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: 3k-forcing-022225-step2
+  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. -->
+
+# 3k-forcing-022225-step2
+
+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",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "k_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 sha256:490a74fbf9ca1a284857a4f62d24ef89360cba60cd2f4f2ced08da15e394d225
+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": 0.011961126050382227,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.1729,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.012495487043171834,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 0.1737,
+      "step": 2
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.011797942011954408,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.1695,
+      "step": 3
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.011330397724890659,
+      "learning_rate": 2.1333333333333335e-05,
+      "loss": 0.1696,
+      "step": 4
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.013180588138757849,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.1718,
+      "step": 5
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.012856228480381246,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.171,
+      "step": 6
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.013357527426426253,
+      "learning_rate": 3.733333333333334e-05,
+      "loss": 0.1689,
+      "step": 7
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.01535054950324841,
+      "learning_rate": 4.266666666666667e-05,
+      "loss": 0.171,
+      "step": 8
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.01685220167799772,
+      "learning_rate": 4.8e-05,
+      "loss": 0.168,
+      "step": 9
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.017733440496170347,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 0.1652,
+      "step": 10
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.0183752847883781,
+      "learning_rate": 5.8666666666666665e-05,
+      "loss": 0.1606,
+      "step": 11
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.017087858350959936,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.1566,
+      "step": 12
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.01778964515544899,
+      "learning_rate": 6.933333333333334e-05,
+      "loss": 0.1527,
+      "step": 13
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.019401042785043864,
+      "learning_rate": 7.466666666666667e-05,
+      "loss": 0.1477,
+      "step": 14
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.019947803352434824,
+      "learning_rate": 8e-05,
+      "loss": 0.1464,
+      "step": 15
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.018362749111872842,
+      "learning_rate": 7.998916964717848e-05,
+      "loss": 0.1393,
+      "step": 16
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.018249984062600075,
+      "learning_rate": 7.9956684453541e-05,
+      "loss": 0.1369,
+      "step": 17
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.022423754667191067,
+      "learning_rate": 7.990256201039297e-05,
+      "loss": 0.1321,
+      "step": 18
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.024022800349523917,
+      "learning_rate": 7.982683162599218e-05,
+      "loss": 0.132,
+      "step": 19
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.01859955964029079,
+      "learning_rate": 7.972953430967773e-05,
+      "loss": 0.1235,
+      "step": 20
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.014505491607192594,
+      "learning_rate": 7.961072274966282e-05,
+      "loss": 0.1193,
+      "step": 21
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.011692343557332834,
+      "learning_rate": 7.947046128450319e-05,
+      "loss": 0.1142,
+      "step": 22
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.011774495696736942,
+      "learning_rate": 7.930882586825653e-05,
+      "loss": 0.114,
+      "step": 23
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.010748865426946815,
+      "learning_rate": 7.912590402935223e-05,
+      "loss": 0.1068,
+      "step": 24
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.011221972882448422,
+      "learning_rate": 7.892179482319297e-05,
+      "loss": 0.1024,
+      "step": 25
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.010849164056223836,
+      "learning_rate": 7.869660877851456e-05,
+      "loss": 0.1015,
+      "step": 26
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.01145277424285684,
+      "learning_rate": 7.845046783753276e-05,
+      "loss": 0.1004,
+      "step": 27
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.01047847572773384,
+      "learning_rate": 7.818350528990929e-05,
+      "loss": 0.0911,
+      "step": 28
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.01099140986579559,
+      "learning_rate": 7.789586570057317e-05,
+      "loss": 0.0868,
+      "step": 29
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.011285933019057035,
+      "learning_rate": 7.758770483143634e-05,
+      "loss": 0.0827,
+      "step": 30
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.013742722705259508,
+      "learning_rate": 7.72591895570457e-05,
+      "loss": 0.0806,
+      "step": 31
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.011207464534629577,
+      "learning_rate": 7.69104977742177e-05,
+      "loss": 0.0762,
+      "step": 32
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.009870201254286276,
+      "learning_rate": 7.654181830570404e-05,
+      "loss": 0.0761,
+      "step": 33
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.009907498673550263,
+      "learning_rate": 7.615335079794083e-05,
+      "loss": 0.0739,
+      "step": 34
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.00929717630596548,
+      "learning_rate": 7.57453056129365e-05,
+      "loss": 0.0686,
+      "step": 35
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.010403441829800162,
+      "learning_rate": 7.531790371435709e-05,
+      "loss": 0.0693,
+      "step": 36
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.009538810238554256,
+      "learning_rate": 7.48713765478705e-05,
+      "loss": 0.0689,
+      "step": 37
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.010362674458882627,
+      "learning_rate": 7.440596591581463e-05,
+      "loss": 0.0641,
+      "step": 38
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.010384920083052097,
+      "learning_rate": 7.392192384625704e-05,
+      "loss": 0.0633,
+      "step": 39
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.011068565763517255,
+      "learning_rate": 7.341951245651747e-05,
+      "loss": 0.0644,
+      "step": 40
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.009911480787941308,
+      "learning_rate": 7.28990038112265e-05,
+      "loss": 0.0587,
+      "step": 41
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.011444934784456977,
+      "learning_rate": 7.236067977499791e-05,
+      "loss": 0.0586,
+      "step": 42
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.012174455704821313,
+      "learning_rate": 7.180483185979392e-05,
+      "loss": 0.0562,
+      "step": 43
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.011027196540882314,
+      "learning_rate": 7.123176106706638e-05,
+      "loss": 0.0561,
+      "step": 44
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.014602761468925063,
+      "learning_rate": 7.064177772475912e-05,
+      "loss": 0.0568,
+      "step": 45
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.0124168387889601,
+      "learning_rate": 7.003520131925997e-05,
+      "loss": 0.0546,
+      "step": 46
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.011875612180352437,
+      "learning_rate": 6.941236032239316e-05,
+      "loss": 0.0515,
+      "step": 47
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.01000103195534259,
+      "learning_rate": 6.877359201354606e-05,
+      "loss": 0.0506,
+      "step": 48
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.010687030639912179,
+      "learning_rate": 6.811924229702648e-05,
+      "loss": 0.0509,
+      "step": 49
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.010928485004262169,
+      "learning_rate": 6.744966551474936e-05,
+      "loss": 0.0492,
+      "step": 50
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.010976479576320582,
+      "learning_rate": 6.676522425435433e-05,
+      "loss": 0.0494,
+      "step": 51
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.009973986142038508,
+      "learning_rate": 6.606628915285822e-05,
+      "loss": 0.0481,
+      "step": 52
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.009006243878951752,
+      "learning_rate": 6.53532386959484e-05,
+      "loss": 0.0435,
+      "step": 53
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.012115443878624487,
+      "learning_rate": 6.462645901302633e-05,
+      "loss": 0.0456,
+      "step": 54
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.009616540589092386,
+      "learning_rate": 6.388634366811146e-05,
+      "loss": 0.0448,
+      "step": 55
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.01079627605725315,
+      "learning_rate": 6.313329344671946e-05,
+      "loss": 0.0453,
+      "step": 56
+    },
+    {
+      "epoch": 1.1400000000000001,
+      "grad_norm": 0.010967823014601513,
+      "learning_rate": 6.236771613882987e-05,
+      "loss": 0.0464,
+      "step": 57
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.012334254190563294,
+      "learning_rate": 6.159002631806052e-05,
+      "loss": 0.0476,
+      "step": 58
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.010603540883722219,
+      "learning_rate": 6.0800645117168616e-05,
+      "loss": 0.0449,
+      "step": 59
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.008974374349500885,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 0.0414,
+      "step": 60
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.00796514423045999,
+      "learning_rate": 5.918852453000986e-05,
+      "loss": 0.0415,
+      "step": 61
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.009017286522537455,
+      "learning_rate": 5.836665813548047e-05,
+      "loss": 0.0415,
+      "step": 62
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.008902315642576783,
+      "learning_rate": 5.75348458715631e-05,
+      "loss": 0.0434,
+      "step": 63
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.0072432644991190405,
+      "learning_rate": 5.669353817927272e-05,
+      "loss": 0.0428,
+      "step": 64
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.007565135853012563,
+      "learning_rate": 5.584319064156628e-05,
+      "loss": 0.0424,
+      "step": 65
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.007656715689533865,
+      "learning_rate": 5.4984263736636494e-05,
+      "loss": 0.043,
+      "step": 66
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.00857445718726149,
+      "learning_rate": 5.4117222588554756e-05,
+      "loss": 0.0409,
+      "step": 67
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.012127144717271747,
+      "learning_rate": 5.324253671539833e-05,
+      "loss": 0.0431,
+      "step": 68
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.006321807804546262,
+      "learning_rate": 5.23606797749979e-05,
+      "loss": 0.0425,
+      "step": 69
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.007170643256020277,
+      "learning_rate": 5.1472129308443616e-05,
+      "loss": 0.0437,
+      "step": 70
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.00847628665679872,
+      "learning_rate": 5.05773664814881e-05,
+      "loss": 0.0433,
+      "step": 71
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.0070810325532377205,
+      "learning_rate": 4.967687582398671e-05,
+      "loss": 0.0414,
+      "step": 72
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.007094325583352017,
+      "learning_rate": 4.877114496751613e-05,
+      "loss": 0.0417,
+      "step": 73
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.007011685235101666,
+      "learning_rate": 4.786066438131321e-05,
+      "loss": 0.0402,
+      "step": 74
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.00676236005134386,
+      "learning_rate": 4.694592710667723e-05,
+      "loss": 0.0421,
+      "step": 75
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.006940814734732793,
+      "learning_rate": 4.602742848997933e-05,
+      "loss": 0.0406,
+      "step": 76
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.0074495731926392875,
+      "learning_rate": 4.51056659144238e-05,
+      "loss": 0.0411,
+      "step": 77
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.0074908172317441225,
+      "learning_rate": 4.418113853070614e-05,
+      "loss": 0.0421,
+      "step": 78
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.006495810458787161,
+      "learning_rate": 4.3254346986714334e-05,
+      "loss": 0.0402,
+      "step": 79
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.006991049503670582,
+      "learning_rate": 4.2325793156419035e-05,
+      "loss": 0.0409,
+      "step": 80
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.0062390740555716495,
+      "learning_rate": 4.139597986810005e-05,
+      "loss": 0.0389,
+      "step": 81
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.007950404715564428,
+      "learning_rate": 4.046541063205589e-05,
+      "loss": 0.0408,
+      "step": 82
+    },
+    {
+      "epoch": 1.6600000000000001,
+      "grad_norm": 0.00617295664574344,
+      "learning_rate": 3.953458936794413e-05,
+      "loss": 0.0405,
+      "step": 83
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.006435508882130319,
+      "learning_rate": 3.860402013189998e-05,
+      "loss": 0.0411,
+      "step": 84
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.006465991846151632,
+      "learning_rate": 3.767420684358097e-05,
+      "loss": 0.0429,
+      "step": 85
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.006713869591845229,
+      "learning_rate": 3.674565301328568e-05,
+      "loss": 0.04,
+      "step": 86
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.00621843564502302,
+      "learning_rate": 3.581886146929387e-05,
+      "loss": 0.0419,
+      "step": 87
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.006851459148927824,
+      "learning_rate": 3.4894334085576215e-05,
+      "loss": 0.0415,
+      "step": 88
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.0066449206381994485,
+      "learning_rate": 3.397257151002068e-05,
+      "loss": 0.0397,
+      "step": 89
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.007942127966904144,
+      "learning_rate": 3.305407289332279e-05,
+      "loss": 0.0392,
+      "step": 90
+    },
+    {
+      "epoch": 1.8199999999999998,
+      "grad_norm": 0.00632123737417067,
+      "learning_rate": 3.213933561868679e-05,
+      "loss": 0.0415,
+      "step": 91
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.007273234102086418,
+      "learning_rate": 3.122885503248386e-05,
+      "loss": 0.0403,
+      "step": 92
+    },
+    {
+      "epoch": 1.8599999999999999,
+      "grad_norm": 0.007262737340442578,
+      "learning_rate": 3.0323124176013297e-05,
+      "loss": 0.0427,
+      "step": 93
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.006899193661360951,
+      "learning_rate": 2.9422633518511926e-05,
+      "loss": 0.0396,
+      "step": 94
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.006222625196055189,
+      "learning_rate": 2.8527870691556404e-05,
+      "loss": 0.0397,
+      "step": 95
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.00636584769241112,
+      "learning_rate": 2.7639320225002108e-05,
+      "loss": 0.0404,
+      "step": 96
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.007393088261513111,
+      "learning_rate": 2.6757463284601682e-05,
+      "loss": 0.0397,
+      "step": 97
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.006414710704007147,
+      "learning_rate": 2.5882777411445254e-05,
+      "loss": 0.0392,
+      "step": 98
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.006739528983115201,
+      "learning_rate": 2.501573626336352e-05,
+      "loss": 0.0409,
+      "step": 99
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.006640001818866118,
+      "learning_rate": 2.4156809358433728e-05,
+      "loss": 0.0402,
+      "step": 100
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 0.005937386545776868,
+      "learning_rate": 2.330646182072729e-05,
+      "loss": 0.0376,
+      "step": 101
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.006127693507524208,
+      "learning_rate": 2.24651541284369e-05,
+      "loss": 0.04,
+      "step": 102
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 0.005796508128662314,
+      "learning_rate": 2.1633341864519526e-05,
+      "loss": 0.038,
+      "step": 103
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.006086543193926668,
+      "learning_rate": 2.0811475469990167e-05,
+      "loss": 0.0386,
+      "step": 104
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.00596974764159407,
+      "learning_rate": 2.0000000000000012e-05,
+      "loss": 0.0384,
+      "step": 105
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.0060519669056320995,
+      "learning_rate": 1.9199354882831387e-05,
+      "loss": 0.0413,
+      "step": 106
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 0.006134717465956922,
+      "learning_rate": 1.8409973681939498e-05,
+      "loss": 0.0395,
+      "step": 107
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.006363079532394663,
+      "learning_rate": 1.7632283861170135e-05,
+      "loss": 0.0382,
+      "step": 108
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 0.0065238862142379,
+      "learning_rate": 1.686670655328054e-05,
+      "loss": 0.04,
+      "step": 109
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.005893030714536999,
+      "learning_rate": 1.6113656331888563e-05,
+      "loss": 0.038,
+      "step": 110
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 0.006707611068606809,
+      "learning_rate": 1.537354098697367e-05,
+      "loss": 0.0388,
+      "step": 111
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.006309559943197239,
+      "learning_rate": 1.4646761304051587e-05,
+      "loss": 0.0364,
+      "step": 112
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 0.006154754444434981,
+      "learning_rate": 1.3933710847141795e-05,
+      "loss": 0.0393,
+      "step": 113
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 0.006155315314544149,
+      "learning_rate": 1.3234775745645684e-05,
+      "loss": 0.0385,
+      "step": 114
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.006386182050348752,
+      "learning_rate": 1.2550334485250661e-05,
+      "loss": 0.0358,
+      "step": 115
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.0072637895261356495,
+      "learning_rate": 1.1880757702973531e-05,
+      "loss": 0.0386,
+      "step": 116
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.006655532151246649,
+      "learning_rate": 1.1226407986453963e-05,
+      "loss": 0.0395,
+      "step": 117
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.007237285094750996,
+      "learning_rate": 1.0587639677606857e-05,
+      "loss": 0.0366,
+      "step": 118
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.006456192364668318,
+      "learning_rate": 9.964798680740033e-06,
+      "loss": 0.0409,
+      "step": 119
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.006552246603754037,
+      "learning_rate": 9.358222275240884e-06,
+      "loss": 0.0396,
+      "step": 120
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 0.0066231947051160495,
+      "learning_rate": 8.768238932933632e-06,
+      "loss": 0.0384,
+      "step": 121
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.006276738368821293,
+      "learning_rate": 8.195168140206084e-06,
+      "loss": 0.037,
+      "step": 122
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 0.006433287016526394,
+      "learning_rate": 7.639320225002106e-06,
+      "loss": 0.0398,
+      "step": 123
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.006242668314119763,
+      "learning_rate": 7.1009961887735075e-06,
+      "loss": 0.0379,
+      "step": 124
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.00636979988795205,
+      "learning_rate": 6.58048754348255e-06,
+      "loss": 0.0381,
+      "step": 125
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.006397915078524727,
+      "learning_rate": 6.078076153742962e-06,
+      "loss": 0.0381,
+      "step": 126
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 0.006180860852592625,
+      "learning_rate": 5.5940340841853915e-06,
+      "loss": 0.0382,
+      "step": 127
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.006421428646832079,
+      "learning_rate": 5.128623452129508e-06,
+      "loss": 0.04,
+      "step": 128
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 0.007158297863621274,
+      "learning_rate": 4.6820962856429205e-06,
+      "loss": 0.0395,
+      "step": 129
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.006597336392522376,
+      "learning_rate": 4.254694387063514e-06,
+      "loss": 0.0377,
+      "step": 130
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 0.006341675053186332,
+      "learning_rate": 3.846649202059181e-06,
+      "loss": 0.0387,
+      "step": 131
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.006459780928396446,
+      "learning_rate": 3.458181694295961e-06,
+      "loss": 0.0384,
+      "step": 132
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 0.006165176844370891,
+      "learning_rate": 3.0895022257823083e-06,
+      "loss": 0.0371,
+      "step": 133
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.006182221441411298,
+      "learning_rate": 2.7408104429543025e-06,
+      "loss": 0.0365,
+      "step": 134
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.00704766713838941,
+      "learning_rate": 2.4122951685636674e-06,
+      "loss": 0.04,
+      "step": 135
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.006798258976708036,
+      "learning_rate": 2.104134299426832e-06,
+      "loss": 0.0392,
+      "step": 136
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 0.006811592487013504,
+      "learning_rate": 1.8164947100907238e-06,
+      "loss": 0.0396,
+      "step": 137
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.006550701891452861,
+      "learning_rate": 1.5495321624672443e-06,
+      "loss": 0.0376,
+      "step": 138
+    },
+    {
+      "epoch": 2.7800000000000002,
+      "grad_norm": 0.00620895492561466,
+      "learning_rate": 1.3033912214854482e-06,
+      "loss": 0.0393,
+      "step": 139
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.006392498446410143,
+      "learning_rate": 1.0782051768070477e-06,
+      "loss": 0.0392,
+      "step": 140
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 0.006416363205177153,
+      "learning_rate": 8.740959706477725e-07,
+      "loss": 0.0394,
+      "step": 141
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.006454293287720483,
+      "learning_rate": 6.911741317434706e-07,
+      "loss": 0.0391,
+      "step": 142
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 0.0067304916467907485,
+      "learning_rate": 5.295387154968312e-07,
+      "loss": 0.0382,
+      "step": 143
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.006489542022620059,
+      "learning_rate": 3.8927725033718553e-07,
+      "loss": 0.0386,
+      "step": 144
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.0068259349881315485,
+      "learning_rate": 2.704656903222791e-07,
+      "loss": 0.0403,
+      "step": 145
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.006969371649061031,
+      "learning_rate": 1.7316837400782604e-07,
+      "loss": 0.0408,
+      "step": 146
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 0.006100654008271577,
+      "learning_rate": 9.74379896070321e-08,
+      "loss": 0.0373,
+      "step": 147
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.006392245107970697,
+      "learning_rate": 4.331554645901737e-08,
+      "loss": 0.0379,
+      "step": 148
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 0.0065395345763724,
+      "learning_rate": 1.0830352821531442e-08,
+      "loss": 0.0401,
+      "step": 149
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.006121024784436261,
+      "learning_rate": 0.0,
+      "loss": 0.0385,
+      "step": 150
+    },
+    {
+      "epoch": 3.0,
+      "step": 150,
+      "total_flos": 112494170603520.0,
+      "train_loss": 0.06291282273828984,
+      "train_runtime": 1254.7784,
+      "train_samples_per_second": 0.956,
+      "train_steps_per_second": 0.12
+    }
+  ],
+  "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": 112494170603520.0,
+  "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 sha256:5aeb9e991d148dc8fb3400d60f977f95ebaa63a56773b80116bddc77366b13b1
+size 7224