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 +1,61 @@
+---
+library_name: peft
+license: mit
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: model_3k_forcing_022225_step1_1500buffer
+  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. -->
+
+# model_3k_forcing_022225_step1_1500buffer
+
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 8e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 100
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 8
+- total_eval_batch_size: 8
+- 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: 3
+
+### Training results
+
+
+
+### 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-32B",
+  "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": 32,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "up_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 sha256:8ed758a33700d7b883c35053b2488346dcf47d43362fe1552f970f211e92b91a
+size 2147607752

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:fa00f924d6bcc8400fc15a30c4cae46269afbd4f0d04c848c9126a0c7431c9ee
+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｜><think>\\n'}}{% 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
+}

trainer_state.json

@@ -0,0 +1,2142 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.00975973888931374,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 0.1789,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.009969429066062586,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.1742,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.009285111583115442,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.178,
+      "step": 3
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.009718578509161862,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 0.1834,
+      "step": 4
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.008978663147300486,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.1862,
+      "step": 5
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.009330523259646785,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.1826,
+      "step": 6
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.009481936990823576,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 0.1842,
+      "step": 7
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.0096143452400136,
+      "learning_rate": 2.1333333333333335e-05,
+      "loss": 0.1773,
+      "step": 8
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.010401070952623532,
+      "learning_rate": 2.4e-05,
+      "loss": 0.1825,
+      "step": 9
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.010633511876520278,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.1858,
+      "step": 10
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.012753339317992721,
+      "learning_rate": 2.9333333333333333e-05,
+      "loss": 0.1787,
+      "step": 11
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.012737915674957006,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.1735,
+      "step": 12
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.014237237743851433,
+      "learning_rate": 3.466666666666667e-05,
+      "loss": 0.1737,
+      "step": 13
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.013481977038419132,
+      "learning_rate": 3.733333333333334e-05,
+      "loss": 0.1771,
+      "step": 14
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.014211210454419258,
+      "learning_rate": 4e-05,
+      "loss": 0.18,
+      "step": 15
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.01406671564349945,
+      "learning_rate": 4.266666666666667e-05,
+      "loss": 0.164,
+      "step": 16
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.013382254076509769,
+      "learning_rate": 4.5333333333333335e-05,
+      "loss": 0.1627,
+      "step": 17
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.012462250592034499,
+      "learning_rate": 4.8e-05,
+      "loss": 0.1599,
+      "step": 18
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.011623909141186887,
+      "learning_rate": 5.066666666666667e-05,
+      "loss": 0.1561,
+      "step": 19
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.010567055994868338,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 0.1608,
+      "step": 20
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.011578898312408135,
+      "learning_rate": 5.6e-05,
+      "loss": 0.149,
+      "step": 21
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.01263043598230939,
+      "learning_rate": 5.8666666666666665e-05,
+      "loss": 0.1502,
+      "step": 22
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.014619527333110586,
+      "learning_rate": 6.133333333333334e-05,
+      "loss": 0.147,
+      "step": 23
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.015562732552308571,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.1477,
+      "step": 24
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.01988850057450678,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.1315,
+      "step": 25
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.01592720334780788,
+      "learning_rate": 6.933333333333334e-05,
+      "loss": 0.1381,
+      "step": 26
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.01213399023718665,
+      "learning_rate": 7.2e-05,
+      "loss": 0.1284,
+      "step": 27
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.010747416386187284,
+      "learning_rate": 7.466666666666667e-05,
+      "loss": 0.1266,
+      "step": 28
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.012311136597983292,
+      "learning_rate": 7.733333333333333e-05,
+      "loss": 0.1224,
+      "step": 29
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.010735578550951882,
+      "learning_rate": 8e-05,
+      "loss": 0.1204,
+      "step": 30
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.011081512456623081,
+      "learning_rate": 7.99972923201505e-05,
+      "loss": 0.1219,
+      "step": 31
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.010968193335996256,
+      "learning_rate": 7.998916964717848e-05,
+      "loss": 0.1034,
+      "step": 32
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.011606564844140702,
+      "learning_rate": 7.997563308076384e-05,
+      "loss": 0.1023,
+      "step": 33
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.010825973020931393,
+      "learning_rate": 7.9956684453541e-05,
+      "loss": 0.1048,
+      "step": 34
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.010361943126689283,
+      "learning_rate": 7.993232633085074e-05,
+      "loss": 0.1091,
+      "step": 35
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.010438830032426665,
+      "learning_rate": 7.990256201039297e-05,
+      "loss": 0.1057,
+      "step": 36
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.009998624784288302,
+      "learning_rate": 7.986739552178024e-05,
+      "loss": 0.1013,
+      "step": 37
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.009377781647301162,
+      "learning_rate": 7.982683162599218e-05,
+      "loss": 0.0912,
+      "step": 38
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.009251354252244855,
+      "learning_rate": 7.978087581473094e-05,
+      "loss": 0.0892,
+      "step": 39
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.009398969645095491,
+      "learning_rate": 7.972953430967773e-05,
+      "loss": 0.0889,
+      "step": 40
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.008917003010329064,
+      "learning_rate": 7.967281406165047e-05,
+      "loss": 0.0836,
+      "step": 41
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.008369371218976972,
+      "learning_rate": 7.961072274966282e-05,
+      "loss": 0.0881,
+      "step": 42
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.008645208177411155,
+      "learning_rate": 7.954326877988446e-05,
+      "loss": 0.0784,
+      "step": 43
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.010050615184569308,
+      "learning_rate": 7.947046128450319e-05,
+      "loss": 0.0836,
+      "step": 44
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.009987779690915787,
+      "learning_rate": 7.939231012048833e-05,
+      "loss": 0.0935,
+      "step": 45
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.009980160564781465,
+      "learning_rate": 7.930882586825653e-05,
+      "loss": 0.0763,
+      "step": 46
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.009655054144220078,
+      "learning_rate": 7.922001983023918e-05,
+      "loss": 0.0848,
+      "step": 47
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.011213143459668503,
+      "learning_rate": 7.912590402935223e-05,
+      "loss": 0.0731,
+      "step": 48
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.009739459573280887,
+      "learning_rate": 7.902649120736858e-05,
+      "loss": 0.0757,
+      "step": 49
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.011246440365487474,
+      "learning_rate": 7.892179482319297e-05,
+      "loss": 0.0719,
+      "step": 50
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.010656568377013767,
+      "learning_rate": 7.881182905103986e-05,
+      "loss": 0.0665,
+      "step": 51
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.010705942104817151,
+      "learning_rate": 7.869660877851456e-05,
+      "loss": 0.068,
+      "step": 52
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.013046752315013016,
+      "learning_rate": 7.857614960459756e-05,
+      "loss": 0.0705,
+      "step": 53
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.01138775668359661,
+      "learning_rate": 7.845046783753276e-05,
+      "loss": 0.0607,
+      "step": 54
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.01483943168489928,
+      "learning_rate": 7.831958049261956e-05,
+      "loss": 0.071,
+      "step": 55
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.013889643142845373,
+      "learning_rate": 7.818350528990929e-05,
+      "loss": 0.064,
+      "step": 56
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.014913835125302678,
+      "learning_rate": 7.804226065180615e-05,
+      "loss": 0.0627,
+      "step": 57
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.013783358495679316,
+      "learning_rate": 7.789586570057317e-05,
+      "loss": 0.0628,
+      "step": 58
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.012881559012047194,
+      "learning_rate": 7.774434025574335e-05,
+      "loss": 0.0583,
+      "step": 59
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.009203767304861093,
+      "learning_rate": 7.758770483143634e-05,
+      "loss": 0.0618,
+      "step": 60
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.007757149142200283,
+      "learning_rate": 7.742598063358127e-05,
+      "loss": 0.0611,
+      "step": 61
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.011419138129620103,
+      "learning_rate": 7.72591895570457e-05,
+      "loss": 0.0592,
+      "step": 62
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.009871217127379156,
+      "learning_rate": 7.70873541826715e-05,
+      "loss": 0.0648,
+      "step": 63
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.013741722887867229,
+      "learning_rate": 7.69104977742177e-05,
+      "loss": 0.0551,
+      "step": 64
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.0075585956152919576,
+      "learning_rate": 7.672864427521097e-05,
+      "loss": 0.0614,
+      "step": 65
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.01180566302338812,
+      "learning_rate": 7.654181830570404e-05,
+      "loss": 0.0587,
+      "step": 66
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.014184242311912936,
+      "learning_rate": 7.635004515894258e-05,
+      "loss": 0.0543,
+      "step": 67
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.012798772576387809,
+      "learning_rate": 7.615335079794083e-05,
+      "loss": 0.0672,
+      "step": 68
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.017304492348577144,
+      "learning_rate": 7.595176185196669e-05,
+      "loss": 0.0532,
+      "step": 69
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.010226411164996575,
+      "learning_rate": 7.57453056129365e-05,
+      "loss": 0.0617,
+      "step": 70
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.03880893650808376,
+      "learning_rate": 7.553401003172018e-05,
+      "loss": 0.0657,
+      "step": 71
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.009123262384208996,
+      "learning_rate": 7.531790371435709e-05,
+      "loss": 0.0585,
+      "step": 72
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.0310525568086072,
+      "learning_rate": 7.509701591818328e-05,
+      "loss": 0.0632,
+      "step": 73
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.010585387066448279,
+      "learning_rate": 7.48713765478705e-05,
+      "loss": 0.0607,
+      "step": 74
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.009989777131862311,
+      "learning_rate": 7.464101615137756e-05,
+      "loss": 0.0585,
+      "step": 75
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.014604925899626916,
+      "learning_rate": 7.440596591581463e-05,
+      "loss": 0.061,
+      "step": 76
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.009727832966346583,
+      "learning_rate": 7.416625766322104e-05,
+      "loss": 0.06,
+      "step": 77
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.008571172568577179,
+      "learning_rate": 7.392192384625704e-05,
+      "loss": 0.0584,
+      "step": 78
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.011006866583398434,
+      "learning_rate": 7.36729975438103e-05,
+      "loss": 0.0673,
+      "step": 79
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.008511317955868526,
+      "learning_rate": 7.341951245651747e-05,
+      "loss": 0.0637,
+      "step": 80
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.009222703977899139,
+      "learning_rate": 7.316150290220167e-05,
+      "loss": 0.0576,
+      "step": 81
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.007069722171739626,
+      "learning_rate": 7.28990038112265e-05,
+      "loss": 0.0595,
+      "step": 82
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.008636882699174933,
+      "learning_rate": 7.26320507217669e-05,
+      "loss": 0.0538,
+      "step": 83
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.006728336243965822,
+      "learning_rate": 7.236067977499791e-05,
+      "loss": 0.0765,
+      "step": 84
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.008128573468751916,
+      "learning_rate": 7.208492771020176e-05,
+      "loss": 0.0592,
+      "step": 85
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.006526872173502966,
+      "learning_rate": 7.180483185979392e-05,
+      "loss": 0.0633,
+      "step": 86
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.006782232793070975,
+      "learning_rate": 7.152043014426888e-05,
+      "loss": 0.0529,
+      "step": 87
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.00755302555939971,
+      "learning_rate": 7.123176106706638e-05,
+      "loss": 0.0592,
+      "step": 88
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.006827724421058533,
+      "learning_rate": 7.093886370935857e-05,
+      "loss": 0.053,
+      "step": 89
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.006668204199113761,
+      "learning_rate": 7.064177772475912e-05,
+      "loss": 0.0553,
+      "step": 90
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.006661786544837106,
+      "learning_rate": 7.034054333395477e-05,
+      "loss": 0.0529,
+      "step": 91
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.006619846137095159,
+      "learning_rate": 7.003520131925997e-05,
+      "loss": 0.0535,
+      "step": 92
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.0070011563265403465,
+      "learning_rate": 6.972579301909577e-05,
+      "loss": 0.0634,
+      "step": 93
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.0061134490312462,
+      "learning_rate": 6.941236032239316e-05,
+      "loss": 0.0615,
+      "step": 94
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.006537916555469948,
+      "learning_rate": 6.909494566292195e-05,
+      "loss": 0.0603,
+      "step": 95
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.007553056346823884,
+      "learning_rate": 6.877359201354606e-05,
+      "loss": 0.0539,
+      "step": 96
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.006093993013213828,
+      "learning_rate": 6.844834288040548e-05,
+      "loss": 0.0554,
+      "step": 97
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.006310803981190944,
+      "learning_rate": 6.811924229702648e-05,
+      "loss": 0.0571,
+      "step": 98
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.007570131129374107,
+      "learning_rate": 6.778633481835989e-05,
+      "loss": 0.0557,
+      "step": 99
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.007487562294217722,
+      "learning_rate": 6.744966551474936e-05,
+      "loss": 0.0583,
+      "step": 100
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.006359837564784104,
+      "learning_rate": 6.71092799658293e-05,
+      "loss": 0.0628,
+      "step": 101
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.006138388003369084,
+      "learning_rate": 6.676522425435433e-05,
+      "loss": 0.0547,
+      "step": 102
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.006703101906314633,
+      "learning_rate": 6.641754495996031e-05,
+      "loss": 0.0461,
+      "step": 103
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.0062725720861589685,
+      "learning_rate": 6.606628915285822e-05,
+      "loss": 0.0527,
+      "step": 104
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.0063865423382953946,
+      "learning_rate": 6.571150438746157e-05,
+      "loss": 0.0506,
+      "step": 105
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.005990465904804074,
+      "learning_rate": 6.53532386959484e-05,
+      "loss": 0.0537,
+      "step": 106
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.009220140374447247,
+      "learning_rate": 6.499154058175841e-05,
+      "loss": 0.0522,
+      "step": 107
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.00540998255469808,
+      "learning_rate": 6.462645901302633e-05,
+      "loss": 0.0516,
+      "step": 108
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 0.006217449253873114,
+      "learning_rate": 6.425804341595255e-05,
+      "loss": 0.0518,
+      "step": 109
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.006471438407438729,
+      "learning_rate": 6.388634366811146e-05,
+      "loss": 0.0496,
+      "step": 110
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.007161952818479216,
+      "learning_rate": 6.351141009169893e-05,
+      "loss": 0.0582,
+      "step": 111
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.0068160508026970205,
+      "learning_rate": 6.313329344671946e-05,
+      "loss": 0.0546,
+      "step": 112
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.00590373606923259,
+      "learning_rate": 6.275204492411408e-05,
+      "loss": 0.0519,
+      "step": 113
+    },
+    {
+      "epoch": 1.1400000000000001,
+      "grad_norm": 0.006433610458016062,
+      "learning_rate": 6.236771613882987e-05,
+      "loss": 0.0553,
+      "step": 114
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.006835005084642541,
+      "learning_rate": 6.198035912283225e-05,
+      "loss": 0.0474,
+      "step": 115
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.0065486780447602125,
+      "learning_rate": 6.159002631806052e-05,
+      "loss": 0.0527,
+      "step": 116
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.006115599641372958,
+      "learning_rate": 6.11967705693282e-05,
+      "loss": 0.0593,
+      "step": 117
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.006410277773462344,
+      "learning_rate": 6.0800645117168616e-05,
+      "loss": 0.0495,
+      "step": 118
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.00624207587040104,
+      "learning_rate": 6.040170359062702e-05,
+      "loss": 0.056,
+      "step": 119
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.006452317218711539,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 0.0537,
+      "step": 120
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.007465405568860055,
+      "learning_rate": 5.959558872952349e-05,
+      "loss": 0.0539,
+      "step": 121
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.006441358307073292,
+      "learning_rate": 5.918852453000986e-05,
+      "loss": 0.0567,
+      "step": 122
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.007033751482965206,
+      "learning_rate": 5.877886251143564e-05,
+      "loss": 0.0488,
+      "step": 123
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.006453511474714476,
+      "learning_rate": 5.836665813548047e-05,
+      "loss": 0.0517,
+      "step": 124
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.006202405357875232,
+      "learning_rate": 5.79519672080185e-05,
+      "loss": 0.0531,
+      "step": 125
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.0063350763498242054,
+      "learning_rate": 5.75348458715631e-05,
+      "loss": 0.0542,
+      "step": 126
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.006585920886645376,
+      "learning_rate": 5.711535059766617e-05,
+      "loss": 0.0511,
+      "step": 127
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.007114089940186752,
+      "learning_rate": 5.669353817927272e-05,
+      "loss": 0.0507,
+      "step": 128
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.0063686838958942745,
+      "learning_rate": 5.626946572303202e-05,
+      "loss": 0.0517,
+      "step": 129
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.007118365650739293,
+      "learning_rate": 5.584319064156628e-05,
+      "loss": 0.0617,
+      "step": 130
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.009985325431920227,
+      "learning_rate": 5.541477064569794e-05,
+      "loss": 0.06,
+      "step": 131
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.007584023655357705,
+      "learning_rate": 5.4984263736636494e-05,
+      "loss": 0.0524,
+      "step": 132
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.008166009187369436,
+      "learning_rate": 5.4551728198126066e-05,
+      "loss": 0.0568,
+      "step": 133
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.007807828168493425,
+      "learning_rate": 5.4117222588554756e-05,
+      "loss": 0.0528,
+      "step": 134
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.007275027029853539,
+      "learning_rate": 5.368080573302676e-05,
+      "loss": 0.0523,
+      "step": 135
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.009982025448270036,
+      "learning_rate": 5.324253671539833e-05,
+      "loss": 0.0561,
+      "step": 136
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.007917078584406574,
+      "learning_rate": 5.280247487027886e-05,
+      "loss": 0.0529,
+      "step": 137
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.007156905015064814,
+      "learning_rate": 5.23606797749979e-05,
+      "loss": 0.0513,
+      "step": 138
+    },
+    {
+      "epoch": 1.3900000000000001,
+      "grad_norm": 0.007915384457070518,
+      "learning_rate": 5.191721124153928e-05,
+      "loss": 0.0504,
+      "step": 139
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.0071454076520816884,
+      "learning_rate": 5.1472129308443616e-05,
+      "loss": 0.0505,
+      "step": 140
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.007440864860172307,
+      "learning_rate": 5.102549423267997e-05,
+      "loss": 0.0513,
+      "step": 141
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.006781489697269766,
+      "learning_rate": 5.05773664814881e-05,
+      "loss": 0.0557,
+      "step": 142
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.0076834133529257624,
+      "learning_rate": 5.012780672419208e-05,
+      "loss": 0.0544,
+      "step": 143
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.007302367654679525,
+      "learning_rate": 4.967687582398671e-05,
+      "loss": 0.0582,
+      "step": 144
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.007567079535660508,
+      "learning_rate": 4.922463482969761e-05,
+      "loss": 0.058,
+      "step": 145
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.008102048310381298,
+      "learning_rate": 4.877114496751613e-05,
+      "loss": 0.0552,
+      "step": 146
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.007034402622201175,
+      "learning_rate": 4.831646763271037e-05,
+      "loss": 0.0613,
+      "step": 147
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.00724145626141598,
+      "learning_rate": 4.786066438131321e-05,
+      "loss": 0.0561,
+      "step": 148
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.007102845006067121,
+      "learning_rate": 4.740379692178858e-05,
+      "loss": 0.0554,
+      "step": 149
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.009236373859778914,
+      "learning_rate": 4.694592710667723e-05,
+      "loss": 0.0495,
+      "step": 150
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.00714453517731578,
+      "learning_rate": 4.648711692422271e-05,
+      "loss": 0.0556,
+      "step": 151
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.007085617774269391,
+      "learning_rate": 4.602742848997933e-05,
+      "loss": 0.056,
+      "step": 152
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 0.008430545103813795,
+      "learning_rate": 4.556692403840262e-05,
+      "loss": 0.0524,
+      "step": 153
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.007287113804117382,
+      "learning_rate": 4.51056659144238e-05,
+      "loss": 0.0516,
+      "step": 154
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.008349043652432166,
+      "learning_rate": 4.464371656500921e-05,
+      "loss": 0.0631,
+      "step": 155
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.007598972785573559,
+      "learning_rate": 4.418113853070614e-05,
+      "loss": 0.0587,
+      "step": 156
+    },
+    {
+      "epoch": 1.5699999999999998,
+      "grad_norm": 0.007569896238311314,
+      "learning_rate": 4.37179944371757e-05,
+      "loss": 0.055,
+      "step": 157
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.007131863103812141,
+      "learning_rate": 4.3254346986714334e-05,
+      "loss": 0.0584,
+      "step": 158
+    },
+    {
+      "epoch": 1.5899999999999999,
+      "grad_norm": 0.007080408626366854,
+      "learning_rate": 4.2790258949765014e-05,
+      "loss": 0.0519,
+      "step": 159
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.008114262196864164,
+      "learning_rate": 4.2325793156419035e-05,
+      "loss": 0.0482,
+      "step": 160
+    },
+    {
+      "epoch": 1.6099999999999999,
+      "grad_norm": 0.008190674953788812,
+      "learning_rate": 4.186101248790988e-05,
+      "loss": 0.0484,
+      "step": 161
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.007020507001428916,
+      "learning_rate": 4.139597986810005e-05,
+      "loss": 0.0521,
+      "step": 162
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.007650354154095339,
+      "learning_rate": 4.093075825496225e-05,
+      "loss": 0.0568,
+      "step": 163
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.008182046330938405,
+      "learning_rate": 4.046541063205589e-05,
+      "loss": 0.0516,
+      "step": 164
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.007465154265220012,
+      "learning_rate": 4e-05,
+      "loss": 0.0482,
+      "step": 165
+    },
+    {
+      "epoch": 1.6600000000000001,
+      "grad_norm": 0.008452117611695243,
+      "learning_rate": 3.953458936794413e-05,
+      "loss": 0.05,
+      "step": 166
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.008074789265636787,
+      "learning_rate": 3.9069241745037753e-05,
+      "loss": 0.0513,
+      "step": 167
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.009042811977756882,
+      "learning_rate": 3.860402013189998e-05,
+      "loss": 0.0485,
+      "step": 168
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.00762433164262109,
+      "learning_rate": 3.813898751209013e-05,
+      "loss": 0.0512,
+      "step": 169
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.008811253254955806,
+      "learning_rate": 3.767420684358097e-05,
+      "loss": 0.0521,
+      "step": 170
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.0075299486046352315,
+      "learning_rate": 3.720974105023499e-05,
+      "loss": 0.0504,
+      "step": 171
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.007798017673528889,
+      "learning_rate": 3.674565301328568e-05,
+      "loss": 0.0577,
+      "step": 172
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.007622433433874874,
+      "learning_rate": 3.628200556282432e-05,
+      "loss": 0.0518,
+      "step": 173
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.008467491545172878,
+      "learning_rate": 3.581886146929387e-05,
+      "loss": 0.0522,
+      "step": 174
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.007506213631952832,
+      "learning_rate": 3.535628343499079e-05,
+      "loss": 0.0581,
+      "step": 175
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.008763895813966242,
+      "learning_rate": 3.4894334085576215e-05,
+      "loss": 0.058,
+      "step": 176
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.007669952397480411,
+      "learning_rate": 3.44330759615974e-05,
+      "loss": 0.052,
+      "step": 177
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.007054625454305199,
+      "learning_rate": 3.397257151002068e-05,
+      "loss": 0.0549,
+      "step": 178
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.009288756626833644,
+      "learning_rate": 3.351288307577731e-05,
+      "loss": 0.0554,
+      "step": 179
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.008233310749170903,
+      "learning_rate": 3.305407289332279e-05,
+      "loss": 0.0565,
+      "step": 180
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.007833837204017957,
+      "learning_rate": 3.2596203078211424e-05,
+      "loss": 0.0467,
+      "step": 181
+    },
+    {
+      "epoch": 1.8199999999999998,
+      "grad_norm": 0.007089341594394346,
+      "learning_rate": 3.213933561868679e-05,
+      "loss": 0.052,
+      "step": 182
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.007473306580606742,
+      "learning_rate": 3.168353236728964e-05,
+      "loss": 0.0487,
+      "step": 183
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.008372809544562218,
+      "learning_rate": 3.122885503248386e-05,
+      "loss": 0.0492,
+      "step": 184
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.0071497318025102955,
+      "learning_rate": 3.07753651703024e-05,
+      "loss": 0.0608,
+      "step": 185
+    },
+    {
+      "epoch": 1.8599999999999999,
+      "grad_norm": 0.007493452653104603,
+      "learning_rate": 3.0323124176013297e-05,
+      "loss": 0.0478,
+      "step": 186
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.007202322342127042,
+      "learning_rate": 2.9872193275807933e-05,
+      "loss": 0.0542,
+      "step": 187
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.00732058753845859,
+      "learning_rate": 2.9422633518511926e-05,
+      "loss": 0.0518,
+      "step": 188
+    },
+    {
+      "epoch": 1.8900000000000001,
+      "grad_norm": 0.007508749793397996,
+      "learning_rate": 2.8974505767320037e-05,
+      "loss": 0.052,
+      "step": 189
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.00766611988918056,
+      "learning_rate": 2.8527870691556404e-05,
+      "loss": 0.0516,
+      "step": 190
+    },
+    {
+      "epoch": 1.9100000000000001,
+      "grad_norm": 0.007388182140516179,
+      "learning_rate": 2.808278875846072e-05,
+      "loss": 0.0457,
+      "step": 191
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.008028421092160346,
+      "learning_rate": 2.7639320225002108e-05,
+      "loss": 0.0559,
+      "step": 192
+    },
+    {
+      "epoch": 1.9300000000000002,
+      "grad_norm": 0.0074198301332096695,
+      "learning_rate": 2.7197525129721138e-05,
+      "loss": 0.0559,
+      "step": 193
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.008148658738087657,
+      "learning_rate": 2.6757463284601682e-05,
+      "loss": 0.0506,
+      "step": 194
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.0075285729396853684,
+      "learning_rate": 2.6319194266973256e-05,
+      "loss": 0.0505,
+      "step": 195
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.007423097745506451,
+      "learning_rate": 2.5882777411445254e-05,
+      "loss": 0.048,
+      "step": 196
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.00710016303959488,
+      "learning_rate": 2.5448271801873957e-05,
+      "loss": 0.0506,
+      "step": 197
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.008113205739100461,
+      "learning_rate": 2.501573626336352e-05,
+      "loss": 0.0609,
+      "step": 198
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 0.008764046165710386,
+      "learning_rate": 2.4585229354302077e-05,
+      "loss": 0.0454,
+      "step": 199
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.00821153513962698,
+      "learning_rate": 2.4156809358433728e-05,
+      "loss": 0.0606,
+      "step": 200
+    },
+    {
+      "epoch": 2.01,
+      "grad_norm": 0.007680698523728549,
+      "learning_rate": 2.3730534276968e-05,
+      "loss": 0.0476,
+      "step": 201
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 0.0072058892547023625,
+      "learning_rate": 2.330646182072729e-05,
+      "loss": 0.0452,
+      "step": 202
+    },
+    {
+      "epoch": 2.03,
+      "grad_norm": 0.007455986857229059,
+      "learning_rate": 2.288464940233384e-05,
+      "loss": 0.0532,
+      "step": 203
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.008403832982531088,
+      "learning_rate": 2.24651541284369e-05,
+      "loss": 0.059,
+      "step": 204
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.008164085332218317,
+      "learning_rate": 2.2048032791981515e-05,
+      "loss": 0.051,
+      "step": 205
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 0.008887334881050327,
+      "learning_rate": 2.1633341864519526e-05,
+      "loss": 0.0472,
+      "step": 206
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 0.006913827555493125,
+      "learning_rate": 2.122113748856438e-05,
+      "loss": 0.0495,
+      "step": 207
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.007764341801266272,
+      "learning_rate": 2.0811475469990167e-05,
+      "loss": 0.0521,
+      "step": 208
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 0.00796973985641782,
+      "learning_rate": 2.0404411270476527e-05,
+      "loss": 0.042,
+      "step": 209
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.007679599584638068,
+      "learning_rate": 2.0000000000000012e-05,
+      "loss": 0.043,
+      "step": 210
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 0.007741532652410615,
+      "learning_rate": 1.959829640937299e-05,
+      "loss": 0.0513,
+      "step": 211
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.008209511734690264,
+      "learning_rate": 1.9199354882831387e-05,
+      "loss": 0.0449,
+      "step": 212
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 0.00748273073895644,
+      "learning_rate": 1.880322943067181e-05,
+      "loss": 0.0516,
+      "step": 213
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 0.008058884957159639,
+      "learning_rate": 1.8409973681939498e-05,
+      "loss": 0.0491,
+      "step": 214
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.007896720503622225,
+      "learning_rate": 1.8019640877167763e-05,
+      "loss": 0.0508,
+      "step": 215
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.0076269938815235775,
+      "learning_rate": 1.7632283861170135e-05,
+      "loss": 0.0486,
+      "step": 216
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 0.007351997904615261,
+      "learning_rate": 1.7247955075885938e-05,
+      "loss": 0.0538,
+      "step": 217
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 0.008997677074227179,
+      "learning_rate": 1.686670655328054e-05,
+      "loss": 0.0428,
+      "step": 218
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 0.007628347779794642,
+      "learning_rate": 1.648858990830108e-05,
+      "loss": 0.0519,
+      "step": 219
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.007848198798166058,
+      "learning_rate": 1.6113656331888563e-05,
+      "loss": 0.0396,
+      "step": 220
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 0.00818161455778652,
+      "learning_rate": 1.5741956584047478e-05,
+      "loss": 0.0402,
+      "step": 221
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 0.008100183400441816,
+      "learning_rate": 1.537354098697367e-05,
+      "loss": 0.0453,
+      "step": 222
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 0.00794023122702451,
+      "learning_rate": 1.5008459418241601e-05,
+      "loss": 0.0472,
+      "step": 223
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.009769674822868987,
+      "learning_rate": 1.4646761304051587e-05,
+      "loss": 0.0465,
+      "step": 224
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.00783561890669205,
+      "learning_rate": 1.4288495612538427e-05,
+      "loss": 0.0466,
+      "step": 225
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 0.007694729315287434,
+      "learning_rate": 1.3933710847141795e-05,
+      "loss": 0.0507,
+      "step": 226
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 0.0075756047835537,
+      "learning_rate": 1.3582455040039699e-05,
+      "loss": 0.0518,
+      "step": 227
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 0.009015454228459657,
+      "learning_rate": 1.3234775745645684e-05,
+      "loss": 0.0499,
+      "step": 228
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 0.00921692465849527,
+      "learning_rate": 1.2890720034170712e-05,
+      "loss": 0.0561,
+      "step": 229
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.007278637992549301,
+      "learning_rate": 1.2550334485250661e-05,
+      "loss": 0.0453,
+      "step": 230
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 0.008589962697891675,
+      "learning_rate": 1.2213665181640106e-05,
+      "loss": 0.0502,
+      "step": 231
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.007498032503423722,
+      "learning_rate": 1.1880757702973531e-05,
+      "loss": 0.0544,
+      "step": 232
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 0.00711635543171786,
+      "learning_rate": 1.1551657119594517e-05,
+      "loss": 0.042,
+      "step": 233
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.008216933132714868,
+      "learning_rate": 1.1226407986453963e-05,
+      "loss": 0.0504,
+      "step": 234
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.008104809687511125,
+      "learning_rate": 1.0905054337078051e-05,
+      "loss": 0.0458,
+      "step": 235
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.007698489937667685,
+      "learning_rate": 1.0587639677606857e-05,
+      "loss": 0.0484,
+      "step": 236
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 0.008350303786833624,
+      "learning_rate": 1.0274206980904226e-05,
+      "loss": 0.053,
+      "step": 237
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.00787749812285185,
+      "learning_rate": 9.964798680740033e-06,
+      "loss": 0.0583,
+      "step": 238
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 0.007815320631397374,
+      "learning_rate": 9.659456666045247e-06,
+      "loss": 0.0505,
+      "step": 239
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.007102002524475694,
+      "learning_rate": 9.358222275240884e-06,
+      "loss": 0.0492,
+      "step": 240
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 0.007621055980572488,
+      "learning_rate": 9.061136290641448e-06,
+      "loss": 0.05,
+      "step": 241
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 0.011297785905862773,
+      "learning_rate": 8.768238932933632e-06,
+      "loss": 0.0468,
+      "step": 242
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 0.008601495621167033,
+      "learning_rate": 8.479569855731125e-06,
+      "loss": 0.0535,
+      "step": 243
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.007878980554869908,
+      "learning_rate": 8.195168140206084e-06,
+      "loss": 0.0451,
+      "step": 244
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 0.0074909986850030886,
+      "learning_rate": 7.915072289798247e-06,
+      "loss": 0.0521,
+      "step": 245
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 0.00848573741778448,
+      "learning_rate": 7.639320225002106e-06,
+      "loss": 0.0452,
+      "step": 246
+    },
+    {
+      "epoch": 2.4699999999999998,
+      "grad_norm": 0.00790578716548238,
+      "learning_rate": 7.367949278233126e-06,
+      "loss": 0.0539,
+      "step": 247
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.008232378642808477,
+      "learning_rate": 7.1009961887735075e-06,
+      "loss": 0.0464,
+      "step": 248
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 0.007433470022835041,
+      "learning_rate": 6.838497097798336e-06,
+      "loss": 0.0467,
+      "step": 249
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.007738887190809639,
+      "learning_rate": 6.58048754348255e-06,
+      "loss": 0.0587,
+      "step": 250
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 0.00880827917948987,
+      "learning_rate": 6.327002456189699e-06,
+      "loss": 0.054,
+      "step": 251
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.007965487571289098,
+      "learning_rate": 6.078076153742962e-06,
+      "loss": 0.0512,
+      "step": 252
+    },
+    {
+      "epoch": 2.5300000000000002,
+      "grad_norm": 0.007469099301562679,
+      "learning_rate": 5.833742336778981e-06,
+      "loss": 0.0477,
+      "step": 253
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 0.008484709423463018,
+      "learning_rate": 5.5940340841853915e-06,
+      "loss": 0.0494,
+      "step": 254
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 0.0077139322549110954,
+      "learning_rate": 5.358983848622452e-06,
+      "loss": 0.0431,
+      "step": 255
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.007419456022316517,
+      "learning_rate": 5.128623452129508e-06,
+      "loss": 0.0458,
+      "step": 256
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.007497816758801154,
+      "learning_rate": 4.902984081816717e-06,
+      "loss": 0.0525,
+      "step": 257
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 0.00773414898278967,
+      "learning_rate": 4.6820962856429205e-06,
+      "loss": 0.0501,
+      "step": 258
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 0.008029479128266754,
+      "learning_rate": 4.4659899682798446e-06,
+      "loss": 0.058,
+      "step": 259
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.00817201238048331,
+      "learning_rate": 4.254694387063514e-06,
+      "loss": 0.0517,
+      "step": 260
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 0.007833872573765003,
+      "learning_rate": 4.048238148033328e-06,
+      "loss": 0.0447,
+      "step": 261
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 0.007283917683521356,
+      "learning_rate": 3.846649202059181e-06,
+      "loss": 0.0507,
+      "step": 262
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 0.007281030186329541,
+      "learning_rate": 3.6499548410574303e-06,
+      "loss": 0.0513,
+      "step": 263
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.008227694669530704,
+      "learning_rate": 3.458181694295961e-06,
+      "loss": 0.0479,
+      "step": 264
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.008050977932771895,
+      "learning_rate": 3.2713557247890447e-06,
+      "loss": 0.0454,
+      "step": 265
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 0.008423892005773738,
+      "learning_rate": 3.0895022257823083e-06,
+      "loss": 0.0468,
+      "step": 266
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 0.007881578517262917,
+      "learning_rate": 2.9126458173285077e-06,
+      "loss": 0.0407,
+      "step": 267
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.007992533123823718,
+      "learning_rate": 2.7408104429543025e-06,
+      "loss": 0.0494,
+      "step": 268
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 0.007436604743620323,
+      "learning_rate": 2.574019366418745e-06,
+      "loss": 0.0549,
+      "step": 269
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.007663239639283421,
+      "learning_rate": 2.4122951685636674e-06,
+      "loss": 0.0475,
+      "step": 270
+    },
+    {
+      "epoch": 2.71,
+      "grad_norm": 0.007838468915328882,
+      "learning_rate": 2.25565974425666e-06,
+      "loss": 0.0464,
+      "step": 271
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.00914425008382166,
+      "learning_rate": 2.104134299426832e-06,
+      "loss": 0.0383,
+      "step": 272
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 0.007947682642468833,
+      "learning_rate": 1.957739348193859e-06,
+      "loss": 0.0519,
+      "step": 273
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 0.0070935838733125825,
+      "learning_rate": 1.8164947100907238e-06,
+      "loss": 0.0465,
+      "step": 274
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.008179536491946084,
+      "learning_rate": 1.6804195073804442e-06,
+      "loss": 0.0459,
+      "step": 275
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.007753507765305779,
+      "learning_rate": 1.5495321624672443e-06,
+      "loss": 0.0468,
+      "step": 276
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 0.007199406022151337,
+      "learning_rate": 1.423850395402444e-06,
+      "loss": 0.0514,
+      "step": 277
+    },
+    {
+      "epoch": 2.7800000000000002,
+      "grad_norm": 0.008333418338222438,
+      "learning_rate": 1.3033912214854482e-06,
+      "loss": 0.05,
+      "step": 278
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 0.008081800995925644,
+      "learning_rate": 1.1881709489601413e-06,
+      "loss": 0.0545,
+      "step": 279
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.007699849451471151,
+      "learning_rate": 1.0782051768070477e-06,
+      "loss": 0.0458,
+      "step": 280
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 0.008054323381976133,
+      "learning_rate": 9.735087926314324e-07,
+      "loss": 0.0431,
+      "step": 281
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 0.008480619590691966,
+      "learning_rate": 8.740959706477725e-07,
+      "loss": 0.0549,
+      "step": 282
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 0.00767280596192848,
+      "learning_rate": 7.799801697608278e-07,
+      "loss": 0.0488,
+      "step": 283
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.007292852487745584,
+      "learning_rate": 6.911741317434706e-07,
+      "loss": 0.0483,
+      "step": 284
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.00795167167707837,
+      "learning_rate": 6.076898795116792e-07,
+      "loss": 0.0457,
+      "step": 285
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 0.007486907497841981,
+      "learning_rate": 5.295387154968312e-07,
+      "loss": 0.0485,
+      "step": 286
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 0.00743096916544247,
+      "learning_rate": 4.5673122011553605e-07,
+      "loss": 0.0519,
+      "step": 287
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.008243440663466602,
+      "learning_rate": 3.8927725033718553e-07,
+      "loss": 0.0597,
+      "step": 288
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 0.008492105017339772,
+      "learning_rate": 3.2718593834953237e-07,
+      "loss": 0.0454,
+      "step": 289
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.007494753123818296,
+      "learning_rate": 2.704656903222791e-07,
+      "loss": 0.0481,
+      "step": 290
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 0.007642204782814251,
+      "learning_rate": 2.1912418526906841e-07,
+      "loss": 0.0482,
+      "step": 291
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.007883004012316045,
+      "learning_rate": 1.7316837400782604e-07,
+      "loss": 0.0455,
+      "step": 292
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 0.007928279317356624,
+      "learning_rate": 1.3260447821975775e-07,
+      "loss": 0.0456,
+      "step": 293
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 0.007445473197648637,
+      "learning_rate": 9.74379896070321e-08,
+      "loss": 0.0405,
+      "step": 294
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.008153580081268767,
+      "learning_rate": 6.767366914927298e-08,
+      "loss": 0.0458,
+      "step": 295
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.007821316249018594,
+      "learning_rate": 4.331554645901737e-08,
+      "loss": 0.0481,
+      "step": 296
+    },
+    {
+      "epoch": 2.9699999999999998,
+      "grad_norm": 0.007329108353965065,
+      "learning_rate": 2.4366919236169518e-08,
+      "loss": 0.0526,
+      "step": 297
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 0.007906132996865366,
+      "learning_rate": 1.0830352821531442e-08,
+      "loss": 0.0392,
+      "step": 298
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 0.008017394398038166,
+      "learning_rate": 2.7076798495118127e-09,
+      "loss": 0.0467,
+      "step": 299
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.00838965584897803,
+      "learning_rate": 0.0,
+      "loss": 0.0492,
+      "step": 300
+    },
+    {
+      "epoch": 3.0,
+      "step": 300,
+      "total_flos": 225998445477888.0,
+      "train_loss": 0.066388065914313,
+      "train_runtime": 2513.5793,
+      "train_samples_per_second": 0.955,
+      "train_steps_per_second": 0.119
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 225998445477888.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e30bcfbda170d3f3fb7df7709d0674a5f23427dfcede9b0ffdfa92382ba2bd95
+size 7288