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_step2_3augs_buffer_short
+  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_step2_3augs_buffer_short
+
+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: 2
+- eval_batch_size: 1
+- seed: 100
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 16
+- 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: 2
+
+### 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": [
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "k_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:c7a369f6454c2c957a70aee80d022885a9916166eb43f445c23c9da567b1eb9e
+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:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

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 +1,574 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 76,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": 0.011518988620826731,
+      "learning_rate": 1e-05,
+      "loss": 0.1758,
+      "step": 1
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 0.011769415675267096,
+      "learning_rate": 2e-05,
+      "loss": 0.1755,
+      "step": 2
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 0.012019294923116772,
+      "learning_rate": 3.0000000000000004e-05,
+      "loss": 0.1768,
+      "step": 3
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 0.011438929874712248,
+      "learning_rate": 4e-05,
+      "loss": 0.174,
+      "step": 4
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 0.012678409461035527,
+      "learning_rate": 5e-05,
+      "loss": 0.1776,
+      "step": 5
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 0.013302694501158712,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 0.1722,
+      "step": 6
+    },
+    {
+      "epoch": 0.18421052631578946,
+      "grad_norm": 0.015877560046165782,
+      "learning_rate": 7.000000000000001e-05,
+      "loss": 0.1717,
+      "step": 7
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.017316329988102695,
+      "learning_rate": 8e-05,
+      "loss": 0.1655,
+      "step": 8
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 0.01761728040990777,
+      "learning_rate": 7.995731899209491e-05,
+      "loss": 0.1615,
+      "step": 9
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 0.017422282759872943,
+      "learning_rate": 7.982936705180139e-05,
+      "loss": 0.1554,
+      "step": 10
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 0.02050212432466269,
+      "learning_rate": 7.961641723500821e-05,
+      "loss": 0.1502,
+      "step": 11
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.020386102383746066,
+      "learning_rate": 7.931892398735608e-05,
+      "loss": 0.1455,
+      "step": 12
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 0.017501699031872063,
+      "learning_rate": 7.893752217442773e-05,
+      "loss": 0.1391,
+      "step": 13
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 0.01644790453050047,
+      "learning_rate": 7.847302572691277e-05,
+      "loss": 0.1379,
+      "step": 14
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 0.016205477891979105,
+      "learning_rate": 7.792642590363864e-05,
+      "loss": 0.1318,
+      "step": 15
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.017772585025772586,
+      "learning_rate": 7.729888917617424e-05,
+      "loss": 0.1292,
+      "step": 16
+    },
+    {
+      "epoch": 0.4473684210526316,
+      "grad_norm": 0.01437597741326583,
+      "learning_rate": 7.659175473952085e-05,
+      "loss": 0.1232,
+      "step": 17
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.012880938282018417,
+      "learning_rate": 7.58065316542025e-05,
+      "loss": 0.119,
+      "step": 18
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.011093246487293535,
+      "learning_rate": 7.494489562585479e-05,
+      "loss": 0.1172,
+      "step": 19
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.010467102848930952,
+      "learning_rate": 7.400868542918457e-05,
+      "loss": 0.1114,
+      "step": 20
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 0.010047970328554336,
+      "learning_rate": 7.299989898393209e-05,
+      "loss": 0.1072,
+      "step": 21
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.009892044194784507,
+      "learning_rate": 7.192068909120959e-05,
+      "loss": 0.1026,
+      "step": 22
+    },
+    {
+      "epoch": 0.6052631578947368,
+      "grad_norm": 0.00977895435289584,
+      "learning_rate": 7.077335883931516e-05,
+      "loss": 0.1003,
+      "step": 23
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.009536071160931239,
+      "learning_rate": 6.956035668882637e-05,
+      "loss": 0.0963,
+      "step": 24
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.009733333762799204,
+      "learning_rate": 6.828427124746191e-05,
+      "loss": 0.0913,
+      "step": 25
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.009570441521026768,
+      "learning_rate": 6.69478257458623e-05,
+      "loss": 0.0891,
+      "step": 26
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 0.01000020090090365,
+      "learning_rate": 6.555387222607845e-05,
+      "loss": 0.0829,
+      "step": 27
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.00996936468337858,
+      "learning_rate": 6.410538545517026e-05,
+      "loss": 0.0807,
+      "step": 28
+    },
+    {
+      "epoch": 0.7631578947368421,
+      "grad_norm": 0.00953954885336217,
+      "learning_rate": 6.260545657690369e-05,
+      "loss": 0.0805,
+      "step": 29
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.009088232136551395,
+      "learning_rate": 6.105728651509424e-05,
+      "loss": 0.0768,
+      "step": 30
+    },
+    {
+      "epoch": 0.8157894736842105,
+      "grad_norm": 0.008652738141347285,
+      "learning_rate": 5.946417914267425e-05,
+      "loss": 0.074,
+      "step": 31
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.007369187149441024,
+      "learning_rate": 5.782953423106154e-05,
+      "loss": 0.0726,
+      "step": 32
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 0.007130681951299134,
+      "learning_rate": 5.61568401948758e-05,
+      "loss": 0.0719,
+      "step": 33
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.007528001216497669,
+      "learning_rate": 5.444966664748613e-05,
+      "loss": 0.0706,
+      "step": 34
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 0.008072156901279035,
+      "learning_rate": 5.271165678327607e-05,
+      "loss": 0.0707,
+      "step": 35
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.007829567280354091,
+      "learning_rate": 5.0946519602883326e-05,
+      "loss": 0.0669,
+      "step": 36
+    },
+    {
+      "epoch": 0.9736842105263158,
+      "grad_norm": 0.00799333236262416,
+      "learning_rate": 4.9158021998005366e-05,
+      "loss": 0.0661,
+      "step": 37
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.00816214803013346,
+      "learning_rate": 4.734998071266282e-05,
+      "loss": 0.063,
+      "step": 38
+    },
+    {
+      "epoch": 1.0263157894736843,
+      "grad_norm": 0.007720443171687867,
+      "learning_rate": 4.552625419807529e-05,
+      "loss": 0.0608,
+      "step": 39
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.008122893547240941,
+      "learning_rate": 4.369073437853208e-05,
+      "loss": 0.0608,
+      "step": 40
+    },
+    {
+      "epoch": 1.0789473684210527,
+      "grad_norm": 0.008220632700161948,
+      "learning_rate": 4.184733834582959e-05,
+      "loss": 0.0586,
+      "step": 41
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.008642996154857054,
+      "learning_rate": 4e-05,
+      "loss": 0.0618,
+      "step": 42
+    },
+    {
+      "epoch": 1.131578947368421,
+      "grad_norm": 0.008332657542430085,
+      "learning_rate": 3.815266165417043e-05,
+      "loss": 0.0574,
+      "step": 43
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.008567867343178283,
+      "learning_rate": 3.630926562146792e-05,
+      "loss": 0.0589,
+      "step": 44
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "grad_norm": 0.008265949758336088,
+      "learning_rate": 3.447374580192473e-05,
+      "loss": 0.0543,
+      "step": 45
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.008431332834549176,
+      "learning_rate": 3.2650019287337184e-05,
+      "loss": 0.0536,
+      "step": 46
+    },
+    {
+      "epoch": 1.236842105263158,
+      "grad_norm": 0.007829990670514665,
+      "learning_rate": 3.084197800199465e-05,
+      "loss": 0.0531,
+      "step": 47
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.00805463741954765,
+      "learning_rate": 2.905348039711669e-05,
+      "loss": 0.0532,
+      "step": 48
+    },
+    {
+      "epoch": 1.2894736842105263,
+      "grad_norm": 0.007944851951870653,
+      "learning_rate": 2.728834321672394e-05,
+      "loss": 0.0529,
+      "step": 49
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.00787719509680645,
+      "learning_rate": 2.5550333352513885e-05,
+      "loss": 0.051,
+      "step": 50
+    },
+    {
+      "epoch": 1.3421052631578947,
+      "grad_norm": 0.007689730911636538,
+      "learning_rate": 2.3843159805124207e-05,
+      "loss": 0.0499,
+      "step": 51
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.008145577867986397,
+      "learning_rate": 2.2170465768938473e-05,
+      "loss": 0.0497,
+      "step": 52
+    },
+    {
+      "epoch": 1.3947368421052633,
+      "grad_norm": 0.007765854028854914,
+      "learning_rate": 2.0535820857325755e-05,
+      "loss": 0.0488,
+      "step": 53
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.010541614489525645,
+      "learning_rate": 1.8942713484905762e-05,
+      "loss": 0.05,
+      "step": 54
+    },
+    {
+      "epoch": 1.4473684210526316,
+      "grad_norm": 0.009377352769384973,
+      "learning_rate": 1.7394543423096327e-05,
+      "loss": 0.0504,
+      "step": 55
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.007879030184576382,
+      "learning_rate": 1.589461454482975e-05,
+      "loss": 0.0485,
+      "step": 56
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.008528311766387752,
+      "learning_rate": 1.4446127773921559e-05,
+      "loss": 0.0506,
+      "step": 57
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.0076161967841271135,
+      "learning_rate": 1.3052174254137713e-05,
+      "loss": 0.0486,
+      "step": 58
+    },
+    {
+      "epoch": 1.5526315789473686,
+      "grad_norm": 0.0069022846350392285,
+      "learning_rate": 1.1715728752538103e-05,
+      "loss": 0.0469,
+      "step": 59
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.00963107640357555,
+      "learning_rate": 1.0439643311173642e-05,
+      "loss": 0.0488,
+      "step": 60
+    },
+    {
+      "epoch": 1.6052631578947367,
+      "grad_norm": 0.006604996990410402,
+      "learning_rate": 9.226641160684843e-06,
+      "loss": 0.0484,
+      "step": 61
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.0059879956487925235,
+      "learning_rate": 8.07931090879042e-06,
+      "loss": 0.0461,
+      "step": 62
+    },
+    {
+      "epoch": 1.6578947368421053,
+      "grad_norm": 0.0061371313058644255,
+      "learning_rate": 7.000101016067913e-06,
+      "loss": 0.0454,
+      "step": 63
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.007073804479577813,
+      "learning_rate": 5.991314570815441e-06,
+      "loss": 0.049,
+      "step": 64
+    },
+    {
+      "epoch": 1.7105263157894737,
+      "grad_norm": 0.006925567210585072,
+      "learning_rate": 5.055104374145221e-06,
+      "loss": 0.0471,
+      "step": 65
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.00679527298679942,
+      "learning_rate": 4.193468345797511e-06,
+      "loss": 0.0464,
+      "step": 66
+    },
+    {
+      "epoch": 1.763157894736842,
+      "grad_norm": 0.005915070559407378,
+      "learning_rate": 3.4082452604791594e-06,
+      "loss": 0.0449,
+      "step": 67
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.0065205977736393144,
+      "learning_rate": 2.7011108238257723e-06,
+      "loss": 0.0471,
+      "step": 68
+    },
+    {
+      "epoch": 1.8157894736842106,
+      "grad_norm": 0.006260173837861193,
+      "learning_rate": 2.073574096361366e-06,
+      "loss": 0.0486,
+      "step": 69
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.006245995730039592,
+      "learning_rate": 1.5269742730872384e-06,
+      "loss": 0.0473,
+      "step": 70
+    },
+    {
+      "epoch": 1.868421052631579,
+      "grad_norm": 0.00654850126698062,
+      "learning_rate": 1.0624778255722857e-06,
+      "loss": 0.0477,
+      "step": 71
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.008481528591018958,
+      "learning_rate": 6.810760126439287e-07,
+      "loss": 0.0488,
+      "step": 72
+    },
+    {
+      "epoch": 1.9210526315789473,
+      "grad_norm": 0.006002865737944914,
+      "learning_rate": 3.835827649917967e-07,
+      "loss": 0.0456,
+      "step": 73
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.0061084652605397196,
+      "learning_rate": 1.706329481986213e-07,
+      "loss": 0.0484,
+      "step": 74
+    },
+    {
+      "epoch": 1.973684210526316,
+      "grad_norm": 0.006251582720819486,
+      "learning_rate": 4.268100790510321e-08,
+      "loss": 0.0461,
+      "step": 75
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.007872514188147876,
+      "learning_rate": 0.0,
+      "loss": 0.0473,
+      "step": 76
+    },
+    {
+      "epoch": 2.0,
+      "step": 76,
+      "total_flos": 114338546712576.0,
+      "train_loss": 0.08416653395091232,
+      "train_runtime": 2655.6769,
+      "train_samples_per_second": 0.451,
+      "train_steps_per_second": 0.029
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 76,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 114338546712576.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c130579a2034ed763c63e140e95fc2a14b4b5116856dd3e2208548bf39c063dd
+size 7288