Upload folder using huggingface_hub

README.md

@@ -0,0 +1,165 @@
+---
+library_name: peft
+base_model: HuggingFaceM4/tiny-random-LlamaForCausalLM
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 4aaa096e-6137-4be8-bec2-b203dccb0315
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+adapter: lora
+base_model: HuggingFaceM4/tiny-random-LlamaForCausalLM
+bf16: auto
+chat_template: llama3
+data_processes: 16
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - f73991f5cd91c359_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/f73991f5cd91c359_train_data.json
+  type:
+    field_instruction: source_article
+    field_output: logical_fallacies
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device_map: auto
+do_eval: true
+early_stopping_patience: 1
+eval_batch_size: 8
+eval_max_new_tokens: 128
+eval_steps: 25
+eval_table_size: null
+evals_per_epoch: null
+flash_attention: true
+fp16: null
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: sn5601/4aaa096e-6137-4be8-bec2-b203dccb0315
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0003
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: 32
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 16
+lora_target_linear: true
+lr_scheduler: cosine
+max_grad_norm: 1.0
+max_memory:
+  0: 70GB
+max_steps: 200
+micro_batch_size: 8
+mlflow_experiment_name: /tmp/f73991f5cd91c359_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 2
+optim_args:
+  adam_beta1: 0.9
+  adam_beta2: 0.95
+  adam_epsilon: 1e-5
+optimizer: adamw_torch
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 50
+saves_per_epoch: null
+sequence_len: 1028
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 50
+wandb_entity: sn56-miner
+wandb_mode: disabled
+wandb_name: 4aaa096e-6137-4be8-bec2-b203dccb0315
+wandb_project: god
+wandb_run: 1ffj
+wandb_runid: 4aaa096e-6137-4be8-bec2-b203dccb0315
+warmup_steps: 10
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 4aaa096e-6137-4be8-bec2-b203dccb0315
+
+This model is a fine-tuned version of [HuggingFaceM4/tiny-random-LlamaForCausalLM](https://huggingface.co/HuggingFaceM4/tiny-random-LlamaForCausalLM) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.3421
+
+## 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: 0.0003
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- training_steps: 55
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 10.3832       | 0.0364 | 1    | 10.3782         |
+| 10.3575       | 0.9091 | 25   | 10.3589         |
+| 10.2515       | 1.8182 | 50   | 10.3421         |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceM4/tiny-random-LlamaForCausalLM",
+  "bias": "none",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be4f380541773c323d50b0123abe13a44b04af3e0c033b89438093de313fce7b
+size 57218

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:720094059549fcf949f590d63d51c3664a9b27559b01b45d98a2a451b713e7c7
+size 50624

config.json

@@ -0,0 +1,32 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "HuggingFaceM4/tiny-random-LlamaForCausalLM",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "head_dim": 4,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "pad_token_id": -1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: HuggingFaceM4/tiny-random-LlamaForCausalLM
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **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]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+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
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[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 0.13.2

last-checkpoint/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceM4/tiny-random-LlamaForCausalLM",
+  "bias": "none",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08387f8600697465ba9a491255fc6ac96d723384a7765957397f847eb21cc26f
+size 50624

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a90035845e92a04b624f9d8e89ea0ea156c9d13d2f83650c5d38069a9c23869
+size 118090

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cccbbe8b3a7f210f134f20451255943ad2a2fc7b83f11c3f61d2fc33985bfd4
+size 15024

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe0439324d17dc7b562b80e24e173a3a219afc7889095d3d6b290fa9cb1697e
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f614c7b6eb2d3ec336cedccb565b4ee318fd85a0dee96e5aba91bc0f0e70173
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bbee8346ba18531760fa9aaff3a4f6c1f08d06972b4eec1b3624257a2bd8738
+size 15024

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f590ad1ae5c8e7b4f203a10a7ab525a3ee9074e4623aa7b9c3bf0ec215582052
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,451 @@
+{
+  "best_metric": 10.342057228088379,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.0,
+  "eval_steps": 25,
+  "global_step": 55,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03636363636363636,
+      "grad_norm": 0.053593236953020096,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 10.3832,
+      "step": 1
+    },
+    {
+      "epoch": 0.03636363636363636,
+      "eval_loss": 10.378164291381836,
+      "eval_runtime": 0.0279,
+      "eval_samples_per_second": 1791.519,
+      "eval_steps_per_second": 71.661,
+      "step": 1
+    },
+    {
+      "epoch": 0.07272727272727272,
+      "grad_norm": 0.0719698965549469,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 10.3838,
+      "step": 2
+    },
+    {
+      "epoch": 0.10909090909090909,
+      "grad_norm": 0.06865470856428146,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 10.387,
+      "step": 3
+    },
+    {
+      "epoch": 0.14545454545454545,
+      "grad_norm": 0.06494639068841934,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 10.3776,
+      "step": 4
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 0.07901167124509811,
+      "learning_rate": 0.00015,
+      "loss": 10.3681,
+      "step": 5
+    },
+    {
+      "epoch": 0.21818181818181817,
+      "grad_norm": 0.08017783612012863,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 10.3657,
+      "step": 6
+    },
+    {
+      "epoch": 0.2545454545454545,
+      "grad_norm": 0.09101555496454239,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 10.3732,
+      "step": 7
+    },
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 0.0688958540558815,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 10.3835,
+      "step": 8
+    },
+    {
+      "epoch": 0.32727272727272727,
+      "grad_norm": 0.06125740706920624,
+      "learning_rate": 0.00027,
+      "loss": 10.3758,
+      "step": 9
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.06640874594449997,
+      "learning_rate": 0.0003,
+      "loss": 10.3775,
+      "step": 10
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.0719643160700798,
+      "learning_rate": 0.0002996346075389736,
+      "loss": 10.3663,
+      "step": 11
+    },
+    {
+      "epoch": 0.43636363636363634,
+      "grad_norm": 0.07772038131952286,
+      "learning_rate": 0.0002985402103112355,
+      "loss": 10.3645,
+      "step": 12
+    },
+    {
+      "epoch": 0.4727272727272727,
+      "grad_norm": 0.0938938781619072,
+      "learning_rate": 0.0002967221401100708,
+      "loss": 10.367,
+      "step": 13
+    },
+    {
+      "epoch": 0.509090909090909,
+      "grad_norm": 0.08113312721252441,
+      "learning_rate": 0.0002941892543907478,
+      "loss": 10.3683,
+      "step": 14
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 0.06998950242996216,
+      "learning_rate": 0.0002909538931178862,
+      "loss": 10.3734,
+      "step": 15
+    },
+    {
+      "epoch": 0.5818181818181818,
+      "grad_norm": 0.08119933307170868,
+      "learning_rate": 0.0002870318186463901,
+      "loss": 10.3699,
+      "step": 16
+    },
+    {
+      "epoch": 0.6181818181818182,
+      "grad_norm": 0.08904324471950531,
+      "learning_rate": 0.000282442138928839,
+      "loss": 10.3694,
+      "step": 17
+    },
+    {
+      "epoch": 0.6545454545454545,
+      "grad_norm": 0.10189718008041382,
+      "learning_rate": 0.00027720721442346387,
+      "loss": 10.364,
+      "step": 18
+    },
+    {
+      "epoch": 0.6909090909090909,
+      "grad_norm": 0.11545747518539429,
+      "learning_rate": 0.0002713525491562421,
+      "loss": 10.3577,
+      "step": 19
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.13165277242660522,
+      "learning_rate": 0.00026490666646784665,
+      "loss": 10.3543,
+      "step": 20
+    },
+    {
+      "epoch": 0.7636363636363637,
+      "grad_norm": 0.08963130414485931,
+      "learning_rate": 0.00025790097005079764,
+      "loss": 10.365,
+      "step": 21
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.09903620183467865,
+      "learning_rate": 0.0002503695909538287,
+      "loss": 10.3707,
+      "step": 22
+    },
+    {
+      "epoch": 0.8363636363636363,
+      "grad_norm": 0.11109227687120438,
+      "learning_rate": 0.0002423492212988487,
+      "loss": 10.3652,
+      "step": 23
+    },
+    {
+      "epoch": 0.8727272727272727,
+      "grad_norm": 0.1090570017695427,
+      "learning_rate": 0.00023387893552061199,
+      "loss": 10.3653,
+      "step": 24
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.13384577631950378,
+      "learning_rate": 0.000225,
+      "loss": 10.3575,
+      "step": 25
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "eval_loss": 10.358928680419922,
+      "eval_runtime": 0.0255,
+      "eval_samples_per_second": 1959.552,
+      "eval_steps_per_second": 78.382,
+      "step": 25
+    },
+    {
+      "epoch": 0.9454545454545454,
+      "grad_norm": 0.15895330905914307,
+      "learning_rate": 0.0002157556720183616,
+      "loss": 10.3534,
+      "step": 26
+    },
+    {
+      "epoch": 0.9818181818181818,
+      "grad_norm": 0.20174622535705566,
+      "learning_rate": 0.0002061909890123868,
+      "loss": 10.3444,
+      "step": 27
+    },
+    {
+      "epoch": 1.018181818181818,
+      "grad_norm": 0.16725529730319977,
+      "learning_rate": 0.0001963525491562421,
+      "loss": 15.2738,
+      "step": 28
+    },
+    {
+      "epoch": 1.0545454545454545,
+      "grad_norm": 0.14053358137607574,
+      "learning_rate": 0.00018628828433995013,
+      "loss": 10.7264,
+      "step": 29
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.1419118493795395,
+      "learning_rate": 0.00017604722665003956,
+      "loss": 10.3282,
+      "step": 30
+    },
+    {
+      "epoch": 1.1272727272727272,
+      "grad_norm": 0.1286211758852005,
+      "learning_rate": 0.000165679269490148,
+      "loss": 10.4223,
+      "step": 31
+    },
+    {
+      "epoch": 1.1636363636363636,
+      "grad_norm": 0.1603860706090927,
+      "learning_rate": 0.00015523492450537517,
+      "loss": 10.01,
+      "step": 32
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.1688288301229477,
+      "learning_rate": 0.0001447650754946249,
+      "loss": 10.4474,
+      "step": 33
+    },
+    {
+      "epoch": 1.2363636363636363,
+      "grad_norm": 0.19430461525917053,
+      "learning_rate": 0.000134320730509852,
+      "loss": 10.3057,
+      "step": 34
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 0.13318559527397156,
+      "learning_rate": 0.00012395277334996044,
+      "loss": 10.1536,
+      "step": 35
+    },
+    {
+      "epoch": 1.309090909090909,
+      "grad_norm": 0.1425338089466095,
+      "learning_rate": 0.00011371171566004985,
+      "loss": 10.5162,
+      "step": 36
+    },
+    {
+      "epoch": 1.3454545454545455,
+      "grad_norm": 0.16739521920681,
+      "learning_rate": 0.0001036474508437579,
+      "loss": 10.507,
+      "step": 37
+    },
+    {
+      "epoch": 1.3818181818181818,
+      "grad_norm": 0.1579529196023941,
+      "learning_rate": 9.380901098761319e-05,
+      "loss": 10.5032,
+      "step": 38
+    },
+    {
+      "epoch": 1.4181818181818182,
+      "grad_norm": 0.1803933084011078,
+      "learning_rate": 8.424432798163836e-05,
+      "loss": 10.1584,
+      "step": 39
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 0.16928422451019287,
+      "learning_rate": 7.500000000000002e-05,
+      "loss": 10.4381,
+      "step": 40
+    },
+    {
+      "epoch": 1.490909090909091,
+      "grad_norm": 0.21556209027767181,
+      "learning_rate": 6.612106447938799e-05,
+      "loss": 9.8712,
+      "step": 41
+    },
+    {
+      "epoch": 1.5272727272727273,
+      "grad_norm": 0.15240442752838135,
+      "learning_rate": 5.765077870115125e-05,
+      "loss": 10.8775,
+      "step": 42
+    },
+    {
+      "epoch": 1.5636363636363635,
+      "grad_norm": 0.16723187267780304,
+      "learning_rate": 4.963040904617131e-05,
+      "loss": 10.2402,
+      "step": 43
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.14805755019187927,
+      "learning_rate": 4.209902994920235e-05,
+      "loss": 10.3794,
+      "step": 44
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 0.15014056861400604,
+      "learning_rate": 3.509333353215331e-05,
+      "loss": 10.2888,
+      "step": 45
+    },
+    {
+      "epoch": 1.6727272727272728,
+      "grad_norm": 0.18044382333755493,
+      "learning_rate": 2.8647450843757897e-05,
+      "loss": 10.233,
+      "step": 46
+    },
+    {
+      "epoch": 1.709090909090909,
+      "grad_norm": 0.19778087735176086,
+      "learning_rate": 2.2792785576536105e-05,
+      "loss": 10.4606,
+      "step": 47
+    },
+    {
+      "epoch": 1.7454545454545456,
+      "grad_norm": 0.17388062179088593,
+      "learning_rate": 1.755786107116095e-05,
+      "loss": 9.9209,
+      "step": 48
+    },
+    {
+      "epoch": 1.7818181818181817,
+      "grad_norm": 0.17143942415714264,
+      "learning_rate": 1.2968181353609852e-05,
+      "loss": 10.6057,
+      "step": 49
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.17745201289653778,
+      "learning_rate": 9.046106882113751e-06,
+      "loss": 10.2515,
+      "step": 50
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "eval_loss": 10.342057228088379,
+      "eval_runtime": 0.0256,
+      "eval_samples_per_second": 1953.256,
+      "eval_steps_per_second": 78.13,
+      "step": 50
+    },
+    {
+      "epoch": 1.8545454545454545,
+      "grad_norm": 0.16553938388824463,
+      "learning_rate": 5.810745609252165e-06,
+      "loss": 10.6196,
+      "step": 51
+    },
+    {
+      "epoch": 1.8909090909090909,
+      "grad_norm": 0.179793581366539,
+      "learning_rate": 3.2778598899291465e-06,
+      "loss": 10.0928,
+      "step": 52
+    },
+    {
+      "epoch": 1.9272727272727272,
+      "grad_norm": 0.17320050299167633,
+      "learning_rate": 1.4597896887644456e-06,
+      "loss": 10.5475,
+      "step": 53
+    },
+    {
+      "epoch": 1.9636363636363636,
+      "grad_norm": 0.2175627201795578,
+      "learning_rate": 3.653924610263703e-07,
+      "loss": 10.4599,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.26624709367752075,
+      "learning_rate": 0.0,
+      "loss": 15.3055,
+      "step": 55
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 55,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 1,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 24451393781760.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d4b104e07637dc08c7b48deaa0635de70547826b08e60db5c2b0c75ca2886d3
+size 6840

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d4b104e07637dc08c7b48deaa0635de70547826b08e60db5c2b0c75ca2886d3
+size 6840