.bin b/checkpoint-468/optimizer.bin new file mode 100644 index 0000000000000000000000000000000000000000..84e7ab7659a72d647870f25d34e9604f3df3bc1e --- /dev/null +++ b/checkpoint-468/optimizer.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e7ee52aa632a2bd148886ab8c542b934c5936d5472dcaeae5f6cb9d47686bbc +size 646273514 diff --git a/checkpoint-468/pytorch_model_fsdp.bin b/checkpoint-468/pytorch_model_fsdp.bin new file mode 100644 index 0000000000000000000000000000000000000000..59f54779af68f3d8cca3901d0a213fc9979c7d09 --- /dev/null +++ b/checkpoint-468/pytorch_model_fsdp.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82c5a3a13aaca29276efce1e936eb5253f686afc0d4c48f4e504b127c7de0b42 +size 323107814 diff --git a/checkpoint-468/rng_state_0.pth b/checkpoint-468/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..c3fb011071e85c144622093bbefdac320dcb83e6 --- /dev/null +++ b/checkpoint-468/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02a6427db4cfb85e415dca1e545df74f00e257dc04180cd01cec9dea981d96d4 +size 14512 diff --git a/checkpoint-468/rng_state_1.pth b/checkpoint-468/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..500a8b52c7065ac78035b9758c98dd4b9f3488a4 --- /dev/null +++ b/checkpoint-468/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:074fb102295cd998ffe03d4ace767f0b3387f94ba762aab5efd0168556f42f05 +size 14512 diff --git a/checkpoint-468/scheduler.pt b/checkpoint-468/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..a45ab09baa46de1465bc6e9e5b44243c4dfd5204 --- /dev/null +++ b/checkpoint-468/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d9d5bc4bd8cbd6ad2f885036e809b26ec312eff058ed18571dab24711118e2c +size 1064 diff --git a/checkpoint-468/special_tokens_map.json b/checkpoint-468/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1 --- /dev/null +++ b/checkpoint-468/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-468/tokenizer.json b/checkpoint-468/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/checkpoint-468/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/checkpoint-468/tokenizer_config.json b/checkpoint-468/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b068ffca3220a746ba50cc69f850e544217e3a86 --- /dev/null +++ b/checkpoint-468/tokenizer_config.json @@ -0,0 +1,195 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": null, + "use_default_system_prompt": false +} diff --git a/checkpoint-468/trainer_state.json b/checkpoint-468/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..606acecabb1f719dbdd98a337133e09b94b52e28 --- /dev/null +++ b/checkpoint-468/trainer_state.json @@ -0,0 +1,3309 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 4.0, + "eval_steps": 500, + "global_step": 468, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.008547008547008548, + "grad_norm": 0.15355850756168365, + "learning_rate": 2e-05, + "loss": 1.4892, + "step": 1 + }, + { + "epoch": 0.017094017094017096, + "grad_norm": 0.1224861666560173, + "learning_rate": 4e-05, + "loss": 1.1445, + "step": 2 + }, + { + "epoch": 0.02564102564102564, + "grad_norm": 0.1645984649658203, + "learning_rate": 6e-05, + "loss": 1.5538, + "step": 3 + }, + { + "epoch": 0.03418803418803419, + "grad_norm": 0.125856414437294, + "learning_rate": 8e-05, + "loss": 1.7634, + "step": 4 + }, + { + "epoch": 0.042735042735042736, + "grad_norm": 0.1726977378129959, + "learning_rate": 0.0001, + "loss": 1.4105, + "step": 5 + }, + { + "epoch": 0.05128205128205128, + "grad_norm": 0.18316921591758728, + "learning_rate": 0.00012, + "loss": 1.8364, + "step": 6 + }, + { + "epoch": 0.05982905982905983, + "grad_norm": 0.17618055641651154, + "learning_rate": 0.00014, + "loss": 1.3885, + "step": 7 + }, + { + "epoch": 0.06837606837606838, + "grad_norm": 0.17036275565624237, + "learning_rate": 0.00016, + "loss": 1.3574, + "step": 8 + }, + { + "epoch": 0.07692307692307693, + "grad_norm": 0.18832312524318695, + "learning_rate": 0.00018, + "loss": 1.2256, + "step": 9 + }, + { + "epoch": 0.08547008547008547, + "grad_norm": 0.22157786786556244, + "learning_rate": 0.0002, + "loss": 1.515, + "step": 10 + }, + { + "epoch": 0.09401709401709402, + "grad_norm": 0.21728643774986267, + "learning_rate": 0.0001999976474595967, + "loss": 1.4505, + "step": 11 + }, + { + "epoch": 0.10256410256410256, + "grad_norm": 0.16113220155239105, + "learning_rate": 0.00019999058994907564, + "loss": 1.132, + "step": 12 + }, + { + "epoch": 0.1111111111111111, + "grad_norm": 0.1798534393310547, + "learning_rate": 0.00019997882780049847, + "loss": 1.2355, + "step": 13 + }, + { + "epoch": 0.11965811965811966, + "grad_norm": 0.19335126876831055, + "learning_rate": 0.0001999623615672837, + "loss": 1.4485, + "step": 14 + }, + { + "epoch": 0.1282051282051282, + "grad_norm": 0.14973561465740204, + "learning_rate": 0.00019994119202418098, + "loss": 1.4852, + "step": 15 + }, + { + "epoch": 0.13675213675213677, + "grad_norm": 0.1763419359922409, + "learning_rate": 0.00019991532016723439, + "loss": 1.0831, + "step": 16 + }, + { + "epoch": 0.1452991452991453, + "grad_norm": 0.148220494389534, + "learning_rate": 0.00019988474721373568, + "loss": 1.5454, + "step": 17 + }, + { + "epoch": 0.15384615384615385, + "grad_norm": 0.1581086665391922, + "learning_rate": 0.00019984947460216707, + "loss": 0.9387, + "step": 18 + }, + { + "epoch": 0.1623931623931624, + "grad_norm": 0.1937003880739212, + "learning_rate": 0.00019980950399213344, + "loss": 1.1612, + "step": 19 + }, + { + "epoch": 0.17094017094017094, + "grad_norm": 0.15193545818328857, + "learning_rate": 0.00019976483726428422, + "loss": 0.9678, + "step": 20 + }, + { + "epoch": 0.1794871794871795, + "grad_norm": 0.17265811562538147, + "learning_rate": 0.0001997154765202251, + "loss": 1.0147, + "step": 21 + }, + { + "epoch": 0.18803418803418803, + "grad_norm": 0.16466519236564636, + "learning_rate": 0.00019966142408241901, + "loss": 1.1492, + "step": 22 + }, + { + "epoch": 0.19658119658119658, + "grad_norm": 0.17746295034885406, + "learning_rate": 0.00019960268249407675, + "loss": 1.2277, + "step": 23 + }, + { + "epoch": 0.20512820512820512, + "grad_norm": 0.1838495433330536, + "learning_rate": 0.00019953925451903756, + "loss": 1.1559, + "step": 24 + }, + { + "epoch": 0.21367521367521367, + "grad_norm": 0.1542479395866394, + "learning_rate": 0.0001994711431416389, + "loss": 1.855, + "step": 25 + }, + { + "epoch": 0.2222222222222222, + "grad_norm": 0.1788703054189682, + "learning_rate": 0.00019939835156657616, + "loss": 1.6273, + "step": 26 + }, + { + "epoch": 0.23076923076923078, + "grad_norm": 0.15661294758319855, + "learning_rate": 0.00019932088321875172, + "loss": 1.0783, + "step": 27 + }, + { + "epoch": 0.23931623931623933, + "grad_norm": 0.1869712620973587, + "learning_rate": 0.00019923874174311394, + "loss": 0.9181, + "step": 28 + }, + { + "epoch": 0.24786324786324787, + "grad_norm": 0.14521349966526031, + "learning_rate": 0.0001991519310044857, + "loss": 1.4428, + "step": 29 + }, + { + "epoch": 0.2564102564102564, + "grad_norm": 0.17194955050945282, + "learning_rate": 0.00019906045508738228, + "loss": 1.3213, + "step": 30 + }, + { + "epoch": 0.26495726495726496, + "grad_norm": 0.14739835262298584, + "learning_rate": 0.0001989643182958196, + "loss": 0.9933, + "step": 31 + }, + { + "epoch": 0.27350427350427353, + "grad_norm": 0.17825335264205933, + "learning_rate": 0.00019886352515311134, + "loss": 1.034, + "step": 32 + }, + { + "epoch": 0.28205128205128205, + "grad_norm": 0.16200387477874756, + "learning_rate": 0.0001987580804016563, + "loss": 1.3064, + "step": 33 + }, + { + "epoch": 0.2905982905982906, + "grad_norm": 0.170911967754364, + "learning_rate": 0.00019864798900271532, + "loss": 1.2321, + "step": 34 + }, + { + "epoch": 0.29914529914529914, + "grad_norm": 0.16599859297275543, + "learning_rate": 0.0001985332561361776, + "loss": 0.9447, + "step": 35 + }, + { + "epoch": 0.3076923076923077, + "grad_norm": 0.14686603844165802, + "learning_rate": 0.00019841388720031727, + "loss": 0.8823, + "step": 36 + }, + { + "epoch": 0.3162393162393162, + "grad_norm": 0.1870049089193344, + "learning_rate": 0.00019828988781153917, + "loss": 1.1041, + "step": 37 + }, + { + "epoch": 0.3247863247863248, + "grad_norm": 0.1619299054145813, + "learning_rate": 0.00019816126380411476, + "loss": 0.9918, + "step": 38 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 0.18731147050857544, + "learning_rate": 0.00019802802122990758, + "loss": 1.0642, + "step": 39 + }, + { + "epoch": 0.3418803418803419, + "grad_norm": 0.17905616760253906, + "learning_rate": 0.00019789016635808837, + "loss": 1.0877, + "step": 40 + }, + { + "epoch": 0.3504273504273504, + "grad_norm": 0.15318270027637482, + "learning_rate": 0.00019774770567484022, + "loss": 1.2165, + "step": 41 + }, + { + "epoch": 0.358974358974359, + "grad_norm": 0.14854711294174194, + "learning_rate": 0.00019760064588305345, + "loss": 0.9812, + "step": 42 + }, + { + "epoch": 0.36752136752136755, + "grad_norm": 0.15519340336322784, + "learning_rate": 0.00019744899390201006, + "loss": 0.9977, + "step": 43 + }, + { + "epoch": 0.37606837606837606, + "grad_norm": 0.1589617133140564, + "learning_rate": 0.0001972927568670583, + "loss": 1.4097, + "step": 44 + }, + { + "epoch": 0.38461538461538464, + "grad_norm": 0.17286093533039093, + "learning_rate": 0.00019713194212927696, + "loss": 1.1385, + "step": 45 + }, + { + "epoch": 0.39316239316239315, + "grad_norm": 0.19325074553489685, + "learning_rate": 0.00019696655725512933, + "loss": 0.9997, + "step": 46 + }, + { + "epoch": 0.4017094017094017, + "grad_norm": 0.18447531759738922, + "learning_rate": 0.00019679661002610743, + "loss": 1.0873, + "step": 47 + }, + { + "epoch": 0.41025641025641024, + "grad_norm": 0.16223366558551788, + "learning_rate": 0.00019662210843836574, + "loss": 0.99, + "step": 48 + }, + { + "epoch": 0.4188034188034188, + "grad_norm": 0.1919640749692917, + "learning_rate": 0.0001964430607023449, + "loss": 1.0171, + "step": 49 + }, + { + "epoch": 0.42735042735042733, + "grad_norm": 0.22606882452964783, + "learning_rate": 0.00019625947524238563, + "loss": 1.4172, + "step": 50 + }, + { + "epoch": 0.4358974358974359, + "grad_norm": 0.17758312821388245, + "learning_rate": 0.00019607136069633212, + "loss": 0.9964, + "step": 51 + }, + { + "epoch": 0.4444444444444444, + "grad_norm": 0.16785483062267303, + "learning_rate": 0.0001958787259151258, + "loss": 0.9883, + "step": 52 + }, + { + "epoch": 0.452991452991453, + "grad_norm": 0.19499914348125458, + "learning_rate": 0.00019568157996238884, + "loss": 1.0293, + "step": 53 + }, + { + "epoch": 0.46153846153846156, + "grad_norm": 0.15674076974391937, + "learning_rate": 0.0001954799321139975, + "loss": 1.3643, + "step": 54 + }, + { + "epoch": 0.4700854700854701, + "grad_norm": 0.16759538650512695, + "learning_rate": 0.00019527379185764612, + "loss": 0.8998, + "step": 55 + }, + { + "epoch": 0.47863247863247865, + "grad_norm": 0.20853222906589508, + "learning_rate": 0.00019506316889240027, + "loss": 1.4597, + "step": 56 + }, + { + "epoch": 0.48717948717948717, + "grad_norm": 0.18584011495113373, + "learning_rate": 0.00019484807312824067, + "loss": 0.8848, + "step": 57 + }, + { + "epoch": 0.49572649572649574, + "grad_norm": 0.24146708846092224, + "learning_rate": 0.0001946285146855968, + "loss": 1.0529, + "step": 58 + }, + { + "epoch": 0.5042735042735043, + "grad_norm": 0.20457321405410767, + "learning_rate": 0.0001944045038948709, + "loss": 0.9917, + "step": 59 + }, + { + "epoch": 0.5128205128205128, + "grad_norm": 0.21354275941848755, + "learning_rate": 0.00019417605129595157, + "loss": 0.9096, + "step": 60 + }, + { + "epoch": 0.5213675213675214, + "grad_norm": 0.2198089212179184, + "learning_rate": 0.0001939431676377183, + "loss": 0.9228, + "step": 61 + }, + { + "epoch": 0.5299145299145299, + "grad_norm": 0.18545866012573242, + "learning_rate": 0.0001937058638775353, + "loss": 0.8399, + "step": 62 + }, + { + "epoch": 0.5384615384615384, + "grad_norm": 0.1578792780637741, + "learning_rate": 0.00019346415118073632, + "loss": 1.6315, + "step": 63 + }, + { + "epoch": 0.5470085470085471, + "grad_norm": 0.23443493247032166, + "learning_rate": 0.00019321804092009906, + "loss": 1.0905, + "step": 64 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 0.20623010396957397, + "learning_rate": 0.00019296754467531014, + "loss": 0.9367, + "step": 65 + }, + { + "epoch": 0.5641025641025641, + "grad_norm": 0.24046015739440918, + "learning_rate": 0.00019271267423242024, + "loss": 0.9195, + "step": 66 + }, + { + "epoch": 0.5726495726495726, + "grad_norm": 0.22675752639770508, + "learning_rate": 0.00019245344158328972, + "loss": 1.1275, + "step": 67 + }, + { + "epoch": 0.5811965811965812, + "grad_norm": 0.22297680377960205, + "learning_rate": 0.0001921898589250242, + "loss": 0.9244, + "step": 68 + }, + { + "epoch": 0.5897435897435898, + "grad_norm": 0.21324071288108826, + "learning_rate": 0.0001919219386594007, + "loss": 0.9706, + "step": 69 + }, + { + "epoch": 0.5982905982905983, + "grad_norm": 0.21497191488742828, + "learning_rate": 0.00019164969339228422, + "loss": 1.0559, + "step": 70 + }, + { + "epoch": 0.6068376068376068, + "grad_norm": 0.2526251971721649, + "learning_rate": 0.00019137313593303463, + "loss": 1.0632, + "step": 71 + }, + { + "epoch": 0.6153846153846154, + "grad_norm": 0.19590331614017487, + "learning_rate": 0.00019109227929390378, + "loss": 1.8134, + "step": 72 + }, + { + "epoch": 0.6239316239316239, + "grad_norm": 0.21532683074474335, + "learning_rate": 0.00019080713668942356, + "loss": 0.9466, + "step": 73 + }, + { + "epoch": 0.6324786324786325, + "grad_norm": 0.2264883816242218, + "learning_rate": 0.00019051772153578389, + "loss": 0.8941, + "step": 74 + }, + { + "epoch": 0.6410256410256411, + "grad_norm": 0.22985824942588806, + "learning_rate": 0.00019022404745020163, + "loss": 0.8991, + "step": 75 + }, + { + "epoch": 0.6495726495726496, + "grad_norm": 0.19453634321689606, + "learning_rate": 0.00018992612825027976, + "loss": 0.9837, + "step": 76 + }, + { + "epoch": 0.6581196581196581, + "grad_norm": 0.2547195851802826, + "learning_rate": 0.0001896239779533575, + "loss": 1.1035, + "step": 77 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 0.20812910795211792, + "learning_rate": 0.00018931761077585035, + "loss": 0.8916, + "step": 78 + }, + { + "epoch": 0.6752136752136753, + "grad_norm": 0.2176084816455841, + "learning_rate": 0.00018900704113258165, + "loss": 0.8826, + "step": 79 + }, + { + "epoch": 0.6837606837606838, + "grad_norm": 0.2221064418554306, + "learning_rate": 0.00018869228363610404, + "loss": 0.9069, + "step": 80 + }, + { + "epoch": 0.6923076923076923, + "grad_norm": 0.2675364911556244, + "learning_rate": 0.00018837335309601213, + "loss": 1.035, + "step": 81 + }, + { + "epoch": 0.7008547008547008, + "grad_norm": 0.1994653195142746, + "learning_rate": 0.00018805026451824546, + "loss": 1.5854, + "step": 82 + }, + { + "epoch": 0.7094017094017094, + "grad_norm": 0.20346811413764954, + "learning_rate": 0.00018772303310438275, + "loss": 1.4788, + "step": 83 + }, + { + "epoch": 0.717948717948718, + "grad_norm": 0.22119802236557007, + "learning_rate": 0.00018739167425092644, + "loss": 1.4946, + "step": 84 + }, + { + "epoch": 0.7264957264957265, + "grad_norm": 0.2174052894115448, + "learning_rate": 0.00018705620354857833, + "loss": 0.8667, + "step": 85 + }, + { + "epoch": 0.7350427350427351, + "grad_norm": 0.2322807013988495, + "learning_rate": 0.00018671663678150607, + "loss": 0.861, + "step": 86 + }, + { + "epoch": 0.7435897435897436, + "grad_norm": 0.22151263058185577, + "learning_rate": 0.0001863729899266004, + "loss": 0.8966, + "step": 87 + }, + { + "epoch": 0.7521367521367521, + "grad_norm": 0.243766650557518, + "learning_rate": 0.0001860252791527236, + "loss": 1.2998, + "step": 88 + }, + { + "epoch": 0.7606837606837606, + "grad_norm": 0.19212521612644196, + "learning_rate": 0.00018567352081994852, + "loss": 1.5215, + "step": 89 + }, + { + "epoch": 0.7692307692307693, + "grad_norm": 0.20964723825454712, + "learning_rate": 0.00018531773147878895, + "loss": 1.4717, + "step": 90 + }, + { + "epoch": 0.7777777777777778, + "grad_norm": 0.24561531841754913, + "learning_rate": 0.0001849579278694209, + "loss": 0.9569, + "step": 91 + }, + { + "epoch": 0.7863247863247863, + "grad_norm": 0.23924781382083893, + "learning_rate": 0.00018459412692089494, + "loss": 0.9441, + "step": 92 + }, + { + "epoch": 0.7948717948717948, + "grad_norm": 0.2302614450454712, + "learning_rate": 0.0001842263457503397, + "loss": 0.8417, + "step": 93 + }, + { + "epoch": 0.8034188034188035, + "grad_norm": 0.24661926925182343, + "learning_rate": 0.00018385460166215638, + "loss": 1.1297, + "step": 94 + }, + { + "epoch": 0.811965811965812, + "grad_norm": 0.24925513565540314, + "learning_rate": 0.00018347891214720477, + "loss": 0.8999, + "step": 95 + }, + { + "epoch": 0.8205128205128205, + "grad_norm": 0.19934344291687012, + "learning_rate": 0.00018309929488198012, + "loss": 1.4818, + "step": 96 + }, + { + "epoch": 0.8290598290598291, + "grad_norm": 0.24845215678215027, + "learning_rate": 0.00018271576772778154, + "loss": 0.9454, + "step": 97 + }, + { + "epoch": 0.8376068376068376, + "grad_norm": 0.22845034301280975, + "learning_rate": 0.00018232834872987147, + "loss": 1.5063, + "step": 98 + }, + { + "epoch": 0.8461538461538461, + "grad_norm": 0.2563302516937256, + "learning_rate": 0.00018193705611662696, + "loss": 0.9946, + "step": 99 + }, + { + "epoch": 0.8547008547008547, + "grad_norm": 0.30030304193496704, + "learning_rate": 0.0001815419082986815, + "loss": 1.0936, + "step": 100 + }, + { + "epoch": 0.8632478632478633, + "grad_norm": 0.22599591314792633, + "learning_rate": 0.00018114292386805936, + "loss": 1.346, + "step": 101 + }, + { + "epoch": 0.8717948717948718, + "grad_norm": 0.20411820709705353, + "learning_rate": 0.00018074012159730032, + "loss": 1.5147, + "step": 102 + }, + { + "epoch": 0.8803418803418803, + "grad_norm": 0.20635190606117249, + "learning_rate": 0.00018033352043857675, + "loss": 1.1425, + "step": 103 + }, + { + "epoch": 0.8888888888888888, + "grad_norm": 0.22327086329460144, + "learning_rate": 0.00017992313952280172, + "loss": 1.4435, + "step": 104 + }, + { + "epoch": 0.8974358974358975, + "grad_norm": 0.2183496206998825, + "learning_rate": 0.00017950899815872892, + "loss": 1.5659, + "step": 105 + }, + { + "epoch": 0.905982905982906, + "grad_norm": 0.31636252999305725, + "learning_rate": 0.00017909111583204422, + "loss": 1.4703, + "step": 106 + }, + { + "epoch": 0.9145299145299145, + "grad_norm": 0.3305496275424957, + "learning_rate": 0.0001786695122044487, + "loss": 1.0904, + "step": 107 + }, + { + "epoch": 0.9230769230769231, + "grad_norm": 0.22857435047626495, + "learning_rate": 0.0001782442071127338, + "loss": 1.3801, + "step": 108 + }, + { + "epoch": 0.9316239316239316, + "grad_norm": 0.31968221068382263, + "learning_rate": 0.0001778152205678477, + "loss": 1.4907, + "step": 109 + }, + { + "epoch": 0.9401709401709402, + "grad_norm": 0.27950960397720337, + "learning_rate": 0.00017738257275395404, + "loss": 1.0864, + "step": 110 + }, + { + "epoch": 0.9487179487179487, + "grad_norm": 0.2740281820297241, + "learning_rate": 0.00017694628402748202, + "loss": 0.9241, + "step": 111 + }, + { + "epoch": 0.9572649572649573, + "grad_norm": 0.26951318979263306, + "learning_rate": 0.0001765063749161688, + "loss": 0.9894, + "step": 112 + }, + { + "epoch": 0.9658119658119658, + "grad_norm": 0.2811899781227112, + "learning_rate": 0.00017606286611809353, + "loss": 0.9659, + "step": 113 + }, + { + "epoch": 0.9743589743589743, + "grad_norm": 0.23854824900627136, + "learning_rate": 0.00017561577850070355, + "loss": 1.0623, + "step": 114 + }, + { + "epoch": 0.9829059829059829, + "grad_norm": 0.21959957480430603, + "learning_rate": 0.00017516513309983253, + "loss": 0.8671, + "step": 115 + }, + { + "epoch": 0.9914529914529915, + "grad_norm": 0.3096697926521301, + "learning_rate": 0.00017471095111871074, + "loss": 1.0756, + "step": 116 + }, + { + "epoch": 1.0, + "grad_norm": 0.23363932967185974, + "learning_rate": 0.0001742532539269674, + "loss": 0.8988, + "step": 117 + }, + { + "epoch": 1.0085470085470085, + "grad_norm": 0.23965218663215637, + "learning_rate": 0.00017379206305962526, + "loss": 0.7737, + "step": 118 + }, + { + "epoch": 1.017094017094017, + "grad_norm": 0.24553611874580383, + "learning_rate": 0.00017332740021608722, + "loss": 0.7793, + "step": 119 + }, + { + "epoch": 1.0256410256410255, + "grad_norm": 0.267673522233963, + "learning_rate": 0.00017285928725911562, + "loss": 0.8077, + "step": 120 + }, + { + "epoch": 1.0341880341880343, + "grad_norm": 0.3069080114364624, + "learning_rate": 0.00017238774621380337, + "loss": 0.8226, + "step": 121 + }, + { + "epoch": 1.0427350427350428, + "grad_norm": 0.26568329334259033, + "learning_rate": 0.00017191279926653761, + "loss": 1.5833, + "step": 122 + }, + { + "epoch": 1.0512820512820513, + "grad_norm": 0.2673753499984741, + "learning_rate": 0.00017143446876395602, + "loss": 1.3896, + "step": 123 + }, + { + "epoch": 1.0598290598290598, + "grad_norm": 0.23525093495845795, + "learning_rate": 0.00017095277721189528, + "loss": 1.3125, + "step": 124 + }, + { + "epoch": 1.0683760683760684, + "grad_norm": 0.3066873550415039, + "learning_rate": 0.00017046774727433222, + "loss": 0.8894, + "step": 125 + }, + { + "epoch": 1.0769230769230769, + "grad_norm": 0.27280548214912415, + "learning_rate": 0.00016997940177231722, + "loss": 0.7649, + "step": 126 + }, + { + "epoch": 1.0854700854700854, + "grad_norm": 0.23357781767845154, + "learning_rate": 0.00016948776368290084, + "loss": 1.4143, + "step": 127 + }, + { + "epoch": 1.0940170940170941, + "grad_norm": 0.2928774356842041, + "learning_rate": 0.00016899285613805246, + "loss": 0.6522, + "step": 128 + }, + { + "epoch": 1.1025641025641026, + "grad_norm": 0.33789336681365967, + "learning_rate": 0.00016849470242357196, + "loss": 0.7737, + "step": 129 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 0.3078365921974182, + "learning_rate": 0.00016799332597799413, + "loss": 0.8068, + "step": 130 + }, + { + "epoch": 1.1196581196581197, + "grad_norm": 0.3175398111343384, + "learning_rate": 0.00016748875039148593, + "loss": 1.223, + "step": 131 + }, + { + "epoch": 1.1282051282051282, + "grad_norm": 0.27531448006629944, + "learning_rate": 0.0001669809994047364, + "loss": 1.3081, + "step": 132 + }, + { + "epoch": 1.1367521367521367, + "grad_norm": 0.34105026721954346, + "learning_rate": 0.0001664700969078398, + "loss": 0.9031, + "step": 133 + }, + { + "epoch": 1.1452991452991452, + "grad_norm": 0.25465068221092224, + "learning_rate": 0.00016595606693917142, + "loss": 1.3237, + "step": 134 + }, + { + "epoch": 1.1538461538461537, + "grad_norm": 0.2841501533985138, + "learning_rate": 0.00016543893368425666, + "loss": 0.7393, + "step": 135 + }, + { + "epoch": 1.1623931623931625, + "grad_norm": 0.3230992257595062, + "learning_rate": 0.00016491872147463306, + "loss": 0.7437, + "step": 136 + }, + { + "epoch": 1.170940170940171, + "grad_norm": 0.25824740529060364, + "learning_rate": 0.00016439545478670543, + "loss": 1.883, + "step": 137 + }, + { + "epoch": 1.1794871794871795, + "grad_norm": 0.31415536999702454, + "learning_rate": 0.00016386915824059427, + "loss": 0.703, + "step": 138 + }, + { + "epoch": 1.188034188034188, + "grad_norm": 0.26885557174682617, + "learning_rate": 0.00016333985659897735, + "loss": 0.6592, + "step": 139 + }, + { + "epoch": 1.1965811965811965, + "grad_norm": 0.4018881618976593, + "learning_rate": 0.00016280757476592466, + "loss": 0.7733, + "step": 140 + }, + { + "epoch": 1.205128205128205, + "grad_norm": 0.3181138038635254, + "learning_rate": 0.0001622723377857265, + "loss": 0.7577, + "step": 141 + }, + { + "epoch": 1.2136752136752136, + "grad_norm": 0.2720906436443329, + "learning_rate": 0.00016173417084171536, + "loss": 1.3883, + "step": 142 + }, + { + "epoch": 1.2222222222222223, + "grad_norm": 0.34472835063934326, + "learning_rate": 0.00016119309925508078, + "loss": 0.7757, + "step": 143 + }, + { + "epoch": 1.2307692307692308, + "grad_norm": 0.40166720747947693, + "learning_rate": 0.0001606491484836782, + "loss": 0.79, + "step": 144 + }, + { + "epoch": 1.2393162393162394, + "grad_norm": 0.38203030824661255, + "learning_rate": 0.00016010234412083086, + "loss": 0.8184, + "step": 145 + }, + { + "epoch": 1.2478632478632479, + "grad_norm": 0.3825059235095978, + "learning_rate": 0.00015955271189412598, + "loss": 0.9065, + "step": 146 + }, + { + "epoch": 1.2564102564102564, + "grad_norm": 0.403533935546875, + "learning_rate": 0.00015900027766420393, + "loss": 0.7605, + "step": 147 + }, + { + "epoch": 1.264957264957265, + "grad_norm": 0.3657178282737732, + "learning_rate": 0.00015844506742354164, + "loss": 0.8265, + "step": 148 + }, + { + "epoch": 1.2735042735042734, + "grad_norm": 0.2825511693954468, + "learning_rate": 0.00015788710729522953, + "loss": 1.166, + "step": 149 + }, + { + "epoch": 1.282051282051282, + "grad_norm": 0.4000828266143799, + "learning_rate": 0.00015732642353174259, + "loss": 1.2792, + "step": 150 + }, + { + "epoch": 1.2905982905982907, + "grad_norm": 0.3135271668434143, + "learning_rate": 0.0001567630425137049, + "loss": 0.6227, + "step": 151 + }, + { + "epoch": 1.2991452991452992, + "grad_norm": 0.3828388452529907, + "learning_rate": 0.00015619699074864864, + "loss": 0.6989, + "step": 152 + }, + { + "epoch": 1.3076923076923077, + "grad_norm": 0.45689550042152405, + "learning_rate": 0.00015562829486976673, + "loss": 0.9088, + "step": 153 + }, + { + "epoch": 1.3162393162393162, + "grad_norm": 0.36523374915122986, + "learning_rate": 0.00015505698163465986, + "loss": 0.9859, + "step": 154 + }, + { + "epoch": 1.3247863247863247, + "grad_norm": 0.4206138551235199, + "learning_rate": 0.00015448307792407734, + "loss": 0.7771, + "step": 155 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.3400786817073822, + "learning_rate": 0.00015390661074065256, + "loss": 0.772, + "step": 156 + }, + { + "epoch": 1.341880341880342, + "grad_norm": 0.334692120552063, + "learning_rate": 0.00015332760720763232, + "loss": 1.3839, + "step": 157 + }, + { + "epoch": 1.3504273504273505, + "grad_norm": 0.4513654112815857, + "learning_rate": 0.00015274609456760073, + "loss": 0.8578, + "step": 158 + }, + { + "epoch": 1.358974358974359, + "grad_norm": 0.4215463399887085, + "learning_rate": 0.00015216210018119733, + "loss": 0.9154, + "step": 159 + }, + { + "epoch": 1.3675213675213675, + "grad_norm": 0.38081440329551697, + "learning_rate": 0.00015157565152583002, + "loss": 0.6723, + "step": 160 + }, + { + "epoch": 1.376068376068376, + "grad_norm": 0.38604873418807983, + "learning_rate": 0.0001509867761943818, + "loss": 0.9546, + "step": 161 + }, + { + "epoch": 1.3846153846153846, + "grad_norm": 0.39846640825271606, + "learning_rate": 0.00015039550189391298, + "loss": 0.7379, + "step": 162 + }, + { + "epoch": 1.393162393162393, + "grad_norm": 0.3619799315929413, + "learning_rate": 0.0001498018564443571, + "loss": 1.12, + "step": 163 + }, + { + "epoch": 1.4017094017094016, + "grad_norm": 0.4657539427280426, + "learning_rate": 0.0001492058677772123, + "loss": 1.0395, + "step": 164 + }, + { + "epoch": 1.4102564102564101, + "grad_norm": 0.3850860893726349, + "learning_rate": 0.000148607563934227, + "loss": 0.7949, + "step": 165 + }, + { + "epoch": 1.4188034188034189, + "grad_norm": 0.30473998188972473, + "learning_rate": 0.00014800697306608044, + "loss": 0.6285, + "step": 166 + }, + { + "epoch": 1.4273504273504274, + "grad_norm": 0.36891016364097595, + "learning_rate": 0.00014740412343105828, + "loss": 0.9947, + "step": 167 + }, + { + "epoch": 1.435897435897436, + "grad_norm": 0.3746401071548462, + "learning_rate": 0.00014679904339372302, + "loss": 0.7204, + "step": 168 + }, + { + "epoch": 1.4444444444444444, + "grad_norm": 0.4085482060909271, + "learning_rate": 0.00014619176142357935, + "loss": 0.7145, + "step": 169 + }, + { + "epoch": 1.452991452991453, + "grad_norm": 0.40742969512939453, + "learning_rate": 0.0001455823060937347, + "loss": 0.8273, + "step": 170 + }, + { + "epoch": 1.4615384615384617, + "grad_norm": 0.3882700502872467, + "learning_rate": 0.00014497070607955476, + "loss": 0.7025, + "step": 171 + }, + { + "epoch": 1.4700854700854702, + "grad_norm": 0.43999457359313965, + "learning_rate": 0.00014435699015731448, + "loss": 0.7473, + "step": 172 + }, + { + "epoch": 1.4786324786324787, + "grad_norm": 0.3841669261455536, + "learning_rate": 0.00014374118720284388, + "loss": 0.8794, + "step": 173 + }, + { + "epoch": 1.4871794871794872, + "grad_norm": 0.3169039189815521, + "learning_rate": 0.00014312332619016965, + "loss": 1.007, + "step": 174 + }, + { + "epoch": 1.4957264957264957, + "grad_norm": 0.44292953610420227, + "learning_rate": 0.0001425034361901516, + "loss": 0.846, + "step": 175 + }, + { + "epoch": 1.5042735042735043, + "grad_norm": 0.3945798873901367, + "learning_rate": 0.00014188154636911524, + "loss": 1.3956, + "step": 176 + }, + { + "epoch": 1.5128205128205128, + "grad_norm": 0.4760408103466034, + "learning_rate": 0.0001412576859874791, + "loss": 0.7811, + "step": 177 + }, + { + "epoch": 1.5213675213675213, + "grad_norm": 0.401869535446167, + "learning_rate": 0.00014063188439837832, + "loss": 0.6903, + "step": 178 + }, + { + "epoch": 1.5299145299145298, + "grad_norm": 0.3994334042072296, + "learning_rate": 0.0001400041710462833, + "loss": 0.688, + "step": 179 + }, + { + "epoch": 1.5384615384615383, + "grad_norm": 0.41962575912475586, + "learning_rate": 0.0001393745754656146, + "loss": 0.7697, + "step": 180 + }, + { + "epoch": 1.547008547008547, + "grad_norm": 0.36107930541038513, + "learning_rate": 0.00013874312727935292, + "loss": 0.715, + "step": 181 + }, + { + "epoch": 1.5555555555555556, + "grad_norm": 0.3828651010990143, + "learning_rate": 0.00013810985619764572, + "loss": 1.3298, + "step": 182 + }, + { + "epoch": 1.564102564102564, + "grad_norm": 0.3839617967605591, + "learning_rate": 0.00013747479201640914, + "loss": 0.6851, + "step": 183 + }, + { + "epoch": 1.5726495726495726, + "grad_norm": 0.4327555298805237, + "learning_rate": 0.00013683796461592604, + "loss": 0.7906, + "step": 184 + }, + { + "epoch": 1.5811965811965814, + "grad_norm": 0.3910170793533325, + "learning_rate": 0.00013619940395944027, + "loss": 0.7832, + "step": 185 + }, + { + "epoch": 1.5897435897435899, + "grad_norm": 0.4029540419578552, + "learning_rate": 0.00013555914009174663, + "loss": 0.7723, + "step": 186 + }, + { + "epoch": 1.5982905982905984, + "grad_norm": 0.3986589014530182, + "learning_rate": 0.00013491720313777756, + "loss": 1.1658, + "step": 187 + }, + { + "epoch": 1.606837606837607, + "grad_norm": 0.3962538242340088, + "learning_rate": 0.00013427362330118543, + "loss": 0.7481, + "step": 188 + }, + { + "epoch": 1.6153846153846154, + "grad_norm": 0.4297255277633667, + "learning_rate": 0.0001336284308629216, + "loss": 0.9531, + "step": 189 + }, + { + "epoch": 1.623931623931624, + "grad_norm": 0.3742808699607849, + "learning_rate": 0.00013298165617981172, + "loss": 0.9516, + "step": 190 + }, + { + "epoch": 1.6324786324786325, + "grad_norm": 0.44721004366874695, + "learning_rate": 0.00013233332968312715, + "loss": 1.075, + "step": 191 + }, + { + "epoch": 1.641025641025641, + "grad_norm": 0.41275331377983093, + "learning_rate": 0.0001316834818771535, + "loss": 0.8295, + "step": 192 + }, + { + "epoch": 1.6495726495726495, + "grad_norm": 0.46620428562164307, + "learning_rate": 0.00013103214333775521, + "loss": 0.8314, + "step": 193 + }, + { + "epoch": 1.658119658119658, + "grad_norm": 0.4467974901199341, + "learning_rate": 0.00013037934471093682, + "loss": 0.7321, + "step": 194 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.42806383967399597, + "learning_rate": 0.00012972511671140125, + "loss": 0.7144, + "step": 195 + }, + { + "epoch": 1.6752136752136753, + "grad_norm": 0.3721958100795746, + "learning_rate": 0.00012906949012110456, + "loss": 1.0117, + "step": 196 + }, + { + "epoch": 1.6837606837606838, + "grad_norm": 0.46833130717277527, + "learning_rate": 0.00012841249578780757, + "loss": 0.9599, + "step": 197 + }, + { + "epoch": 1.6923076923076923, + "grad_norm": 0.3547254502773285, + "learning_rate": 0.00012775416462362457, + "loss": 0.8255, + "step": 198 + }, + { + "epoch": 1.7008547008547008, + "grad_norm": 0.36470168828964233, + "learning_rate": 0.00012709452760356884, + "loss": 1.3796, + "step": 199 + }, + { + "epoch": 1.7094017094017095, + "grad_norm": 0.4088481068611145, + "learning_rate": 0.00012643361576409516, + "loss": 0.818, + "step": 200 + }, + { + "epoch": 1.717948717948718, + "grad_norm": 0.43268319964408875, + "learning_rate": 0.00012577146020163968, + "loss": 0.8157, + "step": 201 + }, + { + "epoch": 1.7264957264957266, + "grad_norm": 0.4660526216030121, + "learning_rate": 0.00012510809207115666, + "loss": 0.775, + "step": 202 + }, + { + "epoch": 1.735042735042735, + "grad_norm": 0.41217854619026184, + "learning_rate": 0.00012444354258465268, + "loss": 0.7172, + "step": 203 + }, + { + "epoch": 1.7435897435897436, + "grad_norm": 0.4177812933921814, + "learning_rate": 0.00012377784300971807, + "loss": 1.1308, + "step": 204 + }, + { + "epoch": 1.7521367521367521, + "grad_norm": 0.3943150043487549, + "learning_rate": 0.0001231110246680558, + "loss": 1.4001, + "step": 205 + }, + { + "epoch": 1.7606837606837606, + "grad_norm": 0.48257848620414734, + "learning_rate": 0.00012244311893400763, + "loss": 0.9118, + "step": 206 + }, + { + "epoch": 1.7692307692307692, + "grad_norm": 0.4754193127155304, + "learning_rate": 0.00012177415723307808, + "loss": 0.825, + "step": 207 + }, + { + "epoch": 1.7777777777777777, + "grad_norm": 0.3812815546989441, + "learning_rate": 0.00012110417104045575, + "loss": 0.6433, + "step": 208 + }, + { + "epoch": 1.7863247863247862, + "grad_norm": 0.3967946469783783, + "learning_rate": 0.00012043319187953241, + "loss": 0.8549, + "step": 209 + }, + { + "epoch": 1.7948717948717947, + "grad_norm": 0.4312019348144531, + "learning_rate": 0.00011976125132041974, + "loss": 0.8387, + "step": 210 + }, + { + "epoch": 1.8034188034188035, + "grad_norm": 0.4585026204586029, + "learning_rate": 0.00011908838097846404, + "loss": 0.9471, + "step": 211 + }, + { + "epoch": 1.811965811965812, + "grad_norm": 0.4149639904499054, + "learning_rate": 0.00011841461251275867, + "loss": 1.0415, + "step": 212 + }, + { + "epoch": 1.8205128205128205, + "grad_norm": 0.48069992661476135, + "learning_rate": 0.00011773997762465429, + "loss": 0.7534, + "step": 213 + }, + { + "epoch": 1.8290598290598292, + "grad_norm": 0.3820441961288452, + "learning_rate": 0.0001170645080562676, + "loss": 0.8292, + "step": 214 + }, + { + "epoch": 1.8376068376068377, + "grad_norm": 0.3951680660247803, + "learning_rate": 0.00011638823558898762, + "loss": 0.6923, + "step": 215 + }, + { + "epoch": 1.8461538461538463, + "grad_norm": 0.40777531266212463, + "learning_rate": 0.00011571119204198037, + "loss": 0.7335, + "step": 216 + }, + { + "epoch": 1.8547008547008548, + "grad_norm": 0.3792341649532318, + "learning_rate": 0.00011503340927069189, + "loss": 0.8608, + "step": 217 + }, + { + "epoch": 1.8632478632478633, + "grad_norm": 0.36157581210136414, + "learning_rate": 0.00011435491916534919, + "loss": 0.7314, + "step": 218 + }, + { + "epoch": 1.8717948717948718, + "grad_norm": 0.41833943128585815, + "learning_rate": 0.00011367575364946006, + "loss": 0.7662, + "step": 219 + }, + { + "epoch": 1.8803418803418803, + "grad_norm": 0.45951926708221436, + "learning_rate": 0.00011299594467831078, + "loss": 0.6988, + "step": 220 + }, + { + "epoch": 1.8888888888888888, + "grad_norm": 0.4588642120361328, + "learning_rate": 0.00011231552423746283, + "loss": 0.8544, + "step": 221 + }, + { + "epoch": 1.8974358974358974, + "grad_norm": 0.3614063560962677, + "learning_rate": 0.00011163452434124773, + "loss": 0.728, + "step": 222 + }, + { + "epoch": 1.9059829059829059, + "grad_norm": 0.4452153742313385, + "learning_rate": 0.00011095297703126093, + "loss": 0.7399, + "step": 223 + }, + { + "epoch": 1.9145299145299144, + "grad_norm": 0.42948612570762634, + "learning_rate": 0.00011027091437485404, + "loss": 0.9105, + "step": 224 + }, + { + "epoch": 1.9230769230769231, + "grad_norm": 0.37950897216796875, + "learning_rate": 0.00010958836846362621, + "loss": 0.9612, + "step": 225 + }, + { + "epoch": 1.9316239316239316, + "grad_norm": 0.4386560916900635, + "learning_rate": 0.00010890537141191417, + "loss": 0.683, + "step": 226 + }, + { + "epoch": 1.9401709401709402, + "grad_norm": 0.4166669547557831, + "learning_rate": 0.00010822195535528106, + "loss": 1.1851, + "step": 227 + }, + { + "epoch": 1.9487179487179487, + "grad_norm": 0.4029337465763092, + "learning_rate": 0.00010753815244900458, + "loss": 0.6721, + "step": 228 + }, + { + "epoch": 1.9572649572649574, + "grad_norm": 0.47789204120635986, + "learning_rate": 0.00010685399486656406, + "loss": 0.8654, + "step": 229 + }, + { + "epoch": 1.965811965811966, + "grad_norm": 0.4141186475753784, + "learning_rate": 0.00010616951479812658, + "loss": 0.7619, + "step": 230 + }, + { + "epoch": 1.9743589743589745, + "grad_norm": 0.4745655655860901, + "learning_rate": 0.00010548474444903247, + "loss": 0.698, + "step": 231 + }, + { + "epoch": 1.982905982905983, + "grad_norm": 0.4075687825679779, + "learning_rate": 0.00010479971603828, + "loss": 0.7387, + "step": 232 + }, + { + "epoch": 1.9914529914529915, + "grad_norm": 0.37726572155952454, + "learning_rate": 0.00010411446179700943, + "loss": 0.714, + "step": 233 + }, + { + "epoch": 2.0, + "grad_norm": 0.5989537239074707, + "learning_rate": 0.00010342901396698659, + "loss": 0.7816, + "step": 234 + }, + { + "epoch": 2.0085470085470085, + "grad_norm": 0.3381822109222412, + "learning_rate": 0.00010274340479908568, + "loss": 0.443, + "step": 235 + }, + { + "epoch": 2.017094017094017, + "grad_norm": 0.375904381275177, + "learning_rate": 0.00010205766655177215, + "loss": 0.4966, + "step": 236 + }, + { + "epoch": 2.0256410256410255, + "grad_norm": 0.3564665615558624, + "learning_rate": 0.00010137183148958463, + "loss": 0.6866, + "step": 237 + }, + { + "epoch": 2.034188034188034, + "grad_norm": 0.4133633077144623, + "learning_rate": 0.00010068593188161697, + "loss": 0.5057, + "step": 238 + }, + { + "epoch": 2.0427350427350426, + "grad_norm": 0.4830314517021179, + "learning_rate": 0.0001, + "loss": 0.6148, + "step": 239 + }, + { + "epoch": 2.051282051282051, + "grad_norm": 0.4566143751144409, + "learning_rate": 9.931406811838308e-05, + "loss": 0.5323, + "step": 240 + }, + { + "epoch": 2.0598290598290596, + "grad_norm": 0.4714205265045166, + "learning_rate": 9.862816851041541e-05, + "loss": 0.4689, + "step": 241 + }, + { + "epoch": 2.0683760683760686, + "grad_norm": 0.4094763696193695, + "learning_rate": 9.79423334482279e-05, + "loss": 0.6019, + "step": 242 + }, + { + "epoch": 2.076923076923077, + "grad_norm": 0.5059089660644531, + "learning_rate": 9.725659520091433e-05, + "loss": 0.5675, + "step": 243 + }, + { + "epoch": 2.0854700854700856, + "grad_norm": 0.49986734986305237, + "learning_rate": 9.657098603301346e-05, + "loss": 0.6499, + "step": 244 + }, + { + "epoch": 2.094017094017094, + "grad_norm": 0.42914658784866333, + "learning_rate": 9.588553820299056e-05, + "loss": 0.513, + "step": 245 + }, + { + "epoch": 2.1025641025641026, + "grad_norm": 0.5760869979858398, + "learning_rate": 9.520028396172003e-05, + "loss": 0.8912, + "step": 246 + }, + { + "epoch": 2.111111111111111, + "grad_norm": 0.5276662707328796, + "learning_rate": 9.451525555096753e-05, + "loss": 0.5903, + "step": 247 + }, + { + "epoch": 2.1196581196581197, + "grad_norm": 0.5043647289276123, + "learning_rate": 9.383048520187344e-05, + "loss": 0.5089, + "step": 248 + }, + { + "epoch": 2.128205128205128, + "grad_norm": 0.522574782371521, + "learning_rate": 9.314600513343595e-05, + "loss": 0.5059, + "step": 249 + }, + { + "epoch": 2.1367521367521367, + "grad_norm": 0.48663464188575745, + "learning_rate": 9.246184755099545e-05, + "loss": 0.9519, + "step": 250 + }, + { + "epoch": 2.1452991452991452, + "grad_norm": 0.5056342482566833, + "learning_rate": 9.177804464471898e-05, + "loss": 1.1279, + "step": 251 + }, + { + "epoch": 2.1538461538461537, + "grad_norm": 0.5033504366874695, + "learning_rate": 9.109462858808586e-05, + "loss": 1.1843, + "step": 252 + }, + { + "epoch": 2.1623931623931623, + "grad_norm": 0.48481982946395874, + "learning_rate": 9.041163153637381e-05, + "loss": 0.5202, + "step": 253 + }, + { + "epoch": 2.1709401709401708, + "grad_norm": 0.5677529573440552, + "learning_rate": 8.972908562514598e-05, + "loss": 0.5685, + "step": 254 + }, + { + "epoch": 2.1794871794871793, + "grad_norm": 0.6009398102760315, + "learning_rate": 8.904702296873912e-05, + "loss": 0.6472, + "step": 255 + }, + { + "epoch": 2.1880341880341883, + "grad_norm": 0.5119011998176575, + "learning_rate": 8.836547565875227e-05, + "loss": 0.501, + "step": 256 + }, + { + "epoch": 2.1965811965811968, + "grad_norm": 0.44192251563072205, + "learning_rate": 8.76844757625372e-05, + "loss": 1.1073, + "step": 257 + }, + { + "epoch": 2.2051282051282053, + "grad_norm": 0.5733199715614319, + "learning_rate": 8.70040553216892e-05, + "loss": 0.5188, + "step": 258 + }, + { + "epoch": 2.213675213675214, + "grad_norm": 0.5789536237716675, + "learning_rate": 8.632424635053997e-05, + "loss": 0.719, + "step": 259 + }, + { + "epoch": 2.2222222222222223, + "grad_norm": 0.4420778453350067, + "learning_rate": 8.564508083465079e-05, + "loss": 0.4935, + "step": 260 + }, + { + "epoch": 2.230769230769231, + "grad_norm": 0.4915638267993927, + "learning_rate": 8.496659072930813e-05, + "loss": 0.5342, + "step": 261 + }, + { + "epoch": 2.2393162393162394, + "grad_norm": 0.4589202404022217, + "learning_rate": 8.428880795801965e-05, + "loss": 0.4839, + "step": 262 + }, + { + "epoch": 2.247863247863248, + "grad_norm": 0.5273900628089905, + "learning_rate": 8.36117644110124e-05, + "loss": 0.8426, + "step": 263 + }, + { + "epoch": 2.2564102564102564, + "grad_norm": 0.5588923096656799, + "learning_rate": 8.293549194373243e-05, + "loss": 0.5051, + "step": 264 + }, + { + "epoch": 2.264957264957265, + "grad_norm": 0.4949032664299011, + "learning_rate": 8.226002237534572e-05, + "loss": 0.4751, + "step": 265 + }, + { + "epoch": 2.2735042735042734, + "grad_norm": 0.6772957444190979, + "learning_rate": 8.158538748724139e-05, + "loss": 0.9695, + "step": 266 + }, + { + "epoch": 2.282051282051282, + "grad_norm": 0.5875369906425476, + "learning_rate": 8.091161902153595e-05, + "loss": 0.5566, + "step": 267 + }, + { + "epoch": 2.2905982905982905, + "grad_norm": 0.4558923840522766, + "learning_rate": 8.023874867958027e-05, + "loss": 0.8852, + "step": 268 + }, + { + "epoch": 2.299145299145299, + "grad_norm": 0.5420984625816345, + "learning_rate": 7.95668081204676e-05, + "loss": 0.8007, + "step": 269 + }, + { + "epoch": 2.3076923076923075, + "grad_norm": 0.5497881770133972, + "learning_rate": 7.889582895954427e-05, + "loss": 0.5261, + "step": 270 + }, + { + "epoch": 2.316239316239316, + "grad_norm": 0.5697259306907654, + "learning_rate": 7.822584276692191e-05, + "loss": 0.4692, + "step": 271 + }, + { + "epoch": 2.324786324786325, + "grad_norm": 0.5963535904884338, + "learning_rate": 7.755688106599241e-05, + "loss": 0.5553, + "step": 272 + }, + { + "epoch": 2.3333333333333335, + "grad_norm": 0.5704771280288696, + "learning_rate": 7.688897533194424e-05, + "loss": 0.6445, + "step": 273 + }, + { + "epoch": 2.341880341880342, + "grad_norm": 0.6348976492881775, + "learning_rate": 7.622215699028196e-05, + "loss": 0.5257, + "step": 274 + }, + { + "epoch": 2.3504273504273505, + "grad_norm": 0.4737604260444641, + "learning_rate": 7.555645741534736e-05, + "loss": 0.4532, + "step": 275 + }, + { + "epoch": 2.358974358974359, + "grad_norm": 0.6055320501327515, + "learning_rate": 7.489190792884338e-05, + "loss": 1.0912, + "step": 276 + }, + { + "epoch": 2.3675213675213675, + "grad_norm": 0.6330887079238892, + "learning_rate": 7.422853979836034e-05, + "loss": 0.8996, + "step": 277 + }, + { + "epoch": 2.376068376068376, + "grad_norm": 0.5483549237251282, + "learning_rate": 7.356638423590485e-05, + "loss": 0.6033, + "step": 278 + }, + { + "epoch": 2.3846153846153846, + "grad_norm": 0.5688058733940125, + "learning_rate": 7.290547239643117e-05, + "loss": 0.5904, + "step": 279 + }, + { + "epoch": 2.393162393162393, + "grad_norm": 0.49569448828697205, + "learning_rate": 7.224583537637544e-05, + "loss": 0.6198, + "step": 280 + }, + { + "epoch": 2.4017094017094016, + "grad_norm": 0.5610498189926147, + "learning_rate": 7.158750421219244e-05, + "loss": 1.2213, + "step": 281 + }, + { + "epoch": 2.41025641025641, + "grad_norm": 0.5684900283813477, + "learning_rate": 7.093050987889547e-05, + "loss": 0.5249, + "step": 282 + }, + { + "epoch": 2.4188034188034186, + "grad_norm": 0.5226355195045471, + "learning_rate": 7.027488328859876e-05, + "loss": 0.4525, + "step": 283 + }, + { + "epoch": 2.427350427350427, + "grad_norm": 0.4944767653942108, + "learning_rate": 6.96206552890632e-05, + "loss": 0.5517, + "step": 284 + }, + { + "epoch": 2.435897435897436, + "grad_norm": 0.5820432305335999, + "learning_rate": 6.896785666224481e-05, + "loss": 0.5575, + "step": 285 + }, + { + "epoch": 2.4444444444444446, + "grad_norm": 0.6503978967666626, + "learning_rate": 6.831651812284652e-05, + "loss": 0.5344, + "step": 286 + }, + { + "epoch": 2.452991452991453, + "grad_norm": 0.5511913299560547, + "learning_rate": 6.766667031687286e-05, + "loss": 0.6221, + "step": 287 + }, + { + "epoch": 2.4615384615384617, + "grad_norm": 0.5843252539634705, + "learning_rate": 6.701834382018832e-05, + "loss": 0.5421, + "step": 288 + }, + { + "epoch": 2.47008547008547, + "grad_norm": 0.5561351180076599, + "learning_rate": 6.637156913707839e-05, + "loss": 0.4725, + "step": 289 + }, + { + "epoch": 2.4786324786324787, + "grad_norm": 0.5449361205101013, + "learning_rate": 6.572637669881458e-05, + "loss": 0.5561, + "step": 290 + }, + { + "epoch": 2.4871794871794872, + "grad_norm": 0.5354922413825989, + "learning_rate": 6.508279686222243e-05, + "loss": 1.0458, + "step": 291 + }, + { + "epoch": 2.4957264957264957, + "grad_norm": 0.6082772612571716, + "learning_rate": 6.444085990825338e-05, + "loss": 0.6117, + "step": 292 + }, + { + "epoch": 2.5042735042735043, + "grad_norm": 0.5007249712944031, + "learning_rate": 6.380059604055974e-05, + "loss": 0.4964, + "step": 293 + }, + { + "epoch": 2.5128205128205128, + "grad_norm": 0.728626549243927, + "learning_rate": 6.316203538407397e-05, + "loss": 0.7009, + "step": 294 + }, + { + "epoch": 2.5213675213675213, + "grad_norm": 0.5644152760505676, + "learning_rate": 6.252520798359092e-05, + "loss": 0.5498, + "step": 295 + }, + { + "epoch": 2.52991452991453, + "grad_norm": 0.5440083742141724, + "learning_rate": 6.18901438023543e-05, + "loss": 0.4946, + "step": 296 + }, + { + "epoch": 2.5384615384615383, + "grad_norm": 0.5415129661560059, + "learning_rate": 6.125687272064713e-05, + "loss": 0.5534, + "step": 297 + }, + { + "epoch": 2.547008547008547, + "grad_norm": 0.457343727350235, + "learning_rate": 6.0625424534385425e-05, + "loss": 0.6737, + "step": 298 + }, + { + "epoch": 2.5555555555555554, + "grad_norm": 0.6592293977737427, + "learning_rate": 5.9995828953716695e-05, + "loss": 0.64, + "step": 299 + }, + { + "epoch": 2.564102564102564, + "grad_norm": 0.591465413570404, + "learning_rate": 5.936811560162169e-05, + "loss": 0.5807, + "step": 300 + }, + { + "epoch": 2.5726495726495724, + "grad_norm": 0.5375930666923523, + "learning_rate": 5.87423140125209e-05, + "loss": 0.4945, + "step": 301 + }, + { + "epoch": 2.5811965811965814, + "grad_norm": 0.5260182619094849, + "learning_rate": 5.811845363088477e-05, + "loss": 0.4258, + "step": 302 + }, + { + "epoch": 2.58974358974359, + "grad_norm": 0.6136443614959717, + "learning_rate": 5.749656380984844e-05, + "loss": 0.5744, + "step": 303 + }, + { + "epoch": 2.5982905982905984, + "grad_norm": 0.6215261220932007, + "learning_rate": 5.687667380983037e-05, + "loss": 0.4933, + "step": 304 + }, + { + "epoch": 2.606837606837607, + "grad_norm": 0.5154852867126465, + "learning_rate": 5.625881279715615e-05, + "loss": 0.4296, + "step": 305 + }, + { + "epoch": 2.6153846153846154, + "grad_norm": 0.5293765664100647, + "learning_rate": 5.5643009842685554e-05, + "loss": 1.0884, + "step": 306 + }, + { + "epoch": 2.623931623931624, + "grad_norm": 0.5633432269096375, + "learning_rate": 5.502929392044528e-05, + "loss": 0.5541, + "step": 307 + }, + { + "epoch": 2.6324786324786325, + "grad_norm": 0.590496301651001, + "learning_rate": 5.4417693906265365e-05, + "loss": 0.4662, + "step": 308 + }, + { + "epoch": 2.641025641025641, + "grad_norm": 0.6000109910964966, + "learning_rate": 5.380823857642069e-05, + "loss": 0.5581, + "step": 309 + }, + { + "epoch": 2.6495726495726495, + "grad_norm": 0.5975021719932556, + "learning_rate": 5.3200956606277006e-05, + "loss": 0.861, + "step": 310 + }, + { + "epoch": 2.658119658119658, + "grad_norm": 0.5424284934997559, + "learning_rate": 5.259587656894174e-05, + "loss": 0.5272, + "step": 311 + }, + { + "epoch": 2.6666666666666665, + "grad_norm": 0.6322450041770935, + "learning_rate": 5.199302693391959e-05, + "loss": 0.6545, + "step": 312 + }, + { + "epoch": 2.6752136752136755, + "grad_norm": 0.9423356652259827, + "learning_rate": 5.139243606577302e-05, + "loss": 0.8078, + "step": 313 + }, + { + "epoch": 2.683760683760684, + "grad_norm": 0.6575957536697388, + "learning_rate": 5.0794132222787707e-05, + "loss": 0.5547, + "step": 314 + }, + { + "epoch": 2.6923076923076925, + "grad_norm": 0.6143584251403809, + "learning_rate": 5.019814355564292e-05, + "loss": 0.5707, + "step": 315 + }, + { + "epoch": 2.700854700854701, + "grad_norm": 0.5541775822639465, + "learning_rate": 4.960449810608705e-05, + "loss": 0.7209, + "step": 316 + }, + { + "epoch": 2.7094017094017095, + "grad_norm": 0.5190094113349915, + "learning_rate": 4.90132238056182e-05, + "loss": 0.5075, + "step": 317 + }, + { + "epoch": 2.717948717948718, + "grad_norm": 0.5351387858390808, + "learning_rate": 4.8424348474170014e-05, + "loss": 1.1994, + "step": 318 + }, + { + "epoch": 2.7264957264957266, + "grad_norm": 0.64601731300354, + "learning_rate": 4.783789981880267e-05, + "loss": 0.5779, + "step": 319 + }, + { + "epoch": 2.735042735042735, + "grad_norm": 0.46943098306655884, + "learning_rate": 4.725390543239929e-05, + "loss": 0.4131, + "step": 320 + }, + { + "epoch": 2.7435897435897436, + "grad_norm": 0.5379695296287537, + "learning_rate": 4.667239279236768e-05, + "loss": 0.6601, + "step": 321 + }, + { + "epoch": 2.752136752136752, + "grad_norm": 0.599001407623291, + "learning_rate": 4.609338925934743e-05, + "loss": 0.5375, + "step": 322 + }, + { + "epoch": 2.7606837606837606, + "grad_norm": 0.5188902616500854, + "learning_rate": 4.551692207592265e-05, + "loss": 0.9628, + "step": 323 + }, + { + "epoch": 2.769230769230769, + "grad_norm": 0.5495883226394653, + "learning_rate": 4.494301836534016e-05, + "loss": 0.5334, + "step": 324 + }, + { + "epoch": 2.7777777777777777, + "grad_norm": 0.6632270216941833, + "learning_rate": 4.4371705130233275e-05, + "loss": 0.5572, + "step": 325 + }, + { + "epoch": 2.786324786324786, + "grad_norm": 0.5476614236831665, + "learning_rate": 4.380300925135138e-05, + "loss": 0.4915, + "step": 326 + }, + { + "epoch": 2.7948717948717947, + "grad_norm": 0.5509811043739319, + "learning_rate": 4.3236957486295115e-05, + "loss": 1.2116, + "step": 327 + }, + { + "epoch": 2.8034188034188032, + "grad_norm": 0.4459514617919922, + "learning_rate": 4.267357646825746e-05, + "loss": 1.3973, + "step": 328 + }, + { + "epoch": 2.8119658119658117, + "grad_norm": 0.5664827823638916, + "learning_rate": 4.211289270477047e-05, + "loss": 0.5076, + "step": 329 + }, + { + "epoch": 2.8205128205128203, + "grad_norm": 0.5930613875389099, + "learning_rate": 4.1554932576458415e-05, + "loss": 0.5522, + "step": 330 + }, + { + "epoch": 2.8290598290598292, + "grad_norm": 0.5950198769569397, + "learning_rate": 4.0999722335796075e-05, + "loss": 1.1402, + "step": 331 + }, + { + "epoch": 2.8376068376068377, + "grad_norm": 0.5899688601493835, + "learning_rate": 4.044728810587406e-05, + "loss": 0.5293, + "step": 332 + }, + { + "epoch": 2.8461538461538463, + "grad_norm": 0.6274430751800537, + "learning_rate": 3.989765587916914e-05, + "loss": 0.4995, + "step": 333 + }, + { + "epoch": 2.8547008547008548, + "grad_norm": 0.5911152958869934, + "learning_rate": 3.935085151632185e-05, + "loss": 0.6738, + "step": 334 + }, + { + "epoch": 2.8632478632478633, + "grad_norm": 0.5615319013595581, + "learning_rate": 3.8806900744919205e-05, + "loss": 0.3968, + "step": 335 + }, + { + "epoch": 2.871794871794872, + "grad_norm": 0.5533549189567566, + "learning_rate": 3.826582915828468e-05, + "loss": 0.6669, + "step": 336 + }, + { + "epoch": 2.8803418803418803, + "grad_norm": 0.5834083557128906, + "learning_rate": 3.7727662214273495e-05, + "loss": 0.4875, + "step": 337 + }, + { + "epoch": 2.888888888888889, + "grad_norm": 0.4788981080055237, + "learning_rate": 3.719242523407539e-05, + "loss": 0.454, + "step": 338 + }, + { + "epoch": 2.8974358974358974, + "grad_norm": 0.49913716316223145, + "learning_rate": 3.666014340102268e-05, + "loss": 1.0155, + "step": 339 + }, + { + "epoch": 2.905982905982906, + "grad_norm": 0.5248069763183594, + "learning_rate": 3.613084175940578e-05, + "loss": 0.986, + "step": 340 + }, + { + "epoch": 2.9145299145299144, + "grad_norm": 0.5040814280509949, + "learning_rate": 3.5604545213294616e-05, + "loss": 0.9928, + "step": 341 + }, + { + "epoch": 2.9230769230769234, + "grad_norm": 0.538275420665741, + "learning_rate": 3.508127852536698e-05, + "loss": 0.8618, + "step": 342 + }, + { + "epoch": 2.931623931623932, + "grad_norm": 0.676364541053772, + "learning_rate": 3.456106631574336e-05, + "loss": 0.6912, + "step": 343 + }, + { + "epoch": 2.9401709401709404, + "grad_norm": 0.5177461504936218, + "learning_rate": 3.4043933060828605e-05, + "loss": 0.5507, + "step": 344 + }, + { + "epoch": 2.948717948717949, + "grad_norm": 0.5291532278060913, + "learning_rate": 3.352990309216022e-05, + "loss": 1.0143, + "step": 345 + }, + { + "epoch": 2.9572649572649574, + "grad_norm": 0.7094171047210693, + "learning_rate": 3.3019000595263574e-05, + "loss": 0.5838, + "step": 346 + }, + { + "epoch": 2.965811965811966, + "grad_norm": 0.5676212906837463, + "learning_rate": 3.251124960851408e-05, + "loss": 0.4447, + "step": 347 + }, + { + "epoch": 2.9743589743589745, + "grad_norm": 0.6674243211746216, + "learning_rate": 3.200667402200586e-05, + "loss": 0.6201, + "step": 348 + }, + { + "epoch": 2.982905982905983, + "grad_norm": 0.6357935070991516, + "learning_rate": 3.1505297576428075e-05, + "loss": 0.4907, + "step": 349 + }, + { + "epoch": 2.9914529914529915, + "grad_norm": 0.5493906736373901, + "learning_rate": 3.100714386194757e-05, + "loss": 0.5175, + "step": 350 + }, + { + "epoch": 3.0, + "grad_norm": 0.5719403028488159, + "learning_rate": 3.0512236317099175e-05, + "loss": 0.4602, + "step": 351 + }, + { + "epoch": 3.0085470085470085, + "grad_norm": 0.47898948192596436, + "learning_rate": 3.0020598227682795e-05, + "loss": 0.4222, + "step": 352 + }, + { + "epoch": 3.017094017094017, + "grad_norm": 0.5215709805488586, + "learning_rate": 2.953225272566782e-05, + "loss": 0.4546, + "step": 353 + }, + { + "epoch": 3.0256410256410255, + "grad_norm": 0.5061070919036865, + "learning_rate": 2.904722278810471e-05, + "loss": 0.3829, + "step": 354 + }, + { + "epoch": 3.034188034188034, + "grad_norm": 0.5508171319961548, + "learning_rate": 2.8565531236043997e-05, + "loss": 0.3597, + "step": 355 + }, + { + "epoch": 3.0427350427350426, + "grad_norm": 0.536913275718689, + "learning_rate": 2.8087200733462425e-05, + "loss": 0.4779, + "step": 356 + }, + { + "epoch": 3.051282051282051, + "grad_norm": 0.49380025267601013, + "learning_rate": 2.7612253786196664e-05, + "loss": 0.6221, + "step": 357 + }, + { + "epoch": 3.0598290598290596, + "grad_norm": 0.5332152247428894, + "learning_rate": 2.7140712740884376e-05, + "loss": 0.3698, + "step": 358 + }, + { + "epoch": 3.0683760683760686, + "grad_norm": 0.6104136109352112, + "learning_rate": 2.667259978391281e-05, + "loss": 0.4661, + "step": 359 + }, + { + "epoch": 3.076923076923077, + "grad_norm": 0.5976638793945312, + "learning_rate": 2.6207936940374767e-05, + "loss": 0.4368, + "step": 360 + }, + { + "epoch": 3.0854700854700856, + "grad_norm": 0.6200399398803711, + "learning_rate": 2.5746746073032625e-05, + "loss": 0.6395, + "step": 361 + }, + { + "epoch": 3.094017094017094, + "grad_norm": 0.4517454504966736, + "learning_rate": 2.5289048881289256e-05, + "loss": 0.3528, + "step": 362 + }, + { + "epoch": 3.1025641025641026, + "grad_norm": 0.5492653250694275, + "learning_rate": 2.4834866900167475e-05, + "loss": 0.4948, + "step": 363 + }, + { + "epoch": 3.111111111111111, + "grad_norm": 0.5452569723129272, + "learning_rate": 2.4384221499296466e-05, + "loss": 0.3313, + "step": 364 + }, + { + "epoch": 3.1196581196581197, + "grad_norm": 0.5563036799430847, + "learning_rate": 2.393713388190648e-05, + "loss": 0.3595, + "step": 365 + }, + { + "epoch": 3.128205128205128, + "grad_norm": 0.5114560723304749, + "learning_rate": 2.3493625083831217e-05, + "loss": 0.6397, + "step": 366 + }, + { + "epoch": 3.1367521367521367, + "grad_norm": 0.5896928310394287, + "learning_rate": 2.3053715972518e-05, + "loss": 0.4115, + "step": 367 + }, + { + "epoch": 3.1452991452991452, + "grad_norm": 0.5223737955093384, + "learning_rate": 2.2617427246045973e-05, + "loss": 0.9631, + "step": 368 + }, + { + "epoch": 3.1538461538461537, + "grad_norm": 0.5724557042121887, + "learning_rate": 2.218477943215229e-05, + "loss": 0.8638, + "step": 369 + }, + { + "epoch": 3.1623931623931623, + "grad_norm": 0.5983072519302368, + "learning_rate": 2.1755792887266234e-05, + "loss": 0.4377, + "step": 370 + }, + { + "epoch": 3.1709401709401708, + "grad_norm": 0.5746665596961975, + "learning_rate": 2.133048779555129e-05, + "loss": 0.7967, + "step": 371 + }, + { + "epoch": 3.1794871794871793, + "grad_norm": 0.6954648494720459, + "learning_rate": 2.0908884167955824e-05, + "loss": 0.5664, + "step": 372 + }, + { + "epoch": 3.1880341880341883, + "grad_norm": 0.6002750992774963, + "learning_rate": 2.0491001841271074e-05, + "loss": 0.3827, + "step": 373 + }, + { + "epoch": 3.1965811965811968, + "grad_norm": 0.5801351070404053, + "learning_rate": 2.0076860477198313e-05, + "loss": 0.2977, + "step": 374 + }, + { + "epoch": 3.2051282051282053, + "grad_norm": 0.5990070700645447, + "learning_rate": 1.9666479561423244e-05, + "loss": 0.412, + "step": 375 + }, + { + "epoch": 3.213675213675214, + "grad_norm": 0.6645095944404602, + "learning_rate": 1.9259878402699705e-05, + "loss": 0.3139, + "step": 376 + }, + { + "epoch": 3.2222222222222223, + "grad_norm": 0.6228720545768738, + "learning_rate": 1.8857076131940642e-05, + "loss": 0.2904, + "step": 377 + }, + { + "epoch": 3.230769230769231, + "grad_norm": 0.5699615478515625, + "learning_rate": 1.8458091701318504e-05, + "loss": 0.4066, + "step": 378 + }, + { + "epoch": 3.2393162393162394, + "grad_norm": 0.6185857653617859, + "learning_rate": 1.806294388337305e-05, + "loss": 0.3796, + "step": 379 + }, + { + "epoch": 3.247863247863248, + "grad_norm": 0.6687190532684326, + "learning_rate": 1.7671651270128532e-05, + "loss": 0.4525, + "step": 380 + }, + { + "epoch": 3.2564102564102564, + "grad_norm": 0.6033667325973511, + "learning_rate": 1.7284232272218504e-05, + "loss": 0.3511, + "step": 381 + }, + { + "epoch": 3.264957264957265, + "grad_norm": 0.5065014362335205, + "learning_rate": 1.69007051180199e-05, + "loss": 0.9888, + "step": 382 + }, + { + "epoch": 3.2735042735042734, + "grad_norm": 0.7028838396072388, + "learning_rate": 1.652108785279526e-05, + "loss": 0.3583, + "step": 383 + }, + { + "epoch": 3.282051282051282, + "grad_norm": 0.6298937201499939, + "learning_rate": 1.6145398337843652e-05, + "loss": 0.2703, + "step": 384 + }, + { + "epoch": 3.2905982905982905, + "grad_norm": 0.6196032762527466, + "learning_rate": 1.577365424966034e-05, + "loss": 0.3237, + "step": 385 + }, + { + "epoch": 3.299145299145299, + "grad_norm": 0.6455730199813843, + "learning_rate": 1.540587307910508e-05, + "loss": 0.7186, + "step": 386 + }, + { + "epoch": 3.3076923076923075, + "grad_norm": 0.5806525945663452, + "learning_rate": 1.504207213057912e-05, + "loss": 0.9131, + "step": 387 + }, + { + "epoch": 3.316239316239316, + "grad_norm": 0.5811147093772888, + "learning_rate": 1.4682268521211073e-05, + "loss": 1.0932, + "step": 388 + }, + { + "epoch": 3.324786324786325, + "grad_norm": 0.5248343348503113, + "learning_rate": 1.43264791800515e-05, + "loss": 0.3267, + "step": 389 + }, + { + "epoch": 3.3333333333333335, + "grad_norm": 0.5175590515136719, + "learning_rate": 1.3974720847276412e-05, + "loss": 0.2435, + "step": 390 + }, + { + "epoch": 3.341880341880342, + "grad_norm": 0.6030406951904297, + "learning_rate": 1.3627010073399604e-05, + "loss": 0.4121, + "step": 391 + }, + { + "epoch": 3.3504273504273505, + "grad_norm": 0.6788750886917114, + "learning_rate": 1.328336321849396e-05, + "loss": 0.3838, + "step": 392 + }, + { + "epoch": 3.358974358974359, + "grad_norm": 0.651418149471283, + "learning_rate": 1.2943796451421686e-05, + "loss": 0.6817, + "step": 393 + }, + { + "epoch": 3.3675213675213675, + "grad_norm": 0.7357457876205444, + "learning_rate": 1.2608325749073591e-05, + "loss": 0.3874, + "step": 394 + }, + { + "epoch": 3.376068376068376, + "grad_norm": 0.6203145980834961, + "learning_rate": 1.227696689561727e-05, + "loss": 0.3317, + "step": 395 + }, + { + "epoch": 3.3846153846153846, + "grad_norm": 0.6154266595840454, + "learning_rate": 1.1949735481754565e-05, + "loss": 0.261, + "step": 396 + }, + { + "epoch": 3.393162393162393, + "grad_norm": 0.5869407057762146, + "learning_rate": 1.1626646903987904e-05, + "loss": 0.3414, + "step": 397 + }, + { + "epoch": 3.4017094017094016, + "grad_norm": 0.8472902178764343, + "learning_rate": 1.130771636389596e-05, + "loss": 0.4548, + "step": 398 + }, + { + "epoch": 3.41025641025641, + "grad_norm": 0.7946684956550598, + "learning_rate": 1.0992958867418357e-05, + "loss": 0.3432, + "step": 399 + }, + { + "epoch": 3.4188034188034186, + "grad_norm": 0.6546379327774048, + "learning_rate": 1.0682389224149647e-05, + "loss": 0.3254, + "step": 400 + }, + { + "epoch": 3.427350427350427, + "grad_norm": 0.605717658996582, + "learning_rate": 1.037602204664252e-05, + "loss": 0.288, + "step": 401 + }, + { + "epoch": 3.435897435897436, + "grad_norm": 0.6145480275154114, + "learning_rate": 1.0073871749720221e-05, + "loss": 0.3971, + "step": 402 + }, + { + "epoch": 3.4444444444444446, + "grad_norm": 0.5344141125679016, + "learning_rate": 9.775952549798406e-06, + "loss": 0.3396, + "step": 403 + }, + { + "epoch": 3.452991452991453, + "grad_norm": 0.572514533996582, + "learning_rate": 9.482278464216121e-06, + "loss": 0.9024, + "step": 404 + }, + { + "epoch": 3.4615384615384617, + "grad_norm": 0.6153191328048706, + "learning_rate": 9.192863310576472e-06, + "loss": 0.6065, + "step": 405 + }, + { + "epoch": 3.47008547008547, + "grad_norm": 0.6530014872550964, + "learning_rate": 8.907720706096224e-06, + "loss": 0.906, + "step": 406 + }, + { + "epoch": 3.4786324786324787, + "grad_norm": 0.6044769883155823, + "learning_rate": 8.626864066965402e-06, + "loss": 0.3723, + "step": 407 + }, + { + "epoch": 3.4871794871794872, + "grad_norm": 0.6298689246177673, + "learning_rate": 8.350306607715774e-06, + "loss": 0.4325, + "step": 408 + }, + { + "epoch": 3.4957264957264957, + "grad_norm": 0.7200799584388733, + "learning_rate": 8.07806134059933e-06, + "loss": 0.3955, + "step": 409 + }, + { + "epoch": 3.5042735042735043, + "grad_norm": 0.6333838701248169, + "learning_rate": 7.810141074975818e-06, + "loss": 0.5314, + "step": 410 + }, + { + "epoch": 3.5128205128205128, + "grad_norm": 0.6816018223762512, + "learning_rate": 7.546558416710292e-06, + "loss": 0.3222, + "step": 411 + }, + { + "epoch": 3.5213675213675213, + "grad_norm": 0.801074743270874, + "learning_rate": 7.287325767579756e-06, + "loss": 0.5049, + "step": 412 + }, + { + "epoch": 3.52991452991453, + "grad_norm": 0.7386384010314941, + "learning_rate": 7.032455324689902e-06, + "loss": 0.4566, + "step": 413 + }, + { + "epoch": 3.5384615384615383, + "grad_norm": 0.5370846390724182, + "learning_rate": 6.781959079900957e-06, + "loss": 0.46, + "step": 414 + }, + { + "epoch": 3.547008547008547, + "grad_norm": 0.6192382574081421, + "learning_rate": 6.535848819263679e-06, + "loss": 0.7709, + "step": 415 + }, + { + "epoch": 3.5555555555555554, + "grad_norm": 0.7281822562217712, + "learning_rate": 6.2941361224647e-06, + "loss": 0.4262, + "step": 416 + }, + { + "epoch": 3.564102564102564, + "grad_norm": 0.6416460871696472, + "learning_rate": 6.056832362281728e-06, + "loss": 0.3682, + "step": 417 + }, + { + "epoch": 3.5726495726495724, + "grad_norm": 0.6256207823753357, + "learning_rate": 5.823948704048443e-06, + "loss": 0.3682, + "step": 418 + }, + { + "epoch": 3.5811965811965814, + "grad_norm": 0.6697499752044678, + "learning_rate": 5.5954961051291384e-06, + "loss": 0.3754, + "step": 419 + }, + { + "epoch": 3.58974358974359, + "grad_norm": 0.6696683168411255, + "learning_rate": 5.371485314403202e-06, + "loss": 0.4513, + "step": 420 + }, + { + "epoch": 3.5982905982905984, + "grad_norm": 0.7542429566383362, + "learning_rate": 5.151926871759349e-06, + "loss": 0.4494, + "step": 421 + }, + { + "epoch": 3.606837606837607, + "grad_norm": 0.8225255012512207, + "learning_rate": 4.936831107599749e-06, + "loss": 0.4065, + "step": 422 + }, + { + "epoch": 3.6153846153846154, + "grad_norm": 0.7125111818313599, + "learning_rate": 4.7262081423538716e-06, + "loss": 0.9624, + "step": 423 + }, + { + "epoch": 3.623931623931624, + "grad_norm": 0.6715333461761475, + "learning_rate": 4.5200678860024885e-06, + "loss": 0.6208, + "step": 424 + }, + { + "epoch": 3.6324786324786325, + "grad_norm": 0.629646897315979, + "learning_rate": 4.3184200376111815e-06, + "loss": 0.2705, + "step": 425 + }, + { + "epoch": 3.641025641025641, + "grad_norm": 0.6048184037208557, + "learning_rate": 4.121274084874194e-06, + "loss": 0.3177, + "step": 426 + }, + { + "epoch": 3.6495726495726495, + "grad_norm": 0.6677070260047913, + "learning_rate": 3.928639303667891e-06, + "loss": 0.3325, + "step": 427 + }, + { + "epoch": 3.658119658119658, + "grad_norm": 0.6173528432846069, + "learning_rate": 3.7405247576144054e-06, + "loss": 0.3395, + "step": 428 + }, + { + "epoch": 3.6666666666666665, + "grad_norm": 0.7127820253372192, + "learning_rate": 3.556939297655115e-06, + "loss": 0.475, + "step": 429 + }, + { + "epoch": 3.6752136752136755, + "grad_norm": 0.7372745871543884, + "learning_rate": 3.3778915616342943e-06, + "loss": 0.388, + "step": 430 + }, + { + "epoch": 3.683760683760684, + "grad_norm": 0.6171187162399292, + "learning_rate": 3.203389973892579e-06, + "loss": 0.3461, + "step": 431 + }, + { + "epoch": 3.6923076923076925, + "grad_norm": 0.6665316820144653, + "learning_rate": 3.0334427448706847e-06, + "loss": 0.3346, + "step": 432 + }, + { + "epoch": 3.700854700854701, + "grad_norm": 0.5912784934043884, + "learning_rate": 2.868057870723073e-06, + "loss": 0.3323, + "step": 433 + }, + { + "epoch": 3.7094017094017095, + "grad_norm": 0.6046373248100281, + "learning_rate": 2.707243132941717e-06, + "loss": 0.3549, + "step": 434 + }, + { + "epoch": 3.717948717948718, + "grad_norm": 0.6346151828765869, + "learning_rate": 2.5510060979899607e-06, + "loss": 0.3929, + "step": 435 + }, + { + "epoch": 3.7264957264957266, + "grad_norm": 0.6302003264427185, + "learning_rate": 2.3993541169465837e-06, + "loss": 0.8806, + "step": 436 + }, + { + "epoch": 3.735042735042735, + "grad_norm": 0.7293457388877869, + "learning_rate": 2.2522943251597873e-06, + "loss": 0.3121, + "step": 437 + }, + { + "epoch": 3.7435897435897436, + "grad_norm": 0.6578421592712402, + "learning_rate": 2.1098336419116625e-06, + "loss": 0.4226, + "step": 438 + }, + { + "epoch": 3.752136752136752, + "grad_norm": 0.7294906377792358, + "learning_rate": 1.971978770092431e-06, + "loss": 0.4121, + "step": 439 + }, + { + "epoch": 3.7606837606837606, + "grad_norm": 0.7280606031417847, + "learning_rate": 1.838736195885238e-06, + "loss": 0.6495, + "step": 440 + }, + { + "epoch": 3.769230769230769, + "grad_norm": 0.5946572422981262, + "learning_rate": 1.710112188460844e-06, + "loss": 0.3117, + "step": 441 + }, + { + "epoch": 3.7777777777777777, + "grad_norm": 0.7124819159507751, + "learning_rate": 1.5861127996827597e-06, + "loss": 0.4253, + "step": 442 + }, + { + "epoch": 3.786324786324786, + "grad_norm": 0.6873694062232971, + "learning_rate": 1.4667438638224062e-06, + "loss": 0.3372, + "step": 443 + }, + { + "epoch": 3.7948717948717947, + "grad_norm": 0.7644034028053284, + "learning_rate": 1.3520109972846917e-06, + "loss": 0.6939, + "step": 444 + }, + { + "epoch": 3.8034188034188032, + "grad_norm": 0.6656678318977356, + "learning_rate": 1.2419195983436881e-06, + "loss": 0.4534, + "step": 445 + }, + { + "epoch": 3.8119658119658117, + "grad_norm": 0.6700231432914734, + "learning_rate": 1.1364748468886687e-06, + "loss": 1.0909, + "step": 446 + }, + { + "epoch": 3.8205128205128203, + "grad_norm": 0.6248735785484314, + "learning_rate": 1.0356817041804246e-06, + "loss": 0.9308, + "step": 447 + }, + { + "epoch": 3.8290598290598292, + "grad_norm": 0.5876209139823914, + "learning_rate": 9.395449126177291e-07, + "loss": 0.2772, + "step": 448 + }, + { + "epoch": 3.8376068376068377, + "grad_norm": 0.6204436421394348, + "learning_rate": 8.480689955143395e-07, + "loss": 0.5241, + "step": 449 + }, + { + "epoch": 3.8461538461538463, + "grad_norm": 0.6888920068740845, + "learning_rate": 7.612582568860549e-07, + "loss": 0.4183, + "step": 450 + }, + { + "epoch": 3.8547008547008548, + "grad_norm": 0.5856114029884338, + "learning_rate": 6.791167812483012e-07, + "loss": 0.739, + "step": 451 + }, + { + "epoch": 3.8632478632478633, + "grad_norm": 0.7206133604049683, + "learning_rate": 6.016484334238515e-07, + "loss": 0.598, + "step": 452 + }, + { + "epoch": 3.871794871794872, + "grad_norm": 0.6243966817855835, + "learning_rate": 5.288568583610931e-07, + "loss": 0.323, + "step": 453 + }, + { + "epoch": 3.8803418803418803, + "grad_norm": 0.5875467658042908, + "learning_rate": 4.607454809624434e-07, + "loss": 0.3422, + "step": 454 + }, + { + "epoch": 3.888888888888889, + "grad_norm": 0.6117106080055237, + "learning_rate": 3.9731750592325587e-07, + "loss": 0.3257, + "step": 455 + }, + { + "epoch": 3.8974358974358974, + "grad_norm": 0.5987035036087036, + "learning_rate": 3.385759175809966e-07, + "loss": 0.3459, + "step": 456 + }, + { + "epoch": 3.905982905982906, + "grad_norm": 0.688611626625061, + "learning_rate": 2.845234797748897e-07, + "loss": 0.6111, + "step": 457 + }, + { + "epoch": 3.9145299145299144, + "grad_norm": 0.651611328125, + "learning_rate": 2.3516273571577708e-07, + "loss": 0.3729, + "step": 458 + }, + { + "epoch": 3.9230769230769234, + "grad_norm": 0.6339864730834961, + "learning_rate": 1.9049600786658073e-07, + "loss": 0.4055, + "step": 459 + }, + { + "epoch": 3.931623931623932, + "grad_norm": 0.5652241706848145, + "learning_rate": 1.505253978329235e-07, + "loss": 0.7407, + "step": 460 + }, + { + "epoch": 3.9401709401709404, + "grad_norm": 0.7055443525314331, + "learning_rate": 1.1525278626431934e-07, + "loss": 0.4277, + "step": 461 + }, + { + "epoch": 3.948717948717949, + "grad_norm": 0.5502326488494873, + "learning_rate": 8.467983276563284e-08, + "loss": 0.8916, + "step": 462 + }, + { + "epoch": 3.9572649572649574, + "grad_norm": 0.6527960896492004, + "learning_rate": 5.880797581904185e-08, + "loss": 0.3563, + "step": 463 + }, + { + "epoch": 3.965811965811966, + "grad_norm": 0.6903603672981262, + "learning_rate": 3.763843271631373e-08, + "loss": 0.5626, + "step": 464 + }, + { + "epoch": 3.9743589743589745, + "grad_norm": 0.7031790614128113, + "learning_rate": 2.1172199501573455e-08, + "loss": 0.3928, + "step": 465 + }, + { + "epoch": 3.982905982905983, + "grad_norm": 0.7574213147163391, + "learning_rate": 9.410050924374415e-09, + "loss": 0.5154, + "step": 466 + }, + { + "epoch": 3.9914529914529915, + "grad_norm": 0.7292647361755371, + "learning_rate": 2.3525404033275523e-09, + "loss": 0.4163, + "step": 467 + }, + { + "epoch": 4.0, + "grad_norm": 0.6970239281654358, + "learning_rate": 0.0, + "loss": 0.4192, + "step": 468 + } + ], + "logging_steps": 1, + "max_steps": 468, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 117, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 3.039339273686876e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-468/training_args.bin b/checkpoint-468/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..6aa0501cedc8c6a042abaac1eb0d2755310396ba --- /dev/null +++ b/checkpoint-468/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7fe3839cfcc5a93b060094e1030e134d680eeeb9bb2bdbde204831612dbb1c1 +size 6840 diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a579fb3d7618057647f9bd24875e46febe9c5b31 --- /dev/null +++ b/config.json @@ -0,0 +1,31 @@ +{ + "_attn_implementation_autoset": true, + "_name_or_path": "/cpool/DeepSeek-R1-Distill-Qwen-7B", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151646, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "max_position_embeddings": 131072, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.47.1", + "use_cache": false, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151665 +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b068ffca3220a746ba50cc69f850e544217e3a86 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,195 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": null, + "use_default_system_prompt": false +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..6aa0501cedc8c6a042abaac1eb0d2755310396ba --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7fe3839cfcc5a93b060094e1030e134d680eeeb9bb2bdbde204831612dbb1c1 +size 6840