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: models-3k-unsolved-priority-022525-step5
+  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. -->
+
+# models-3k-unsolved-priority-022525-step5
+
+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: 768216
+- 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",
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "v_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:c929d83c3209148174244efde05112a6ae7c2fa1b28df4dff44ed04c597c15cd
+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 sha256:15d47ed6e005668936b58e1f6cea886e9887bc093656f986d227f0bcc8bdf826
+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 +1,1092 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.014245815540935456,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.1812,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.011678985360941864,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 0.1826,
+      "step": 2
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.013683218714134537,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.1828,
+      "step": 3
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.013081118010886171,
+      "learning_rate": 2.1333333333333335e-05,
+      "loss": 0.1799,
+      "step": 4
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.014681382604404434,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.1821,
+      "step": 5
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.01573943754760229,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.1772,
+      "step": 6
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.016131221633516758,
+      "learning_rate": 3.733333333333334e-05,
+      "loss": 0.1799,
+      "step": 7
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.018482494228041057,
+      "learning_rate": 4.266666666666667e-05,
+      "loss": 0.1791,
+      "step": 8
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.020142480622451088,
+      "learning_rate": 4.8e-05,
+      "loss": 0.1862,
+      "step": 9
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.021615920903386463,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 0.1703,
+      "step": 10
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.020662685727481003,
+      "learning_rate": 5.8666666666666665e-05,
+      "loss": 0.1748,
+      "step": 11
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.020205880330378585,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.1597,
+      "step": 12
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.017332288297298905,
+      "learning_rate": 6.933333333333334e-05,
+      "loss": 0.1564,
+      "step": 13
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.021087764610898934,
+      "learning_rate": 7.466666666666667e-05,
+      "loss": 0.1639,
+      "step": 14
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.022357380623845263,
+      "learning_rate": 8e-05,
+      "loss": 0.152,
+      "step": 15
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.021120182120764885,
+      "learning_rate": 7.998916964717848e-05,
+      "loss": 0.1373,
+      "step": 16
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.018854666948084492,
+      "learning_rate": 7.9956684453541e-05,
+      "loss": 0.1342,
+      "step": 17
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.018640319488929483,
+      "learning_rate": 7.990256201039297e-05,
+      "loss": 0.1349,
+      "step": 18
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.01585149362511202,
+      "learning_rate": 7.982683162599218e-05,
+      "loss": 0.1309,
+      "step": 19
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.016067552449652155,
+      "learning_rate": 7.972953430967773e-05,
+      "loss": 0.119,
+      "step": 20
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.01662906310189762,
+      "learning_rate": 7.961072274966282e-05,
+      "loss": 0.1209,
+      "step": 21
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.02038260151316938,
+      "learning_rate": 7.947046128450319e-05,
+      "loss": 0.1246,
+      "step": 22
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.013778671931513236,
+      "learning_rate": 7.930882586825653e-05,
+      "loss": 0.1155,
+      "step": 23
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.013268255836007683,
+      "learning_rate": 7.912590402935223e-05,
+      "loss": 0.1059,
+      "step": 24
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.014573172860358636,
+      "learning_rate": 7.892179482319297e-05,
+      "loss": 0.1099,
+      "step": 25
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.013378387483974673,
+      "learning_rate": 7.869660877851456e-05,
+      "loss": 0.0932,
+      "step": 26
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.012770203409940485,
+      "learning_rate": 7.845046783753276e-05,
+      "loss": 0.1138,
+      "step": 27
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.014009873756376339,
+      "learning_rate": 7.818350528990929e-05,
+      "loss": 0.0939,
+      "step": 28
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.013259776902526943,
+      "learning_rate": 7.789586570057317e-05,
+      "loss": 0.0832,
+      "step": 29
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.013801636483476697,
+      "learning_rate": 7.758770483143634e-05,
+      "loss": 0.0759,
+      "step": 30
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.012658663728197517,
+      "learning_rate": 7.72591895570457e-05,
+      "loss": 0.0727,
+      "step": 31
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.01129394715924571,
+      "learning_rate": 7.69104977742177e-05,
+      "loss": 0.083,
+      "step": 32
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.011357316578949873,
+      "learning_rate": 7.654181830570404e-05,
+      "loss": 0.0675,
+      "step": 33
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.00999274077993758,
+      "learning_rate": 7.615335079794083e-05,
+      "loss": 0.0678,
+      "step": 34
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.010293230412485229,
+      "learning_rate": 7.57453056129365e-05,
+      "loss": 0.0657,
+      "step": 35
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.011302747201298096,
+      "learning_rate": 7.531790371435709e-05,
+      "loss": 0.0679,
+      "step": 36
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.011420087119432673,
+      "learning_rate": 7.48713765478705e-05,
+      "loss": 0.0607,
+      "step": 37
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.013295515437027249,
+      "learning_rate": 7.440596591581463e-05,
+      "loss": 0.074,
+      "step": 38
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.010754750357654117,
+      "learning_rate": 7.392192384625704e-05,
+      "loss": 0.0546,
+      "step": 39
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.013270948767383927,
+      "learning_rate": 7.341951245651747e-05,
+      "loss": 0.0651,
+      "step": 40
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.01144204144854218,
+      "learning_rate": 7.28990038112265e-05,
+      "loss": 0.0612,
+      "step": 41
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.010297477029200386,
+      "learning_rate": 7.236067977499791e-05,
+      "loss": 0.0588,
+      "step": 42
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.011689713608558047,
+      "learning_rate": 7.180483185979392e-05,
+      "loss": 0.0538,
+      "step": 43
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.011765135572519698,
+      "learning_rate": 7.123176106706638e-05,
+      "loss": 0.0614,
+      "step": 44
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.011882307696957478,
+      "learning_rate": 7.064177772475912e-05,
+      "loss": 0.06,
+      "step": 45
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.012246870991523197,
+      "learning_rate": 7.003520131925997e-05,
+      "loss": 0.0535,
+      "step": 46
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.011553781828247277,
+      "learning_rate": 6.941236032239316e-05,
+      "loss": 0.0495,
+      "step": 47
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.012107018753251795,
+      "learning_rate": 6.877359201354606e-05,
+      "loss": 0.0583,
+      "step": 48
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.012295348779794046,
+      "learning_rate": 6.811924229702648e-05,
+      "loss": 0.0452,
+      "step": 49
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.017042907543333055,
+      "learning_rate": 6.744966551474936e-05,
+      "loss": 0.0537,
+      "step": 50
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.013116599789691154,
+      "learning_rate": 6.676522425435433e-05,
+      "loss": 0.0401,
+      "step": 51
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.01636485068761413,
+      "learning_rate": 6.606628915285822e-05,
+      "loss": 0.0457,
+      "step": 52
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.013458013205107476,
+      "learning_rate": 6.53532386959484e-05,
+      "loss": 0.0415,
+      "step": 53
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.012534603278992,
+      "learning_rate": 6.462645901302633e-05,
+      "loss": 0.0488,
+      "step": 54
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.011830884153188502,
+      "learning_rate": 6.388634366811146e-05,
+      "loss": 0.0445,
+      "step": 55
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.012473180655027562,
+      "learning_rate": 6.313329344671946e-05,
+      "loss": 0.0389,
+      "step": 56
+    },
+    {
+      "epoch": 1.1400000000000001,
+      "grad_norm": 0.012285243656164641,
+      "learning_rate": 6.236771613882987e-05,
+      "loss": 0.0381,
+      "step": 57
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.014856008323946193,
+      "learning_rate": 6.159002631806052e-05,
+      "loss": 0.0391,
+      "step": 58
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.011489307066506492,
+      "learning_rate": 6.0800645117168616e-05,
+      "loss": 0.037,
+      "step": 59
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.013792643140733179,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 0.0416,
+      "step": 60
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.013009260425118352,
+      "learning_rate": 5.918852453000986e-05,
+      "loss": 0.0375,
+      "step": 61
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.010790507033715792,
+      "learning_rate": 5.836665813548047e-05,
+      "loss": 0.0441,
+      "step": 62
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.019727935573675578,
+      "learning_rate": 5.75348458715631e-05,
+      "loss": 0.0336,
+      "step": 63
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.01043710276424308,
+      "learning_rate": 5.669353817927272e-05,
+      "loss": 0.0451,
+      "step": 64
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.013048450414334011,
+      "learning_rate": 5.584319064156628e-05,
+      "loss": 0.0339,
+      "step": 65
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.011824589469927935,
+      "learning_rate": 5.4984263736636494e-05,
+      "loss": 0.0344,
+      "step": 66
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.00911978110614152,
+      "learning_rate": 5.4117222588554756e-05,
+      "loss": 0.036,
+      "step": 67
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.009256444919926277,
+      "learning_rate": 5.324253671539833e-05,
+      "loss": 0.0368,
+      "step": 68
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.010559723253649787,
+      "learning_rate": 5.23606797749979e-05,
+      "loss": 0.0313,
+      "step": 69
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.01583256937063591,
+      "learning_rate": 5.1472129308443616e-05,
+      "loss": 0.031,
+      "step": 70
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.00984330877068537,
+      "learning_rate": 5.05773664814881e-05,
+      "loss": 0.0373,
+      "step": 71
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.010518525362805689,
+      "learning_rate": 4.967687582398671e-05,
+      "loss": 0.0361,
+      "step": 72
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.01088134056729706,
+      "learning_rate": 4.877114496751613e-05,
+      "loss": 0.0305,
+      "step": 73
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.009343315711062923,
+      "learning_rate": 4.786066438131321e-05,
+      "loss": 0.0415,
+      "step": 74
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.00905384574236871,
+      "learning_rate": 4.694592710667723e-05,
+      "loss": 0.034,
+      "step": 75
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.012916755518828515,
+      "learning_rate": 4.602742848997933e-05,
+      "loss": 0.0348,
+      "step": 76
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.009465399920875778,
+      "learning_rate": 4.51056659144238e-05,
+      "loss": 0.0322,
+      "step": 77
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.008669570916701187,
+      "learning_rate": 4.418113853070614e-05,
+      "loss": 0.0336,
+      "step": 78
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.010088549327598855,
+      "learning_rate": 4.3254346986714334e-05,
+      "loss": 0.0354,
+      "step": 79
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.009197819087264669,
+      "learning_rate": 4.2325793156419035e-05,
+      "loss": 0.0346,
+      "step": 80
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.009419530758714696,
+      "learning_rate": 4.139597986810005e-05,
+      "loss": 0.0448,
+      "step": 81
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.019477140531626032,
+      "learning_rate": 4.046541063205589e-05,
+      "loss": 0.0404,
+      "step": 82
+    },
+    {
+      "epoch": 1.6600000000000001,
+      "grad_norm": 0.009876560079124927,
+      "learning_rate": 3.953458936794413e-05,
+      "loss": 0.0387,
+      "step": 83
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.010083538482453403,
+      "learning_rate": 3.860402013189998e-05,
+      "loss": 0.0312,
+      "step": 84
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.013290532573607808,
+      "learning_rate": 3.767420684358097e-05,
+      "loss": 0.032,
+      "step": 85
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.012101459040237357,
+      "learning_rate": 3.674565301328568e-05,
+      "loss": 0.0333,
+      "step": 86
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.00962920984746278,
+      "learning_rate": 3.581886146929387e-05,
+      "loss": 0.05,
+      "step": 87
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.00954332694067924,
+      "learning_rate": 3.4894334085576215e-05,
+      "loss": 0.0448,
+      "step": 88
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.008651140813427955,
+      "learning_rate": 3.397257151002068e-05,
+      "loss": 0.0311,
+      "step": 89
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.009462892297780596,
+      "learning_rate": 3.305407289332279e-05,
+      "loss": 0.0313,
+      "step": 90
+    },
+    {
+      "epoch": 1.8199999999999998,
+      "grad_norm": 0.011905537158357755,
+      "learning_rate": 3.213933561868679e-05,
+      "loss": 0.0406,
+      "step": 91
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.008468362419003322,
+      "learning_rate": 3.122885503248386e-05,
+      "loss": 0.0434,
+      "step": 92
+    },
+    {
+      "epoch": 1.8599999999999999,
+      "grad_norm": 0.014355913944547521,
+      "learning_rate": 3.0323124176013297e-05,
+      "loss": 0.0331,
+      "step": 93
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.013648772205275517,
+      "learning_rate": 2.9422633518511926e-05,
+      "loss": 0.0378,
+      "step": 94
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.008607000073285164,
+      "learning_rate": 2.8527870691556404e-05,
+      "loss": 0.0343,
+      "step": 95
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.010066297633858636,
+      "learning_rate": 2.7639320225002108e-05,
+      "loss": 0.029,
+      "step": 96
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.014613033897596035,
+      "learning_rate": 2.6757463284601682e-05,
+      "loss": 0.036,
+      "step": 97
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.010261161081495104,
+      "learning_rate": 2.5882777411445254e-05,
+      "loss": 0.0311,
+      "step": 98
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.008902776955957523,
+      "learning_rate": 2.501573626336352e-05,
+      "loss": 0.0355,
+      "step": 99
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.008267508679365178,
+      "learning_rate": 2.4156809358433728e-05,
+      "loss": 0.0271,
+      "step": 100
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 0.00815102874040394,
+      "learning_rate": 2.330646182072729e-05,
+      "loss": 0.0272,
+      "step": 101
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.007924226270178603,
+      "learning_rate": 2.24651541284369e-05,
+      "loss": 0.0369,
+      "step": 102
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 0.008643513592875567,
+      "learning_rate": 2.1633341864519526e-05,
+      "loss": 0.0305,
+      "step": 103
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.009095698574298977,
+      "learning_rate": 2.0811475469990167e-05,
+      "loss": 0.0371,
+      "step": 104
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.008735007911471806,
+      "learning_rate": 2.0000000000000012e-05,
+      "loss": 0.0331,
+      "step": 105
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.008572419601972687,
+      "learning_rate": 1.9199354882831387e-05,
+      "loss": 0.041,
+      "step": 106
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 0.0076285126533740515,
+      "learning_rate": 1.8409973681939498e-05,
+      "loss": 0.0264,
+      "step": 107
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.007891528791812695,
+      "learning_rate": 1.7632283861170135e-05,
+      "loss": 0.0408,
+      "step": 108
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 0.008465016815780687,
+      "learning_rate": 1.686670655328054e-05,
+      "loss": 0.0318,
+      "step": 109
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.007910680826265571,
+      "learning_rate": 1.6113656331888563e-05,
+      "loss": 0.0307,
+      "step": 110
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 0.007745638002298969,
+      "learning_rate": 1.537354098697367e-05,
+      "loss": 0.0375,
+      "step": 111
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.009109740702202291,
+      "learning_rate": 1.4646761304051587e-05,
+      "loss": 0.0259,
+      "step": 112
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 0.008821304718316452,
+      "learning_rate": 1.3933710847141795e-05,
+      "loss": 0.0286,
+      "step": 113
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 0.007810747270127242,
+      "learning_rate": 1.3234775745645684e-05,
+      "loss": 0.0338,
+      "step": 114
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.00850989127587288,
+      "learning_rate": 1.2550334485250661e-05,
+      "loss": 0.0254,
+      "step": 115
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.008182456186622158,
+      "learning_rate": 1.1880757702973531e-05,
+      "loss": 0.034,
+      "step": 116
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.007730715374377881,
+      "learning_rate": 1.1226407986453963e-05,
+      "loss": 0.0342,
+      "step": 117
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.008102408287875335,
+      "learning_rate": 1.0587639677606857e-05,
+      "loss": 0.0318,
+      "step": 118
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.007775861248105198,
+      "learning_rate": 9.964798680740033e-06,
+      "loss": 0.0321,
+      "step": 119
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.007847559948882279,
+      "learning_rate": 9.358222275240884e-06,
+      "loss": 0.0293,
+      "step": 120
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 0.008084400567799072,
+      "learning_rate": 8.768238932933632e-06,
+      "loss": 0.0281,
+      "step": 121
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.008812570885629261,
+      "learning_rate": 8.195168140206084e-06,
+      "loss": 0.0368,
+      "step": 122
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 0.008858379550228713,
+      "learning_rate": 7.639320225002106e-06,
+      "loss": 0.0305,
+      "step": 123
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.007948154432919631,
+      "learning_rate": 7.1009961887735075e-06,
+      "loss": 0.0363,
+      "step": 124
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.008247081153993604,
+      "learning_rate": 6.58048754348255e-06,
+      "loss": 0.0506,
+      "step": 125
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.0073845572213735566,
+      "learning_rate": 6.078076153742962e-06,
+      "loss": 0.0239,
+      "step": 126
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 0.008356459516087945,
+      "learning_rate": 5.5940340841853915e-06,
+      "loss": 0.0419,
+      "step": 127
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.007482534711264407,
+      "learning_rate": 5.128623452129508e-06,
+      "loss": 0.0317,
+      "step": 128
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 0.007849649709237932,
+      "learning_rate": 4.6820962856429205e-06,
+      "loss": 0.0297,
+      "step": 129
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.007000845238829418,
+      "learning_rate": 4.254694387063514e-06,
+      "loss": 0.0291,
+      "step": 130
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 0.007945632438219172,
+      "learning_rate": 3.846649202059181e-06,
+      "loss": 0.0331,
+      "step": 131
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.008231362444666917,
+      "learning_rate": 3.458181694295961e-06,
+      "loss": 0.0284,
+      "step": 132
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 0.008157781436566817,
+      "learning_rate": 3.0895022257823083e-06,
+      "loss": 0.0338,
+      "step": 133
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.00796531827031158,
+      "learning_rate": 2.7408104429543025e-06,
+      "loss": 0.0339,
+      "step": 134
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.007411480771225177,
+      "learning_rate": 2.4122951685636674e-06,
+      "loss": 0.0376,
+      "step": 135
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.008018481773503752,
+      "learning_rate": 2.104134299426832e-06,
+      "loss": 0.0295,
+      "step": 136
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 0.009573348064675996,
+      "learning_rate": 1.8164947100907238e-06,
+      "loss": 0.037,
+      "step": 137
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.007841983699099485,
+      "learning_rate": 1.5495321624672443e-06,
+      "loss": 0.0304,
+      "step": 138
+    },
+    {
+      "epoch": 2.7800000000000002,
+      "grad_norm": 0.007684534272399171,
+      "learning_rate": 1.3033912214854482e-06,
+      "loss": 0.0278,
+      "step": 139
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.008369650665075699,
+      "learning_rate": 1.0782051768070477e-06,
+      "loss": 0.027,
+      "step": 140
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 0.008059300836807068,
+      "learning_rate": 8.740959706477725e-07,
+      "loss": 0.0256,
+      "step": 141
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.00824612755108195,
+      "learning_rate": 6.911741317434706e-07,
+      "loss": 0.0349,
+      "step": 142
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 0.007868044271373583,
+      "learning_rate": 5.295387154968312e-07,
+      "loss": 0.0411,
+      "step": 143
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.007987210130892423,
+      "learning_rate": 3.8927725033718553e-07,
+      "loss": 0.0321,
+      "step": 144
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.008452306826475502,
+      "learning_rate": 2.704656903222791e-07,
+      "loss": 0.0305,
+      "step": 145
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.008259088244697014,
+      "learning_rate": 1.7316837400782604e-07,
+      "loss": 0.0299,
+      "step": 146
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 0.008012111307604415,
+      "learning_rate": 9.74379896070321e-08,
+      "loss": 0.0322,
+      "step": 147
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.008072123812115566,
+      "learning_rate": 4.331554645901737e-08,
+      "loss": 0.0302,
+      "step": 148
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 0.007952847005699813,
+      "learning_rate": 1.0830352821531442e-08,
+      "loss": 0.0351,
+      "step": 149
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.007865241861699823,
+      "learning_rate": 0.0,
+      "loss": 0.0359,
+      "step": 150
+    },
+    {
+      "epoch": 3.0,
+      "step": 150,
+      "total_flos": 113539555655680.0,
+      "train_loss": 0.06015361967186133,
+      "train_runtime": 1340.2935,
+      "train_samples_per_second": 0.895,
+      "train_steps_per_second": 0.112
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 150,
+  "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": 113539555655680.0,
+  "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 sha256:5b8977d0dcf07d6dff53008c2e67cb6c87e697b8d559ee63867835ddd4b160aa
+size 7288