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-250-force-022525
+  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-250-force-022525
+
+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": [
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "gate_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:bae8f0c9ea25d6cb264b168ba03e36b6ee97befb7ce5c2d4a79203bdd714e3a7
+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 +1,987 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 135,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022222222222222223,
+      "grad_norm": 0.010148976875346981,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.1826,
+      "step": 1
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 0.009652900143804658,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 0.1756,
+      "step": 2
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 0.009794367173049278,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.1788,
+      "step": 3
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.01040986980721775,
+      "learning_rate": 2.2857142857142858e-05,
+      "loss": 0.177,
+      "step": 4
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.00941020307795566,
+      "learning_rate": 2.8571428571428574e-05,
+      "loss": 0.1814,
+      "step": 5
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.010026446548467056,
+      "learning_rate": 3.4285714285714284e-05,
+      "loss": 0.1815,
+      "step": 6
+    },
+    {
+      "epoch": 0.15555555555555556,
+      "grad_norm": 0.009357055547490747,
+      "learning_rate": 4e-05,
+      "loss": 0.1743,
+      "step": 7
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.01316179358697311,
+      "learning_rate": 4.5714285714285716e-05,
+      "loss": 0.1839,
+      "step": 8
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.011404036770711537,
+      "learning_rate": 5.1428571428571436e-05,
+      "loss": 0.1738,
+      "step": 9
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.011899741387012646,
+      "learning_rate": 5.714285714285715e-05,
+      "loss": 0.1679,
+      "step": 10
+    },
+    {
+      "epoch": 0.24444444444444444,
+      "grad_norm": 0.013130790938965147,
+      "learning_rate": 6.285714285714286e-05,
+      "loss": 0.1683,
+      "step": 11
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.011960707797143826,
+      "learning_rate": 6.857142857142857e-05,
+      "loss": 0.165,
+      "step": 12
+    },
+    {
+      "epoch": 0.28888888888888886,
+      "grad_norm": 0.014314589403224253,
+      "learning_rate": 7.42857142857143e-05,
+      "loss": 0.1566,
+      "step": 13
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 0.023514521523801454,
+      "learning_rate": 8e-05,
+      "loss": 0.1534,
+      "step": 14
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.025422550167483834,
+      "learning_rate": 7.998651861214051e-05,
+      "loss": 0.1489,
+      "step": 15
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.015356073165798081,
+      "learning_rate": 7.994608353595293e-05,
+      "loss": 0.1404,
+      "step": 16
+    },
+    {
+      "epoch": 0.37777777777777777,
+      "grad_norm": 0.013349029329353128,
+      "learning_rate": 7.987872202748455e-05,
+      "loss": 0.1365,
+      "step": 17
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.011466105584548447,
+      "learning_rate": 7.978447949306646e-05,
+      "loss": 0.129,
+      "step": 18
+    },
+    {
+      "epoch": 0.4222222222222222,
+      "grad_norm": 0.010954423265976895,
+      "learning_rate": 7.966341945870666e-05,
+      "loss": 0.1204,
+      "step": 19
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.012827278030479188,
+      "learning_rate": 7.951562352726902e-05,
+      "loss": 0.1177,
+      "step": 20
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.013031892253516296,
+      "learning_rate": 7.934119132346731e-05,
+      "loss": 0.1099,
+      "step": 21
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.012987717385317626,
+      "learning_rate": 7.914024042671127e-05,
+      "loss": 0.1029,
+      "step": 22
+    },
+    {
+      "epoch": 0.5111111111111111,
+      "grad_norm": 0.012650876537582024,
+      "learning_rate": 7.89129062918499e-05,
+      "loss": 0.1017,
+      "step": 23
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.013688334914445315,
+      "learning_rate": 7.865934215786548e-05,
+      "loss": 0.0942,
+      "step": 24
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.012685353682793745,
+      "learning_rate": 7.837971894457991e-05,
+      "loss": 0.087,
+      "step": 25
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 0.012251334140438528,
+      "learning_rate": 7.807422513744279e-05,
+      "loss": 0.0866,
+      "step": 26
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.010210384711765356,
+      "learning_rate": 7.774306666047929e-05,
+      "loss": 0.0761,
+      "step": 27
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.009727432900918705,
+      "learning_rate": 7.738646673748293e-05,
+      "loss": 0.0737,
+      "step": 28
+    },
+    {
+      "epoch": 0.6444444444444445,
+      "grad_norm": 0.009974804632031459,
+      "learning_rate": 7.700466574154735e-05,
+      "loss": 0.072,
+      "step": 29
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.010606136103409193,
+      "learning_rate": 7.659792103303814e-05,
+      "loss": 0.0725,
+      "step": 30
+    },
+    {
+      "epoch": 0.6888888888888889,
+      "grad_norm": 0.009312939834117455,
+      "learning_rate": 7.616650678611401e-05,
+      "loss": 0.0657,
+      "step": 31
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.009999797765802218,
+      "learning_rate": 7.571071380391455e-05,
+      "loss": 0.062,
+      "step": 32
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.009996388519467523,
+      "learning_rate": 7.523084932253858e-05,
+      "loss": 0.0665,
+      "step": 33
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 0.008456046882503818,
+      "learning_rate": 7.472723680394576e-05,
+      "loss": 0.0622,
+      "step": 34
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.010229350256695281,
+      "learning_rate": 7.420021571792081e-05,
+      "loss": 0.0625,
+      "step": 35
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.010833149949081107,
+      "learning_rate": 7.365014131324725e-05,
+      "loss": 0.0534,
+      "step": 36
+    },
+    {
+      "epoch": 0.8222222222222222,
+      "grad_norm": 0.00991260658237493,
+      "learning_rate": 7.307738437824515e-05,
+      "loss": 0.0583,
+      "step": 37
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 0.009989329487829542,
+      "learning_rate": 7.248233099083401e-05,
+      "loss": 0.0533,
+      "step": 38
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.011634367074334458,
+      "learning_rate": 7.186538225828944e-05,
+      "loss": 0.0553,
+      "step": 39
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.0098208067680476,
+      "learning_rate": 7.122695404686912e-05,
+      "loss": 0.0483,
+      "step": 40
+    },
+    {
+      "epoch": 0.9111111111111111,
+      "grad_norm": 0.013627702881694244,
+      "learning_rate": 7.056747670148997e-05,
+      "loss": 0.0471,
+      "step": 41
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.020506980394637372,
+      "learning_rate": 6.988739475564586e-05,
+      "loss": 0.0484,
+      "step": 42
+    },
+    {
+      "epoch": 0.9555555555555556,
+      "grad_norm": 0.01717827574356156,
+      "learning_rate": 6.91871666317612e-05,
+      "loss": 0.0424,
+      "step": 43
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.015208267892398203,
+      "learning_rate": 6.846726433218241e-05,
+      "loss": 0.0383,
+      "step": 44
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.018747524684879564,
+      "learning_rate": 6.772817312101557e-05,
+      "loss": 0.0418,
+      "step": 45
+    },
+    {
+      "epoch": 1.0222222222222221,
+      "grad_norm": 0.012261829354385795,
+      "learning_rate": 6.697039119702473e-05,
+      "loss": 0.0424,
+      "step": 46
+    },
+    {
+      "epoch": 1.0444444444444445,
+      "grad_norm": 0.01356180893811529,
+      "learning_rate": 6.619442935781141e-05,
+      "loss": 0.0383,
+      "step": 47
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.017705526236978113,
+      "learning_rate": 6.540081065550154e-05,
+      "loss": 0.0333,
+      "step": 48
+    },
+    {
+      "epoch": 1.0888888888888888,
+      "grad_norm": 0.016728257058634857,
+      "learning_rate": 6.459007004417204e-05,
+      "loss": 0.0317,
+      "step": 49
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.01615093498659183,
+      "learning_rate": 6.376275401925466e-05,
+      "loss": 0.0317,
+      "step": 50
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.01480392073506929,
+      "learning_rate": 6.29194202491601e-05,
+      "loss": 0.0366,
+      "step": 51
+    },
+    {
+      "epoch": 1.1555555555555554,
+      "grad_norm": 0.01669725486973189,
+      "learning_rate": 6.206063719937084e-05,
+      "loss": 0.0309,
+      "step": 52
+    },
+    {
+      "epoch": 1.1777777777777778,
+      "grad_norm": 0.01017912718099357,
+      "learning_rate": 6.118698374925596e-05,
+      "loss": 0.0362,
+      "step": 53
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.011872210519155648,
+      "learning_rate": 6.029904880186623e-05,
+      "loss": 0.0299,
+      "step": 54
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.018088349022595537,
+      "learning_rate": 5.9397430886972675e-05,
+      "loss": 0.0334,
+      "step": 55
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 0.010389611439533196,
+      "learning_rate": 5.848273775761585e-05,
+      "loss": 0.0299,
+      "step": 56
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.007958543889706023,
+      "learning_rate": 5.755558598043824e-05,
+      "loss": 0.0273,
+      "step": 57
+    },
+    {
+      "epoch": 1.2888888888888888,
+      "grad_norm": 0.021835894371233705,
+      "learning_rate": 5.661660052007547e-05,
+      "loss": 0.029,
+      "step": 58
+    },
+    {
+      "epoch": 1.3111111111111111,
+      "grad_norm": 0.01570676870430943,
+      "learning_rate": 5.566641431788682e-05,
+      "loss": 0.0343,
+      "step": 59
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.013446483551405763,
+      "learning_rate": 5.4705667865308805e-05,
+      "loss": 0.033,
+      "step": 60
+    },
+    {
+      "epoch": 1.3555555555555556,
+      "grad_norm": 0.012118052335476718,
+      "learning_rate": 5.373500877211955e-05,
+      "loss": 0.0301,
+      "step": 61
+    },
+    {
+      "epoch": 1.3777777777777778,
+      "grad_norm": 0.012215850200500552,
+      "learning_rate": 5.275509132990476e-05,
+      "loss": 0.0306,
+      "step": 62
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.005847246928013908,
+      "learning_rate": 5.176657607101986e-05,
+      "loss": 0.03,
+      "step": 63
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 0.00691959170426608,
+      "learning_rate": 5.0770129323345385e-05,
+      "loss": 0.0274,
+      "step": 64
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.007502101592514973,
+      "learning_rate": 4.976642276113566e-05,
+      "loss": 0.031,
+      "step": 65
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.0066123181847872895,
+      "learning_rate": 4.87561329522638e-05,
+      "loss": 0.0325,
+      "step": 66
+    },
+    {
+      "epoch": 1.488888888888889,
+      "grad_norm": 0.007228306517629785,
+      "learning_rate": 4.773994090216799e-05,
+      "loss": 0.0307,
+      "step": 67
+    },
+    {
+      "epoch": 1.511111111111111,
+      "grad_norm": 0.0057910364139641644,
+      "learning_rate": 4.6718531594806595e-05,
+      "loss": 0.0304,
+      "step": 68
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.004919645221567056,
+      "learning_rate": 4.5692593530931416e-05,
+      "loss": 0.0303,
+      "step": 69
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.0071083220932738715,
+      "learning_rate": 4.466281826399037e-05,
+      "loss": 0.0303,
+      "step": 70
+    },
+    {
+      "epoch": 1.5777777777777777,
+      "grad_norm": 0.004773951051897729,
+      "learning_rate": 4.3629899933972576e-05,
+      "loss": 0.0315,
+      "step": 71
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.005700131420540827,
+      "learning_rate": 4.259453479950972e-05,
+      "loss": 0.0293,
+      "step": 72
+    },
+    {
+      "epoch": 1.6222222222222222,
+      "grad_norm": 0.00875664482311268,
+      "learning_rate": 4.1557420768549515e-05,
+      "loss": 0.0291,
+      "step": 73
+    },
+    {
+      "epoch": 1.6444444444444444,
+      "grad_norm": 0.005174150018233112,
+      "learning_rate": 4.051925692791724e-05,
+      "loss": 0.0315,
+      "step": 74
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.005398094296644888,
+      "learning_rate": 3.9480743072082775e-05,
+      "loss": 0.0278,
+      "step": 75
+    },
+    {
+      "epoch": 1.6888888888888889,
+      "grad_norm": 0.005449378420482257,
+      "learning_rate": 3.84425792314505e-05,
+      "loss": 0.0293,
+      "step": 76
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 0.005693831978067397,
+      "learning_rate": 3.7405465200490277e-05,
+      "loss": 0.0298,
+      "step": 77
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.004882722471540408,
+      "learning_rate": 3.637010006602743e-05,
+      "loss": 0.0284,
+      "step": 78
+    },
+    {
+      "epoch": 1.7555555555555555,
+      "grad_norm": 0.005072188109777626,
+      "learning_rate": 3.533718173600964e-05,
+      "loss": 0.0273,
+      "step": 79
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.005204573882446381,
+      "learning_rate": 3.4307406469068604e-05,
+      "loss": 0.0286,
+      "step": 80
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.0054230215882230745,
+      "learning_rate": 3.3281468405193405e-05,
+      "loss": 0.0313,
+      "step": 81
+    },
+    {
+      "epoch": 1.8222222222222222,
+      "grad_norm": 0.005299822153520074,
+      "learning_rate": 3.2260059097832015e-05,
+      "loss": 0.0306,
+      "step": 82
+    },
+    {
+      "epoch": 1.8444444444444446,
+      "grad_norm": 0.005385640521568125,
+      "learning_rate": 3.124386704773621e-05,
+      "loss": 0.0265,
+      "step": 83
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.008049495791548384,
+      "learning_rate": 3.0233577238864353e-05,
+      "loss": 0.0324,
+      "step": 84
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.0063768040227751704,
+      "learning_rate": 2.922987067665462e-05,
+      "loss": 0.0325,
+      "step": 85
+    },
+    {
+      "epoch": 1.911111111111111,
+      "grad_norm": 0.0054793736206258685,
+      "learning_rate": 2.8233423928980152e-05,
+      "loss": 0.0376,
+      "step": 86
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.010995484662127622,
+      "learning_rate": 2.7244908670095262e-05,
+      "loss": 0.0246,
+      "step": 87
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 0.005711182758377403,
+      "learning_rate": 2.6264991227880474e-05,
+      "loss": 0.0286,
+      "step": 88
+    },
+    {
+      "epoch": 1.9777777777777779,
+      "grad_norm": 0.006124402047670869,
+      "learning_rate": 2.5294332134691195e-05,
+      "loss": 0.0274,
+      "step": 89
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.005519208351091231,
+      "learning_rate": 2.4333585682113192e-05,
+      "loss": 0.0262,
+      "step": 90
+    },
+    {
+      "epoch": 2.022222222222222,
+      "grad_norm": 0.006508287494590022,
+      "learning_rate": 2.338339947992455e-05,
+      "loss": 0.027,
+      "step": 91
+    },
+    {
+      "epoch": 2.0444444444444443,
+      "grad_norm": 0.005260011382567675,
+      "learning_rate": 2.2444414019561775e-05,
+      "loss": 0.0241,
+      "step": 92
+    },
+    {
+      "epoch": 2.066666666666667,
+      "grad_norm": 0.006399714358794207,
+      "learning_rate": 2.151726224238415e-05,
+      "loss": 0.0283,
+      "step": 93
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 0.005521374324233929,
+      "learning_rate": 2.0602569113027338e-05,
+      "loss": 0.0287,
+      "step": 94
+    },
+    {
+      "epoch": 2.111111111111111,
+      "grad_norm": 0.0050677729572333585,
+      "learning_rate": 1.970095119813378e-05,
+      "loss": 0.0274,
+      "step": 95
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.005409586955687618,
+      "learning_rate": 1.8813016250744068e-05,
+      "loss": 0.0306,
+      "step": 96
+    },
+    {
+      "epoch": 2.1555555555555554,
+      "grad_norm": 0.005070467422125071,
+      "learning_rate": 1.7939362800629178e-05,
+      "loss": 0.0276,
+      "step": 97
+    },
+    {
+      "epoch": 2.1777777777777776,
+      "grad_norm": 0.005231531992678733,
+      "learning_rate": 1.7080579750839925e-05,
+      "loss": 0.0287,
+      "step": 98
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.005402811260897175,
+      "learning_rate": 1.6237245980745352e-05,
+      "loss": 0.0331,
+      "step": 99
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.00488307202579084,
+      "learning_rate": 1.540992995582797e-05,
+      "loss": 0.0278,
+      "step": 100
+    },
+    {
+      "epoch": 2.2444444444444445,
+      "grad_norm": 0.006002313824987473,
+      "learning_rate": 1.4599189344498461e-05,
+      "loss": 0.0284,
+      "step": 101
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.005586203561151411,
+      "learning_rate": 1.3805570642188602e-05,
+      "loss": 0.0276,
+      "step": 102
+    },
+    {
+      "epoch": 2.2888888888888888,
+      "grad_norm": 0.005587100815333487,
+      "learning_rate": 1.3029608802975284e-05,
+      "loss": 0.0266,
+      "step": 103
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 0.004864472059960341,
+      "learning_rate": 1.2271826878984454e-05,
+      "loss": 0.027,
+      "step": 104
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.005229755034468365,
+      "learning_rate": 1.1532735667817599e-05,
+      "loss": 0.026,
+      "step": 105
+    },
+    {
+      "epoch": 2.3555555555555556,
+      "grad_norm": 0.005420694162246136,
+      "learning_rate": 1.08128333682388e-05,
+      "loss": 0.0243,
+      "step": 106
+    },
+    {
+      "epoch": 2.3777777777777778,
+      "grad_norm": 0.005204280383882613,
+      "learning_rate": 1.0112605244354147e-05,
+      "loss": 0.027,
+      "step": 107
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.0064267369108633975,
+      "learning_rate": 9.432523298510041e-06,
+      "loss": 0.0273,
+      "step": 108
+    },
+    {
+      "epoch": 2.422222222222222,
+      "grad_norm": 0.005772072518410093,
+      "learning_rate": 8.773045953130878e-06,
+      "loss": 0.0261,
+      "step": 109
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.00510877146569064,
+      "learning_rate": 8.13461774171056e-06,
+      "loss": 0.0301,
+      "step": 110
+    },
+    {
+      "epoch": 2.466666666666667,
+      "grad_norm": 0.005121955993714767,
+      "learning_rate": 7.517669009166009e-06,
+      "loss": 0.0248,
+      "step": 111
+    },
+    {
+      "epoch": 2.488888888888889,
+      "grad_norm": 0.005500370304620924,
+      "learning_rate": 6.922615621754856e-06,
+      "loss": 0.0309,
+      "step": 112
+    },
+    {
+      "epoch": 2.511111111111111,
+      "grad_norm": 0.0050844873377091674,
+      "learning_rate": 6.349858686752748e-06,
+      "loss": 0.0248,
+      "step": 113
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.005357622522152558,
+      "learning_rate": 5.7997842820792e-06,
+      "loss": 0.0291,
+      "step": 114
+    },
+    {
+      "epoch": 2.5555555555555554,
+      "grad_norm": 0.005216843049432994,
+      "learning_rate": 5.2727631960542495e-06,
+      "loss": 0.0258,
+      "step": 115
+    },
+    {
+      "epoch": 2.5777777777777775,
+      "grad_norm": 0.007135561025778617,
+      "learning_rate": 4.769150677461434e-06,
+      "loss": 0.0309,
+      "step": 116
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.005241921591841645,
+      "learning_rate": 4.289286196085454e-06,
+      "loss": 0.0302,
+      "step": 117
+    },
+    {
+      "epoch": 2.6222222222222222,
+      "grad_norm": 0.005357365507350075,
+      "learning_rate": 3.833493213885993e-06,
+      "loss": 0.028,
+      "step": 118
+    },
+    {
+      "epoch": 2.6444444444444444,
+      "grad_norm": 0.0052851473311310085,
+      "learning_rate": 3.4020789669618747e-06,
+      "loss": 0.0249,
+      "step": 119
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.005268369057289017,
+      "learning_rate": 2.9953342584526513e-06,
+      "loss": 0.0254,
+      "step": 120
+    },
+    {
+      "epoch": 2.688888888888889,
+      "grad_norm": 0.004858000947772199,
+      "learning_rate": 2.613533262517072e-06,
+      "loss": 0.0241,
+      "step": 121
+    },
+    {
+      "epoch": 2.7111111111111112,
+      "grad_norm": 0.005642695680648904,
+      "learning_rate": 2.256933339520724e-06,
+      "loss": 0.0273,
+      "step": 122
+    },
+    {
+      "epoch": 2.7333333333333334,
+      "grad_norm": 0.005083556809229362,
+      "learning_rate": 1.9257748625572193e-06,
+      "loss": 0.0279,
+      "step": 123
+    },
+    {
+      "epoch": 2.7555555555555555,
+      "grad_norm": 0.005218766530307722,
+      "learning_rate": 1.6202810554201099e-06,
+      "loss": 0.0247,
+      "step": 124
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.005432173058928109,
+      "learning_rate": 1.3406578421345206e-06,
+      "loss": 0.0273,
+      "step": 125
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.0052620641642096184,
+      "learning_rate": 1.0870937081501088e-06,
+      "loss": 0.0269,
+      "step": 126
+    },
+    {
+      "epoch": 2.822222222222222,
+      "grad_norm": 0.00487619866740712,
+      "learning_rate": 8.597595732887387e-07,
+      "loss": 0.0237,
+      "step": 127
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "grad_norm": 0.005211071045457219,
+      "learning_rate": 6.588086765327051e-07,
+      "loss": 0.0284,
+      "step": 128
+    },
+    {
+      "epoch": 2.8666666666666667,
+      "grad_norm": 0.004667081364681297,
+      "learning_rate": 4.843764727309941e-07,
+      "loss": 0.0246,
+      "step": 129
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.004885379080378288,
+      "learning_rate": 3.365805412933476e-07,
+      "loss": 0.0305,
+      "step": 130
+    },
+    {
+      "epoch": 2.911111111111111,
+      "grad_norm": 0.005089087399007557,
+      "learning_rate": 2.1552050693354643e-07,
+      "loss": 0.027,
+      "step": 131
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.005522925310639564,
+      "learning_rate": 1.212779725154656e-07,
+      "loss": 0.0278,
+      "step": 132
+    },
+    {
+      "epoch": 2.9555555555555557,
+      "grad_norm": 0.005274259131866139,
+      "learning_rate": 5.3916464047079064e-08,
+      "loss": 0.0321,
+      "step": 133
+    },
+    {
+      "epoch": 2.977777777777778,
+      "grad_norm": 0.004788181394019615,
+      "learning_rate": 1.3481387859504147e-08,
+      "loss": 0.0283,
+      "step": 134
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.004951466566335892,
+      "learning_rate": 0.0,
+      "loss": 0.0268,
+      "step": 135
+    },
+    {
+      "epoch": 3.0,
+      "step": 135,
+      "total_flos": 75845759008768.0,
+      "train_loss": 0.055722353069318664,
+      "train_runtime": 807.1106,
+      "train_samples_per_second": 1.338,
+      "train_steps_per_second": 0.167
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 135,
+  "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": 75845759008768.0,
+  "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:e6c7b6ce822b109d3f050f8569bb2952d67d65b061589b0fe07274d475c9def6
+size 7224