Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,67 @@
+---
+base_model: deepseek-ai/Deepseek-R1-Distill-Qwen-7B
+library_name: peft
+license: mit
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: sft_r1_7b
+  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. -->
+
+# sft_r1_7b
+
+This model is a fine-tuned version of [deepseek-ai/Deepseek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/Deepseek-R1-Distill-Qwen-7B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4983
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 4
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.4731        | 1.0   | 92   | 0.5096          |
+| 0.4312        | 2.0   | 184  | 0.4983          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.47.0.dev0
+- Pytorch 2.4.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/Deepseek-R1-Distill-Qwen-7B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13e6bd98976df2118efb78f933306157c3709c4439036140dcbc1e310de0f34d
+size 323014560

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 732097236697088.0,
+    "train_loss": 0.4726724639211012,
+    "train_runtime": 4376.5193,
+    "train_samples": 2913,
+    "train_samples_per_second": 1.331,
+    "train_steps_per_second": 0.042
+}

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c42f6337724d3114cf007972f32c083db52da83d993476413f818033e2727313
+size 11422878

tokenizer_config.json

@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 732097236697088.0,
+    "train_loss": 0.4726724639211012,
+    "train_runtime": 4376.5193,
+    "train_samples": 2913,
+    "train_samples_per_second": 1.331,
+    "train_steps_per_second": 0.042
+}

trainer_state.json

@@ -0,0 +1,1346 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 184,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010869565217391304,
+      "grad_norm": 0.06446830024857261,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 0.6273,
+      "step": 1
+    },
+    {
+      "epoch": 0.021739130434782608,
+      "grad_norm": 0.062056614285800726,
+      "learning_rate": 5.263157894736842e-06,
+      "loss": 0.5862,
+      "step": 2
+    },
+    {
+      "epoch": 0.03260869565217391,
+      "grad_norm": 0.06646214317948872,
+      "learning_rate": 7.894736842105263e-06,
+      "loss": 0.6067,
+      "step": 3
+    },
+    {
+      "epoch": 0.043478260869565216,
+      "grad_norm": 0.07354038159494317,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.6496,
+      "step": 4
+    },
+    {
+      "epoch": 0.05434782608695652,
+      "grad_norm": 0.06334758662021339,
+      "learning_rate": 1.3157894736842106e-05,
+      "loss": 0.6211,
+      "step": 5
+    },
+    {
+      "epoch": 0.06521739130434782,
+      "grad_norm": 0.07889185706390375,
+      "learning_rate": 1.5789473684210526e-05,
+      "loss": 0.6803,
+      "step": 6
+    },
+    {
+      "epoch": 0.07608695652173914,
+      "grad_norm": 0.07122356580779679,
+      "learning_rate": 1.8421052631578947e-05,
+      "loss": 0.6454,
+      "step": 7
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 0.0726526461148344,
+      "learning_rate": 2.105263157894737e-05,
+      "loss": 0.6181,
+      "step": 8
+    },
+    {
+      "epoch": 0.09782608695652174,
+      "grad_norm": 0.07519466472153859,
+      "learning_rate": 2.368421052631579e-05,
+      "loss": 0.6491,
+      "step": 9
+    },
+    {
+      "epoch": 0.10869565217391304,
+      "grad_norm": 0.06929132915577016,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 0.5945,
+      "step": 10
+    },
+    {
+      "epoch": 0.11956521739130435,
+      "grad_norm": 0.06838631422480553,
+      "learning_rate": 2.8947368421052634e-05,
+      "loss": 0.6035,
+      "step": 11
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "grad_norm": 0.06748241023218382,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 0.6313,
+      "step": 12
+    },
+    {
+      "epoch": 0.14130434782608695,
+      "grad_norm": 0.06763063714106336,
+      "learning_rate": 3.421052631578947e-05,
+      "loss": 0.6192,
+      "step": 13
+    },
+    {
+      "epoch": 0.15217391304347827,
+      "grad_norm": 0.06406565409885041,
+      "learning_rate": 3.6842105263157895e-05,
+      "loss": 0.6099,
+      "step": 14
+    },
+    {
+      "epoch": 0.16304347826086957,
+      "grad_norm": 0.05611379594819528,
+      "learning_rate": 3.9473684210526316e-05,
+      "loss": 0.5288,
+      "step": 15
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 0.056016792470898205,
+      "learning_rate": 4.210526315789474e-05,
+      "loss": 0.547,
+      "step": 16
+    },
+    {
+      "epoch": 0.18478260869565216,
+      "grad_norm": 0.057447749047072574,
+      "learning_rate": 4.473684210526316e-05,
+      "loss": 0.572,
+      "step": 17
+    },
+    {
+      "epoch": 0.1956521739130435,
+      "grad_norm": 0.06757576045083137,
+      "learning_rate": 4.736842105263158e-05,
+      "loss": 0.6117,
+      "step": 18
+    },
+    {
+      "epoch": 0.20652173913043478,
+      "grad_norm": 0.05833530053395128,
+      "learning_rate": 5e-05,
+      "loss": 0.5957,
+      "step": 19
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 0.055564140118895974,
+      "learning_rate": 4.999546863808815e-05,
+      "loss": 0.5366,
+      "step": 20
+    },
+    {
+      "epoch": 0.22826086956521738,
+      "grad_norm": 0.05583550785841034,
+      "learning_rate": 4.9981876195011844e-05,
+      "loss": 0.5655,
+      "step": 21
+    },
+    {
+      "epoch": 0.2391304347826087,
+      "grad_norm": 0.06221651589740258,
+      "learning_rate": 4.995922759815339e-05,
+      "loss": 0.5862,
+      "step": 22
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.053678378393037476,
+      "learning_rate": 4.992753105783194e-05,
+      "loss": 0.5244,
+      "step": 23
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 0.05455931843393149,
+      "learning_rate": 4.988679806432712e-05,
+      "loss": 0.5488,
+      "step": 24
+    },
+    {
+      "epoch": 0.2717391304347826,
+      "grad_norm": 0.04838711952705311,
+      "learning_rate": 4.9837043383713753e-05,
+      "loss": 0.5014,
+      "step": 25
+    },
+    {
+      "epoch": 0.2826086956521739,
+      "grad_norm": 0.05075534754049686,
+      "learning_rate": 4.977828505250903e-05,
+      "loss": 0.4883,
+      "step": 26
+    },
+    {
+      "epoch": 0.29347826086956524,
+      "grad_norm": 0.051330835365128794,
+      "learning_rate": 4.971054437113406e-05,
+      "loss": 0.4789,
+      "step": 27
+    },
+    {
+      "epoch": 0.30434782608695654,
+      "grad_norm": 0.05899844288428667,
+      "learning_rate": 4.963384589619233e-05,
+      "loss": 0.5511,
+      "step": 28
+    },
+    {
+      "epoch": 0.31521739130434784,
+      "grad_norm": 0.05435772107938851,
+      "learning_rate": 4.9548217431567665e-05,
+      "loss": 0.4933,
+      "step": 29
+    },
+    {
+      "epoch": 0.32608695652173914,
+      "grad_norm": 0.051288148979554415,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.5147,
+      "step": 30
+    },
+    {
+      "epoch": 0.33695652173913043,
+      "grad_norm": 0.044739618080675524,
+      "learning_rate": 4.935029792355834e-05,
+      "loss": 0.4572,
+      "step": 31
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 0.044048925999206415,
+      "learning_rate": 4.923807862776728e-05,
+      "loss": 0.5116,
+      "step": 32
+    },
+    {
+      "epoch": 0.358695652173913,
+      "grad_norm": 0.040802762738242064,
+      "learning_rate": 4.91170728114714e-05,
+      "loss": 0.4805,
+      "step": 33
+    },
+    {
+      "epoch": 0.3695652173913043,
+      "grad_norm": 0.04120040656965703,
+      "learning_rate": 4.898732434036244e-05,
+      "loss": 0.4931,
+      "step": 34
+    },
+    {
+      "epoch": 0.3804347826086957,
+      "grad_norm": 0.04130900195243818,
+      "learning_rate": 4.8848880249422815e-05,
+      "loss": 0.5377,
+      "step": 35
+    },
+    {
+      "epoch": 0.391304347826087,
+      "grad_norm": 0.031293618411126614,
+      "learning_rate": 4.870179072587499e-05,
+      "loss": 0.4671,
+      "step": 36
+    },
+    {
+      "epoch": 0.40217391304347827,
+      "grad_norm": 0.03221202304069264,
+      "learning_rate": 4.854610909098812e-05,
+      "loss": 0.4427,
+      "step": 37
+    },
+    {
+      "epoch": 0.41304347826086957,
+      "grad_norm": 0.03275335982206069,
+      "learning_rate": 4.838189178074867e-05,
+      "loss": 0.4743,
+      "step": 38
+    },
+    {
+      "epoch": 0.42391304347826086,
+      "grad_norm": 0.03171962425309376,
+      "learning_rate": 4.8209198325401815e-05,
+      "loss": 0.4985,
+      "step": 39
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 0.03097196810932539,
+      "learning_rate": 4.802809132787125e-05,
+      "loss": 0.4843,
+      "step": 40
+    },
+    {
+      "epoch": 0.44565217391304346,
+      "grad_norm": 0.030787155908233246,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.4902,
+      "step": 41
+    },
+    {
+      "epoch": 0.45652173913043476,
+      "grad_norm": 0.03193164352858942,
+      "learning_rate": 4.764090234407577e-05,
+      "loss": 0.4977,
+      "step": 42
+    },
+    {
+      "epoch": 0.4673913043478261,
+      "grad_norm": 0.02939685278525522,
+      "learning_rate": 4.743496071728396e-05,
+      "loss": 0.4669,
+      "step": 43
+    },
+    {
+      "epoch": 0.4782608695652174,
+      "grad_norm": 0.03138434773322448,
+      "learning_rate": 4.722088621637309e-05,
+      "loss": 0.459,
+      "step": 44
+    },
+    {
+      "epoch": 0.4891304347826087,
+      "grad_norm": 0.029033753781315723,
+      "learning_rate": 4.6998756445266336e-05,
+      "loss": 0.4669,
+      "step": 45
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.02973134262831363,
+      "learning_rate": 4.6768651927994434e-05,
+      "loss": 0.4895,
+      "step": 46
+    },
+    {
+      "epoch": 0.5108695652173914,
+      "grad_norm": 0.029461115258857515,
+      "learning_rate": 4.653065607950502e-05,
+      "loss": 0.4651,
+      "step": 47
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 0.02854635172938924,
+      "learning_rate": 4.628485517542392e-05,
+      "loss": 0.486,
+      "step": 48
+    },
+    {
+      "epoch": 0.532608695652174,
+      "grad_norm": 0.02785283132466107,
+      "learning_rate": 4.6031338320779534e-05,
+      "loss": 0.4543,
+      "step": 49
+    },
+    {
+      "epoch": 0.5434782608695652,
+      "grad_norm": 0.027076274809747055,
+      "learning_rate": 4.5770197417701365e-05,
+      "loss": 0.4649,
+      "step": 50
+    },
+    {
+      "epoch": 0.5543478260869565,
+      "grad_norm": 0.024572695423530987,
+      "learning_rate": 4.550152713210478e-05,
+      "loss": 0.4442,
+      "step": 51
+    },
+    {
+      "epoch": 0.5652173913043478,
+      "grad_norm": 0.029440322020197175,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.4681,
+      "step": 52
+    },
+    {
+      "epoch": 0.5760869565217391,
+      "grad_norm": 0.02704471782415786,
+      "learning_rate": 4.4941990689053886e-05,
+      "loss": 0.4022,
+      "step": 53
+    },
+    {
+      "epoch": 0.5869565217391305,
+      "grad_norm": 0.0278198283303202,
+      "learning_rate": 4.465132736856969e-05,
+      "loss": 0.496,
+      "step": 54
+    },
+    {
+      "epoch": 0.5978260869565217,
+      "grad_norm": 0.027465561137178875,
+      "learning_rate": 4.4353540265977064e-05,
+      "loss": 0.4952,
+      "step": 55
+    },
+    {
+      "epoch": 0.6086956521739131,
+      "grad_norm": 0.026098660261279747,
+      "learning_rate": 4.404873733176678e-05,
+      "loss": 0.466,
+      "step": 56
+    },
+    {
+      "epoch": 0.6195652173913043,
+      "grad_norm": 0.029183017276866886,
+      "learning_rate": 4.373702905973135e-05,
+      "loss": 0.485,
+      "step": 57
+    },
+    {
+      "epoch": 0.6304347826086957,
+      "grad_norm": 0.027231190275777434,
+      "learning_rate": 4.341852844691012e-05,
+      "loss": 0.4791,
+      "step": 58
+    },
+    {
+      "epoch": 0.6413043478260869,
+      "grad_norm": 0.028527517121768726,
+      "learning_rate": 4.309335095262676e-05,
+      "loss": 0.4667,
+      "step": 59
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 0.027829570984709555,
+      "learning_rate": 4.276161445663423e-05,
+      "loss": 0.4634,
+      "step": 60
+    },
+    {
+      "epoch": 0.6630434782608695,
+      "grad_norm": 0.026719494350055748,
+      "learning_rate": 4.242343921638234e-05,
+      "loss": 0.4852,
+      "step": 61
+    },
+    {
+      "epoch": 0.6739130434782609,
+      "grad_norm": 0.0290818214177707,
+      "learning_rate": 4.2078947823423364e-05,
+      "loss": 0.4765,
+      "step": 62
+    },
+    {
+      "epoch": 0.6847826086956522,
+      "grad_norm": 0.025970242758085023,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 0.4475,
+      "step": 63
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 0.025365809180570274,
+      "learning_rate": 4.137151834863213e-05,
+      "loss": 0.4759,
+      "step": 64
+    },
+    {
+      "epoch": 0.7065217391304348,
+      "grad_norm": 0.02558231810144299,
+      "learning_rate": 4.100883671631806e-05,
+      "loss": 0.465,
+      "step": 65
+    },
+    {
+      "epoch": 0.717391304347826,
+      "grad_norm": 0.02649072047475919,
+      "learning_rate": 4.064035173736804e-05,
+      "loss": 0.4383,
+      "step": 66
+    },
+    {
+      "epoch": 0.7282608695652174,
+      "grad_norm": 0.02592754121161366,
+      "learning_rate": 4.0266196990885955e-05,
+      "loss": 0.4968,
+      "step": 67
+    },
+    {
+      "epoch": 0.7391304347826086,
+      "grad_norm": 0.027886835170981908,
+      "learning_rate": 3.98865081113172e-05,
+      "loss": 0.4341,
+      "step": 68
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.02706758584184985,
+      "learning_rate": 3.9501422739279956e-05,
+      "loss": 0.4876,
+      "step": 69
+    },
+    {
+      "epoch": 0.7608695652173914,
+      "grad_norm": 0.027937833551864757,
+      "learning_rate": 3.911108047166924e-05,
+      "loss": 0.476,
+      "step": 70
+    },
+    {
+      "epoch": 0.7717391304347826,
+      "grad_norm": 0.02699429519045641,
+      "learning_rate": 3.871562281105175e-05,
+      "loss": 0.4865,
+      "step": 71
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 0.02677684283218904,
+      "learning_rate": 3.8315193114369996e-05,
+      "loss": 0.4687,
+      "step": 72
+    },
+    {
+      "epoch": 0.7934782608695652,
+      "grad_norm": 0.027026467831716267,
+      "learning_rate": 3.790993654097405e-05,
+      "loss": 0.4154,
+      "step": 73
+    },
+    {
+      "epoch": 0.8043478260869565,
+      "grad_norm": 0.029853445450123403,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.4799,
+      "step": 74
+    },
+    {
+      "epoch": 0.8152173913043478,
+      "grad_norm": 0.02779494518977547,
+      "learning_rate": 3.708553209711409e-05,
+      "loss": 0.4768,
+      "step": 75
+    },
+    {
+      "epoch": 0.8260869565217391,
+      "grad_norm": 0.029882464608419132,
+      "learning_rate": 3.6666683080641846e-05,
+      "loss": 0.493,
+      "step": 76
+    },
+    {
+      "epoch": 0.8369565217391305,
+      "grad_norm": 0.024880649807331918,
+      "learning_rate": 3.624360478710165e-05,
+      "loss": 0.4469,
+      "step": 77
+    },
+    {
+      "epoch": 0.8478260869565217,
+      "grad_norm": 0.030227564311718032,
+      "learning_rate": 3.581645058616271e-05,
+      "loss": 0.4457,
+      "step": 78
+    },
+    {
+      "epoch": 0.8586956521739131,
+      "grad_norm": 0.028920955745364636,
+      "learning_rate": 3.5385375325047166e-05,
+      "loss": 0.4228,
+      "step": 79
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.02778139180982866,
+      "learning_rate": 3.495053527239656e-05,
+      "loss": 0.4121,
+      "step": 80
+    },
+    {
+      "epoch": 0.8804347826086957,
+      "grad_norm": 0.027063684693506,
+      "learning_rate": 3.4512088061623075e-05,
+      "loss": 0.3919,
+      "step": 81
+    },
+    {
+      "epoch": 0.8913043478260869,
+      "grad_norm": 0.030751718592946106,
+      "learning_rate": 3.4070192633766025e-05,
+      "loss": 0.4546,
+      "step": 82
+    },
+    {
+      "epoch": 0.9021739130434783,
+      "grad_norm": 0.027370669082255016,
+      "learning_rate": 3.3625009179874265e-05,
+      "loss": 0.4224,
+      "step": 83
+    },
+    {
+      "epoch": 0.9130434782608695,
+      "grad_norm": 0.0290833913742289,
+      "learning_rate": 3.3176699082935545e-05,
+      "loss": 0.4505,
+      "step": 84
+    },
+    {
+      "epoch": 0.9239130434782609,
+      "grad_norm": 0.02872084331872566,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.4428,
+      "step": 85
+    },
+    {
+      "epoch": 0.9347826086956522,
+      "grad_norm": 0.02842959967092123,
+      "learning_rate": 3.2271350100134975e-05,
+      "loss": 0.4715,
+      "step": 86
+    },
+    {
+      "epoch": 0.9456521739130435,
+      "grad_norm": 0.02912682762386685,
+      "learning_rate": 3.181463941138495e-05,
+      "loss": 0.4759,
+      "step": 87
+    },
+    {
+      "epoch": 0.9565217391304348,
+      "grad_norm": 0.03004010168860804,
+      "learning_rate": 3.135545835483718e-05,
+      "loss": 0.4831,
+      "step": 88
+    },
+    {
+      "epoch": 0.967391304347826,
+      "grad_norm": 0.027284355596240775,
+      "learning_rate": 3.0893973387735687e-05,
+      "loss": 0.4696,
+      "step": 89
+    },
+    {
+      "epoch": 0.9782608695652174,
+      "grad_norm": 0.026953435729993373,
+      "learning_rate": 3.0430351802512698e-05,
+      "loss": 0.4532,
+      "step": 90
+    },
+    {
+      "epoch": 0.9891304347826086,
+      "grad_norm": 0.028583272669610076,
+      "learning_rate": 2.996476166614364e-05,
+      "loss": 0.4061,
+      "step": 91
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.029729560360053246,
+      "learning_rate": 2.9497371759221347e-05,
+      "loss": 0.4731,
+      "step": 92
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5096498131752014,
+      "eval_runtime": 0.7736,
+      "eval_samples_per_second": 1.293,
+      "eval_steps_per_second": 1.293,
+      "step": 92
+    },
+    {
+      "epoch": 1.0108695652173914,
+      "grad_norm": 0.0329604180531002,
+      "learning_rate": 2.9028351514771606e-05,
+      "loss": 0.449,
+      "step": 93
+    },
+    {
+      "epoch": 1.0217391304347827,
+      "grad_norm": 0.0310287876309693,
+      "learning_rate": 2.8557870956832132e-05,
+      "loss": 0.4313,
+      "step": 94
+    },
+    {
+      "epoch": 1.0326086956521738,
+      "grad_norm": 0.03183621040805215,
+      "learning_rate": 2.808610063881737e-05,
+      "loss": 0.4594,
+      "step": 95
+    },
+    {
+      "epoch": 1.0434782608695652,
+      "grad_norm": 0.02894418085309856,
+      "learning_rate": 2.761321158169134e-05,
+      "loss": 0.4435,
+      "step": 96
+    },
+    {
+      "epoch": 1.0543478260869565,
+      "grad_norm": 0.03259207682886363,
+      "learning_rate": 2.7139375211970996e-05,
+      "loss": 0.4327,
+      "step": 97
+    },
+    {
+      "epoch": 1.065217391304348,
+      "grad_norm": 0.032615787786452764,
+      "learning_rate": 2.6664763299582602e-05,
+      "loss": 0.4453,
+      "step": 98
+    },
+    {
+      "epoch": 1.0760869565217392,
+      "grad_norm": 0.02920933982393603,
+      "learning_rate": 2.6189547895593562e-05,
+      "loss": 0.4334,
+      "step": 99
+    },
+    {
+      "epoch": 1.0869565217391304,
+      "grad_norm": 0.030385939028875233,
+      "learning_rate": 2.5713901269842404e-05,
+      "loss": 0.4693,
+      "step": 100
+    },
+    {
+      "epoch": 1.0978260869565217,
+      "grad_norm": 0.02896436319251362,
+      "learning_rate": 2.523799584848942e-05,
+      "loss": 0.4531,
+      "step": 101
+    },
+    {
+      "epoch": 1.108695652173913,
+      "grad_norm": 0.028856562462423248,
+      "learning_rate": 2.4762004151510584e-05,
+      "loss": 0.4441,
+      "step": 102
+    },
+    {
+      "epoch": 1.1195652173913044,
+      "grad_norm": 0.03130243797765354,
+      "learning_rate": 2.42860987301576e-05,
+      "loss": 0.4523,
+      "step": 103
+    },
+    {
+      "epoch": 1.1304347826086956,
+      "grad_norm": 0.031318332283648456,
+      "learning_rate": 2.3810452104406444e-05,
+      "loss": 0.4485,
+      "step": 104
+    },
+    {
+      "epoch": 1.141304347826087,
+      "grad_norm": 0.03156888620059668,
+      "learning_rate": 2.3335236700417404e-05,
+      "loss": 0.4467,
+      "step": 105
+    },
+    {
+      "epoch": 1.1521739130434783,
+      "grad_norm": 0.0340027690840538,
+      "learning_rate": 2.2860624788029013e-05,
+      "loss": 0.4709,
+      "step": 106
+    },
+    {
+      "epoch": 1.1630434782608696,
+      "grad_norm": 0.03151439831414056,
+      "learning_rate": 2.238678841830867e-05,
+      "loss": 0.4506,
+      "step": 107
+    },
+    {
+      "epoch": 1.1739130434782608,
+      "grad_norm": 0.029732732695034236,
+      "learning_rate": 2.1913899361182632e-05,
+      "loss": 0.4386,
+      "step": 108
+    },
+    {
+      "epoch": 1.184782608695652,
+      "grad_norm": 0.02966345433227014,
+      "learning_rate": 2.1442129043167874e-05,
+      "loss": 0.4385,
+      "step": 109
+    },
+    {
+      "epoch": 1.1956521739130435,
+      "grad_norm": 0.030579536250691982,
+      "learning_rate": 2.09716484852284e-05,
+      "loss": 0.4563,
+      "step": 110
+    },
+    {
+      "epoch": 1.2065217391304348,
+      "grad_norm": 0.07663854356939952,
+      "learning_rate": 2.0502628240778655e-05,
+      "loss": 0.4524,
+      "step": 111
+    },
+    {
+      "epoch": 1.2173913043478262,
+      "grad_norm": 0.03574951140650218,
+      "learning_rate": 2.003523833385637e-05,
+      "loss": 0.4522,
+      "step": 112
+    },
+    {
+      "epoch": 1.2282608695652173,
+      "grad_norm": 0.033715836624894406,
+      "learning_rate": 1.956964819748731e-05,
+      "loss": 0.4304,
+      "step": 113
+    },
+    {
+      "epoch": 1.2391304347826086,
+      "grad_norm": 0.03230999155502022,
+      "learning_rate": 1.9106026612264316e-05,
+      "loss": 0.4525,
+      "step": 114
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.033145535116222535,
+      "learning_rate": 1.8644541645162834e-05,
+      "loss": 0.4562,
+      "step": 115
+    },
+    {
+      "epoch": 1.2608695652173914,
+      "grad_norm": 0.02972751464032265,
+      "learning_rate": 1.8185360588615058e-05,
+      "loss": 0.4327,
+      "step": 116
+    },
+    {
+      "epoch": 1.2717391304347827,
+      "grad_norm": 0.031443897376726704,
+      "learning_rate": 1.7728649899865024e-05,
+      "loss": 0.466,
+      "step": 117
+    },
+    {
+      "epoch": 1.2826086956521738,
+      "grad_norm": 0.04524975054448682,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.4279,
+      "step": 118
+    },
+    {
+      "epoch": 1.2934782608695652,
+      "grad_norm": 0.041692610790207876,
+      "learning_rate": 1.682330091706446e-05,
+      "loss": 0.4438,
+      "step": 119
+    },
+    {
+      "epoch": 1.3043478260869565,
+      "grad_norm": 0.03410523098288268,
+      "learning_rate": 1.637499082012574e-05,
+      "loss": 0.4176,
+      "step": 120
+    },
+    {
+      "epoch": 1.315217391304348,
+      "grad_norm": 0.051871393993261065,
+      "learning_rate": 1.5929807366233977e-05,
+      "loss": 0.4952,
+      "step": 121
+    },
+    {
+      "epoch": 1.3260869565217392,
+      "grad_norm": 0.05120080345054176,
+      "learning_rate": 1.5487911938376924e-05,
+      "loss": 0.4479,
+      "step": 122
+    },
+    {
+      "epoch": 1.3369565217391304,
+      "grad_norm": 0.032445596553352274,
+      "learning_rate": 1.5049464727603452e-05,
+      "loss": 0.3941,
+      "step": 123
+    },
+    {
+      "epoch": 1.3478260869565217,
+      "grad_norm": 0.030442348678231555,
+      "learning_rate": 1.4614624674952842e-05,
+      "loss": 0.4247,
+      "step": 124
+    },
+    {
+      "epoch": 1.358695652173913,
+      "grad_norm": 0.03098439705449045,
+      "learning_rate": 1.4183549413837289e-05,
+      "loss": 0.4371,
+      "step": 125
+    },
+    {
+      "epoch": 1.3695652173913042,
+      "grad_norm": 0.02967122146970817,
+      "learning_rate": 1.3756395212898359e-05,
+      "loss": 0.3796,
+      "step": 126
+    },
+    {
+      "epoch": 1.3804347826086958,
+      "grad_norm": 0.03613211413589584,
+      "learning_rate": 1.3333316919358157e-05,
+      "loss": 0.4379,
+      "step": 127
+    },
+    {
+      "epoch": 1.391304347826087,
+      "grad_norm": 0.03978488612096793,
+      "learning_rate": 1.2914467902885901e-05,
+      "loss": 0.4472,
+      "step": 128
+    },
+    {
+      "epoch": 1.4021739130434783,
+      "grad_norm": 0.0345769520481644,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.4508,
+      "step": 129
+    },
+    {
+      "epoch": 1.4130434782608696,
+      "grad_norm": 0.034629050507341406,
+      "learning_rate": 1.2090063459025955e-05,
+      "loss": 0.4631,
+      "step": 130
+    },
+    {
+      "epoch": 1.4239130434782608,
+      "grad_norm": 0.03355235886442604,
+      "learning_rate": 1.1684806885630004e-05,
+      "loss": 0.4559,
+      "step": 131
+    },
+    {
+      "epoch": 1.434782608695652,
+      "grad_norm": 0.033880957057972026,
+      "learning_rate": 1.1284377188948258e-05,
+      "loss": 0.4323,
+      "step": 132
+    },
+    {
+      "epoch": 1.4456521739130435,
+      "grad_norm": 0.03600104544225976,
+      "learning_rate": 1.0888919528330777e-05,
+      "loss": 0.4633,
+      "step": 133
+    },
+    {
+      "epoch": 1.4565217391304348,
+      "grad_norm": 0.03135942768167873,
+      "learning_rate": 1.049857726072005e-05,
+      "loss": 0.4336,
+      "step": 134
+    },
+    {
+      "epoch": 1.4673913043478262,
+      "grad_norm": 0.032587488974480605,
+      "learning_rate": 1.0113491888682802e-05,
+      "loss": 0.4246,
+      "step": 135
+    },
+    {
+      "epoch": 1.4782608695652173,
+      "grad_norm": 0.032257461647341154,
+      "learning_rate": 9.733803009114045e-06,
+      "loss": 0.4461,
+      "step": 136
+    },
+    {
+      "epoch": 1.4891304347826086,
+      "grad_norm": 0.03355955610850801,
+      "learning_rate": 9.359648262631961e-06,
+      "loss": 0.4511,
+      "step": 137
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.031020189598797942,
+      "learning_rate": 8.991163283681944e-06,
+      "loss": 0.4114,
+      "step": 138
+    },
+    {
+      "epoch": 1.5108695652173914,
+      "grad_norm": 0.030450316885070394,
+      "learning_rate": 8.628481651367876e-06,
+      "loss": 0.4391,
+      "step": 139
+    },
+    {
+      "epoch": 1.5217391304347827,
+      "grad_norm": 0.029909561148195523,
+      "learning_rate": 8.271734841028553e-06,
+      "loss": 0.407,
+      "step": 140
+    },
+    {
+      "epoch": 1.5326086956521738,
+      "grad_norm": 0.031867190056939,
+      "learning_rate": 7.921052176576644e-06,
+      "loss": 0.4494,
+      "step": 141
+    },
+    {
+      "epoch": 1.5434782608695652,
+      "grad_norm": 0.03143703000347331,
+      "learning_rate": 7.576560783617668e-06,
+      "loss": 0.463,
+      "step": 142
+    },
+    {
+      "epoch": 1.5543478260869565,
+      "grad_norm": 0.0306274677481807,
+      "learning_rate": 7.238385543365783e-06,
+      "loss": 0.4163,
+      "step": 143
+    },
+    {
+      "epoch": 1.5652173913043477,
+      "grad_norm": 0.03415487768584906,
+      "learning_rate": 6.906649047373246e-06,
+      "loss": 0.4209,
+      "step": 144
+    },
+    {
+      "epoch": 1.5760869565217392,
+      "grad_norm": 0.03395906756126541,
+      "learning_rate": 6.5814715530898745e-06,
+      "loss": 0.4413,
+      "step": 145
+    },
+    {
+      "epoch": 1.5869565217391304,
+      "grad_norm": 0.03578344063040742,
+      "learning_rate": 6.2629709402686535e-06,
+      "loss": 0.4687,
+      "step": 146
+    },
+    {
+      "epoch": 1.5978260869565217,
+      "grad_norm": 0.03408017026213467,
+      "learning_rate": 5.951262668233232e-06,
+      "loss": 0.44,
+      "step": 147
+    },
+    {
+      "epoch": 1.608695652173913,
+      "grad_norm": 0.030405121236560202,
+      "learning_rate": 5.646459734022938e-06,
+      "loss": 0.4372,
+      "step": 148
+    },
+    {
+      "epoch": 1.6195652173913042,
+      "grad_norm": 0.032778732079215056,
+      "learning_rate": 5.348672631430318e-06,
+      "loss": 0.4467,
+      "step": 149
+    },
+    {
+      "epoch": 1.6304347826086958,
+      "grad_norm": 0.03166008300069132,
+      "learning_rate": 5.058009310946119e-06,
+      "loss": 0.4566,
+      "step": 150
+    },
+    {
+      "epoch": 1.641304347826087,
+      "grad_norm": 0.03724620904241277,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.4522,
+      "step": 151
+    },
+    {
+      "epoch": 1.6521739130434783,
+      "grad_norm": 0.030892864922034177,
+      "learning_rate": 4.498472867895223e-06,
+      "loss": 0.4466,
+      "step": 152
+    },
+    {
+      "epoch": 1.6630434782608696,
+      "grad_norm": 0.031444111314916375,
+      "learning_rate": 4.229802582298633e-06,
+      "loss": 0.4425,
+      "step": 153
+    },
+    {
+      "epoch": 1.6739130434782608,
+      "grad_norm": 0.03225616382556156,
+      "learning_rate": 3.968661679220468e-06,
+      "loss": 0.4732,
+      "step": 154
+    },
+    {
+      "epoch": 1.6847826086956523,
+      "grad_norm": 0.035916385502472725,
+      "learning_rate": 3.715144824576078e-06,
+      "loss": 0.46,
+      "step": 155
+    },
+    {
+      "epoch": 1.6956521739130435,
+      "grad_norm": 0.032745928232069496,
+      "learning_rate": 3.4693439204949858e-06,
+      "loss": 0.4372,
+      "step": 156
+    },
+    {
+      "epoch": 1.7065217391304348,
+      "grad_norm": 0.033867412228700364,
+      "learning_rate": 3.2313480720055745e-06,
+      "loss": 0.4772,
+      "step": 157
+    },
+    {
+      "epoch": 1.7173913043478262,
+      "grad_norm": 0.032133387953619336,
+      "learning_rate": 3.0012435547336737e-06,
+      "loss": 0.4555,
+      "step": 158
+    },
+    {
+      "epoch": 1.7282608695652173,
+      "grad_norm": 0.03134558875240705,
+      "learning_rate": 2.779113783626916e-06,
+      "loss": 0.3917,
+      "step": 159
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 0.03409844296849388,
+      "learning_rate": 2.565039282716045e-06,
+      "loss": 0.4689,
+      "step": 160
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.03537910471416336,
+      "learning_rate": 2.3590976559242278e-06,
+      "loss": 0.4606,
+      "step": 161
+    },
+    {
+      "epoch": 1.7608695652173914,
+      "grad_norm": 0.031573900934466374,
+      "learning_rate": 2.1613635589349756e-06,
+      "loss": 0.4259,
+      "step": 162
+    },
+    {
+      "epoch": 1.7717391304347827,
+      "grad_norm": 0.03571692266634309,
+      "learning_rate": 1.97190867212875e-06,
+      "loss": 0.4613,
+      "step": 163
+    },
+    {
+      "epoch": 1.7826086956521738,
+      "grad_norm": 0.02973827157275551,
+      "learning_rate": 1.790801674598186e-06,
+      "loss": 0.4029,
+      "step": 164
+    },
+    {
+      "epoch": 1.7934782608695652,
+      "grad_norm": 0.031463567483157054,
+      "learning_rate": 1.6181082192513353e-06,
+      "loss": 0.4342,
+      "step": 165
+    },
+    {
+      "epoch": 1.8043478260869565,
+      "grad_norm": 0.03332907386091376,
+      "learning_rate": 1.4538909090118846e-06,
+      "loss": 0.4338,
+      "step": 166
+    },
+    {
+      "epoch": 1.8152173913043477,
+      "grad_norm": 0.03061942618017436,
+      "learning_rate": 1.2982092741250145e-06,
+      "loss": 0.4535,
+      "step": 167
+    },
+    {
+      "epoch": 1.8260869565217392,
+      "grad_norm": 0.029813922009518108,
+      "learning_rate": 1.1511197505771843e-06,
+      "loss": 0.3958,
+      "step": 168
+    },
+    {
+      "epoch": 1.8369565217391304,
+      "grad_norm": 0.031385101945736384,
+      "learning_rate": 1.0126756596375686e-06,
+      "loss": 0.4716,
+      "step": 169
+    },
+    {
+      "epoch": 1.8478260869565217,
+      "grad_norm": 0.030961258459950885,
+      "learning_rate": 8.829271885286094e-07,
+      "loss": 0.4139,
+      "step": 170
+    },
+    {
+      "epoch": 1.858695652173913,
+      "grad_norm": 0.03209183921922134,
+      "learning_rate": 7.619213722327185e-07,
+      "loss": 0.4138,
+      "step": 171
+    },
+    {
+      "epoch": 1.8695652173913042,
+      "grad_norm": 0.03723653448131294,
+      "learning_rate": 6.497020764416633e-07,
+      "loss": 0.4498,
+      "step": 172
+    },
+    {
+      "epoch": 1.8804347826086958,
+      "grad_norm": 0.031817587519438334,
+      "learning_rate": 5.463099816548579e-07,
+      "loss": 0.4529,
+      "step": 173
+    },
+    {
+      "epoch": 1.891304347826087,
+      "grad_norm": 0.03245453845865768,
+      "learning_rate": 4.517825684323324e-07,
+      "loss": 0.4286,
+      "step": 174
+    },
+    {
+      "epoch": 1.9021739130434783,
+      "grad_norm": 0.03320629800246564,
+      "learning_rate": 3.6615410380767544e-07,
+      "loss": 0.4338,
+      "step": 175
+    },
+    {
+      "epoch": 1.9130434782608696,
+      "grad_norm": 0.038389769373416836,
+      "learning_rate": 2.894556288659395e-07,
+      "loss": 0.4503,
+      "step": 176
+    },
+    {
+      "epoch": 1.9239130434782608,
+      "grad_norm": 0.03193065222776472,
+      "learning_rate": 2.2171494749097245e-07,
+      "loss": 0.4282,
+      "step": 177
+    },
+    {
+      "epoch": 1.9347826086956523,
+      "grad_norm": 0.030530425972228197,
+      "learning_rate": 1.6295661628624447e-07,
+      "loss": 0.4681,
+      "step": 178
+    },
+    {
+      "epoch": 1.9456521739130435,
+      "grad_norm": 0.03191982802439677,
+      "learning_rate": 1.1320193567288529e-07,
+      "loss": 0.471,
+      "step": 179
+    },
+    {
+      "epoch": 1.9565217391304348,
+      "grad_norm": 0.028889202221879347,
+      "learning_rate": 7.246894216806355e-08,
+      "loss": 0.4259,
+      "step": 180
+    },
+    {
+      "epoch": 1.9673913043478262,
+      "grad_norm": 0.03012119541455992,
+      "learning_rate": 4.07724018466088e-08,
+      "loss": 0.4286,
+      "step": 181
+    },
+    {
+      "epoch": 1.9782608695652173,
+      "grad_norm": 0.032708796966899434,
+      "learning_rate": 1.812380498815991e-08,
+      "loss": 0.4577,
+      "step": 182
+    },
+    {
+      "epoch": 1.9891304347826086,
+      "grad_norm": 0.03176695899736949,
+      "learning_rate": 4.531361911855325e-09,
+      "loss": 0.4302,
+      "step": 183
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.03249692017136475,
+      "learning_rate": 0.0,
+      "loss": 0.4312,
+      "step": 184
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4982532560825348,
+      "eval_runtime": 1.2432,
+      "eval_samples_per_second": 0.804,
+      "eval_steps_per_second": 0.804,
+      "step": 184
+    },
+    {
+      "epoch": 2.0,
+      "step": 184,
+      "total_flos": 732097236697088.0,
+      "train_loss": 0.4726724639211012,
+      "train_runtime": 4376.5193,
+      "train_samples_per_second": 1.331,
+      "train_steps_per_second": 0.042
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 184,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 732097236697088.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac10a4c6ef76fe7b5433f68ce218d721725c654d3651fe787985eccf67e18c8
+size 7160