Upload folder using huggingface_hub

README.md

@@ -0,0 +1,172 @@
+---
+base_model: deepseek-ai/deepseek-math-7b-rl
+library_name: peft
+license: other
+tags:
+- generated_from_trainer
+model-index:
+- name: workspace/axolotl/vinh/deepseek-ai_deepseek-math-7b-rl-lora-2024-07-01-15-56-34
+  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/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+base_model: deepseek-ai/deepseek-math-7b-rl
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+ 
+datasets:
+  - path: /workspace/axolotl/vinh/PAL/input_output_dsmath.json
+    type: input_output
+dataset_prepared_path:
+val_set_size: 0.05
+eval_sample_packing: false
+output_dir: /workspace/axolotl/vinh/deepseek-ai_deepseek-math-7b-rl-lora-2024-07-01-15-56-34
+
+sequence_len: 2048
+sample_packing: false
+pad_to_sequence_len: false
+
+adapter: lora
+lora_model_dir: 
+lora_r: 64
+lora_alpha: 128
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 128
+micro_batch_size: 1
+num_epochs: 3
+optimizer: paged_adamw_32bit
+lr_scheduler: cosine
+learning_rate: 2e-4
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: false
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention: 
+flash_attention: true
+s2_attention:
+
+loss_watchdog_threshold: 5.0
+loss_watchdog_patience: 3
+
+warmup_steps: 10
+evals_per_epoch: 10
+eval_table_size:
+eval_max_new_tokens: 512
+saves_per_epoch: 2
+save_total_limit: 20
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+   pad_token: <｜end▁of▁sentence｜>
+
+```
+
+</details><br>
+
+# workspace/axolotl/vinh/deepseek-ai_deepseek-math-7b-rl-lora-2024-07-01-15-56-34
+
+This model is a fine-tuned version of [deepseek-ai/deepseek-math-7b-rl](https://huggingface.co/deepseek-ai/deepseek-math-7b-rl) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0276
+
+## 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
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.4197        | 0.0095 | 1    | 0.4128          |
+| 0.0885        | 0.1043 | 11   | 0.0781          |
+| 0.0482        | 0.2086 | 22   | 0.0517          |
+| 0.045         | 0.3129 | 33   | 0.0429          |
+| 0.0425        | 0.4172 | 44   | 0.0400          |
+| 0.0411        | 0.5214 | 55   | 0.0379          |
+| 0.0348        | 0.6257 | 66   | 0.0359          |
+| 0.0288        | 0.7300 | 77   | 0.0342          |
+| 0.0339        | 0.8343 | 88   | 0.0331          |
+| 0.0297        | 0.9386 | 99   | 0.0318          |
+| 0.0281        | 1.0429 | 110  | 0.0312          |
+| 0.027         | 1.1472 | 121  | 0.0303          |
+| 0.023         | 1.2515 | 132  | 0.0298          |
+| 0.0259        | 1.3558 | 143  | 0.0297          |
+| 0.0232        | 1.4600 | 154  | 0.0300          |
+| 0.0203        | 1.5643 | 165  | 0.0291          |
+| 0.0241        | 1.6686 | 176  | 0.0284          |
+| 0.0245        | 1.7729 | 187  | 0.0282          |
+| 0.0222        | 1.8772 | 198  | 0.0277          |
+| 0.0231        | 1.9815 | 209  | 0.0278          |
+| 0.0175        | 2.0858 | 220  | 0.0276          |
+| 0.0165        | 2.1901 | 231  | 0.0281          |
+| 0.0174        | 2.2943 | 242  | 0.0281          |
+| 0.021         | 2.3986 | 253  | 0.0279          |
+| 0.0147        | 2.5029 | 264  | 0.0277          |
+| 0.0162        | 2.6072 | 275  | 0.0277          |
+| 0.0206        | 2.7115 | 286  | 0.0276          |
+| 0.0241        | 2.8158 | 297  | 0.0276          |
+| 0.0162        | 2.9201 | 308  | 0.0276          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.1
+- Pytorch 2.1.2+cu118
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-math-7b-rl",
+  "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": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "o_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 sha256:04a72faa4f827b34b2a88a66fcfc930c11d3617b6c617ed414c1042e14a83028
+size 299979034

checkpoint-106/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-math-7b-rl
+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 0.11.1

checkpoint-106/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-math-7b-rl",
+  "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": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-106/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78020a7762f4fa051ad1d0e3e1517327fa1d786d50fb4390d5596d0f8a339c3e
+size 299884176

checkpoint-106/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d6d19bc5e66b62b88ce625bc6d1e758ed8a601feb313075d95c8844bf761a8
+size 1199568698

checkpoint-106/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0bf9a88a7ce57719cc8be1e643402b7acd3fad27293006e514e23cb535410a1
+size 14244

checkpoint-106/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5c6ccb73029ede53fae960610ee97663cfd6cf8234ebdac5276096c0b56e952
+size 1064

checkpoint-106/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-106/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

checkpoint-106/trainer_state.json

@@ -0,0 +1,855 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0049625953633063,
+  "eval_steps": 11,
+  "global_step": 106,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009480779201540626,
+      "grad_norm": 0.38671875,
+      "learning_rate": 2e-05,
+      "loss": 0.4197,
+      "step": 1
+    },
+    {
+      "epoch": 0.009480779201540626,
+      "eval_loss": 0.41279804706573486,
+      "eval_runtime": 34.6855,
+      "eval_samples_per_second": 20.498,
+      "eval_steps_per_second": 20.498,
+      "step": 1
+    },
+    {
+      "epoch": 0.018961558403081252,
+      "grad_norm": 0.359375,
+      "learning_rate": 4e-05,
+      "loss": 0.3966,
+      "step": 2
+    },
+    {
+      "epoch": 0.02844233760462188,
+      "grad_norm": 0.388671875,
+      "learning_rate": 6e-05,
+      "loss": 0.4257,
+      "step": 3
+    },
+    {
+      "epoch": 0.037923116806162505,
+      "grad_norm": 0.408203125,
+      "learning_rate": 8e-05,
+      "loss": 0.4026,
+      "step": 4
+    },
+    {
+      "epoch": 0.04740389600770313,
+      "grad_norm": 0.384765625,
+      "learning_rate": 0.0001,
+      "loss": 0.3229,
+      "step": 5
+    },
+    {
+      "epoch": 0.05688467520924376,
+      "grad_norm": 0.251953125,
+      "learning_rate": 0.00012,
+      "loss": 0.2408,
+      "step": 6
+    },
+    {
+      "epoch": 0.06636545441078438,
+      "grad_norm": 0.203125,
+      "learning_rate": 0.00014,
+      "loss": 0.1709,
+      "step": 7
+    },
+    {
+      "epoch": 0.07584623361232501,
+      "grad_norm": 0.150390625,
+      "learning_rate": 0.00016,
+      "loss": 0.1328,
+      "step": 8
+    },
+    {
+      "epoch": 0.08532701281386564,
+      "grad_norm": 0.1201171875,
+      "learning_rate": 0.00018,
+      "loss": 0.0993,
+      "step": 9
+    },
+    {
+      "epoch": 0.09480779201540626,
+      "grad_norm": 0.10888671875,
+      "learning_rate": 0.0002,
+      "loss": 0.0914,
+      "step": 10
+    },
+    {
+      "epoch": 0.10428857121694689,
+      "grad_norm": 0.119140625,
+      "learning_rate": 0.00019999469523400122,
+      "loss": 0.0885,
+      "step": 11
+    },
+    {
+      "epoch": 0.10428857121694689,
+      "eval_loss": 0.07809103280305862,
+      "eval_runtime": 34.2892,
+      "eval_samples_per_second": 20.735,
+      "eval_steps_per_second": 20.735,
+      "step": 11
+    },
+    {
+      "epoch": 0.11376935041848751,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00019997878149881574,
+      "loss": 0.0761,
+      "step": 12
+    },
+    {
+      "epoch": 0.12325012962002814,
+      "grad_norm": 0.0703125,
+      "learning_rate": 0.0001999522604828164,
+      "loss": 0.0683,
+      "step": 13
+    },
+    {
+      "epoch": 0.13273090882156877,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 0.00019991513499975882,
+      "loss": 0.0696,
+      "step": 14
+    },
+    {
+      "epoch": 0.1422116880231094,
+      "grad_norm": 0.044921875,
+      "learning_rate": 0.00019986740898848306,
+      "loss": 0.0615,
+      "step": 15
+    },
+    {
+      "epoch": 0.15169246722465002,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019980908751249555,
+      "loss": 0.0625,
+      "step": 16
+    },
+    {
+      "epoch": 0.16117324642619066,
+      "grad_norm": 0.04736328125,
+      "learning_rate": 0.00019974017675943192,
+      "loss": 0.0598,
+      "step": 17
+    },
+    {
+      "epoch": 0.17065402562773127,
+      "grad_norm": 0.039306640625,
+      "learning_rate": 0.0001996606840404006,
+      "loss": 0.0573,
+      "step": 18
+    },
+    {
+      "epoch": 0.1801348048292719,
+      "grad_norm": 0.036376953125,
+      "learning_rate": 0.00019957061778920701,
+      "loss": 0.0482,
+      "step": 19
+    },
+    {
+      "epoch": 0.18961558403081252,
+      "grad_norm": 0.039306640625,
+      "learning_rate": 0.0001994699875614589,
+      "loss": 0.0555,
+      "step": 20
+    },
+    {
+      "epoch": 0.19909636323235316,
+      "grad_norm": 0.0380859375,
+      "learning_rate": 0.00019935880403355253,
+      "loss": 0.0495,
+      "step": 21
+    },
+    {
+      "epoch": 0.20857714243389378,
+      "grad_norm": 0.038818359375,
+      "learning_rate": 0.00019923707900153982,
+      "loss": 0.0482,
+      "step": 22
+    },
+    {
+      "epoch": 0.20857714243389378,
+      "eval_loss": 0.05171125754714012,
+      "eval_runtime": 34.4113,
+      "eval_samples_per_second": 20.662,
+      "eval_steps_per_second": 20.662,
+      "step": 22
+    },
+    {
+      "epoch": 0.21805792163543442,
+      "grad_norm": 0.038818359375,
+      "learning_rate": 0.00019910482537987702,
+      "loss": 0.0529,
+      "step": 23
+    },
+    {
+      "epoch": 0.22753870083697503,
+      "grad_norm": 0.031494140625,
+      "learning_rate": 0.0001989620572000544,
+      "loss": 0.0495,
+      "step": 24
+    },
+    {
+      "epoch": 0.23701948003851567,
+      "grad_norm": 0.0380859375,
+      "learning_rate": 0.00019880878960910772,
+      "loss": 0.059,
+      "step": 25
+    },
+    {
+      "epoch": 0.24650025924005628,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.00019864503886801106,
+      "loss": 0.0545,
+      "step": 26
+    },
+    {
+      "epoch": 0.2559810384415969,
+      "grad_norm": 0.029296875,
+      "learning_rate": 0.00019847082234995171,
+      "loss": 0.0417,
+      "step": 27
+    },
+    {
+      "epoch": 0.26546181764313753,
+      "grad_norm": 0.037109375,
+      "learning_rate": 0.00019828615853848688,
+      "loss": 0.0459,
+      "step": 28
+    },
+    {
+      "epoch": 0.27494259684467814,
+      "grad_norm": 0.027099609375,
+      "learning_rate": 0.00019809106702558277,
+      "loss": 0.0412,
+      "step": 29
+    },
+    {
+      "epoch": 0.2844233760462188,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.0001978855685095358,
+      "loss": 0.0403,
+      "step": 30
+    },
+    {
+      "epoch": 0.2939041552477594,
+      "grad_norm": 0.0289306640625,
+      "learning_rate": 0.00019766968479277683,
+      "loss": 0.0463,
+      "step": 31
+    },
+    {
+      "epoch": 0.30338493444930004,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 0.00019744343877955788,
+      "loss": 0.041,
+      "step": 32
+    },
+    {
+      "epoch": 0.3128657136508407,
+      "grad_norm": 0.033447265625,
+      "learning_rate": 0.00019720685447352209,
+      "loss": 0.045,
+      "step": 33
+    },
+    {
+      "epoch": 0.3128657136508407,
+      "eval_loss": 0.04294149950146675,
+      "eval_runtime": 34.2719,
+      "eval_samples_per_second": 20.746,
+      "eval_steps_per_second": 20.746,
+      "step": 33
+    },
+    {
+      "epoch": 0.3223464928523813,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 0.0001969599569751571,
+      "loss": 0.0369,
+      "step": 34
+    },
+    {
+      "epoch": 0.33182727205392193,
+      "grad_norm": 0.029296875,
+      "learning_rate": 0.00019670277247913205,
+      "loss": 0.0465,
+      "step": 35
+    },
+    {
+      "epoch": 0.34130805125546254,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 0.0001964353282715183,
+      "loss": 0.0382,
+      "step": 36
+    },
+    {
+      "epoch": 0.3507888304570032,
+      "grad_norm": 0.0299072265625,
+      "learning_rate": 0.00019615765272689461,
+      "loss": 0.0442,
+      "step": 37
+    },
+    {
+      "epoch": 0.3602696096585438,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00019586977530533677,
+      "loss": 0.0481,
+      "step": 38
+    },
+    {
+      "epoch": 0.36975038886008443,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 0.00019557172654929196,
+      "loss": 0.0423,
+      "step": 39
+    },
+    {
+      "epoch": 0.37923116806162505,
+      "grad_norm": 0.0299072265625,
+      "learning_rate": 0.00019526353808033825,
+      "loss": 0.0384,
+      "step": 40
+    },
+    {
+      "epoch": 0.3887119472631657,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 0.00019494524259582992,
+      "loss": 0.0404,
+      "step": 41
+    },
+    {
+      "epoch": 0.3981927264647063,
+      "grad_norm": 0.0286865234375,
+      "learning_rate": 0.00019461687386542826,
+      "loss": 0.0394,
+      "step": 42
+    },
+    {
+      "epoch": 0.40767350566624694,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 0.00019427846672751873,
+      "loss": 0.0351,
+      "step": 43
+    },
+    {
+      "epoch": 0.41715428486778755,
+      "grad_norm": 0.02783203125,
+      "learning_rate": 0.00019393005708551498,
+      "loss": 0.0425,
+      "step": 44
+    },
+    {
+      "epoch": 0.41715428486778755,
+      "eval_loss": 0.03996235132217407,
+      "eval_runtime": 34.3007,
+      "eval_samples_per_second": 20.728,
+      "eval_steps_per_second": 20.728,
+      "step": 44
+    },
+    {
+      "epoch": 0.4266350640693282,
+      "grad_norm": 0.030517578125,
+      "learning_rate": 0.00019357168190404936,
+      "loss": 0.0365,
+      "step": 45
+    },
+    {
+      "epoch": 0.43611584327086883,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 0.00019320337920505153,
+      "loss": 0.0438,
+      "step": 46
+    },
+    {
+      "epoch": 0.44559662247240944,
+      "grad_norm": 0.0306396484375,
+      "learning_rate": 0.00019282518806371414,
+      "loss": 0.044,
+      "step": 47
+    },
+    {
+      "epoch": 0.45507740167395005,
+      "grad_norm": 0.037841796875,
+      "learning_rate": 0.0001924371486043473,
+      "loss": 0.0496,
+      "step": 48
+    },
+    {
+      "epoch": 0.4645581808754907,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 0.0001920393019961217,
+      "loss": 0.0369,
+      "step": 49
+    },
+    {
+      "epoch": 0.47403896007703133,
+      "grad_norm": 0.0341796875,
+      "learning_rate": 0.0001916316904487005,
+      "loss": 0.0399,
+      "step": 50
+    },
+    {
+      "epoch": 0.48351973927857195,
+      "grad_norm": 0.0255126953125,
+      "learning_rate": 0.00019121435720776122,
+      "loss": 0.0363,
+      "step": 51
+    },
+    {
+      "epoch": 0.49300051848011256,
+      "grad_norm": 0.0311279296875,
+      "learning_rate": 0.0001907873465504076,
+      "loss": 0.0384,
+      "step": 52
+    },
+    {
+      "epoch": 0.5024812976816532,
+      "grad_norm": 0.03271484375,
+      "learning_rate": 0.00019035070378047204,
+      "loss": 0.0371,
+      "step": 53
+    },
+    {
+      "epoch": 0.5119620768831938,
+      "grad_norm": 0.0263671875,
+      "learning_rate": 0.00018990447522370884,
+      "loss": 0.0351,
+      "step": 54
+    },
+    {
+      "epoch": 0.5214428560847345,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00018944870822287956,
+      "loss": 0.0411,
+      "step": 55
+    },
+    {
+      "epoch": 0.5214428560847345,
+      "eval_loss": 0.03788134828209877,
+      "eval_runtime": 34.6048,
+      "eval_samples_per_second": 20.546,
+      "eval_steps_per_second": 20.546,
+      "step": 55
+    },
+    {
+      "epoch": 0.5309236352862751,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00018898345113272998,
+      "loss": 0.0337,
+      "step": 56
+    },
+    {
+      "epoch": 0.5404044144878157,
+      "grad_norm": 0.0245361328125,
+      "learning_rate": 0.00018850875331485995,
+      "loss": 0.0309,
+      "step": 57
+    },
+    {
+      "epoch": 0.5498851936893563,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 0.00018802466513248632,
+      "loss": 0.0329,
+      "step": 58
+    },
+    {
+      "epoch": 0.559365972890897,
+      "grad_norm": 0.0267333984375,
+      "learning_rate": 0.00018753123794509974,
+      "loss": 0.0365,
+      "step": 59
+    },
+    {
+      "epoch": 0.5688467520924376,
+      "grad_norm": 0.02734375,
+      "learning_rate": 0.00018702852410301554,
+      "loss": 0.0373,
+      "step": 60
+    },
+    {
+      "epoch": 0.5783275312939782,
+      "grad_norm": 0.025390625,
+      "learning_rate": 0.0001865165769418196,
+      "loss": 0.0375,
+      "step": 61
+    },
+    {
+      "epoch": 0.5878083104955188,
+      "grad_norm": 0.02978515625,
+      "learning_rate": 0.00018599545077670985,
+      "loss": 0.0376,
+      "step": 62
+    },
+    {
+      "epoch": 0.5972890896970595,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.0001854652008967335,
+      "loss": 0.0337,
+      "step": 63
+    },
+    {
+      "epoch": 0.6067698688986001,
+      "grad_norm": 0.02880859375,
+      "learning_rate": 0.00018492588355892124,
+      "loss": 0.0379,
+      "step": 64
+    },
+    {
+      "epoch": 0.6162506481001407,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018437755598231856,
+      "loss": 0.0392,
+      "step": 65
+    },
+    {
+      "epoch": 0.6257314273016814,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00018382027634191524,
+      "loss": 0.0348,
+      "step": 66
+    },
+    {
+      "epoch": 0.6257314273016814,
+      "eval_loss": 0.03594927862286568,
+      "eval_runtime": 34.2756,
+      "eval_samples_per_second": 20.744,
+      "eval_steps_per_second": 20.744,
+      "step": 66
+    },
+    {
+      "epoch": 0.635212206503222,
+      "grad_norm": 0.03515625,
+      "learning_rate": 0.00018325410376247294,
+      "loss": 0.0379,
+      "step": 67
+    },
+    {
+      "epoch": 0.6446929857047626,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 0.0001826790983122527,
+      "loss": 0.0317,
+      "step": 68
+    },
+    {
+      "epoch": 0.6541737649063032,
+      "grad_norm": 0.0296630859375,
+      "learning_rate": 0.00018209532099664174,
+      "loss": 0.0366,
+      "step": 69
+    },
+    {
+      "epoch": 0.6636545441078439,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00018150283375168114,
+      "loss": 0.0345,
+      "step": 70
+    },
+    {
+      "epoch": 0.6731353233093845,
+      "grad_norm": 0.03125,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0368,
+      "step": 71
+    },
+    {
+      "epoch": 0.6826161025109251,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.00018029198183161998,
+      "loss": 0.0455,
+      "step": 72
+    },
+    {
+      "epoch": 0.6920968817124658,
+      "grad_norm": 0.029296875,
+      "learning_rate": 0.00017967374562224132,
+      "loss": 0.0362,
+      "step": 73
+    },
+    {
+      "epoch": 0.7015776609140064,
+      "grad_norm": 0.0311279296875,
+      "learning_rate": 0.00017904705640132718,
+      "loss": 0.0388,
+      "step": 74
+    },
+    {
+      "epoch": 0.711058440115547,
+      "grad_norm": 0.02685546875,
+      "learning_rate": 0.00017841198065767107,
+      "loss": 0.0288,
+      "step": 75
+    },
+    {
+      "epoch": 0.7205392193170876,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00017776858576983712,
+      "loss": 0.0349,
+      "step": 76
+    },
+    {
+      "epoch": 0.7300199985186282,
+      "grad_norm": 0.026611328125,
+      "learning_rate": 0.0001771169399990119,
+      "loss": 0.0288,
+      "step": 77
+    },
+    {
+      "epoch": 0.7300199985186282,
+      "eval_loss": 0.03419337794184685,
+      "eval_runtime": 34.3669,
+      "eval_samples_per_second": 20.688,
+      "eval_steps_per_second": 20.688,
+      "step": 77
+    },
+    {
+      "epoch": 0.7395007777201689,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.00017645711248176195,
+      "loss": 0.0285,
+      "step": 78
+    },
+    {
+      "epoch": 0.7489815569217095,
+      "grad_norm": 0.025390625,
+      "learning_rate": 0.00017578917322269886,
+      "loss": 0.0338,
+      "step": 79
+    },
+    {
+      "epoch": 0.7584623361232501,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00017511319308705198,
+      "loss": 0.0316,
+      "step": 80
+    },
+    {
+      "epoch": 0.7679431153247908,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.0001744292437931502,
+      "loss": 0.0306,
+      "step": 81
+    },
+    {
+      "epoch": 0.7774238945263314,
+      "grad_norm": 0.027099609375,
+      "learning_rate": 0.00017373739790481262,
+      "loss": 0.0335,
+      "step": 82
+    },
+    {
+      "epoch": 0.786904673727872,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017303772882365016,
+      "loss": 0.0271,
+      "step": 83
+    },
+    {
+      "epoch": 0.7963854529294127,
+      "grad_norm": 0.028564453125,
+      "learning_rate": 0.00017233031078127788,
+      "loss": 0.0334,
+      "step": 84
+    },
+    {
+      "epoch": 0.8058662321309532,
+      "grad_norm": 0.0299072265625,
+      "learning_rate": 0.00017161521883143934,
+      "loss": 0.0403,
+      "step": 85
+    },
+    {
+      "epoch": 0.8153470113324939,
+      "grad_norm": 0.0294189453125,
+      "learning_rate": 0.00017089252884204377,
+      "loss": 0.0368,
+      "step": 86
+    },
+    {
+      "epoch": 0.8248277905340345,
+      "grad_norm": 0.03369140625,
+      "learning_rate": 0.0001701623174871168,
+      "loss": 0.0335,
+      "step": 87
+    },
+    {
+      "epoch": 0.8343085697355751,
+      "grad_norm": 0.0277099609375,
+      "learning_rate": 0.0001694246622386658,
+      "loss": 0.0339,
+      "step": 88
+    },
+    {
+      "epoch": 0.8343085697355751,
+      "eval_loss": 0.033091045916080475,
+      "eval_runtime": 34.4475,
+      "eval_samples_per_second": 20.64,
+      "eval_steps_per_second": 20.64,
+      "step": 88
+    },
+    {
+      "epoch": 0.8437893489371158,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 0.00016867964135846043,
+      "loss": 0.0241,
+      "step": 89
+    },
+    {
+      "epoch": 0.8532701281386564,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00016792733388972932,
+      "loss": 0.0387,
+      "step": 90
+    },
+    {
+      "epoch": 0.862750907340197,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 0.0001671678196487741,
+      "loss": 0.0346,
+      "step": 91
+    },
+    {
+      "epoch": 0.8722316865417377,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 0.00016640117921650117,
+      "loss": 0.0378,
+      "step": 92
+    },
+    {
+      "epoch": 0.8817124657432783,
+      "grad_norm": 0.0279541015625,
+      "learning_rate": 0.00016562749392987254,
+      "loss": 0.0294,
+      "step": 93
+    },
+    {
+      "epoch": 0.8911932449448189,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001648468458732762,
+      "loss": 0.0308,
+      "step": 94
+    },
+    {
+      "epoch": 0.9006740241463596,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00016405931786981755,
+      "loss": 0.0326,
+      "step": 95
+    },
+    {
+      "epoch": 0.9101548033479001,
+      "grad_norm": 0.0262451171875,
+      "learning_rate": 0.00016326499347253207,
+      "loss": 0.032,
+      "step": 96
+    },
+    {
+      "epoch": 0.9196355825494408,
+      "grad_norm": 0.0264892578125,
+      "learning_rate": 0.00016246395695552085,
+      "loss": 0.0321,
+      "step": 97
+    },
+    {
+      "epoch": 0.9291163617509814,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00016165629330500952,
+      "loss": 0.0301,
+      "step": 98
+    },
+    {
+      "epoch": 0.938597140952522,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.0001608420882103315,
+      "loss": 0.0297,
+      "step": 99
+    },
+    {
+      "epoch": 0.938597140952522,
+      "eval_loss": 0.03182319179177284,
+      "eval_runtime": 34.2304,
+      "eval_samples_per_second": 20.771,
+      "eval_steps_per_second": 20.771,
+      "step": 99
+    },
+    {
+      "epoch": 0.9480779201540627,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00016002142805483685,
+      "loss": 0.0327,
+      "step": 100
+    },
+    {
+      "epoch": 0.9575586993556033,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 0.0001591943999067273,
+      "loss": 0.0285,
+      "step": 101
+    },
+    {
+      "epoch": 0.9670394785571439,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.00015836109150981886,
+      "loss": 0.0308,
+      "step": 102
+    },
+    {
+      "epoch": 0.9765202577586846,
+      "grad_norm": 0.0283203125,
+      "learning_rate": 0.00015752159127423263,
+      "loss": 0.0301,
+      "step": 103
+    },
+    {
+      "epoch": 0.9860010369602251,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 0.0001566759882670146,
+      "loss": 0.0287,
+      "step": 104
+    },
+    {
+      "epoch": 0.9954818161617658,
+      "grad_norm": 0.025634765625,
+      "learning_rate": 0.00015582437220268647,
+      "loss": 0.031,
+      "step": 105
+    },
+    {
+      "epoch": 1.0049625953633063,
+      "grad_norm": 0.02490234375,
+      "learning_rate": 0.0001549668334337271,
+      "loss": 0.0275,
+      "step": 106
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 315,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 53,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.4413248091848704e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-106/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6965abb853c761cad48cb468c99194ceaf6bcfe3b5e51b1799b677a2e2e93f5
+size 6072

checkpoint-159/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-math-7b-rl
+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 0.11.1

checkpoint-159/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-math-7b-rl",
+  "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": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-159/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3734a091cc5f92c303bffa355abcb602578abad6f6244719f312df2518cffa2d
+size 299884176

checkpoint-159/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7618cfc4db92dcb474db6f32c9141ab4009413e991b4c051fd5ad84ee0cb743d
+size 1199568698

checkpoint-159/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:012b9f4041e5b2ad5e9cb71e61475cc1b84a9c94785b9fd34d4915ccebe4a353
+size 14244

checkpoint-159/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19809e3e9f97211f78c8259943f11fd298a3c4adde59e98dc5f42c9c642f8a96
+size 1064

checkpoint-159/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-159/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

checkpoint-159/trainer_state.json

@@ -0,0 +1,1266 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5074438930449596,
+  "eval_steps": 11,
+  "global_step": 159,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009480779201540626,
+      "grad_norm": 0.38671875,
+      "learning_rate": 2e-05,
+      "loss": 0.4197,
+      "step": 1
+    },
+    {
+      "epoch": 0.009480779201540626,
+      "eval_loss": 0.41279804706573486,
+      "eval_runtime": 34.6855,
+      "eval_samples_per_second": 20.498,
+      "eval_steps_per_second": 20.498,
+      "step": 1
+    },
+    {
+      "epoch": 0.018961558403081252,
+      "grad_norm": 0.359375,
+      "learning_rate": 4e-05,
+      "loss": 0.3966,
+      "step": 2
+    },
+    {
+      "epoch": 0.02844233760462188,
+      "grad_norm": 0.388671875,
+      "learning_rate": 6e-05,
+      "loss": 0.4257,
+      "step": 3
+    },
+    {
+      "epoch": 0.037923116806162505,
+      "grad_norm": 0.408203125,
+      "learning_rate": 8e-05,
+      "loss": 0.4026,
+      "step": 4
+    },
+    {
+      "epoch": 0.04740389600770313,
+      "grad_norm": 0.384765625,
+      "learning_rate": 0.0001,
+      "loss": 0.3229,
+      "step": 5
+    },
+    {
+      "epoch": 0.05688467520924376,
+      "grad_norm": 0.251953125,
+      "learning_rate": 0.00012,
+      "loss": 0.2408,
+      "step": 6
+    },
+    {
+      "epoch": 0.06636545441078438,
+      "grad_norm": 0.203125,
+      "learning_rate": 0.00014,
+      "loss": 0.1709,
+      "step": 7
+    },
+    {
+      "epoch": 0.07584623361232501,
+      "grad_norm": 0.150390625,
+      "learning_rate": 0.00016,
+      "loss": 0.1328,
+      "step": 8
+    },
+    {
+      "epoch": 0.08532701281386564,
+      "grad_norm": 0.1201171875,
+      "learning_rate": 0.00018,
+      "loss": 0.0993,
+      "step": 9
+    },
+    {
+      "epoch": 0.09480779201540626,
+      "grad_norm": 0.10888671875,
+      "learning_rate": 0.0002,
+      "loss": 0.0914,
+      "step": 10
+    },
+    {
+      "epoch": 0.10428857121694689,
+      "grad_norm": 0.119140625,
+      "learning_rate": 0.00019999469523400122,
+      "loss": 0.0885,
+      "step": 11
+    },
+    {
+      "epoch": 0.10428857121694689,
+      "eval_loss": 0.07809103280305862,
+      "eval_runtime": 34.2892,
+      "eval_samples_per_second": 20.735,
+      "eval_steps_per_second": 20.735,
+      "step": 11
+    },
+    {
+      "epoch": 0.11376935041848751,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00019997878149881574,
+      "loss": 0.0761,
+      "step": 12
+    },
+    {
+      "epoch": 0.12325012962002814,
+      "grad_norm": 0.0703125,
+      "learning_rate": 0.0001999522604828164,
+      "loss": 0.0683,
+      "step": 13
+    },
+    {
+      "epoch": 0.13273090882156877,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 0.00019991513499975882,
+      "loss": 0.0696,
+      "step": 14
+    },
+    {
+      "epoch": 0.1422116880231094,
+      "grad_norm": 0.044921875,
+      "learning_rate": 0.00019986740898848306,
+      "loss": 0.0615,
+      "step": 15
+    },
+    {
+      "epoch": 0.15169246722465002,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019980908751249555,
+      "loss": 0.0625,
+      "step": 16
+    },
+    {
+      "epoch": 0.16117324642619066,
+      "grad_norm": 0.04736328125,
+      "learning_rate": 0.00019974017675943192,
+      "loss": 0.0598,
+      "step": 17
+    },
+    {
+      "epoch": 0.17065402562773127,
+      "grad_norm": 0.039306640625,
+      "learning_rate": 0.0001996606840404006,
+      "loss": 0.0573,
+      "step": 18
+    },
+    {
+      "epoch": 0.1801348048292719,
+      "grad_norm": 0.036376953125,
+      "learning_rate": 0.00019957061778920701,
+      "loss": 0.0482,
+      "step": 19
+    },
+    {
+      "epoch": 0.18961558403081252,
+      "grad_norm": 0.039306640625,
+      "learning_rate": 0.0001994699875614589,
+      "loss": 0.0555,
+      "step": 20
+    },
+    {
+      "epoch": 0.19909636323235316,
+      "grad_norm": 0.0380859375,
+      "learning_rate": 0.00019935880403355253,
+      "loss": 0.0495,
+      "step": 21
+    },
+    {
+      "epoch": 0.20857714243389378,
+      "grad_norm": 0.038818359375,
+      "learning_rate": 0.00019923707900153982,
+      "loss": 0.0482,
+      "step": 22
+    },
+    {
+      "epoch": 0.20857714243389378,
+      "eval_loss": 0.05171125754714012,
+      "eval_runtime": 34.4113,
+      "eval_samples_per_second": 20.662,
+      "eval_steps_per_second": 20.662,
+      "step": 22
+    },
+    {
+      "epoch": 0.21805792163543442,
+      "grad_norm": 0.038818359375,
+      "learning_rate": 0.00019910482537987702,
+      "loss": 0.0529,
+      "step": 23
+    },
+    {
+      "epoch": 0.22753870083697503,
+      "grad_norm": 0.031494140625,
+      "learning_rate": 0.0001989620572000544,
+      "loss": 0.0495,
+      "step": 24
+    },
+    {
+      "epoch": 0.23701948003851567,
+      "grad_norm": 0.0380859375,
+      "learning_rate": 0.00019880878960910772,
+      "loss": 0.059,
+      "step": 25
+    },
+    {
+      "epoch": 0.24650025924005628,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.00019864503886801106,
+      "loss": 0.0545,
+      "step": 26
+    },
+    {
+      "epoch": 0.2559810384415969,
+      "grad_norm": 0.029296875,
+      "learning_rate": 0.00019847082234995171,
+      "loss": 0.0417,
+      "step": 27
+    },
+    {
+      "epoch": 0.26546181764313753,
+      "grad_norm": 0.037109375,
+      "learning_rate": 0.00019828615853848688,
+      "loss": 0.0459,
+      "step": 28
+    },
+    {
+      "epoch": 0.27494259684467814,
+      "grad_norm": 0.027099609375,
+      "learning_rate": 0.00019809106702558277,
+      "loss": 0.0412,
+      "step": 29
+    },
+    {
+      "epoch": 0.2844233760462188,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.0001978855685095358,
+      "loss": 0.0403,
+      "step": 30
+    },
+    {
+      "epoch": 0.2939041552477594,
+      "grad_norm": 0.0289306640625,
+      "learning_rate": 0.00019766968479277683,
+      "loss": 0.0463,
+      "step": 31
+    },
+    {
+      "epoch": 0.30338493444930004,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 0.00019744343877955788,
+      "loss": 0.041,
+      "step": 32
+    },
+    {
+      "epoch": 0.3128657136508407,
+      "grad_norm": 0.033447265625,
+      "learning_rate": 0.00019720685447352209,
+      "loss": 0.045,
+      "step": 33
+    },
+    {
+      "epoch": 0.3128657136508407,
+      "eval_loss": 0.04294149950146675,
+      "eval_runtime": 34.2719,
+      "eval_samples_per_second": 20.746,
+      "eval_steps_per_second": 20.746,
+      "step": 33
+    },
+    {
+      "epoch": 0.3223464928523813,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 0.0001969599569751571,
+      "loss": 0.0369,
+      "step": 34
+    },
+    {
+      "epoch": 0.33182727205392193,
+      "grad_norm": 0.029296875,
+      "learning_rate": 0.00019670277247913205,
+      "loss": 0.0465,
+      "step": 35
+    },
+    {
+      "epoch": 0.34130805125546254,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 0.0001964353282715183,
+      "loss": 0.0382,
+      "step": 36
+    },
+    {
+      "epoch": 0.3507888304570032,
+      "grad_norm": 0.0299072265625,
+      "learning_rate": 0.00019615765272689461,
+      "loss": 0.0442,
+      "step": 37
+    },
+    {
+      "epoch": 0.3602696096585438,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00019586977530533677,
+      "loss": 0.0481,
+      "step": 38
+    },
+    {
+      "epoch": 0.36975038886008443,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 0.00019557172654929196,
+      "loss": 0.0423,
+      "step": 39
+    },
+    {
+      "epoch": 0.37923116806162505,
+      "grad_norm": 0.0299072265625,
+      "learning_rate": 0.00019526353808033825,
+      "loss": 0.0384,
+      "step": 40
+    },
+    {
+      "epoch": 0.3887119472631657,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 0.00019494524259582992,
+      "loss": 0.0404,
+      "step": 41
+    },
+    {
+      "epoch": 0.3981927264647063,
+      "grad_norm": 0.0286865234375,
+      "learning_rate": 0.00019461687386542826,
+      "loss": 0.0394,
+      "step": 42
+    },
+    {
+      "epoch": 0.40767350566624694,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 0.00019427846672751873,
+      "loss": 0.0351,
+      "step": 43
+    },
+    {
+      "epoch": 0.41715428486778755,
+      "grad_norm": 0.02783203125,
+      "learning_rate": 0.00019393005708551498,
+      "loss": 0.0425,
+      "step": 44
+    },
+    {
+      "epoch": 0.41715428486778755,
+      "eval_loss": 0.03996235132217407,
+      "eval_runtime": 34.3007,
+      "eval_samples_per_second": 20.728,
+      "eval_steps_per_second": 20.728,
+      "step": 44
+    },
+    {
+      "epoch": 0.4266350640693282,
+      "grad_norm": 0.030517578125,
+      "learning_rate": 0.00019357168190404936,
+      "loss": 0.0365,
+      "step": 45
+    },
+    {
+      "epoch": 0.43611584327086883,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 0.00019320337920505153,
+      "loss": 0.0438,
+      "step": 46
+    },
+    {
+      "epoch": 0.44559662247240944,
+      "grad_norm": 0.0306396484375,
+      "learning_rate": 0.00019282518806371414,
+      "loss": 0.044,
+      "step": 47
+    },
+    {
+      "epoch": 0.45507740167395005,
+      "grad_norm": 0.037841796875,
+      "learning_rate": 0.0001924371486043473,
+      "loss": 0.0496,
+      "step": 48
+    },
+    {
+      "epoch": 0.4645581808754907,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 0.0001920393019961217,
+      "loss": 0.0369,
+      "step": 49
+    },
+    {
+      "epoch": 0.47403896007703133,
+      "grad_norm": 0.0341796875,
+      "learning_rate": 0.0001916316904487005,
+      "loss": 0.0399,
+      "step": 50
+    },
+    {
+      "epoch": 0.48351973927857195,
+      "grad_norm": 0.0255126953125,
+      "learning_rate": 0.00019121435720776122,
+      "loss": 0.0363,
+      "step": 51
+    },
+    {
+      "epoch": 0.49300051848011256,
+      "grad_norm": 0.0311279296875,
+      "learning_rate": 0.0001907873465504076,
+      "loss": 0.0384,
+      "step": 52
+    },
+    {
+      "epoch": 0.5024812976816532,
+      "grad_norm": 0.03271484375,
+      "learning_rate": 0.00019035070378047204,
+      "loss": 0.0371,
+      "step": 53
+    },
+    {
+      "epoch": 0.5119620768831938,
+      "grad_norm": 0.0263671875,
+      "learning_rate": 0.00018990447522370884,
+      "loss": 0.0351,
+      "step": 54
+    },
+    {
+      "epoch": 0.5214428560847345,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00018944870822287956,
+      "loss": 0.0411,
+      "step": 55
+    },
+    {
+      "epoch": 0.5214428560847345,
+      "eval_loss": 0.03788134828209877,
+      "eval_runtime": 34.6048,
+      "eval_samples_per_second": 20.546,
+      "eval_steps_per_second": 20.546,
+      "step": 55
+    },
+    {
+      "epoch": 0.5309236352862751,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00018898345113272998,
+      "loss": 0.0337,
+      "step": 56
+    },
+    {
+      "epoch": 0.5404044144878157,
+      "grad_norm": 0.0245361328125,
+      "learning_rate": 0.00018850875331485995,
+      "loss": 0.0309,
+      "step": 57
+    },
+    {
+      "epoch": 0.5498851936893563,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 0.00018802466513248632,
+      "loss": 0.0329,
+      "step": 58
+    },
+    {
+      "epoch": 0.559365972890897,
+      "grad_norm": 0.0267333984375,
+      "learning_rate": 0.00018753123794509974,
+      "loss": 0.0365,
+      "step": 59
+    },
+    {
+      "epoch": 0.5688467520924376,
+      "grad_norm": 0.02734375,
+      "learning_rate": 0.00018702852410301554,
+      "loss": 0.0373,
+      "step": 60
+    },
+    {
+      "epoch": 0.5783275312939782,
+      "grad_norm": 0.025390625,
+      "learning_rate": 0.0001865165769418196,
+      "loss": 0.0375,
+      "step": 61
+    },
+    {
+      "epoch": 0.5878083104955188,
+      "grad_norm": 0.02978515625,
+      "learning_rate": 0.00018599545077670985,
+      "loss": 0.0376,
+      "step": 62
+    },
+    {
+      "epoch": 0.5972890896970595,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.0001854652008967335,
+      "loss": 0.0337,
+      "step": 63
+    },
+    {
+      "epoch": 0.6067698688986001,
+      "grad_norm": 0.02880859375,
+      "learning_rate": 0.00018492588355892124,
+      "loss": 0.0379,
+      "step": 64
+    },
+    {
+      "epoch": 0.6162506481001407,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018437755598231856,
+      "loss": 0.0392,
+      "step": 65
+    },
+    {
+      "epoch": 0.6257314273016814,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00018382027634191524,
+      "loss": 0.0348,
+      "step": 66
+    },
+    {
+      "epoch": 0.6257314273016814,
+      "eval_loss": 0.03594927862286568,
+      "eval_runtime": 34.2756,
+      "eval_samples_per_second": 20.744,
+      "eval_steps_per_second": 20.744,
+      "step": 66
+    },
+    {
+      "epoch": 0.635212206503222,
+      "grad_norm": 0.03515625,
+      "learning_rate": 0.00018325410376247294,
+      "loss": 0.0379,
+      "step": 67
+    },
+    {
+      "epoch": 0.6446929857047626,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 0.0001826790983122527,
+      "loss": 0.0317,
+      "step": 68
+    },
+    {
+      "epoch": 0.6541737649063032,
+      "grad_norm": 0.0296630859375,
+      "learning_rate": 0.00018209532099664174,
+      "loss": 0.0366,
+      "step": 69
+    },
+    {
+      "epoch": 0.6636545441078439,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00018150283375168114,
+      "loss": 0.0345,
+      "step": 70
+    },
+    {
+      "epoch": 0.6731353233093845,
+      "grad_norm": 0.03125,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0368,
+      "step": 71
+    },
+    {
+      "epoch": 0.6826161025109251,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.00018029198183161998,
+      "loss": 0.0455,
+      "step": 72
+    },
+    {
+      "epoch": 0.6920968817124658,
+      "grad_norm": 0.029296875,
+      "learning_rate": 0.00017967374562224132,
+      "loss": 0.0362,
+      "step": 73
+    },
+    {
+      "epoch": 0.7015776609140064,
+      "grad_norm": 0.0311279296875,
+      "learning_rate": 0.00017904705640132718,
+      "loss": 0.0388,
+      "step": 74
+    },
+    {
+      "epoch": 0.711058440115547,
+      "grad_norm": 0.02685546875,
+      "learning_rate": 0.00017841198065767107,
+      "loss": 0.0288,
+      "step": 75
+    },
+    {
+      "epoch": 0.7205392193170876,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00017776858576983712,
+      "loss": 0.0349,
+      "step": 76
+    },
+    {
+      "epoch": 0.7300199985186282,
+      "grad_norm": 0.026611328125,
+      "learning_rate": 0.0001771169399990119,
+      "loss": 0.0288,
+      "step": 77
+    },
+    {
+      "epoch": 0.7300199985186282,
+      "eval_loss": 0.03419337794184685,
+      "eval_runtime": 34.3669,
+      "eval_samples_per_second": 20.688,
+      "eval_steps_per_second": 20.688,
+      "step": 77
+    },
+    {
+      "epoch": 0.7395007777201689,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.00017645711248176195,
+      "loss": 0.0285,
+      "step": 78
+    },
+    {
+      "epoch": 0.7489815569217095,
+      "grad_norm": 0.025390625,
+      "learning_rate": 0.00017578917322269886,
+      "loss": 0.0338,
+      "step": 79
+    },
+    {
+      "epoch": 0.7584623361232501,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00017511319308705198,
+      "loss": 0.0316,
+      "step": 80
+    },
+    {
+      "epoch": 0.7679431153247908,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.0001744292437931502,
+      "loss": 0.0306,
+      "step": 81
+    },
+    {
+      "epoch": 0.7774238945263314,
+      "grad_norm": 0.027099609375,
+      "learning_rate": 0.00017373739790481262,
+      "loss": 0.0335,
+      "step": 82
+    },
+    {
+      "epoch": 0.786904673727872,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017303772882365016,
+      "loss": 0.0271,
+      "step": 83
+    },
+    {
+      "epoch": 0.7963854529294127,
+      "grad_norm": 0.028564453125,
+      "learning_rate": 0.00017233031078127788,
+      "loss": 0.0334,
+      "step": 84
+    },
+    {
+      "epoch": 0.8058662321309532,
+      "grad_norm": 0.0299072265625,
+      "learning_rate": 0.00017161521883143934,
+      "loss": 0.0403,
+      "step": 85
+    },
+    {
+      "epoch": 0.8153470113324939,
+      "grad_norm": 0.0294189453125,
+      "learning_rate": 0.00017089252884204377,
+      "loss": 0.0368,
+      "step": 86
+    },
+    {
+      "epoch": 0.8248277905340345,
+      "grad_norm": 0.03369140625,
+      "learning_rate": 0.0001701623174871168,
+      "loss": 0.0335,
+      "step": 87
+    },
+    {
+      "epoch": 0.8343085697355751,
+      "grad_norm": 0.0277099609375,
+      "learning_rate": 0.0001694246622386658,
+      "loss": 0.0339,
+      "step": 88
+    },
+    {
+      "epoch": 0.8343085697355751,
+      "eval_loss": 0.033091045916080475,
+      "eval_runtime": 34.4475,
+      "eval_samples_per_second": 20.64,
+      "eval_steps_per_second": 20.64,
+      "step": 88
+    },
+    {
+      "epoch": 0.8437893489371158,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 0.00016867964135846043,
+      "loss": 0.0241,
+      "step": 89
+    },
+    {
+      "epoch": 0.8532701281386564,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00016792733388972932,
+      "loss": 0.0387,
+      "step": 90
+    },
+    {
+      "epoch": 0.862750907340197,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 0.0001671678196487741,
+      "loss": 0.0346,
+      "step": 91
+    },
+    {
+      "epoch": 0.8722316865417377,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 0.00016640117921650117,
+      "loss": 0.0378,
+      "step": 92
+    },
+    {
+      "epoch": 0.8817124657432783,
+      "grad_norm": 0.0279541015625,
+      "learning_rate": 0.00016562749392987254,
+      "loss": 0.0294,
+      "step": 93
+    },
+    {
+      "epoch": 0.8911932449448189,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001648468458732762,
+      "loss": 0.0308,
+      "step": 94
+    },
+    {
+      "epoch": 0.9006740241463596,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00016405931786981755,
+      "loss": 0.0326,
+      "step": 95
+    },
+    {
+      "epoch": 0.9101548033479001,
+      "grad_norm": 0.0262451171875,
+      "learning_rate": 0.00016326499347253207,
+      "loss": 0.032,
+      "step": 96
+    },
+    {
+      "epoch": 0.9196355825494408,
+      "grad_norm": 0.0264892578125,
+      "learning_rate": 0.00016246395695552085,
+      "loss": 0.0321,
+      "step": 97
+    },
+    {
+      "epoch": 0.9291163617509814,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00016165629330500952,
+      "loss": 0.0301,
+      "step": 98
+    },
+    {
+      "epoch": 0.938597140952522,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.0001608420882103315,
+      "loss": 0.0297,
+      "step": 99
+    },
+    {
+      "epoch": 0.938597140952522,
+      "eval_loss": 0.03182319179177284,
+      "eval_runtime": 34.2304,
+      "eval_samples_per_second": 20.771,
+      "eval_steps_per_second": 20.771,
+      "step": 99
+    },
+    {
+      "epoch": 0.9480779201540627,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00016002142805483685,
+      "loss": 0.0327,
+      "step": 100
+    },
+    {
+      "epoch": 0.9575586993556033,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 0.0001591943999067273,
+      "loss": 0.0285,
+      "step": 101
+    },
+    {
+      "epoch": 0.9670394785571439,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.00015836109150981886,
+      "loss": 0.0308,
+      "step": 102
+    },
+    {
+      "epoch": 0.9765202577586846,
+      "grad_norm": 0.0283203125,
+      "learning_rate": 0.00015752159127423263,
+      "loss": 0.0301,
+      "step": 103
+    },
+    {
+      "epoch": 0.9860010369602251,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 0.0001566759882670146,
+      "loss": 0.0287,
+      "step": 104
+    },
+    {
+      "epoch": 0.9954818161617658,
+      "grad_norm": 0.025634765625,
+      "learning_rate": 0.00015582437220268647,
+      "loss": 0.031,
+      "step": 105
+    },
+    {
+      "epoch": 1.0049625953633063,
+      "grad_norm": 0.02490234375,
+      "learning_rate": 0.0001549668334337271,
+      "loss": 0.0275,
+      "step": 106
+    },
+    {
+      "epoch": 1.0144433745648471,
+      "grad_norm": 0.03369140625,
+      "learning_rate": 0.0001541034629409865,
+      "loss": 0.0302,
+      "step": 107
+    },
+    {
+      "epoch": 1.0239241537663877,
+      "grad_norm": 0.027099609375,
+      "learning_rate": 0.00015323435232403337,
+      "loss": 0.0308,
+      "step": 108
+    },
+    {
+      "epoch": 1.0334049329679282,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.00015235959379143678,
+      "loss": 0.0247,
+      "step": 109
+    },
+    {
+      "epoch": 1.042885712169469,
+      "grad_norm": 0.0255126953125,
+      "learning_rate": 0.0001514792801509831,
+      "loss": 0.0281,
+      "step": 110
+    },
+    {
+      "epoch": 1.042885712169469,
+      "eval_loss": 0.03116695210337639,
+      "eval_runtime": 34.429,
+      "eval_samples_per_second": 20.651,
+      "eval_steps_per_second": 20.651,
+      "step": 110
+    },
+    {
+      "epoch": 1.0523664913710096,
+      "grad_norm": 0.0277099609375,
+      "learning_rate": 0.00015059350479982965,
+      "loss": 0.0243,
+      "step": 111
+    },
+    {
+      "epoch": 1.0618472705725501,
+      "grad_norm": 0.028564453125,
+      "learning_rate": 0.0001497023617145958,
+      "loss": 0.0274,
+      "step": 112
+    },
+    {
+      "epoch": 1.071328049774091,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 0.0001488059454413923,
+      "loss": 0.0265,
+      "step": 113
+    },
+    {
+      "epoch": 1.0808088289756315,
+      "grad_norm": 0.0296630859375,
+      "learning_rate": 0.00014790435108579048,
+      "loss": 0.0287,
+      "step": 114
+    },
+    {
+      "epoch": 1.090289608177172,
+      "grad_norm": 0.025390625,
+      "learning_rate": 0.000146997674302732,
+      "loss": 0.0255,
+      "step": 115
+    },
+    {
+      "epoch": 1.0997703873787126,
+      "grad_norm": 0.02685546875,
+      "learning_rate": 0.00014608601128638027,
+      "loss": 0.0258,
+      "step": 116
+    },
+    {
+      "epoch": 1.1092511665802534,
+      "grad_norm": 0.0277099609375,
+      "learning_rate": 0.00014516945875991472,
+      "loss": 0.0326,
+      "step": 117
+    },
+    {
+      "epoch": 1.118731945781794,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 0.00014424811396526892,
+      "loss": 0.0241,
+      "step": 118
+    },
+    {
+      "epoch": 1.1282127249833347,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 0.00014332207465281364,
+      "loss": 0.0276,
+      "step": 119
+    },
+    {
+      "epoch": 1.1376935041848752,
+      "grad_norm": 0.0306396484375,
+      "learning_rate": 0.0001423914390709861,
+      "loss": 0.0283,
+      "step": 120
+    },
+    {
+      "epoch": 1.1471742833864158,
+      "grad_norm": 0.0274658203125,
+      "learning_rate": 0.00014145630595586607,
+      "loss": 0.027,
+      "step": 121
+    },
+    {
+      "epoch": 1.1471742833864158,
+      "eval_loss": 0.030295666307210922,
+      "eval_runtime": 34.4847,
+      "eval_samples_per_second": 20.618,
+      "eval_steps_per_second": 20.618,
+      "step": 121
+    },
+    {
+      "epoch": 1.1566550625879564,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00014051677452070065,
+      "loss": 0.0248,
+      "step": 122
+    },
+    {
+      "epoch": 1.1661358417894971,
+      "grad_norm": 0.023193359375,
+      "learning_rate": 0.00013957294444537808,
+      "loss": 0.0226,
+      "step": 123
+    },
+    {
+      "epoch": 1.1756166209910377,
+      "grad_norm": 0.02880859375,
+      "learning_rate": 0.0001386249158658522,
+      "loss": 0.0332,
+      "step": 124
+    },
+    {
+      "epoch": 1.1850974001925783,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 0.00013767278936351854,
+      "loss": 0.0292,
+      "step": 125
+    },
+    {
+      "epoch": 1.194578179394119,
+      "grad_norm": 0.0264892578125,
+      "learning_rate": 0.00013671666595454295,
+      "loss": 0.0224,
+      "step": 126
+    },
+    {
+      "epoch": 1.2040589585956596,
+      "grad_norm": 0.027099609375,
+      "learning_rate": 0.00013575664707914448,
+      "loss": 0.0234,
+      "step": 127
+    },
+    {
+      "epoch": 1.2135397377972001,
+      "grad_norm": 0.03125,
+      "learning_rate": 0.0001347928345908329,
+      "loss": 0.029,
+      "step": 128
+    },
+    {
+      "epoch": 1.223020516998741,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00013382533074560255,
+      "loss": 0.0249,
+      "step": 129
+    },
+    {
+      "epoch": 1.2325012962002815,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.0001328542381910835,
+      "loss": 0.026,
+      "step": 130
+    },
+    {
+      "epoch": 1.241982075401822,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.00013187965995565098,
+      "loss": 0.0252,
+      "step": 131
+    },
+    {
+      "epoch": 1.2514628546033628,
+      "grad_norm": 0.0279541015625,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.023,
+      "step": 132
+    },
+    {
+      "epoch": 1.2514628546033628,
+      "eval_loss": 0.029845552518963814,
+      "eval_runtime": 34.1739,
+      "eval_samples_per_second": 20.805,
+      "eval_steps_per_second": 20.805,
+      "step": 132
+    },
+    {
+      "epoch": 1.2609436338049034,
+      "grad_norm": 0.02734375,
+      "learning_rate": 0.00012992046039364893,
+      "loss": 0.0259,
+      "step": 133
+    },
+    {
+      "epoch": 1.270424413006444,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 0.0001289360469289838,
+      "loss": 0.0244,
+      "step": 134
+    },
+    {
+      "epoch": 1.2799051922079845,
+      "grad_norm": 0.0286865234375,
+      "learning_rate": 0.00012794856348516095,
+      "loss": 0.0237,
+      "step": 135
+    },
+    {
+      "epoch": 1.2893859714095253,
+      "grad_norm": 0.0289306640625,
+      "learning_rate": 0.00012695811482955227,
+      "loss": 0.0248,
+      "step": 136
+    },
+    {
+      "epoch": 1.2988667506110658,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 0.00012596480604412484,
+      "loss": 0.0283,
+      "step": 137
+    },
+    {
+      "epoch": 1.3083475298126066,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 0.000124968742514292,
+      "loss": 0.021,
+      "step": 138
+    },
+    {
+      "epoch": 1.3178283090141472,
+      "grad_norm": 0.0279541015625,
+      "learning_rate": 0.00012397002991773275,
+      "loss": 0.0249,
+      "step": 139
+    },
+    {
+      "epoch": 1.3273090882156877,
+      "grad_norm": 0.026611328125,
+      "learning_rate": 0.0001229687742131796,
+      "loss": 0.0231,
+      "step": 140
+    },
+    {
+      "epoch": 1.3367898674172283,
+      "grad_norm": 0.0274658203125,
+      "learning_rate": 0.00012196508162917677,
+      "loss": 0.0276,
+      "step": 141
+    },
+    {
+      "epoch": 1.346270646618769,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 0.00012095905865281025,
+      "loss": 0.0268,
+      "step": 142
+    },
+    {
+      "epoch": 1.3557514258203096,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 0.00011995081201840956,
+      "loss": 0.0259,
+      "step": 143
+    },
+    {
+      "epoch": 1.3557514258203096,
+      "eval_loss": 0.029736338183283806,
+      "eval_runtime": 34.4542,
+      "eval_samples_per_second": 20.636,
+      "eval_steps_per_second": 20.636,
+      "step": 143
+    },
+    {
+      "epoch": 1.3652322050218502,
+      "grad_norm": 0.02734375,
+      "learning_rate": 0.00011894044869622403,
+      "loss": 0.025,
+      "step": 144
+    },
+    {
+      "epoch": 1.374712984223391,
+      "grad_norm": 0.0263671875,
+      "learning_rate": 0.00011792807588107357,
+      "loss": 0.0221,
+      "step": 145
+    },
+    {
+      "epoch": 1.3841937634249315,
+      "grad_norm": 0.031982421875,
+      "learning_rate": 0.00011691380098097597,
+      "loss": 0.0281,
+      "step": 146
+    },
+    {
+      "epoch": 1.393674542626472,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.0001158977316057513,
+      "loss": 0.021,
+      "step": 147
+    },
+    {
+      "epoch": 1.4031553218280126,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 0.00011487997555560503,
+      "loss": 0.0256,
+      "step": 148
+    },
+    {
+      "epoch": 1.4126361010295534,
+      "grad_norm": 0.0306396484375,
+      "learning_rate": 0.00011386064080969094,
+      "loss": 0.0267,
+      "step": 149
+    },
+    {
+      "epoch": 1.422116880231094,
+      "grad_norm": 0.0267333984375,
+      "learning_rate": 0.00011283983551465511,
+      "loss": 0.0211,
+      "step": 150
+    },
+    {
+      "epoch": 1.4315976594326347,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.0001118176679731619,
+      "loss": 0.025,
+      "step": 151
+    },
+    {
+      "epoch": 1.4410784386341753,
+      "grad_norm": 0.0296630859375,
+      "learning_rate": 0.00011079424663240372,
+      "loss": 0.0273,
+      "step": 152
+    },
+    {
+      "epoch": 1.4505592178357158,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 0.00010976968007259519,
+      "loss": 0.0243,
+      "step": 153
+    },
+    {
+      "epoch": 1.4600399970372564,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00010874407699545328,
+      "loss": 0.0232,
+      "step": 154
+    },
+    {
+      "epoch": 1.4600399970372564,
+      "eval_loss": 0.029951849952340126,
+      "eval_runtime": 34.3508,
+      "eval_samples_per_second": 20.698,
+      "eval_steps_per_second": 20.698,
+      "step": 154
+    },
+    {
+      "epoch": 1.4695207762387972,
+      "grad_norm": 0.03271484375,
+      "learning_rate": 0.00010771754621266466,
+      "loss": 0.0283,
+      "step": 155
+    },
+    {
+      "epoch": 1.4790015554403377,
+      "grad_norm": 0.024169921875,
+      "learning_rate": 0.00010669019663434117,
+      "loss": 0.0218,
+      "step": 156
+    },
+    {
+      "epoch": 1.4884823346418785,
+      "grad_norm": 0.029296875,
+      "learning_rate": 0.00010566213725746506,
+      "loss": 0.0273,
+      "step": 157
+    },
+    {
+      "epoch": 1.497963113843419,
+      "grad_norm": 0.0263671875,
+      "learning_rate": 0.00010463347715432488,
+      "loss": 0.0229,
+      "step": 158
+    },
+    {
+      "epoch": 1.5074438930449596,
+      "grad_norm": 0.02978515625,
+      "learning_rate": 0.00010360432546094341,
+      "loss": 0.0242,
+      "step": 159
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 315,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 53,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.6639380295489946e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-159/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6965abb853c761cad48cb468c99194ceaf6bcfe3b5e51b1799b677a2e2e93f5
+size 6072

checkpoint-212/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-math-7b-rl
+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 0.11.1

checkpoint-212/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-math-7b-rl",
+  "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": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-212/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e6f43964a1988848e3cb72ea02c50e1dcad4716924ace2a9a4b2818b250537f
+size 299884176

checkpoint-212/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6059954e6a004313a2a8c8c5a5912e0a2fff32d84c737b1d413abea49fe87de
+size 1199568698

checkpoint-212/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb0ae543fceda07b9b2a7a52d20139ae89ebfd7dcb8751b0d5d8e1fd8b66a32a
+size 14244

checkpoint-212/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a214afa28cba8a61e5d4cc1d5f61fa340ffd678157072501b9e9dc32eae8fe12
+size 1064

checkpoint-212/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-212/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

checkpoint-212/trainer_state.json

@@ -0,0 +1,1677 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0099251907266127,
+  "eval_steps": 11,
+  "global_step": 212,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009480779201540626,
+      "grad_norm": 0.38671875,
+      "learning_rate": 2e-05,
+      "loss": 0.4197,
+      "step": 1
+    },
+    {
+      "epoch": 0.009480779201540626,
+      "eval_loss": 0.41279804706573486,
+      "eval_runtime": 34.6855,
+      "eval_samples_per_second": 20.498,
+      "eval_steps_per_second": 20.498,
+      "step": 1
+    },
+    {
+      "epoch": 0.018961558403081252,
+      "grad_norm": 0.359375,
+      "learning_rate": 4e-05,
+      "loss": 0.3966,
+      "step": 2
+    },
+    {
+      "epoch": 0.02844233760462188,
+      "grad_norm": 0.388671875,
+      "learning_rate": 6e-05,
+      "loss": 0.4257,
+      "step": 3
+    },
+    {
+      "epoch": 0.037923116806162505,
+      "grad_norm": 0.408203125,
+      "learning_rate": 8e-05,
+      "loss": 0.4026,
+      "step": 4
+    },
+    {
+      "epoch": 0.04740389600770313,
+      "grad_norm": 0.384765625,
+      "learning_rate": 0.0001,
+      "loss": 0.3229,
+      "step": 5
+    },
+    {
+      "epoch": 0.05688467520924376,
+      "grad_norm": 0.251953125,
+      "learning_rate": 0.00012,
+      "loss": 0.2408,
+      "step": 6
+    },
+    {
+      "epoch": 0.06636545441078438,
+      "grad_norm": 0.203125,
+      "learning_rate": 0.00014,
+      "loss": 0.1709,
+      "step": 7
+    },
+    {
+      "epoch": 0.07584623361232501,
+      "grad_norm": 0.150390625,
+      "learning_rate": 0.00016,
+      "loss": 0.1328,
+      "step": 8
+    },
+    {
+      "epoch": 0.08532701281386564,
+      "grad_norm": 0.1201171875,
+      "learning_rate": 0.00018,
+      "loss": 0.0993,
+      "step": 9
+    },
+    {
+      "epoch": 0.09480779201540626,
+      "grad_norm": 0.10888671875,
+      "learning_rate": 0.0002,
+      "loss": 0.0914,
+      "step": 10
+    },
+    {
+      "epoch": 0.10428857121694689,
+      "grad_norm": 0.119140625,
+      "learning_rate": 0.00019999469523400122,
+      "loss": 0.0885,
+      "step": 11
+    },
+    {
+      "epoch": 0.10428857121694689,
+      "eval_loss": 0.07809103280305862,
+      "eval_runtime": 34.2892,
+      "eval_samples_per_second": 20.735,
+      "eval_steps_per_second": 20.735,
+      "step": 11
+    },
+    {
+      "epoch": 0.11376935041848751,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00019997878149881574,
+      "loss": 0.0761,
+      "step": 12
+    },
+    {
+      "epoch": 0.12325012962002814,
+      "grad_norm": 0.0703125,
+      "learning_rate": 0.0001999522604828164,
+      "loss": 0.0683,
+      "step": 13
+    },
+    {
+      "epoch": 0.13273090882156877,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 0.00019991513499975882,
+      "loss": 0.0696,
+      "step": 14
+    },
+    {
+      "epoch": 0.1422116880231094,
+      "grad_norm": 0.044921875,
+      "learning_rate": 0.00019986740898848306,
+      "loss": 0.0615,
+      "step": 15
+    },
+    {
+      "epoch": 0.15169246722465002,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019980908751249555,
+      "loss": 0.0625,
+      "step": 16
+    },
+    {
+      "epoch": 0.16117324642619066,
+      "grad_norm": 0.04736328125,
+      "learning_rate": 0.00019974017675943192,
+      "loss": 0.0598,
+      "step": 17
+    },
+    {
+      "epoch": 0.17065402562773127,
+      "grad_norm": 0.039306640625,
+      "learning_rate": 0.0001996606840404006,
+      "loss": 0.0573,
+      "step": 18
+    },
+    {
+      "epoch": 0.1801348048292719,
+      "grad_norm": 0.036376953125,
+      "learning_rate": 0.00019957061778920701,
+      "loss": 0.0482,
+      "step": 19
+    },
+    {
+      "epoch": 0.18961558403081252,
+      "grad_norm": 0.039306640625,
+      "learning_rate": 0.0001994699875614589,
+      "loss": 0.0555,
+      "step": 20
+    },
+    {
+      "epoch": 0.19909636323235316,
+      "grad_norm": 0.0380859375,
+      "learning_rate": 0.00019935880403355253,
+      "loss": 0.0495,
+      "step": 21
+    },
+    {
+      "epoch": 0.20857714243389378,
+      "grad_norm": 0.038818359375,
+      "learning_rate": 0.00019923707900153982,
+      "loss": 0.0482,
+      "step": 22
+    },
+    {
+      "epoch": 0.20857714243389378,
+      "eval_loss": 0.05171125754714012,
+      "eval_runtime": 34.4113,
+      "eval_samples_per_second": 20.662,
+      "eval_steps_per_second": 20.662,
+      "step": 22
+    },
+    {
+      "epoch": 0.21805792163543442,
+      "grad_norm": 0.038818359375,
+      "learning_rate": 0.00019910482537987702,
+      "loss": 0.0529,
+      "step": 23
+    },
+    {
+      "epoch": 0.22753870083697503,
+      "grad_norm": 0.031494140625,
+      "learning_rate": 0.0001989620572000544,
+      "loss": 0.0495,
+      "step": 24
+    },
+    {
+      "epoch": 0.23701948003851567,
+      "grad_norm": 0.0380859375,
+      "learning_rate": 0.00019880878960910772,
+      "loss": 0.059,
+      "step": 25
+    },
+    {
+      "epoch": 0.24650025924005628,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.00019864503886801106,
+      "loss": 0.0545,
+      "step": 26
+    },
+    {
+      "epoch": 0.2559810384415969,
+      "grad_norm": 0.029296875,
+      "learning_rate": 0.00019847082234995171,
+      "loss": 0.0417,
+      "step": 27
+    },
+    {
+      "epoch": 0.26546181764313753,
+      "grad_norm": 0.037109375,
+      "learning_rate": 0.00019828615853848688,
+      "loss": 0.0459,
+      "step": 28
+    },
+    {
+      "epoch": 0.27494259684467814,
+      "grad_norm": 0.027099609375,
+      "learning_rate": 0.00019809106702558277,
+      "loss": 0.0412,
+      "step": 29
+    },
+    {
+      "epoch": 0.2844233760462188,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.0001978855685095358,
+      "loss": 0.0403,
+      "step": 30
+    },
+    {
+      "epoch": 0.2939041552477594,
+      "grad_norm": 0.0289306640625,
+      "learning_rate": 0.00019766968479277683,
+      "loss": 0.0463,
+      "step": 31
+    },
+    {
+      "epoch": 0.30338493444930004,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 0.00019744343877955788,
+      "loss": 0.041,
+      "step": 32
+    },
+    {
+      "epoch": 0.3128657136508407,
+      "grad_norm": 0.033447265625,
+      "learning_rate": 0.00019720685447352209,
+      "loss": 0.045,
+      "step": 33
+    },
+    {
+      "epoch": 0.3128657136508407,
+      "eval_loss": 0.04294149950146675,
+      "eval_runtime": 34.2719,
+      "eval_samples_per_second": 20.746,
+      "eval_steps_per_second": 20.746,
+      "step": 33
+    },
+    {
+      "epoch": 0.3223464928523813,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 0.0001969599569751571,
+      "loss": 0.0369,
+      "step": 34
+    },
+    {
+      "epoch": 0.33182727205392193,
+      "grad_norm": 0.029296875,
+      "learning_rate": 0.00019670277247913205,
+      "loss": 0.0465,
+      "step": 35
+    },
+    {
+      "epoch": 0.34130805125546254,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 0.0001964353282715183,
+      "loss": 0.0382,
+      "step": 36
+    },
+    {
+      "epoch": 0.3507888304570032,
+      "grad_norm": 0.0299072265625,
+      "learning_rate": 0.00019615765272689461,
+      "loss": 0.0442,
+      "step": 37
+    },
+    {
+      "epoch": 0.3602696096585438,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00019586977530533677,
+      "loss": 0.0481,
+      "step": 38
+    },
+    {
+      "epoch": 0.36975038886008443,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 0.00019557172654929196,
+      "loss": 0.0423,
+      "step": 39
+    },
+    {
+      "epoch": 0.37923116806162505,
+      "grad_norm": 0.0299072265625,
+      "learning_rate": 0.00019526353808033825,
+      "loss": 0.0384,
+      "step": 40
+    },
+    {
+      "epoch": 0.3887119472631657,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 0.00019494524259582992,
+      "loss": 0.0404,
+      "step": 41
+    },
+    {
+      "epoch": 0.3981927264647063,
+      "grad_norm": 0.0286865234375,
+      "learning_rate": 0.00019461687386542826,
+      "loss": 0.0394,
+      "step": 42
+    },
+    {
+      "epoch": 0.40767350566624694,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 0.00019427846672751873,
+      "loss": 0.0351,
+      "step": 43
+    },
+    {
+      "epoch": 0.41715428486778755,
+      "grad_norm": 0.02783203125,
+      "learning_rate": 0.00019393005708551498,
+      "loss": 0.0425,
+      "step": 44
+    },
+    {
+      "epoch": 0.41715428486778755,
+      "eval_loss": 0.03996235132217407,
+      "eval_runtime": 34.3007,
+      "eval_samples_per_second": 20.728,
+      "eval_steps_per_second": 20.728,
+      "step": 44
+    },
+    {
+      "epoch": 0.4266350640693282,
+      "grad_norm": 0.030517578125,
+      "learning_rate": 0.00019357168190404936,
+      "loss": 0.0365,
+      "step": 45
+    },
+    {
+      "epoch": 0.43611584327086883,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 0.00019320337920505153,
+      "loss": 0.0438,
+      "step": 46
+    },
+    {
+      "epoch": 0.44559662247240944,
+      "grad_norm": 0.0306396484375,
+      "learning_rate": 0.00019282518806371414,
+      "loss": 0.044,
+      "step": 47
+    },
+    {
+      "epoch": 0.45507740167395005,
+      "grad_norm": 0.037841796875,
+      "learning_rate": 0.0001924371486043473,
+      "loss": 0.0496,
+      "step": 48
+    },
+    {
+      "epoch": 0.4645581808754907,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 0.0001920393019961217,
+      "loss": 0.0369,
+      "step": 49
+    },
+    {
+      "epoch": 0.47403896007703133,
+      "grad_norm": 0.0341796875,
+      "learning_rate": 0.0001916316904487005,
+      "loss": 0.0399,
+      "step": 50
+    },
+    {
+      "epoch": 0.48351973927857195,
+      "grad_norm": 0.0255126953125,
+      "learning_rate": 0.00019121435720776122,
+      "loss": 0.0363,
+      "step": 51
+    },
+    {
+      "epoch": 0.49300051848011256,
+      "grad_norm": 0.0311279296875,
+      "learning_rate": 0.0001907873465504076,
+      "loss": 0.0384,
+      "step": 52
+    },
+    {
+      "epoch": 0.5024812976816532,
+      "grad_norm": 0.03271484375,
+      "learning_rate": 0.00019035070378047204,
+      "loss": 0.0371,
+      "step": 53
+    },
+    {
+      "epoch": 0.5119620768831938,
+      "grad_norm": 0.0263671875,
+      "learning_rate": 0.00018990447522370884,
+      "loss": 0.0351,
+      "step": 54
+    },
+    {
+      "epoch": 0.5214428560847345,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00018944870822287956,
+      "loss": 0.0411,
+      "step": 55
+    },
+    {
+      "epoch": 0.5214428560847345,
+      "eval_loss": 0.03788134828209877,
+      "eval_runtime": 34.6048,
+      "eval_samples_per_second": 20.546,
+      "eval_steps_per_second": 20.546,
+      "step": 55
+    },
+    {
+      "epoch": 0.5309236352862751,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00018898345113272998,
+      "loss": 0.0337,
+      "step": 56
+    },
+    {
+      "epoch": 0.5404044144878157,
+      "grad_norm": 0.0245361328125,
+      "learning_rate": 0.00018850875331485995,
+      "loss": 0.0309,
+      "step": 57
+    },
+    {
+      "epoch": 0.5498851936893563,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 0.00018802466513248632,
+      "loss": 0.0329,
+      "step": 58
+    },
+    {
+      "epoch": 0.559365972890897,
+      "grad_norm": 0.0267333984375,
+      "learning_rate": 0.00018753123794509974,
+      "loss": 0.0365,
+      "step": 59
+    },
+    {
+      "epoch": 0.5688467520924376,
+      "grad_norm": 0.02734375,
+      "learning_rate": 0.00018702852410301554,
+      "loss": 0.0373,
+      "step": 60
+    },
+    {
+      "epoch": 0.5783275312939782,
+      "grad_norm": 0.025390625,
+      "learning_rate": 0.0001865165769418196,
+      "loss": 0.0375,
+      "step": 61
+    },
+    {
+      "epoch": 0.5878083104955188,
+      "grad_norm": 0.02978515625,
+      "learning_rate": 0.00018599545077670985,
+      "loss": 0.0376,
+      "step": 62
+    },
+    {
+      "epoch": 0.5972890896970595,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.0001854652008967335,
+      "loss": 0.0337,
+      "step": 63
+    },
+    {
+      "epoch": 0.6067698688986001,
+      "grad_norm": 0.02880859375,
+      "learning_rate": 0.00018492588355892124,
+      "loss": 0.0379,
+      "step": 64
+    },
+    {
+      "epoch": 0.6162506481001407,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018437755598231856,
+      "loss": 0.0392,
+      "step": 65
+    },
+    {
+      "epoch": 0.6257314273016814,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00018382027634191524,
+      "loss": 0.0348,
+      "step": 66
+    },
+    {
+      "epoch": 0.6257314273016814,
+      "eval_loss": 0.03594927862286568,
+      "eval_runtime": 34.2756,
+      "eval_samples_per_second": 20.744,
+      "eval_steps_per_second": 20.744,
+      "step": 66
+    },
+    {
+      "epoch": 0.635212206503222,
+      "grad_norm": 0.03515625,
+      "learning_rate": 0.00018325410376247294,
+      "loss": 0.0379,
+      "step": 67
+    },
+    {
+      "epoch": 0.6446929857047626,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 0.0001826790983122527,
+      "loss": 0.0317,
+      "step": 68
+    },
+    {
+      "epoch": 0.6541737649063032,
+      "grad_norm": 0.0296630859375,
+      "learning_rate": 0.00018209532099664174,
+      "loss": 0.0366,
+      "step": 69
+    },
+    {
+      "epoch": 0.6636545441078439,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00018150283375168114,
+      "loss": 0.0345,
+      "step": 70
+    },
+    {
+      "epoch": 0.6731353233093845,
+      "grad_norm": 0.03125,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0368,
+      "step": 71
+    },
+    {
+      "epoch": 0.6826161025109251,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.00018029198183161998,
+      "loss": 0.0455,
+      "step": 72
+    },
+    {
+      "epoch": 0.6920968817124658,
+      "grad_norm": 0.029296875,
+      "learning_rate": 0.00017967374562224132,
+      "loss": 0.0362,
+      "step": 73
+    },
+    {
+      "epoch": 0.7015776609140064,
+      "grad_norm": 0.0311279296875,
+      "learning_rate": 0.00017904705640132718,
+      "loss": 0.0388,
+      "step": 74
+    },
+    {
+      "epoch": 0.711058440115547,
+      "grad_norm": 0.02685546875,
+      "learning_rate": 0.00017841198065767107,
+      "loss": 0.0288,
+      "step": 75
+    },
+    {
+      "epoch": 0.7205392193170876,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00017776858576983712,
+      "loss": 0.0349,
+      "step": 76
+    },
+    {
+      "epoch": 0.7300199985186282,
+      "grad_norm": 0.026611328125,
+      "learning_rate": 0.0001771169399990119,
+      "loss": 0.0288,
+      "step": 77
+    },
+    {
+      "epoch": 0.7300199985186282,
+      "eval_loss": 0.03419337794184685,
+      "eval_runtime": 34.3669,
+      "eval_samples_per_second": 20.688,
+      "eval_steps_per_second": 20.688,
+      "step": 77
+    },
+    {
+      "epoch": 0.7395007777201689,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.00017645711248176195,
+      "loss": 0.0285,
+      "step": 78
+    },
+    {
+      "epoch": 0.7489815569217095,
+      "grad_norm": 0.025390625,
+      "learning_rate": 0.00017578917322269886,
+      "loss": 0.0338,
+      "step": 79
+    },
+    {
+      "epoch": 0.7584623361232501,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00017511319308705198,
+      "loss": 0.0316,
+      "step": 80
+    },
+    {
+      "epoch": 0.7679431153247908,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.0001744292437931502,
+      "loss": 0.0306,
+      "step": 81
+    },
+    {
+      "epoch": 0.7774238945263314,
+      "grad_norm": 0.027099609375,
+      "learning_rate": 0.00017373739790481262,
+      "loss": 0.0335,
+      "step": 82
+    },
+    {
+      "epoch": 0.786904673727872,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017303772882365016,
+      "loss": 0.0271,
+      "step": 83
+    },
+    {
+      "epoch": 0.7963854529294127,
+      "grad_norm": 0.028564453125,
+      "learning_rate": 0.00017233031078127788,
+      "loss": 0.0334,
+      "step": 84
+    },
+    {
+      "epoch": 0.8058662321309532,
+      "grad_norm": 0.0299072265625,
+      "learning_rate": 0.00017161521883143934,
+      "loss": 0.0403,
+      "step": 85
+    },
+    {
+      "epoch": 0.8153470113324939,
+      "grad_norm": 0.0294189453125,
+      "learning_rate": 0.00017089252884204377,
+      "loss": 0.0368,
+      "step": 86
+    },
+    {
+      "epoch": 0.8248277905340345,
+      "grad_norm": 0.03369140625,
+      "learning_rate": 0.0001701623174871168,
+      "loss": 0.0335,
+      "step": 87
+    },
+    {
+      "epoch": 0.8343085697355751,
+      "grad_norm": 0.0277099609375,
+      "learning_rate": 0.0001694246622386658,
+      "loss": 0.0339,
+      "step": 88
+    },
+    {
+      "epoch": 0.8343085697355751,
+      "eval_loss": 0.033091045916080475,
+      "eval_runtime": 34.4475,
+      "eval_samples_per_second": 20.64,
+      "eval_steps_per_second": 20.64,
+      "step": 88
+    },
+    {
+      "epoch": 0.8437893489371158,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 0.00016867964135846043,
+      "loss": 0.0241,
+      "step": 89
+    },
+    {
+      "epoch": 0.8532701281386564,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00016792733388972932,
+      "loss": 0.0387,
+      "step": 90
+    },
+    {
+      "epoch": 0.862750907340197,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 0.0001671678196487741,
+      "loss": 0.0346,
+      "step": 91
+    },
+    {
+      "epoch": 0.8722316865417377,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 0.00016640117921650117,
+      "loss": 0.0378,
+      "step": 92
+    },
+    {
+      "epoch": 0.8817124657432783,
+      "grad_norm": 0.0279541015625,
+      "learning_rate": 0.00016562749392987254,
+      "loss": 0.0294,
+      "step": 93
+    },
+    {
+      "epoch": 0.8911932449448189,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001648468458732762,
+      "loss": 0.0308,
+      "step": 94
+    },
+    {
+      "epoch": 0.9006740241463596,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00016405931786981755,
+      "loss": 0.0326,
+      "step": 95
+    },
+    {
+      "epoch": 0.9101548033479001,
+      "grad_norm": 0.0262451171875,
+      "learning_rate": 0.00016326499347253207,
+      "loss": 0.032,
+      "step": 96
+    },
+    {
+      "epoch": 0.9196355825494408,
+      "grad_norm": 0.0264892578125,
+      "learning_rate": 0.00016246395695552085,
+      "loss": 0.0321,
+      "step": 97
+    },
+    {
+      "epoch": 0.9291163617509814,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00016165629330500952,
+      "loss": 0.0301,
+      "step": 98
+    },
+    {
+      "epoch": 0.938597140952522,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.0001608420882103315,
+      "loss": 0.0297,
+      "step": 99
+    },
+    {
+      "epoch": 0.938597140952522,
+      "eval_loss": 0.03182319179177284,
+      "eval_runtime": 34.2304,
+      "eval_samples_per_second": 20.771,
+      "eval_steps_per_second": 20.771,
+      "step": 99
+    },
+    {
+      "epoch": 0.9480779201540627,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00016002142805483685,
+      "loss": 0.0327,
+      "step": 100
+    },
+    {
+      "epoch": 0.9575586993556033,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 0.0001591943999067273,
+      "loss": 0.0285,
+      "step": 101
+    },
+    {
+      "epoch": 0.9670394785571439,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.00015836109150981886,
+      "loss": 0.0308,
+      "step": 102
+    },
+    {
+      "epoch": 0.9765202577586846,
+      "grad_norm": 0.0283203125,
+      "learning_rate": 0.00015752159127423263,
+      "loss": 0.0301,
+      "step": 103
+    },
+    {
+      "epoch": 0.9860010369602251,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 0.0001566759882670146,
+      "loss": 0.0287,
+      "step": 104
+    },
+    {
+      "epoch": 0.9954818161617658,
+      "grad_norm": 0.025634765625,
+      "learning_rate": 0.00015582437220268647,
+      "loss": 0.031,
+      "step": 105
+    },
+    {
+      "epoch": 1.0049625953633063,
+      "grad_norm": 0.02490234375,
+      "learning_rate": 0.0001549668334337271,
+      "loss": 0.0275,
+      "step": 106
+    },
+    {
+      "epoch": 1.0144433745648471,
+      "grad_norm": 0.03369140625,
+      "learning_rate": 0.0001541034629409865,
+      "loss": 0.0302,
+      "step": 107
+    },
+    {
+      "epoch": 1.0239241537663877,
+      "grad_norm": 0.027099609375,
+      "learning_rate": 0.00015323435232403337,
+      "loss": 0.0308,
+      "step": 108
+    },
+    {
+      "epoch": 1.0334049329679282,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.00015235959379143678,
+      "loss": 0.0247,
+      "step": 109
+    },
+    {
+      "epoch": 1.042885712169469,
+      "grad_norm": 0.0255126953125,
+      "learning_rate": 0.0001514792801509831,
+      "loss": 0.0281,
+      "step": 110
+    },
+    {
+      "epoch": 1.042885712169469,
+      "eval_loss": 0.03116695210337639,
+      "eval_runtime": 34.429,
+      "eval_samples_per_second": 20.651,
+      "eval_steps_per_second": 20.651,
+      "step": 110
+    },
+    {
+      "epoch": 1.0523664913710096,
+      "grad_norm": 0.0277099609375,
+      "learning_rate": 0.00015059350479982965,
+      "loss": 0.0243,
+      "step": 111
+    },
+    {
+      "epoch": 1.0618472705725501,
+      "grad_norm": 0.028564453125,
+      "learning_rate": 0.0001497023617145958,
+      "loss": 0.0274,
+      "step": 112
+    },
+    {
+      "epoch": 1.071328049774091,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 0.0001488059454413923,
+      "loss": 0.0265,
+      "step": 113
+    },
+    {
+      "epoch": 1.0808088289756315,
+      "grad_norm": 0.0296630859375,
+      "learning_rate": 0.00014790435108579048,
+      "loss": 0.0287,
+      "step": 114
+    },
+    {
+      "epoch": 1.090289608177172,
+      "grad_norm": 0.025390625,
+      "learning_rate": 0.000146997674302732,
+      "loss": 0.0255,
+      "step": 115
+    },
+    {
+      "epoch": 1.0997703873787126,
+      "grad_norm": 0.02685546875,
+      "learning_rate": 0.00014608601128638027,
+      "loss": 0.0258,
+      "step": 116
+    },
+    {
+      "epoch": 1.1092511665802534,
+      "grad_norm": 0.0277099609375,
+      "learning_rate": 0.00014516945875991472,
+      "loss": 0.0326,
+      "step": 117
+    },
+    {
+      "epoch": 1.118731945781794,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 0.00014424811396526892,
+      "loss": 0.0241,
+      "step": 118
+    },
+    {
+      "epoch": 1.1282127249833347,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 0.00014332207465281364,
+      "loss": 0.0276,
+      "step": 119
+    },
+    {
+      "epoch": 1.1376935041848752,
+      "grad_norm": 0.0306396484375,
+      "learning_rate": 0.0001423914390709861,
+      "loss": 0.0283,
+      "step": 120
+    },
+    {
+      "epoch": 1.1471742833864158,
+      "grad_norm": 0.0274658203125,
+      "learning_rate": 0.00014145630595586607,
+      "loss": 0.027,
+      "step": 121
+    },
+    {
+      "epoch": 1.1471742833864158,
+      "eval_loss": 0.030295666307210922,
+      "eval_runtime": 34.4847,
+      "eval_samples_per_second": 20.618,
+      "eval_steps_per_second": 20.618,
+      "step": 121
+    },
+    {
+      "epoch": 1.1566550625879564,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00014051677452070065,
+      "loss": 0.0248,
+      "step": 122
+    },
+    {
+      "epoch": 1.1661358417894971,
+      "grad_norm": 0.023193359375,
+      "learning_rate": 0.00013957294444537808,
+      "loss": 0.0226,
+      "step": 123
+    },
+    {
+      "epoch": 1.1756166209910377,
+      "grad_norm": 0.02880859375,
+      "learning_rate": 0.0001386249158658522,
+      "loss": 0.0332,
+      "step": 124
+    },
+    {
+      "epoch": 1.1850974001925783,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 0.00013767278936351854,
+      "loss": 0.0292,
+      "step": 125
+    },
+    {
+      "epoch": 1.194578179394119,
+      "grad_norm": 0.0264892578125,
+      "learning_rate": 0.00013671666595454295,
+      "loss": 0.0224,
+      "step": 126
+    },
+    {
+      "epoch": 1.2040589585956596,
+      "grad_norm": 0.027099609375,
+      "learning_rate": 0.00013575664707914448,
+      "loss": 0.0234,
+      "step": 127
+    },
+    {
+      "epoch": 1.2135397377972001,
+      "grad_norm": 0.03125,
+      "learning_rate": 0.0001347928345908329,
+      "loss": 0.029,
+      "step": 128
+    },
+    {
+      "epoch": 1.223020516998741,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00013382533074560255,
+      "loss": 0.0249,
+      "step": 129
+    },
+    {
+      "epoch": 1.2325012962002815,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.0001328542381910835,
+      "loss": 0.026,
+      "step": 130
+    },
+    {
+      "epoch": 1.241982075401822,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.00013187965995565098,
+      "loss": 0.0252,
+      "step": 131
+    },
+    {
+      "epoch": 1.2514628546033628,
+      "grad_norm": 0.0279541015625,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.023,
+      "step": 132
+    },
+    {
+      "epoch": 1.2514628546033628,
+      "eval_loss": 0.029845552518963814,
+      "eval_runtime": 34.1739,
+      "eval_samples_per_second": 20.805,
+      "eval_steps_per_second": 20.805,
+      "step": 132
+    },
+    {
+      "epoch": 1.2609436338049034,
+      "grad_norm": 0.02734375,
+      "learning_rate": 0.00012992046039364893,
+      "loss": 0.0259,
+      "step": 133
+    },
+    {
+      "epoch": 1.270424413006444,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 0.0001289360469289838,
+      "loss": 0.0244,
+      "step": 134
+    },
+    {
+      "epoch": 1.2799051922079845,
+      "grad_norm": 0.0286865234375,
+      "learning_rate": 0.00012794856348516095,
+      "loss": 0.0237,
+      "step": 135
+    },
+    {
+      "epoch": 1.2893859714095253,
+      "grad_norm": 0.0289306640625,
+      "learning_rate": 0.00012695811482955227,
+      "loss": 0.0248,
+      "step": 136
+    },
+    {
+      "epoch": 1.2988667506110658,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 0.00012596480604412484,
+      "loss": 0.0283,
+      "step": 137
+    },
+    {
+      "epoch": 1.3083475298126066,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 0.000124968742514292,
+      "loss": 0.021,
+      "step": 138
+    },
+    {
+      "epoch": 1.3178283090141472,
+      "grad_norm": 0.0279541015625,
+      "learning_rate": 0.00012397002991773275,
+      "loss": 0.0249,
+      "step": 139
+    },
+    {
+      "epoch": 1.3273090882156877,
+      "grad_norm": 0.026611328125,
+      "learning_rate": 0.0001229687742131796,
+      "loss": 0.0231,
+      "step": 140
+    },
+    {
+      "epoch": 1.3367898674172283,
+      "grad_norm": 0.0274658203125,
+      "learning_rate": 0.00012196508162917677,
+      "loss": 0.0276,
+      "step": 141
+    },
+    {
+      "epoch": 1.346270646618769,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 0.00012095905865281025,
+      "loss": 0.0268,
+      "step": 142
+    },
+    {
+      "epoch": 1.3557514258203096,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 0.00011995081201840956,
+      "loss": 0.0259,
+      "step": 143
+    },
+    {
+      "epoch": 1.3557514258203096,
+      "eval_loss": 0.029736338183283806,
+      "eval_runtime": 34.4542,
+      "eval_samples_per_second": 20.636,
+      "eval_steps_per_second": 20.636,
+      "step": 143
+    },
+    {
+      "epoch": 1.3652322050218502,
+      "grad_norm": 0.02734375,
+      "learning_rate": 0.00011894044869622403,
+      "loss": 0.025,
+      "step": 144
+    },
+    {
+      "epoch": 1.374712984223391,
+      "grad_norm": 0.0263671875,
+      "learning_rate": 0.00011792807588107357,
+      "loss": 0.0221,
+      "step": 145
+    },
+    {
+      "epoch": 1.3841937634249315,
+      "grad_norm": 0.031982421875,
+      "learning_rate": 0.00011691380098097597,
+      "loss": 0.0281,
+      "step": 146
+    },
+    {
+      "epoch": 1.393674542626472,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.0001158977316057513,
+      "loss": 0.021,
+      "step": 147
+    },
+    {
+      "epoch": 1.4031553218280126,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 0.00011487997555560503,
+      "loss": 0.0256,
+      "step": 148
+    },
+    {
+      "epoch": 1.4126361010295534,
+      "grad_norm": 0.0306396484375,
+      "learning_rate": 0.00011386064080969094,
+      "loss": 0.0267,
+      "step": 149
+    },
+    {
+      "epoch": 1.422116880231094,
+      "grad_norm": 0.0267333984375,
+      "learning_rate": 0.00011283983551465511,
+      "loss": 0.0211,
+      "step": 150
+    },
+    {
+      "epoch": 1.4315976594326347,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.0001118176679731619,
+      "loss": 0.025,
+      "step": 151
+    },
+    {
+      "epoch": 1.4410784386341753,
+      "grad_norm": 0.0296630859375,
+      "learning_rate": 0.00011079424663240372,
+      "loss": 0.0273,
+      "step": 152
+    },
+    {
+      "epoch": 1.4505592178357158,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 0.00010976968007259519,
+      "loss": 0.0243,
+      "step": 153
+    },
+    {
+      "epoch": 1.4600399970372564,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00010874407699545328,
+      "loss": 0.0232,
+      "step": 154
+    },
+    {
+      "epoch": 1.4600399970372564,
+      "eval_loss": 0.029951849952340126,
+      "eval_runtime": 34.3508,
+      "eval_samples_per_second": 20.698,
+      "eval_steps_per_second": 20.698,
+      "step": 154
+    },
+    {
+      "epoch": 1.4695207762387972,
+      "grad_norm": 0.03271484375,
+      "learning_rate": 0.00010771754621266466,
+      "loss": 0.0283,
+      "step": 155
+    },
+    {
+      "epoch": 1.4790015554403377,
+      "grad_norm": 0.024169921875,
+      "learning_rate": 0.00010669019663434117,
+      "loss": 0.0218,
+      "step": 156
+    },
+    {
+      "epoch": 1.4884823346418785,
+      "grad_norm": 0.029296875,
+      "learning_rate": 0.00010566213725746506,
+      "loss": 0.0273,
+      "step": 157
+    },
+    {
+      "epoch": 1.497963113843419,
+      "grad_norm": 0.0263671875,
+      "learning_rate": 0.00010463347715432488,
+      "loss": 0.0229,
+      "step": 158
+    },
+    {
+      "epoch": 1.5074438930449596,
+      "grad_norm": 0.02978515625,
+      "learning_rate": 0.00010360432546094341,
+      "loss": 0.0242,
+      "step": 159
+    },
+    {
+      "epoch": 1.5169246722465002,
+      "grad_norm": 0.031494140625,
+      "learning_rate": 0.00010257479136549889,
+      "loss": 0.0252,
+      "step": 160
+    },
+    {
+      "epoch": 1.5264054514480407,
+      "grad_norm": 0.0283203125,
+      "learning_rate": 0.00010154498409674051,
+      "loss": 0.0275,
+      "step": 161
+    },
+    {
+      "epoch": 1.5358862306495815,
+      "grad_norm": 0.035400390625,
+      "learning_rate": 0.00010051501291240008,
+      "loss": 0.0299,
+      "step": 162
+    },
+    {
+      "epoch": 1.5453670098511223,
+      "grad_norm": 0.031982421875,
+      "learning_rate": 9.948498708759993e-05,
+      "loss": 0.0264,
+      "step": 163
+    },
+    {
+      "epoch": 1.5548477890526629,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 9.845501590325948e-05,
+      "loss": 0.025,
+      "step": 164
+    },
+    {
+      "epoch": 1.5643285682542034,
+      "grad_norm": 0.029296875,
+      "learning_rate": 9.742520863450115e-05,
+      "loss": 0.0203,
+      "step": 165
+    },
+    {
+      "epoch": 1.5643285682542034,
+      "eval_loss": 0.02908056415617466,
+      "eval_runtime": 34.2083,
+      "eval_samples_per_second": 20.784,
+      "eval_steps_per_second": 20.784,
+      "step": 165
+    },
+    {
+      "epoch": 1.573809347455744,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 9.639567453905661e-05,
+      "loss": 0.0262,
+      "step": 166
+    },
+    {
+      "epoch": 1.5832901266572845,
+      "grad_norm": 0.0245361328125,
+      "learning_rate": 9.536652284567513e-05,
+      "loss": 0.0213,
+      "step": 167
+    },
+    {
+      "epoch": 1.5927709058588253,
+      "grad_norm": 0.031005859375,
+      "learning_rate": 9.433786274253495e-05,
+      "loss": 0.0272,
+      "step": 168
+    },
+    {
+      "epoch": 1.6022516850603659,
+      "grad_norm": 0.0262451171875,
+      "learning_rate": 9.330980336565887e-05,
+      "loss": 0.0217,
+      "step": 169
+    },
+    {
+      "epoch": 1.6117324642619066,
+      "grad_norm": 0.0296630859375,
+      "learning_rate": 9.228245378733537e-05,
+      "loss": 0.0258,
+      "step": 170
+    },
+    {
+      "epoch": 1.6212132434634472,
+      "grad_norm": 0.03466796875,
+      "learning_rate": 9.125592300454676e-05,
+      "loss": 0.0278,
+      "step": 171
+    },
+    {
+      "epoch": 1.6306940226649878,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 9.023031992740488e-05,
+      "loss": 0.0234,
+      "step": 172
+    },
+    {
+      "epoch": 1.6401748018665283,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 8.920575336759629e-05,
+      "loss": 0.025,
+      "step": 173
+    },
+    {
+      "epoch": 1.6496555810680689,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 8.818233202683814e-05,
+      "loss": 0.0268,
+      "step": 174
+    },
+    {
+      "epoch": 1.6591363602696096,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 8.71601644853449e-05,
+      "loss": 0.0241,
+      "step": 175
+    },
+    {
+      "epoch": 1.6686171394711504,
+      "grad_norm": 0.028564453125,
+      "learning_rate": 8.613935919030907e-05,
+      "loss": 0.0241,
+      "step": 176
+    },
+    {
+      "epoch": 1.6686171394711504,
+      "eval_loss": 0.02843022532761097,
+      "eval_runtime": 34.2598,
+      "eval_samples_per_second": 20.753,
+      "eval_steps_per_second": 20.753,
+      "step": 176
+    },
+    {
+      "epoch": 1.678097918672691,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 8.512002444439502e-05,
+      "loss": 0.0228,
+      "step": 177
+    },
+    {
+      "epoch": 1.6875786978742315,
+      "grad_norm": 0.02880859375,
+      "learning_rate": 8.410226839424871e-05,
+      "loss": 0.0272,
+      "step": 178
+    },
+    {
+      "epoch": 1.697059477075772,
+      "grad_norm": 0.0238037109375,
+      "learning_rate": 8.308619901902406e-05,
+      "loss": 0.0196,
+      "step": 179
+    },
+    {
+      "epoch": 1.7065402562773127,
+      "grad_norm": 0.02783203125,
+      "learning_rate": 8.207192411892646e-05,
+      "loss": 0.0218,
+      "step": 180
+    },
+    {
+      "epoch": 1.7160210354788534,
+      "grad_norm": 0.0277099609375,
+      "learning_rate": 8.1059551303776e-05,
+      "loss": 0.022,
+      "step": 181
+    },
+    {
+      "epoch": 1.7255018146803942,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 8.004918798159045e-05,
+      "loss": 0.0219,
+      "step": 182
+    },
+    {
+      "epoch": 1.7349825938819348,
+      "grad_norm": 0.02734375,
+      "learning_rate": 7.904094134718976e-05,
+      "loss": 0.0244,
+      "step": 183
+    },
+    {
+      "epoch": 1.7444633730834753,
+      "grad_norm": 0.036376953125,
+      "learning_rate": 7.803491837082324e-05,
+      "loss": 0.0301,
+      "step": 184
+    },
+    {
+      "epoch": 1.7539441522850159,
+      "grad_norm": 0.03125,
+      "learning_rate": 7.703122578682046e-05,
+      "loss": 0.0259,
+      "step": 185
+    },
+    {
+      "epoch": 1.7634249314865564,
+      "grad_norm": 0.025634765625,
+      "learning_rate": 7.602997008226726e-05,
+      "loss": 0.0216,
+      "step": 186
+    },
+    {
+      "epoch": 1.7729057106880972,
+      "grad_norm": 0.02783203125,
+      "learning_rate": 7.5031257485708e-05,
+      "loss": 0.0245,
+      "step": 187
+    },
+    {
+      "epoch": 1.7729057106880972,
+      "eval_loss": 0.028160251677036285,
+      "eval_runtime": 34.3215,
+      "eval_samples_per_second": 20.716,
+      "eval_steps_per_second": 20.716,
+      "step": 187
+    },
+    {
+      "epoch": 1.7823864898896378,
+      "grad_norm": 0.024658203125,
+      "learning_rate": 7.403519395587521e-05,
+      "loss": 0.0221,
+      "step": 188
+    },
+    {
+      "epoch": 1.7918672690911785,
+      "grad_norm": 0.0263671875,
+      "learning_rate": 7.304188517044774e-05,
+      "loss": 0.0228,
+      "step": 189
+    },
+    {
+      "epoch": 1.801348048292719,
+      "grad_norm": 0.02587890625,
+      "learning_rate": 7.205143651483906e-05,
+      "loss": 0.0226,
+      "step": 190
+    },
+    {
+      "epoch": 1.8108288274942597,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 7.106395307101621e-05,
+      "loss": 0.0213,
+      "step": 191
+    },
+    {
+      "epoch": 1.8203096066958002,
+      "grad_norm": 0.0299072265625,
+      "learning_rate": 7.007953960635109e-05,
+      "loss": 0.0247,
+      "step": 192
+    },
+    {
+      "epoch": 1.8297903858973408,
+      "grad_norm": 0.0341796875,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0276,
+      "step": 193
+    },
+    {
+      "epoch": 1.8392711650988816,
+      "grad_norm": 0.031494140625,
+      "learning_rate": 6.812034004434903e-05,
+      "loss": 0.0233,
+      "step": 194
+    },
+    {
+      "epoch": 1.8487519443004223,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 6.714576180891654e-05,
+      "loss": 0.0213,
+      "step": 195
+    },
+    {
+      "epoch": 1.858232723501963,
+      "grad_norm": 0.0296630859375,
+      "learning_rate": 6.617466925439746e-05,
+      "loss": 0.0213,
+      "step": 196
+    },
+    {
+      "epoch": 1.8677135027035034,
+      "grad_norm": 0.02685546875,
+      "learning_rate": 6.520716540916709e-05,
+      "loss": 0.0227,
+      "step": 197
+    },
+    {
+      "epoch": 1.877194281905044,
+      "grad_norm": 0.02734375,
+      "learning_rate": 6.424335292085553e-05,
+      "loss": 0.0222,
+      "step": 198
+    },
+    {
+      "epoch": 1.877194281905044,
+      "eval_loss": 0.027654768899083138,
+      "eval_runtime": 34.2048,
+      "eval_samples_per_second": 20.787,
+      "eval_steps_per_second": 20.787,
+      "step": 198
+    },
+    {
+      "epoch": 1.8866750611065846,
+      "grad_norm": 0.0255126953125,
+      "learning_rate": 6.32833340454571e-05,
+      "loss": 0.021,
+      "step": 199
+    },
+    {
+      "epoch": 1.8961558403081253,
+      "grad_norm": 0.02978515625,
+      "learning_rate": 6.232721063648148e-05,
+      "loss": 0.0249,
+      "step": 200
+    },
+    {
+      "epoch": 1.905636619509666,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 6.137508413414784e-05,
+      "loss": 0.0238,
+      "step": 201
+    },
+    {
+      "epoch": 1.9151173987112067,
+      "grad_norm": 0.0294189453125,
+      "learning_rate": 6.0427055554621913e-05,
+      "loss": 0.0246,
+      "step": 202
+    },
+    {
+      "epoch": 1.9245981779127472,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 5.948322547929939e-05,
+      "loss": 0.0202,
+      "step": 203
+    },
+    {
+      "epoch": 1.9340789571142878,
+      "grad_norm": 0.024658203125,
+      "learning_rate": 5.854369404413398e-05,
+      "loss": 0.0165,
+      "step": 204
+    },
+    {
+      "epoch": 1.9435597363158283,
+      "grad_norm": 0.026611328125,
+      "learning_rate": 5.7608560929013946e-05,
+      "loss": 0.0226,
+      "step": 205
+    },
+    {
+      "epoch": 1.9530405155173691,
+      "grad_norm": 0.033203125,
+      "learning_rate": 5.667792534718639e-05,
+      "loss": 0.0265,
+      "step": 206
+    },
+    {
+      "epoch": 1.9625212947189097,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 5.5751886034731115e-05,
+      "loss": 0.0233,
+      "step": 207
+    },
+    {
+      "epoch": 1.9720020739204505,
+      "grad_norm": 0.02734375,
+      "learning_rate": 5.483054124008528e-05,
+      "loss": 0.0209,
+      "step": 208
+    },
+    {
+      "epoch": 1.981482853121991,
+      "grad_norm": 0.0286865234375,
+      "learning_rate": 5.391398871361972e-05,
+      "loss": 0.0231,
+      "step": 209
+    },
+    {
+      "epoch": 1.981482853121991,
+      "eval_loss": 0.027809714898467064,
+      "eval_runtime": 34.3727,
+      "eval_samples_per_second": 20.685,
+      "eval_steps_per_second": 20.685,
+      "step": 209
+    },
+    {
+      "epoch": 1.9909636323235316,
+      "grad_norm": 0.03271484375,
+      "learning_rate": 5.300232569726804e-05,
+      "loss": 0.0246,
+      "step": 210
+    },
+    {
+      "epoch": 2.000444411525072,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 5.2095648914209525e-05,
+      "loss": 0.0285,
+      "step": 211
+    },
+    {
+      "epoch": 2.0099251907266127,
+      "grad_norm": 0.026123046875,
+      "learning_rate": 5.119405455860772e-05,
+      "loss": 0.0201,
+      "step": 212
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 315,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 53,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.881706086558597e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-212/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6965abb853c761cad48cb468c99194ceaf6bcfe3b5e51b1799b677a2e2e93f5
+size 6072

checkpoint-265/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-math-7b-rl
+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 0.11.1

checkpoint-265/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-math-7b-rl",
+  "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": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-265/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab21a5d97b432f0c646cd95b77811079630f56cea4f474801f06a464940d4e1d
+size 299884176

checkpoint-265/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ee2b58fac047450527a5d7e4dc9a4d6f8334b58f4e07b6a9334ecf8f0f77865
+size 1199569146

checkpoint-265/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4704d77cd5fd843a3d3e34364480e67fc139d961f2535e2fc1db19e7e50329db
+size 14244

checkpoint-265/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:180da771da4514ced7b8aa789fc9f0fe493376eeccc8ade7d6e8771efc347274
+size 1064

checkpoint-265/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-265/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

checkpoint-265/trainer_state.json

@@ -0,0 +1,2088 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.512406488408266,
+  "eval_steps": 11,
+  "global_step": 265,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009480779201540626,
+      "grad_norm": 0.38671875,
+      "learning_rate": 2e-05,
+      "loss": 0.4197,
+      "step": 1
+    },
+    {
+      "epoch": 0.009480779201540626,
+      "eval_loss": 0.41279804706573486,
+      "eval_runtime": 34.6855,
+      "eval_samples_per_second": 20.498,
+      "eval_steps_per_second": 20.498,
+      "step": 1
+    },
+    {
+      "epoch": 0.018961558403081252,
+      "grad_norm": 0.359375,
+      "learning_rate": 4e-05,
+      "loss": 0.3966,
+      "step": 2
+    },
+    {
+      "epoch": 0.02844233760462188,
+      "grad_norm": 0.388671875,
+      "learning_rate": 6e-05,
+      "loss": 0.4257,
+      "step": 3
+    },
+    {
+      "epoch": 0.037923116806162505,
+      "grad_norm": 0.408203125,
+      "learning_rate": 8e-05,
+      "loss": 0.4026,
+      "step": 4
+    },
+    {
+      "epoch": 0.04740389600770313,
+      "grad_norm": 0.384765625,
+      "learning_rate": 0.0001,
+      "loss": 0.3229,
+      "step": 5
+    },
+    {
+      "epoch": 0.05688467520924376,
+      "grad_norm": 0.251953125,
+      "learning_rate": 0.00012,
+      "loss": 0.2408,
+      "step": 6
+    },
+    {
+      "epoch": 0.06636545441078438,
+      "grad_norm": 0.203125,
+      "learning_rate": 0.00014,
+      "loss": 0.1709,
+      "step": 7
+    },
+    {
+      "epoch": 0.07584623361232501,
+      "grad_norm": 0.150390625,
+      "learning_rate": 0.00016,
+      "loss": 0.1328,
+      "step": 8
+    },
+    {
+      "epoch": 0.08532701281386564,
+      "grad_norm": 0.1201171875,
+      "learning_rate": 0.00018,
+      "loss": 0.0993,
+      "step": 9
+    },
+    {
+      "epoch": 0.09480779201540626,
+      "grad_norm": 0.10888671875,
+      "learning_rate": 0.0002,
+      "loss": 0.0914,
+      "step": 10
+    },
+    {
+      "epoch": 0.10428857121694689,
+      "grad_norm": 0.119140625,
+      "learning_rate": 0.00019999469523400122,
+      "loss": 0.0885,
+      "step": 11
+    },
+    {
+      "epoch": 0.10428857121694689,
+      "eval_loss": 0.07809103280305862,
+      "eval_runtime": 34.2892,
+      "eval_samples_per_second": 20.735,
+      "eval_steps_per_second": 20.735,
+      "step": 11
+    },
+    {
+      "epoch": 0.11376935041848751,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00019997878149881574,
+      "loss": 0.0761,
+      "step": 12
+    },
+    {
+      "epoch": 0.12325012962002814,
+      "grad_norm": 0.0703125,
+      "learning_rate": 0.0001999522604828164,
+      "loss": 0.0683,
+      "step": 13
+    },
+    {
+      "epoch": 0.13273090882156877,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 0.00019991513499975882,
+      "loss": 0.0696,
+      "step": 14
+    },
+    {
+      "epoch": 0.1422116880231094,
+      "grad_norm": 0.044921875,
+      "learning_rate": 0.00019986740898848306,
+      "loss": 0.0615,
+      "step": 15
+    },
+    {
+      "epoch": 0.15169246722465002,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019980908751249555,
+      "loss": 0.0625,
+      "step": 16
+    },
+    {
+      "epoch": 0.16117324642619066,
+      "grad_norm": 0.04736328125,
+      "learning_rate": 0.00019974017675943192,
+      "loss": 0.0598,
+      "step": 17
+    },
+    {
+      "epoch": 0.17065402562773127,
+      "grad_norm": 0.039306640625,
+      "learning_rate": 0.0001996606840404006,
+      "loss": 0.0573,
+      "step": 18
+    },
+    {
+      "epoch": 0.1801348048292719,
+      "grad_norm": 0.036376953125,
+      "learning_rate": 0.00019957061778920701,
+      "loss": 0.0482,
+      "step": 19
+    },
+    {
+      "epoch": 0.18961558403081252,
+      "grad_norm": 0.039306640625,
+      "learning_rate": 0.0001994699875614589,
+      "loss": 0.0555,
+      "step": 20
+    },
+    {
+      "epoch": 0.19909636323235316,
+      "grad_norm": 0.0380859375,
+      "learning_rate": 0.00019935880403355253,
+      "loss": 0.0495,
+      "step": 21
+    },
+    {
+      "epoch": 0.20857714243389378,
+      "grad_norm": 0.038818359375,
+      "learning_rate": 0.00019923707900153982,
+      "loss": 0.0482,
+      "step": 22
+    },
+    {
+      "epoch": 0.20857714243389378,
+      "eval_loss": 0.05171125754714012,
+      "eval_runtime": 34.4113,
+      "eval_samples_per_second": 20.662,
+      "eval_steps_per_second": 20.662,
+      "step": 22
+    },
+    {
+      "epoch": 0.21805792163543442,
+      "grad_norm": 0.038818359375,
+      "learning_rate": 0.00019910482537987702,
+      "loss": 0.0529,
+      "step": 23
+    },
+    {
+      "epoch": 0.22753870083697503,
+      "grad_norm": 0.031494140625,
+      "learning_rate": 0.0001989620572000544,
+      "loss": 0.0495,
+      "step": 24
+    },
+    {
+      "epoch": 0.23701948003851567,
+      "grad_norm": 0.0380859375,
+      "learning_rate": 0.00019880878960910772,
+      "loss": 0.059,
+      "step": 25
+    },
+    {
+      "epoch": 0.24650025924005628,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.00019864503886801106,
+      "loss": 0.0545,
+      "step": 26
+    },
+    {
+      "epoch": 0.2559810384415969,
+      "grad_norm": 0.029296875,
+      "learning_rate": 0.00019847082234995171,
+      "loss": 0.0417,
+      "step": 27
+    },
+    {
+      "epoch": 0.26546181764313753,
+      "grad_norm": 0.037109375,
+      "learning_rate": 0.00019828615853848688,
+      "loss": 0.0459,
+      "step": 28
+    },
+    {
+      "epoch": 0.27494259684467814,
+      "grad_norm": 0.027099609375,
+      "learning_rate": 0.00019809106702558277,
+      "loss": 0.0412,
+      "step": 29
+    },
+    {
+      "epoch": 0.2844233760462188,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.0001978855685095358,
+      "loss": 0.0403,
+      "step": 30
+    },
+    {
+      "epoch": 0.2939041552477594,
+      "grad_norm": 0.0289306640625,
+      "learning_rate": 0.00019766968479277683,
+      "loss": 0.0463,
+      "step": 31
+    },
+    {
+      "epoch": 0.30338493444930004,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 0.00019744343877955788,
+      "loss": 0.041,
+      "step": 32
+    },
+    {
+      "epoch": 0.3128657136508407,
+      "grad_norm": 0.033447265625,
+      "learning_rate": 0.00019720685447352209,
+      "loss": 0.045,
+      "step": 33
+    },
+    {
+      "epoch": 0.3128657136508407,
+      "eval_loss": 0.04294149950146675,
+      "eval_runtime": 34.2719,
+      "eval_samples_per_second": 20.746,
+      "eval_steps_per_second": 20.746,
+      "step": 33
+    },
+    {
+      "epoch": 0.3223464928523813,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 0.0001969599569751571,
+      "loss": 0.0369,
+      "step": 34
+    },
+    {
+      "epoch": 0.33182727205392193,
+      "grad_norm": 0.029296875,
+      "learning_rate": 0.00019670277247913205,
+      "loss": 0.0465,
+      "step": 35
+    },
+    {
+      "epoch": 0.34130805125546254,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 0.0001964353282715183,
+      "loss": 0.0382,
+      "step": 36
+    },
+    {
+      "epoch": 0.3507888304570032,
+      "grad_norm": 0.0299072265625,
+      "learning_rate": 0.00019615765272689461,
+      "loss": 0.0442,
+      "step": 37
+    },
+    {
+      "epoch": 0.3602696096585438,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00019586977530533677,
+      "loss": 0.0481,
+      "step": 38
+    },
+    {
+      "epoch": 0.36975038886008443,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 0.00019557172654929196,
+      "loss": 0.0423,
+      "step": 39
+    },
+    {
+      "epoch": 0.37923116806162505,
+      "grad_norm": 0.0299072265625,
+      "learning_rate": 0.00019526353808033825,
+      "loss": 0.0384,
+      "step": 40
+    },
+    {
+      "epoch": 0.3887119472631657,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 0.00019494524259582992,
+      "loss": 0.0404,
+      "step": 41
+    },
+    {
+      "epoch": 0.3981927264647063,
+      "grad_norm": 0.0286865234375,
+      "learning_rate": 0.00019461687386542826,
+      "loss": 0.0394,
+      "step": 42
+    },
+    {
+      "epoch": 0.40767350566624694,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 0.00019427846672751873,
+      "loss": 0.0351,
+      "step": 43
+    },
+    {
+      "epoch": 0.41715428486778755,
+      "grad_norm": 0.02783203125,
+      "learning_rate": 0.00019393005708551498,
+      "loss": 0.0425,
+      "step": 44
+    },
+    {
+      "epoch": 0.41715428486778755,
+      "eval_loss": 0.03996235132217407,
+      "eval_runtime": 34.3007,
+      "eval_samples_per_second": 20.728,
+      "eval_steps_per_second": 20.728,
+      "step": 44
+    },
+    {
+      "epoch": 0.4266350640693282,
+      "grad_norm": 0.030517578125,
+      "learning_rate": 0.00019357168190404936,
+      "loss": 0.0365,
+      "step": 45
+    },
+    {
+      "epoch": 0.43611584327086883,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 0.00019320337920505153,
+      "loss": 0.0438,
+      "step": 46
+    },
+    {
+      "epoch": 0.44559662247240944,
+      "grad_norm": 0.0306396484375,
+      "learning_rate": 0.00019282518806371414,
+      "loss": 0.044,
+      "step": 47
+    },
+    {
+      "epoch": 0.45507740167395005,
+      "grad_norm": 0.037841796875,
+      "learning_rate": 0.0001924371486043473,
+      "loss": 0.0496,
+      "step": 48
+    },
+    {
+      "epoch": 0.4645581808754907,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 0.0001920393019961217,
+      "loss": 0.0369,
+      "step": 49
+    },
+    {
+      "epoch": 0.47403896007703133,
+      "grad_norm": 0.0341796875,
+      "learning_rate": 0.0001916316904487005,
+      "loss": 0.0399,
+      "step": 50
+    },
+    {
+      "epoch": 0.48351973927857195,
+      "grad_norm": 0.0255126953125,
+      "learning_rate": 0.00019121435720776122,
+      "loss": 0.0363,
+      "step": 51
+    },
+    {
+      "epoch": 0.49300051848011256,
+      "grad_norm": 0.0311279296875,
+      "learning_rate": 0.0001907873465504076,
+      "loss": 0.0384,
+      "step": 52
+    },
+    {
+      "epoch": 0.5024812976816532,
+      "grad_norm": 0.03271484375,
+      "learning_rate": 0.00019035070378047204,
+      "loss": 0.0371,
+      "step": 53
+    },
+    {
+      "epoch": 0.5119620768831938,
+      "grad_norm": 0.0263671875,
+      "learning_rate": 0.00018990447522370884,
+      "loss": 0.0351,
+      "step": 54
+    },
+    {
+      "epoch": 0.5214428560847345,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00018944870822287956,
+      "loss": 0.0411,
+      "step": 55
+    },
+    {
+      "epoch": 0.5214428560847345,
+      "eval_loss": 0.03788134828209877,
+      "eval_runtime": 34.6048,
+      "eval_samples_per_second": 20.546,
+      "eval_steps_per_second": 20.546,
+      "step": 55
+    },
+    {
+      "epoch": 0.5309236352862751,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00018898345113272998,
+      "loss": 0.0337,
+      "step": 56
+    },
+    {
+      "epoch": 0.5404044144878157,
+      "grad_norm": 0.0245361328125,
+      "learning_rate": 0.00018850875331485995,
+      "loss": 0.0309,
+      "step": 57
+    },
+    {
+      "epoch": 0.5498851936893563,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 0.00018802466513248632,
+      "loss": 0.0329,
+      "step": 58
+    },
+    {
+      "epoch": 0.559365972890897,
+      "grad_norm": 0.0267333984375,
+      "learning_rate": 0.00018753123794509974,
+      "loss": 0.0365,
+      "step": 59
+    },
+    {
+      "epoch": 0.5688467520924376,
+      "grad_norm": 0.02734375,
+      "learning_rate": 0.00018702852410301554,
+      "loss": 0.0373,
+      "step": 60
+    },
+    {
+      "epoch": 0.5783275312939782,
+      "grad_norm": 0.025390625,
+      "learning_rate": 0.0001865165769418196,
+      "loss": 0.0375,
+      "step": 61
+    },
+    {
+      "epoch": 0.5878083104955188,
+      "grad_norm": 0.02978515625,
+      "learning_rate": 0.00018599545077670985,
+      "loss": 0.0376,
+      "step": 62
+    },
+    {
+      "epoch": 0.5972890896970595,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.0001854652008967335,
+      "loss": 0.0337,
+      "step": 63
+    },
+    {
+      "epoch": 0.6067698688986001,
+      "grad_norm": 0.02880859375,
+      "learning_rate": 0.00018492588355892124,
+      "loss": 0.0379,
+      "step": 64
+    },
+    {
+      "epoch": 0.6162506481001407,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018437755598231856,
+      "loss": 0.0392,
+      "step": 65
+    },
+    {
+      "epoch": 0.6257314273016814,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00018382027634191524,
+      "loss": 0.0348,
+      "step": 66
+    },
+    {
+      "epoch": 0.6257314273016814,
+      "eval_loss": 0.03594927862286568,
+      "eval_runtime": 34.2756,
+      "eval_samples_per_second": 20.744,
+      "eval_steps_per_second": 20.744,
+      "step": 66
+    },
+    {
+      "epoch": 0.635212206503222,
+      "grad_norm": 0.03515625,
+      "learning_rate": 0.00018325410376247294,
+      "loss": 0.0379,
+      "step": 67
+    },
+    {
+      "epoch": 0.6446929857047626,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 0.0001826790983122527,
+      "loss": 0.0317,
+      "step": 68
+    },
+    {
+      "epoch": 0.6541737649063032,
+      "grad_norm": 0.0296630859375,
+      "learning_rate": 0.00018209532099664174,
+      "loss": 0.0366,
+      "step": 69
+    },
+    {
+      "epoch": 0.6636545441078439,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00018150283375168114,
+      "loss": 0.0345,
+      "step": 70
+    },
+    {
+      "epoch": 0.6731353233093845,
+      "grad_norm": 0.03125,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0368,
+      "step": 71
+    },
+    {
+      "epoch": 0.6826161025109251,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.00018029198183161998,
+      "loss": 0.0455,
+      "step": 72
+    },
+    {
+      "epoch": 0.6920968817124658,
+      "grad_norm": 0.029296875,
+      "learning_rate": 0.00017967374562224132,
+      "loss": 0.0362,
+      "step": 73
+    },
+    {
+      "epoch": 0.7015776609140064,
+      "grad_norm": 0.0311279296875,
+      "learning_rate": 0.00017904705640132718,
+      "loss": 0.0388,
+      "step": 74
+    },
+    {
+      "epoch": 0.711058440115547,
+      "grad_norm": 0.02685546875,
+      "learning_rate": 0.00017841198065767107,
+      "loss": 0.0288,
+      "step": 75
+    },
+    {
+      "epoch": 0.7205392193170876,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00017776858576983712,
+      "loss": 0.0349,
+      "step": 76
+    },
+    {
+      "epoch": 0.7300199985186282,
+      "grad_norm": 0.026611328125,
+      "learning_rate": 0.0001771169399990119,
+      "loss": 0.0288,
+      "step": 77
+    },
+    {
+      "epoch": 0.7300199985186282,
+      "eval_loss": 0.03419337794184685,
+      "eval_runtime": 34.3669,
+      "eval_samples_per_second": 20.688,
+      "eval_steps_per_second": 20.688,
+      "step": 77
+    },
+    {
+      "epoch": 0.7395007777201689,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.00017645711248176195,
+      "loss": 0.0285,
+      "step": 78
+    },
+    {
+      "epoch": 0.7489815569217095,
+      "grad_norm": 0.025390625,
+      "learning_rate": 0.00017578917322269886,
+      "loss": 0.0338,
+      "step": 79
+    },
+    {
+      "epoch": 0.7584623361232501,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00017511319308705198,
+      "loss": 0.0316,
+      "step": 80
+    },
+    {
+      "epoch": 0.7679431153247908,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.0001744292437931502,
+      "loss": 0.0306,
+      "step": 81
+    },
+    {
+      "epoch": 0.7774238945263314,
+      "grad_norm": 0.027099609375,
+      "learning_rate": 0.00017373739790481262,
+      "loss": 0.0335,
+      "step": 82
+    },
+    {
+      "epoch": 0.786904673727872,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017303772882365016,
+      "loss": 0.0271,
+      "step": 83
+    },
+    {
+      "epoch": 0.7963854529294127,
+      "grad_norm": 0.028564453125,
+      "learning_rate": 0.00017233031078127788,
+      "loss": 0.0334,
+      "step": 84
+    },
+    {
+      "epoch": 0.8058662321309532,
+      "grad_norm": 0.0299072265625,
+      "learning_rate": 0.00017161521883143934,
+      "loss": 0.0403,
+      "step": 85
+    },
+    {
+      "epoch": 0.8153470113324939,
+      "grad_norm": 0.0294189453125,
+      "learning_rate": 0.00017089252884204377,
+      "loss": 0.0368,
+      "step": 86
+    },
+    {
+      "epoch": 0.8248277905340345,
+      "grad_norm": 0.03369140625,
+      "learning_rate": 0.0001701623174871168,
+      "loss": 0.0335,
+      "step": 87
+    },
+    {
+      "epoch": 0.8343085697355751,
+      "grad_norm": 0.0277099609375,
+      "learning_rate": 0.0001694246622386658,
+      "loss": 0.0339,
+      "step": 88
+    },
+    {
+      "epoch": 0.8343085697355751,
+      "eval_loss": 0.033091045916080475,
+      "eval_runtime": 34.4475,
+      "eval_samples_per_second": 20.64,
+      "eval_steps_per_second": 20.64,
+      "step": 88
+    },
+    {
+      "epoch": 0.8437893489371158,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 0.00016867964135846043,
+      "loss": 0.0241,
+      "step": 89
+    },
+    {
+      "epoch": 0.8532701281386564,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00016792733388972932,
+      "loss": 0.0387,
+      "step": 90
+    },
+    {
+      "epoch": 0.862750907340197,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 0.0001671678196487741,
+      "loss": 0.0346,
+      "step": 91
+    },
+    {
+      "epoch": 0.8722316865417377,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 0.00016640117921650117,
+      "loss": 0.0378,
+      "step": 92
+    },
+    {
+      "epoch": 0.8817124657432783,
+      "grad_norm": 0.0279541015625,
+      "learning_rate": 0.00016562749392987254,
+      "loss": 0.0294,
+      "step": 93
+    },
+    {
+      "epoch": 0.8911932449448189,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001648468458732762,
+      "loss": 0.0308,
+      "step": 94
+    },
+    {
+      "epoch": 0.9006740241463596,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00016405931786981755,
+      "loss": 0.0326,
+      "step": 95
+    },
+    {
+      "epoch": 0.9101548033479001,
+      "grad_norm": 0.0262451171875,
+      "learning_rate": 0.00016326499347253207,
+      "loss": 0.032,
+      "step": 96
+    },
+    {
+      "epoch": 0.9196355825494408,
+      "grad_norm": 0.0264892578125,
+      "learning_rate": 0.00016246395695552085,
+      "loss": 0.0321,
+      "step": 97
+    },
+    {
+      "epoch": 0.9291163617509814,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00016165629330500952,
+      "loss": 0.0301,
+      "step": 98
+    },
+    {
+      "epoch": 0.938597140952522,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.0001608420882103315,
+      "loss": 0.0297,
+      "step": 99
+    },
+    {
+      "epoch": 0.938597140952522,
+      "eval_loss": 0.03182319179177284,
+      "eval_runtime": 34.2304,
+      "eval_samples_per_second": 20.771,
+      "eval_steps_per_second": 20.771,
+      "step": 99
+    },
+    {
+      "epoch": 0.9480779201540627,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00016002142805483685,
+      "loss": 0.0327,
+      "step": 100
+    },
+    {
+      "epoch": 0.9575586993556033,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 0.0001591943999067273,
+      "loss": 0.0285,
+      "step": 101
+    },
+    {
+      "epoch": 0.9670394785571439,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 0.00015836109150981886,
+      "loss": 0.0308,
+      "step": 102
+    },
+    {
+      "epoch": 0.9765202577586846,
+      "grad_norm": 0.0283203125,
+      "learning_rate": 0.00015752159127423263,
+      "loss": 0.0301,
+      "step": 103
+    },
+    {
+      "epoch": 0.9860010369602251,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 0.0001566759882670146,
+      "loss": 0.0287,
+      "step": 104
+    },
+    {
+      "epoch": 0.9954818161617658,
+      "grad_norm": 0.025634765625,
+      "learning_rate": 0.00015582437220268647,
+      "loss": 0.031,
+      "step": 105
+    },
+    {
+      "epoch": 1.0049625953633063,
+      "grad_norm": 0.02490234375,
+      "learning_rate": 0.0001549668334337271,
+      "loss": 0.0275,
+      "step": 106
+    },
+    {
+      "epoch": 1.0144433745648471,
+      "grad_norm": 0.03369140625,
+      "learning_rate": 0.0001541034629409865,
+      "loss": 0.0302,
+      "step": 107
+    },
+    {
+      "epoch": 1.0239241537663877,
+      "grad_norm": 0.027099609375,
+      "learning_rate": 0.00015323435232403337,
+      "loss": 0.0308,
+      "step": 108
+    },
+    {
+      "epoch": 1.0334049329679282,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.00015235959379143678,
+      "loss": 0.0247,
+      "step": 109
+    },
+    {
+      "epoch": 1.042885712169469,
+      "grad_norm": 0.0255126953125,
+      "learning_rate": 0.0001514792801509831,
+      "loss": 0.0281,
+      "step": 110
+    },
+    {
+      "epoch": 1.042885712169469,
+      "eval_loss": 0.03116695210337639,
+      "eval_runtime": 34.429,
+      "eval_samples_per_second": 20.651,
+      "eval_steps_per_second": 20.651,
+      "step": 110
+    },
+    {
+      "epoch": 1.0523664913710096,
+      "grad_norm": 0.0277099609375,
+      "learning_rate": 0.00015059350479982965,
+      "loss": 0.0243,
+      "step": 111
+    },
+    {
+      "epoch": 1.0618472705725501,
+      "grad_norm": 0.028564453125,
+      "learning_rate": 0.0001497023617145958,
+      "loss": 0.0274,
+      "step": 112
+    },
+    {
+      "epoch": 1.071328049774091,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 0.0001488059454413923,
+      "loss": 0.0265,
+      "step": 113
+    },
+    {
+      "epoch": 1.0808088289756315,
+      "grad_norm": 0.0296630859375,
+      "learning_rate": 0.00014790435108579048,
+      "loss": 0.0287,
+      "step": 114
+    },
+    {
+      "epoch": 1.090289608177172,
+      "grad_norm": 0.025390625,
+      "learning_rate": 0.000146997674302732,
+      "loss": 0.0255,
+      "step": 115
+    },
+    {
+      "epoch": 1.0997703873787126,
+      "grad_norm": 0.02685546875,
+      "learning_rate": 0.00014608601128638027,
+      "loss": 0.0258,
+      "step": 116
+    },
+    {
+      "epoch": 1.1092511665802534,
+      "grad_norm": 0.0277099609375,
+      "learning_rate": 0.00014516945875991472,
+      "loss": 0.0326,
+      "step": 117
+    },
+    {
+      "epoch": 1.118731945781794,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 0.00014424811396526892,
+      "loss": 0.0241,
+      "step": 118
+    },
+    {
+      "epoch": 1.1282127249833347,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 0.00014332207465281364,
+      "loss": 0.0276,
+      "step": 119
+    },
+    {
+      "epoch": 1.1376935041848752,
+      "grad_norm": 0.0306396484375,
+      "learning_rate": 0.0001423914390709861,
+      "loss": 0.0283,
+      "step": 120
+    },
+    {
+      "epoch": 1.1471742833864158,
+      "grad_norm": 0.0274658203125,
+      "learning_rate": 0.00014145630595586607,
+      "loss": 0.027,
+      "step": 121
+    },
+    {
+      "epoch": 1.1471742833864158,
+      "eval_loss": 0.030295666307210922,
+      "eval_runtime": 34.4847,
+      "eval_samples_per_second": 20.618,
+      "eval_steps_per_second": 20.618,
+      "step": 121
+    },
+    {
+      "epoch": 1.1566550625879564,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00014051677452070065,
+      "loss": 0.0248,
+      "step": 122
+    },
+    {
+      "epoch": 1.1661358417894971,
+      "grad_norm": 0.023193359375,
+      "learning_rate": 0.00013957294444537808,
+      "loss": 0.0226,
+      "step": 123
+    },
+    {
+      "epoch": 1.1756166209910377,
+      "grad_norm": 0.02880859375,
+      "learning_rate": 0.0001386249158658522,
+      "loss": 0.0332,
+      "step": 124
+    },
+    {
+      "epoch": 1.1850974001925783,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 0.00013767278936351854,
+      "loss": 0.0292,
+      "step": 125
+    },
+    {
+      "epoch": 1.194578179394119,
+      "grad_norm": 0.0264892578125,
+      "learning_rate": 0.00013671666595454295,
+      "loss": 0.0224,
+      "step": 126
+    },
+    {
+      "epoch": 1.2040589585956596,
+      "grad_norm": 0.027099609375,
+      "learning_rate": 0.00013575664707914448,
+      "loss": 0.0234,
+      "step": 127
+    },
+    {
+      "epoch": 1.2135397377972001,
+      "grad_norm": 0.03125,
+      "learning_rate": 0.0001347928345908329,
+      "loss": 0.029,
+      "step": 128
+    },
+    {
+      "epoch": 1.223020516998741,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00013382533074560255,
+      "loss": 0.0249,
+      "step": 129
+    },
+    {
+      "epoch": 1.2325012962002815,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.0001328542381910835,
+      "loss": 0.026,
+      "step": 130
+    },
+    {
+      "epoch": 1.241982075401822,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.00013187965995565098,
+      "loss": 0.0252,
+      "step": 131
+    },
+    {
+      "epoch": 1.2514628546033628,
+      "grad_norm": 0.0279541015625,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.023,
+      "step": 132
+    },
+    {
+      "epoch": 1.2514628546033628,
+      "eval_loss": 0.029845552518963814,
+      "eval_runtime": 34.1739,
+      "eval_samples_per_second": 20.805,
+      "eval_steps_per_second": 20.805,
+      "step": 132
+    },
+    {
+      "epoch": 1.2609436338049034,
+      "grad_norm": 0.02734375,
+      "learning_rate": 0.00012992046039364893,
+      "loss": 0.0259,
+      "step": 133
+    },
+    {
+      "epoch": 1.270424413006444,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 0.0001289360469289838,
+      "loss": 0.0244,
+      "step": 134
+    },
+    {
+      "epoch": 1.2799051922079845,
+      "grad_norm": 0.0286865234375,
+      "learning_rate": 0.00012794856348516095,
+      "loss": 0.0237,
+      "step": 135
+    },
+    {
+      "epoch": 1.2893859714095253,
+      "grad_norm": 0.0289306640625,
+      "learning_rate": 0.00012695811482955227,
+      "loss": 0.0248,
+      "step": 136
+    },
+    {
+      "epoch": 1.2988667506110658,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 0.00012596480604412484,
+      "loss": 0.0283,
+      "step": 137
+    },
+    {
+      "epoch": 1.3083475298126066,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 0.000124968742514292,
+      "loss": 0.021,
+      "step": 138
+    },
+    {
+      "epoch": 1.3178283090141472,
+      "grad_norm": 0.0279541015625,
+      "learning_rate": 0.00012397002991773275,
+      "loss": 0.0249,
+      "step": 139
+    },
+    {
+      "epoch": 1.3273090882156877,
+      "grad_norm": 0.026611328125,
+      "learning_rate": 0.0001229687742131796,
+      "loss": 0.0231,
+      "step": 140
+    },
+    {
+      "epoch": 1.3367898674172283,
+      "grad_norm": 0.0274658203125,
+      "learning_rate": 0.00012196508162917677,
+      "loss": 0.0276,
+      "step": 141
+    },
+    {
+      "epoch": 1.346270646618769,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 0.00012095905865281025,
+      "loss": 0.0268,
+      "step": 142
+    },
+    {
+      "epoch": 1.3557514258203096,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 0.00011995081201840956,
+      "loss": 0.0259,
+      "step": 143
+    },
+    {
+      "epoch": 1.3557514258203096,
+      "eval_loss": 0.029736338183283806,
+      "eval_runtime": 34.4542,
+      "eval_samples_per_second": 20.636,
+      "eval_steps_per_second": 20.636,
+      "step": 143
+    },
+    {
+      "epoch": 1.3652322050218502,
+      "grad_norm": 0.02734375,
+      "learning_rate": 0.00011894044869622403,
+      "loss": 0.025,
+      "step": 144
+    },
+    {
+      "epoch": 1.374712984223391,
+      "grad_norm": 0.0263671875,
+      "learning_rate": 0.00011792807588107357,
+      "loss": 0.0221,
+      "step": 145
+    },
+    {
+      "epoch": 1.3841937634249315,
+      "grad_norm": 0.031982421875,
+      "learning_rate": 0.00011691380098097597,
+      "loss": 0.0281,
+      "step": 146
+    },
+    {
+      "epoch": 1.393674542626472,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.0001158977316057513,
+      "loss": 0.021,
+      "step": 147
+    },
+    {
+      "epoch": 1.4031553218280126,
+      "grad_norm": 0.032958984375,
+      "learning_rate": 0.00011487997555560503,
+      "loss": 0.0256,
+      "step": 148
+    },
+    {
+      "epoch": 1.4126361010295534,
+      "grad_norm": 0.0306396484375,
+      "learning_rate": 0.00011386064080969094,
+      "loss": 0.0267,
+      "step": 149
+    },
+    {
+      "epoch": 1.422116880231094,
+      "grad_norm": 0.0267333984375,
+      "learning_rate": 0.00011283983551465511,
+      "loss": 0.0211,
+      "step": 150
+    },
+    {
+      "epoch": 1.4315976594326347,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.0001118176679731619,
+      "loss": 0.025,
+      "step": 151
+    },
+    {
+      "epoch": 1.4410784386341753,
+      "grad_norm": 0.0296630859375,
+      "learning_rate": 0.00011079424663240372,
+      "loss": 0.0273,
+      "step": 152
+    },
+    {
+      "epoch": 1.4505592178357158,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 0.00010976968007259519,
+      "loss": 0.0243,
+      "step": 153
+    },
+    {
+      "epoch": 1.4600399970372564,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00010874407699545328,
+      "loss": 0.0232,
+      "step": 154
+    },
+    {
+      "epoch": 1.4600399970372564,
+      "eval_loss": 0.029951849952340126,
+      "eval_runtime": 34.3508,
+      "eval_samples_per_second": 20.698,
+      "eval_steps_per_second": 20.698,
+      "step": 154
+    },
+    {
+      "epoch": 1.4695207762387972,
+      "grad_norm": 0.03271484375,
+      "learning_rate": 0.00010771754621266466,
+      "loss": 0.0283,
+      "step": 155
+    },
+    {
+      "epoch": 1.4790015554403377,
+      "grad_norm": 0.024169921875,
+      "learning_rate": 0.00010669019663434117,
+      "loss": 0.0218,
+      "step": 156
+    },
+    {
+      "epoch": 1.4884823346418785,
+      "grad_norm": 0.029296875,
+      "learning_rate": 0.00010566213725746506,
+      "loss": 0.0273,
+      "step": 157
+    },
+    {
+      "epoch": 1.497963113843419,
+      "grad_norm": 0.0263671875,
+      "learning_rate": 0.00010463347715432488,
+      "loss": 0.0229,
+      "step": 158
+    },
+    {
+      "epoch": 1.5074438930449596,
+      "grad_norm": 0.02978515625,
+      "learning_rate": 0.00010360432546094341,
+      "loss": 0.0242,
+      "step": 159
+    },
+    {
+      "epoch": 1.5169246722465002,
+      "grad_norm": 0.031494140625,
+      "learning_rate": 0.00010257479136549889,
+      "loss": 0.0252,
+      "step": 160
+    },
+    {
+      "epoch": 1.5264054514480407,
+      "grad_norm": 0.0283203125,
+      "learning_rate": 0.00010154498409674051,
+      "loss": 0.0275,
+      "step": 161
+    },
+    {
+      "epoch": 1.5358862306495815,
+      "grad_norm": 0.035400390625,
+      "learning_rate": 0.00010051501291240008,
+      "loss": 0.0299,
+      "step": 162
+    },
+    {
+      "epoch": 1.5453670098511223,
+      "grad_norm": 0.031982421875,
+      "learning_rate": 9.948498708759993e-05,
+      "loss": 0.0264,
+      "step": 163
+    },
+    {
+      "epoch": 1.5548477890526629,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 9.845501590325948e-05,
+      "loss": 0.025,
+      "step": 164
+    },
+    {
+      "epoch": 1.5643285682542034,
+      "grad_norm": 0.029296875,
+      "learning_rate": 9.742520863450115e-05,
+      "loss": 0.0203,
+      "step": 165
+    },
+    {
+      "epoch": 1.5643285682542034,
+      "eval_loss": 0.02908056415617466,
+      "eval_runtime": 34.2083,
+      "eval_samples_per_second": 20.784,
+      "eval_steps_per_second": 20.784,
+      "step": 165
+    },
+    {
+      "epoch": 1.573809347455744,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 9.639567453905661e-05,
+      "loss": 0.0262,
+      "step": 166
+    },
+    {
+      "epoch": 1.5832901266572845,
+      "grad_norm": 0.0245361328125,
+      "learning_rate": 9.536652284567513e-05,
+      "loss": 0.0213,
+      "step": 167
+    },
+    {
+      "epoch": 1.5927709058588253,
+      "grad_norm": 0.031005859375,
+      "learning_rate": 9.433786274253495e-05,
+      "loss": 0.0272,
+      "step": 168
+    },
+    {
+      "epoch": 1.6022516850603659,
+      "grad_norm": 0.0262451171875,
+      "learning_rate": 9.330980336565887e-05,
+      "loss": 0.0217,
+      "step": 169
+    },
+    {
+      "epoch": 1.6117324642619066,
+      "grad_norm": 0.0296630859375,
+      "learning_rate": 9.228245378733537e-05,
+      "loss": 0.0258,
+      "step": 170
+    },
+    {
+      "epoch": 1.6212132434634472,
+      "grad_norm": 0.03466796875,
+      "learning_rate": 9.125592300454676e-05,
+      "loss": 0.0278,
+      "step": 171
+    },
+    {
+      "epoch": 1.6306940226649878,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 9.023031992740488e-05,
+      "loss": 0.0234,
+      "step": 172
+    },
+    {
+      "epoch": 1.6401748018665283,
+      "grad_norm": 0.0301513671875,
+      "learning_rate": 8.920575336759629e-05,
+      "loss": 0.025,
+      "step": 173
+    },
+    {
+      "epoch": 1.6496555810680689,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 8.818233202683814e-05,
+      "loss": 0.0268,
+      "step": 174
+    },
+    {
+      "epoch": 1.6591363602696096,
+      "grad_norm": 0.0260009765625,
+      "learning_rate": 8.71601644853449e-05,
+      "loss": 0.0241,
+      "step": 175
+    },
+    {
+      "epoch": 1.6686171394711504,
+      "grad_norm": 0.028564453125,
+      "learning_rate": 8.613935919030907e-05,
+      "loss": 0.0241,
+      "step": 176
+    },
+    {
+      "epoch": 1.6686171394711504,
+      "eval_loss": 0.02843022532761097,
+      "eval_runtime": 34.2598,
+      "eval_samples_per_second": 20.753,
+      "eval_steps_per_second": 20.753,
+      "step": 176
+    },
+    {
+      "epoch": 1.678097918672691,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 8.512002444439502e-05,
+      "loss": 0.0228,
+      "step": 177
+    },
+    {
+      "epoch": 1.6875786978742315,
+      "grad_norm": 0.02880859375,
+      "learning_rate": 8.410226839424871e-05,
+      "loss": 0.0272,
+      "step": 178
+    },
+    {
+      "epoch": 1.697059477075772,
+      "grad_norm": 0.0238037109375,
+      "learning_rate": 8.308619901902406e-05,
+      "loss": 0.0196,
+      "step": 179
+    },
+    {
+      "epoch": 1.7065402562773127,
+      "grad_norm": 0.02783203125,
+      "learning_rate": 8.207192411892646e-05,
+      "loss": 0.0218,
+      "step": 180
+    },
+    {
+      "epoch": 1.7160210354788534,
+      "grad_norm": 0.0277099609375,
+      "learning_rate": 8.1059551303776e-05,
+      "loss": 0.022,
+      "step": 181
+    },
+    {
+      "epoch": 1.7255018146803942,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 8.004918798159045e-05,
+      "loss": 0.0219,
+      "step": 182
+    },
+    {
+      "epoch": 1.7349825938819348,
+      "grad_norm": 0.02734375,
+      "learning_rate": 7.904094134718976e-05,
+      "loss": 0.0244,
+      "step": 183
+    },
+    {
+      "epoch": 1.7444633730834753,
+      "grad_norm": 0.036376953125,
+      "learning_rate": 7.803491837082324e-05,
+      "loss": 0.0301,
+      "step": 184
+    },
+    {
+      "epoch": 1.7539441522850159,
+      "grad_norm": 0.03125,
+      "learning_rate": 7.703122578682046e-05,
+      "loss": 0.0259,
+      "step": 185
+    },
+    {
+      "epoch": 1.7634249314865564,
+      "grad_norm": 0.025634765625,
+      "learning_rate": 7.602997008226726e-05,
+      "loss": 0.0216,
+      "step": 186
+    },
+    {
+      "epoch": 1.7729057106880972,
+      "grad_norm": 0.02783203125,
+      "learning_rate": 7.5031257485708e-05,
+      "loss": 0.0245,
+      "step": 187
+    },
+    {
+      "epoch": 1.7729057106880972,
+      "eval_loss": 0.028160251677036285,
+      "eval_runtime": 34.3215,
+      "eval_samples_per_second": 20.716,
+      "eval_steps_per_second": 20.716,
+      "step": 187
+    },
+    {
+      "epoch": 1.7823864898896378,
+      "grad_norm": 0.024658203125,
+      "learning_rate": 7.403519395587521e-05,
+      "loss": 0.0221,
+      "step": 188
+    },
+    {
+      "epoch": 1.7918672690911785,
+      "grad_norm": 0.0263671875,
+      "learning_rate": 7.304188517044774e-05,
+      "loss": 0.0228,
+      "step": 189
+    },
+    {
+      "epoch": 1.801348048292719,
+      "grad_norm": 0.02587890625,
+      "learning_rate": 7.205143651483906e-05,
+      "loss": 0.0226,
+      "step": 190
+    },
+    {
+      "epoch": 1.8108288274942597,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 7.106395307101621e-05,
+      "loss": 0.0213,
+      "step": 191
+    },
+    {
+      "epoch": 1.8203096066958002,
+      "grad_norm": 0.0299072265625,
+      "learning_rate": 7.007953960635109e-05,
+      "loss": 0.0247,
+      "step": 192
+    },
+    {
+      "epoch": 1.8297903858973408,
+      "grad_norm": 0.0341796875,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0276,
+      "step": 193
+    },
+    {
+      "epoch": 1.8392711650988816,
+      "grad_norm": 0.031494140625,
+      "learning_rate": 6.812034004434903e-05,
+      "loss": 0.0233,
+      "step": 194
+    },
+    {
+      "epoch": 1.8487519443004223,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 6.714576180891654e-05,
+      "loss": 0.0213,
+      "step": 195
+    },
+    {
+      "epoch": 1.858232723501963,
+      "grad_norm": 0.0296630859375,
+      "learning_rate": 6.617466925439746e-05,
+      "loss": 0.0213,
+      "step": 196
+    },
+    {
+      "epoch": 1.8677135027035034,
+      "grad_norm": 0.02685546875,
+      "learning_rate": 6.520716540916709e-05,
+      "loss": 0.0227,
+      "step": 197
+    },
+    {
+      "epoch": 1.877194281905044,
+      "grad_norm": 0.02734375,
+      "learning_rate": 6.424335292085553e-05,
+      "loss": 0.0222,
+      "step": 198
+    },
+    {
+      "epoch": 1.877194281905044,
+      "eval_loss": 0.027654768899083138,
+      "eval_runtime": 34.2048,
+      "eval_samples_per_second": 20.787,
+      "eval_steps_per_second": 20.787,
+      "step": 198
+    },
+    {
+      "epoch": 1.8866750611065846,
+      "grad_norm": 0.0255126953125,
+      "learning_rate": 6.32833340454571e-05,
+      "loss": 0.021,
+      "step": 199
+    },
+    {
+      "epoch": 1.8961558403081253,
+      "grad_norm": 0.02978515625,
+      "learning_rate": 6.232721063648148e-05,
+      "loss": 0.0249,
+      "step": 200
+    },
+    {
+      "epoch": 1.905636619509666,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 6.137508413414784e-05,
+      "loss": 0.0238,
+      "step": 201
+    },
+    {
+      "epoch": 1.9151173987112067,
+      "grad_norm": 0.0294189453125,
+      "learning_rate": 6.0427055554621913e-05,
+      "loss": 0.0246,
+      "step": 202
+    },
+    {
+      "epoch": 1.9245981779127472,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 5.948322547929939e-05,
+      "loss": 0.0202,
+      "step": 203
+    },
+    {
+      "epoch": 1.9340789571142878,
+      "grad_norm": 0.024658203125,
+      "learning_rate": 5.854369404413398e-05,
+      "loss": 0.0165,
+      "step": 204
+    },
+    {
+      "epoch": 1.9435597363158283,
+      "grad_norm": 0.026611328125,
+      "learning_rate": 5.7608560929013946e-05,
+      "loss": 0.0226,
+      "step": 205
+    },
+    {
+      "epoch": 1.9530405155173691,
+      "grad_norm": 0.033203125,
+      "learning_rate": 5.667792534718639e-05,
+      "loss": 0.0265,
+      "step": 206
+    },
+    {
+      "epoch": 1.9625212947189097,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 5.5751886034731115e-05,
+      "loss": 0.0233,
+      "step": 207
+    },
+    {
+      "epoch": 1.9720020739204505,
+      "grad_norm": 0.02734375,
+      "learning_rate": 5.483054124008528e-05,
+      "loss": 0.0209,
+      "step": 208
+    },
+    {
+      "epoch": 1.981482853121991,
+      "grad_norm": 0.0286865234375,
+      "learning_rate": 5.391398871361972e-05,
+      "loss": 0.0231,
+      "step": 209
+    },
+    {
+      "epoch": 1.981482853121991,
+      "eval_loss": 0.027809714898467064,
+      "eval_runtime": 34.3727,
+      "eval_samples_per_second": 20.685,
+      "eval_steps_per_second": 20.685,
+      "step": 209
+    },
+    {
+      "epoch": 1.9909636323235316,
+      "grad_norm": 0.03271484375,
+      "learning_rate": 5.300232569726804e-05,
+      "loss": 0.0246,
+      "step": 210
+    },
+    {
+      "epoch": 2.000444411525072,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 5.2095648914209525e-05,
+      "loss": 0.0285,
+      "step": 211
+    },
+    {
+      "epoch": 2.0099251907266127,
+      "grad_norm": 0.026123046875,
+      "learning_rate": 5.119405455860772e-05,
+      "loss": 0.0201,
+      "step": 212
+    },
+    {
+      "epoch": 2.0194059699281537,
+      "grad_norm": 0.02490234375,
+      "learning_rate": 5.029763828540419e-05,
+      "loss": 0.0179,
+      "step": 213
+    },
+    {
+      "epoch": 2.0288867491296942,
+      "grad_norm": 0.0255126953125,
+      "learning_rate": 4.940649520017035e-05,
+      "loss": 0.0207,
+      "step": 214
+    },
+    {
+      "epoch": 2.038367528331235,
+      "grad_norm": 0.02587890625,
+      "learning_rate": 4.852071984901696e-05,
+      "loss": 0.0195,
+      "step": 215
+    },
+    {
+      "epoch": 2.0478483075327754,
+      "grad_norm": 0.02490234375,
+      "learning_rate": 4.7640406208563224e-05,
+      "loss": 0.0195,
+      "step": 216
+    },
+    {
+      "epoch": 2.057329086734316,
+      "grad_norm": 0.02490234375,
+      "learning_rate": 4.676564767596663e-05,
+      "loss": 0.0171,
+      "step": 217
+    },
+    {
+      "epoch": 2.0668098659358565,
+      "grad_norm": 0.027099609375,
+      "learning_rate": 4.5896537059013536e-05,
+      "loss": 0.0174,
+      "step": 218
+    },
+    {
+      "epoch": 2.076290645137397,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 4.503316656627294e-05,
+      "loss": 0.0193,
+      "step": 219
+    },
+    {
+      "epoch": 2.085771424338938,
+      "grad_norm": 0.02490234375,
+      "learning_rate": 4.417562779731355e-05,
+      "loss": 0.0175,
+      "step": 220
+    },
+    {
+      "epoch": 2.085771424338938,
+      "eval_loss": 0.027570126578211784,
+      "eval_runtime": 34.4181,
+      "eval_samples_per_second": 20.658,
+      "eval_steps_per_second": 20.658,
+      "step": 220
+    },
+    {
+      "epoch": 2.0952522035404786,
+      "grad_norm": 0.029296875,
+      "learning_rate": 4.3324011732985433e-05,
+      "loss": 0.0202,
+      "step": 221
+    },
+    {
+      "epoch": 2.104732982742019,
+      "grad_norm": 0.0283203125,
+      "learning_rate": 4.247840872576739e-05,
+      "loss": 0.0189,
+      "step": 222
+    },
+    {
+      "epoch": 2.1142137619435597,
+      "grad_norm": 0.0252685546875,
+      "learning_rate": 4.163890849018114e-05,
+      "loss": 0.0191,
+      "step": 223
+    },
+    {
+      "epoch": 2.1236945411451003,
+      "grad_norm": 0.0264892578125,
+      "learning_rate": 4.0805600093272735e-05,
+      "loss": 0.015,
+      "step": 224
+    },
+    {
+      "epoch": 2.133175320346641,
+      "grad_norm": 0.0264892578125,
+      "learning_rate": 3.997857194516319e-05,
+      "loss": 0.0191,
+      "step": 225
+    },
+    {
+      "epoch": 2.142656099548182,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 3.9157911789668525e-05,
+      "loss": 0.0173,
+      "step": 226
+    },
+    {
+      "epoch": 2.1521368787497224,
+      "grad_norm": 0.0250244140625,
+      "learning_rate": 3.8343706694990465e-05,
+      "loss": 0.0168,
+      "step": 227
+    },
+    {
+      "epoch": 2.161617657951263,
+      "grad_norm": 0.0296630859375,
+      "learning_rate": 3.753604304447915e-05,
+      "loss": 0.0166,
+      "step": 228
+    },
+    {
+      "epoch": 2.1710984371528035,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 3.6735006527467965e-05,
+      "loss": 0.0167,
+      "step": 229
+    },
+    {
+      "epoch": 2.180579216354344,
+      "grad_norm": 0.0263671875,
+      "learning_rate": 3.594068213018249e-05,
+      "loss": 0.0167,
+      "step": 230
+    },
+    {
+      "epoch": 2.1900599955558846,
+      "grad_norm": 0.0262451171875,
+      "learning_rate": 3.515315412672384e-05,
+      "loss": 0.0165,
+      "step": 231
+    },
+    {
+      "epoch": 2.1900599955558846,
+      "eval_loss": 0.028142958879470825,
+      "eval_runtime": 34.4859,
+      "eval_samples_per_second": 20.617,
+      "eval_steps_per_second": 20.617,
+      "step": 231
+    },
+    {
+      "epoch": 2.199540774757425,
+      "grad_norm": 0.029296875,
+      "learning_rate": 3.437250607012748e-05,
+      "loss": 0.0172,
+      "step": 232
+    },
+    {
+      "epoch": 2.209021553958966,
+      "grad_norm": 0.0299072265625,
+      "learning_rate": 3.359882078349883e-05,
+      "loss": 0.0187,
+      "step": 233
+    },
+    {
+      "epoch": 2.2185023331605067,
+      "grad_norm": 0.0277099609375,
+      "learning_rate": 3.283218035122592e-05,
+      "loss": 0.0182,
+      "step": 234
+    },
+    {
+      "epoch": 2.2279831123620473,
+      "grad_norm": 0.0311279296875,
+      "learning_rate": 3.207266611027069e-05,
+      "loss": 0.0169,
+      "step": 235
+    },
+    {
+      "epoch": 2.237463891563588,
+      "grad_norm": 0.030029296875,
+      "learning_rate": 3.132035864153958e-05,
+      "loss": 0.0192,
+      "step": 236
+    },
+    {
+      "epoch": 2.2469446707651284,
+      "grad_norm": 0.0303955078125,
+      "learning_rate": 3.057533776133421e-05,
+      "loss": 0.0157,
+      "step": 237
+    },
+    {
+      "epoch": 2.2564254499666694,
+      "grad_norm": 0.0262451171875,
+      "learning_rate": 2.98376825128832e-05,
+      "loss": 0.0149,
+      "step": 238
+    },
+    {
+      "epoch": 2.26590622916821,
+      "grad_norm": 0.031005859375,
+      "learning_rate": 2.910747115795628e-05,
+      "loss": 0.0177,
+      "step": 239
+    },
+    {
+      "epoch": 2.2753870083697505,
+      "grad_norm": 0.03173828125,
+      "learning_rate": 2.8384781168560693e-05,
+      "loss": 0.0193,
+      "step": 240
+    },
+    {
+      "epoch": 2.284867787571291,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 2.766968921872213e-05,
+      "loss": 0.0165,
+      "step": 241
+    },
+    {
+      "epoch": 2.2943485667728316,
+      "grad_norm": 0.032470703125,
+      "learning_rate": 2.6962271176349852e-05,
+      "loss": 0.0174,
+      "step": 242
+    },
+    {
+      "epoch": 2.2943485667728316,
+      "eval_loss": 0.028074759989976883,
+      "eval_runtime": 34.4556,
+      "eval_samples_per_second": 20.635,
+      "eval_steps_per_second": 20.635,
+      "step": 242
+    },
+    {
+      "epoch": 2.303829345974372,
+      "grad_norm": 0.0283203125,
+      "learning_rate": 2.626260209518737e-05,
+      "loss": 0.0172,
+      "step": 243
+    },
+    {
+      "epoch": 2.3133101251759127,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 2.5570756206849832e-05,
+      "loss": 0.0158,
+      "step": 244
+    },
+    {
+      "epoch": 2.3227909043774533,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 2.4886806912948035e-05,
+      "loss": 0.0159,
+      "step": 245
+    },
+    {
+      "epoch": 2.3322716835789943,
+      "grad_norm": 0.0274658203125,
+      "learning_rate": 2.4210826777301153e-05,
+      "loss": 0.0168,
+      "step": 246
+    },
+    {
+      "epoch": 2.341752462780535,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 2.3542887518238056e-05,
+      "loss": 0.0169,
+      "step": 247
+    },
+    {
+      "epoch": 2.3512332419820754,
+      "grad_norm": 0.028564453125,
+      "learning_rate": 2.288306000098811e-05,
+      "loss": 0.0174,
+      "step": 248
+    },
+    {
+      "epoch": 2.360714021183616,
+      "grad_norm": 0.0306396484375,
+      "learning_rate": 2.2231414230162894e-05,
+      "loss": 0.0219,
+      "step": 249
+    },
+    {
+      "epoch": 2.3701948003851565,
+      "grad_norm": 0.03466796875,
+      "learning_rate": 2.1588019342328968e-05,
+      "loss": 0.0234,
+      "step": 250
+    },
+    {
+      "epoch": 2.3796755795866975,
+      "grad_norm": 0.0294189453125,
+      "learning_rate": 2.0952943598672846e-05,
+      "loss": 0.0174,
+      "step": 251
+    },
+    {
+      "epoch": 2.389156358788238,
+      "grad_norm": 0.028076171875,
+      "learning_rate": 2.0326254377758703e-05,
+      "loss": 0.0194,
+      "step": 252
+    },
+    {
+      "epoch": 2.3986371379897786,
+      "grad_norm": 0.0296630859375,
+      "learning_rate": 1.9708018168380037e-05,
+      "loss": 0.021,
+      "step": 253
+    },
+    {
+      "epoch": 2.3986371379897786,
+      "eval_loss": 0.02788708359003067,
+      "eval_runtime": 34.3192,
+      "eval_samples_per_second": 20.717,
+      "eval_steps_per_second": 20.717,
+      "step": 253
+    },
+    {
+      "epoch": 2.408117917191319,
+      "grad_norm": 0.02490234375,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0155,
+      "step": 254
+    },
+    {
+      "epoch": 2.4175986963928597,
+      "grad_norm": 0.027587890625,
+      "learning_rate": 1.8497166248318876e-05,
+      "loss": 0.0176,
+      "step": 255
+    },
+    {
+      "epoch": 2.4270794755944003,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 1.7904679003358283e-05,
+      "loss": 0.0176,
+      "step": 256
+    },
+    {
+      "epoch": 2.436560254795941,
+      "grad_norm": 0.0284423828125,
+      "learning_rate": 1.7320901687747292e-05,
+      "loss": 0.0172,
+      "step": 257
+    },
+    {
+      "epoch": 2.446041033997482,
+      "grad_norm": 0.0294189453125,
+      "learning_rate": 1.674589623752707e-05,
+      "loss": 0.0198,
+      "step": 258
+    },
+    {
+      "epoch": 2.4555218131990224,
+      "grad_norm": 0.0283203125,
+      "learning_rate": 1.617972365808481e-05,
+      "loss": 0.0187,
+      "step": 259
+    },
+    {
+      "epoch": 2.465002592400563,
+      "grad_norm": 0.0233154296875,
+      "learning_rate": 1.562244401768144e-05,
+      "loss": 0.0127,
+      "step": 260
+    },
+    {
+      "epoch": 2.4744833716021035,
+      "grad_norm": 0.03076171875,
+      "learning_rate": 1.507411644107879e-05,
+      "loss": 0.0228,
+      "step": 261
+    },
+    {
+      "epoch": 2.483964150803644,
+      "grad_norm": 0.031494140625,
+      "learning_rate": 1.4534799103266505e-05,
+      "loss": 0.0193,
+      "step": 262
+    },
+    {
+      "epoch": 2.4934449300051846,
+      "grad_norm": 0.0294189453125,
+      "learning_rate": 1.4004549223290164e-05,
+      "loss": 0.0194,
+      "step": 263
+    },
+    {
+      "epoch": 2.5029257092067256,
+      "grad_norm": 0.0238037109375,
+      "learning_rate": 1.3483423058180421e-05,
+      "loss": 0.0147,
+      "step": 264
+    },
+    {
+      "epoch": 2.5029257092067256,
+      "eval_loss": 0.027736255899071693,
+      "eval_runtime": 34.4272,
+      "eval_samples_per_second": 20.652,
+      "eval_steps_per_second": 20.652,
+      "step": 264
+    },
+    {
+      "epoch": 2.512406488408266,
+      "grad_norm": 0.027099609375,
+      "learning_rate": 1.2971475896984475e-05,
+      "loss": 0.0163,
+      "step": 265
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 315,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 53,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.096745551573811e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-265/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6965abb853c761cad48cb468c99194ceaf6bcfe3b5e51b1799b677a2e2e93f5
+size 6072

checkpoint-315/README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/deepseek-math-7b-rl
+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 0.11.1

checkpoint-315/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-math-7b-rl",
+  "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": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-315/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e7de641437258ad8c54706bb652c7633eb7e4038cb4b5b35dbf904a036d7d76
+size 299884176