Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: peft
+license: mit
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: models-3k-forced-p301-final-022825-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. -->
+
+# models-3k-forced-p301-final-022825-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: 787487
+- 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: 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": [
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "gate_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:f0fff0d4a2366267793797d2dc5b6a5914219c19340b12243839f55c1c7bec42
+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 +1,742 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.016487884763607193,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1774,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.014845367883925294,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.1727,
+      "step": 2
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.014866681872690659,
+      "learning_rate": 2.4e-05,
+      "loss": 0.1689,
+      "step": 3
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.015228106532467634,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.172,
+      "step": 4
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.015664751999139453,
+      "learning_rate": 4e-05,
+      "loss": 0.169,
+      "step": 5
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.01808065340125554,
+      "learning_rate": 4.8e-05,
+      "loss": 0.1726,
+      "step": 6
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.018901368682318707,
+      "learning_rate": 5.6e-05,
+      "loss": 0.166,
+      "step": 7
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.021570511577008615,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.1654,
+      "step": 8
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.02166324409497385,
+      "learning_rate": 7.2e-05,
+      "loss": 0.1582,
+      "step": 9
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.019350239992064724,
+      "learning_rate": 8e-05,
+      "loss": 0.1532,
+      "step": 10
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.018196865093959902,
+      "learning_rate": 7.997563308076384e-05,
+      "loss": 0.1466,
+      "step": 11
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.02646127799541148,
+      "learning_rate": 7.990256201039297e-05,
+      "loss": 0.14,
+      "step": 12
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.029518241025129368,
+      "learning_rate": 7.978087581473094e-05,
+      "loss": 0.1438,
+      "step": 13
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.02778464435986613,
+      "learning_rate": 7.961072274966282e-05,
+      "loss": 0.1409,
+      "step": 14
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.02624687095963232,
+      "learning_rate": 7.939231012048833e-05,
+      "loss": 0.1346,
+      "step": 15
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.019416121783048385,
+      "learning_rate": 7.912590402935223e-05,
+      "loss": 0.1306,
+      "step": 16
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.018323801110041928,
+      "learning_rate": 7.881182905103986e-05,
+      "loss": 0.1247,
+      "step": 17
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.013747596718717161,
+      "learning_rate": 7.845046783753276e-05,
+      "loss": 0.123,
+      "step": 18
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.013363373953051648,
+      "learning_rate": 7.804226065180615e-05,
+      "loss": 0.1154,
+      "step": 19
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.013063493439990442,
+      "learning_rate": 7.758770483143634e-05,
+      "loss": 0.1155,
+      "step": 20
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.012349491312784728,
+      "learning_rate": 7.70873541826715e-05,
+      "loss": 0.1135,
+      "step": 21
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.013659255251571547,
+      "learning_rate": 7.654181830570404e-05,
+      "loss": 0.1083,
+      "step": 22
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.012847819928590874,
+      "learning_rate": 7.595176185196669e-05,
+      "loss": 0.1058,
+      "step": 23
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.012497288341258475,
+      "learning_rate": 7.531790371435709e-05,
+      "loss": 0.1009,
+      "step": 24
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.012347577755852105,
+      "learning_rate": 7.464101615137756e-05,
+      "loss": 0.0936,
+      "step": 25
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.011863308575622778,
+      "learning_rate": 7.392192384625704e-05,
+      "loss": 0.0885,
+      "step": 26
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.011325196807598156,
+      "learning_rate": 7.316150290220167e-05,
+      "loss": 0.0828,
+      "step": 27
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.010667999986691448,
+      "learning_rate": 7.236067977499791e-05,
+      "loss": 0.0802,
+      "step": 28
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.010920255066757836,
+      "learning_rate": 7.152043014426888e-05,
+      "loss": 0.0784,
+      "step": 29
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.012547111719013246,
+      "learning_rate": 7.064177772475912e-05,
+      "loss": 0.0777,
+      "step": 30
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.010557031727861984,
+      "learning_rate": 6.972579301909577e-05,
+      "loss": 0.0746,
+      "step": 31
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.009279976822386049,
+      "learning_rate": 6.877359201354606e-05,
+      "loss": 0.072,
+      "step": 32
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.008813054398509332,
+      "learning_rate": 6.778633481835989e-05,
+      "loss": 0.0695,
+      "step": 33
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.00856466500098789,
+      "learning_rate": 6.676522425435433e-05,
+      "loss": 0.0707,
+      "step": 34
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.009524587476392114,
+      "learning_rate": 6.571150438746157e-05,
+      "loss": 0.0731,
+      "step": 35
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.011090829934344763,
+      "learning_rate": 6.462645901302633e-05,
+      "loss": 0.0707,
+      "step": 36
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.009807994526445001,
+      "learning_rate": 6.351141009169893e-05,
+      "loss": 0.0669,
+      "step": 37
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.009969709651377192,
+      "learning_rate": 6.236771613882987e-05,
+      "loss": 0.0656,
+      "step": 38
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.010275734888591436,
+      "learning_rate": 6.11967705693282e-05,
+      "loss": 0.067,
+      "step": 39
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.009562676311749493,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 0.0677,
+      "step": 40
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.03147285301509033,
+      "learning_rate": 5.877886251143564e-05,
+      "loss": 0.0672,
+      "step": 41
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.008526948696477715,
+      "learning_rate": 5.75348458715631e-05,
+      "loss": 0.0646,
+      "step": 42
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.008887793586150342,
+      "learning_rate": 5.626946572303202e-05,
+      "loss": 0.07,
+      "step": 43
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.009254855591640751,
+      "learning_rate": 5.4984263736636494e-05,
+      "loss": 0.0638,
+      "step": 44
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.00978636343331719,
+      "learning_rate": 5.368080573302676e-05,
+      "loss": 0.0632,
+      "step": 45
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.016124658786887517,
+      "learning_rate": 5.23606797749979e-05,
+      "loss": 0.0599,
+      "step": 46
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.009796899093702604,
+      "learning_rate": 5.102549423267997e-05,
+      "loss": 0.0563,
+      "step": 47
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.009239841244895877,
+      "learning_rate": 4.967687582398671e-05,
+      "loss": 0.0632,
+      "step": 48
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.00962077551741907,
+      "learning_rate": 4.831646763271037e-05,
+      "loss": 0.0597,
+      "step": 49
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.010274378649241724,
+      "learning_rate": 4.694592710667723e-05,
+      "loss": 0.0615,
+      "step": 50
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.011240123020720501,
+      "learning_rate": 4.556692403840262e-05,
+      "loss": 0.0613,
+      "step": 51
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.009704156691054655,
+      "learning_rate": 4.418113853070614e-05,
+      "loss": 0.0548,
+      "step": 52
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.00986032816961704,
+      "learning_rate": 4.2790258949765014e-05,
+      "loss": 0.0564,
+      "step": 53
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.010035199810597537,
+      "learning_rate": 4.139597986810005e-05,
+      "loss": 0.0537,
+      "step": 54
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.010849210513759658,
+      "learning_rate": 4e-05,
+      "loss": 0.0551,
+      "step": 55
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.010706188973841822,
+      "learning_rate": 3.860402013189998e-05,
+      "loss": 0.0544,
+      "step": 56
+    },
+    {
+      "epoch": 1.1400000000000001,
+      "grad_norm": 0.009897357266282165,
+      "learning_rate": 3.720974105023499e-05,
+      "loss": 0.0529,
+      "step": 57
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.010836056701195912,
+      "learning_rate": 3.581886146929387e-05,
+      "loss": 0.0514,
+      "step": 58
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.010515705016426754,
+      "learning_rate": 3.44330759615974e-05,
+      "loss": 0.0516,
+      "step": 59
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.011966630530366793,
+      "learning_rate": 3.305407289332279e-05,
+      "loss": 0.0553,
+      "step": 60
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.01108501750287348,
+      "learning_rate": 3.168353236728964e-05,
+      "loss": 0.0532,
+      "step": 61
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.010620843427123319,
+      "learning_rate": 3.0323124176013297e-05,
+      "loss": 0.0537,
+      "step": 62
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.010613269991184194,
+      "learning_rate": 2.8974505767320037e-05,
+      "loss": 0.0499,
+      "step": 63
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.01049430895351889,
+      "learning_rate": 2.7639320225002108e-05,
+      "loss": 0.0499,
+      "step": 64
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.010875433380962772,
+      "learning_rate": 2.6319194266973256e-05,
+      "loss": 0.0493,
+      "step": 65
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.011152762428569843,
+      "learning_rate": 2.501573626336352e-05,
+      "loss": 0.0538,
+      "step": 66
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.00987053050873229,
+      "learning_rate": 2.3730534276968e-05,
+      "loss": 0.0489,
+      "step": 67
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.010227567735559962,
+      "learning_rate": 2.24651541284369e-05,
+      "loss": 0.049,
+      "step": 68
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.01037359456896153,
+      "learning_rate": 2.122113748856438e-05,
+      "loss": 0.0505,
+      "step": 69
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.009617488003825355,
+      "learning_rate": 2.0000000000000012e-05,
+      "loss": 0.0482,
+      "step": 70
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.011681410732130271,
+      "learning_rate": 1.880322943067181e-05,
+      "loss": 0.0481,
+      "step": 71
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.010775762677089275,
+      "learning_rate": 1.7632283861170135e-05,
+      "loss": 0.0482,
+      "step": 72
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.010363138201033269,
+      "learning_rate": 1.648858990830108e-05,
+      "loss": 0.0503,
+      "step": 73
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.009948743998699395,
+      "learning_rate": 1.537354098697367e-05,
+      "loss": 0.0521,
+      "step": 74
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.009514745914022151,
+      "learning_rate": 1.4288495612538427e-05,
+      "loss": 0.0477,
+      "step": 75
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.009964877308242578,
+      "learning_rate": 1.3234775745645684e-05,
+      "loss": 0.0497,
+      "step": 76
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.009979038800338326,
+      "learning_rate": 1.2213665181640106e-05,
+      "loss": 0.0496,
+      "step": 77
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.010143481514708248,
+      "learning_rate": 1.1226407986453963e-05,
+      "loss": 0.0471,
+      "step": 78
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.009553312874527112,
+      "learning_rate": 1.0274206980904226e-05,
+      "loss": 0.0463,
+      "step": 79
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.010009991503113444,
+      "learning_rate": 9.358222275240884e-06,
+      "loss": 0.0497,
+      "step": 80
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.010018599617204103,
+      "learning_rate": 8.479569855731125e-06,
+      "loss": 0.0527,
+      "step": 81
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.009620097241508939,
+      "learning_rate": 7.639320225002106e-06,
+      "loss": 0.0509,
+      "step": 82
+    },
+    {
+      "epoch": 1.6600000000000001,
+      "grad_norm": 0.009475557822185617,
+      "learning_rate": 6.838497097798336e-06,
+      "loss": 0.0485,
+      "step": 83
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.009870281539127288,
+      "learning_rate": 6.078076153742962e-06,
+      "loss": 0.0516,
+      "step": 84
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.009887175976315332,
+      "learning_rate": 5.358983848622452e-06,
+      "loss": 0.0486,
+      "step": 85
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.0092370901917722,
+      "learning_rate": 4.6820962856429205e-06,
+      "loss": 0.0485,
+      "step": 86
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.01010652916035051,
+      "learning_rate": 4.048238148033328e-06,
+      "loss": 0.0487,
+      "step": 87
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.008995779455639702,
+      "learning_rate": 3.458181694295961e-06,
+      "loss": 0.0477,
+      "step": 88
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.010042965977521374,
+      "learning_rate": 2.9126458173285077e-06,
+      "loss": 0.0497,
+      "step": 89
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.009433474933528755,
+      "learning_rate": 2.4122951685636674e-06,
+      "loss": 0.0472,
+      "step": 90
+    },
+    {
+      "epoch": 1.8199999999999998,
+      "grad_norm": 0.00972730193927158,
+      "learning_rate": 1.957739348193859e-06,
+      "loss": 0.0492,
+      "step": 91
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.009997008256553653,
+      "learning_rate": 1.5495321624672443e-06,
+      "loss": 0.0451,
+      "step": 92
+    },
+    {
+      "epoch": 1.8599999999999999,
+      "grad_norm": 0.008479904605059388,
+      "learning_rate": 1.1881709489601413e-06,
+      "loss": 0.0466,
+      "step": 93
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.012357339754182392,
+      "learning_rate": 8.740959706477725e-07,
+      "loss": 0.0492,
+      "step": 94
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.009892902279520414,
+      "learning_rate": 6.076898795116792e-07,
+      "loss": 0.046,
+      "step": 95
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.01039127054466151,
+      "learning_rate": 3.8927725033718553e-07,
+      "loss": 0.0486,
+      "step": 96
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.008916228374595131,
+      "learning_rate": 2.1912418526906841e-07,
+      "loss": 0.0488,
+      "step": 97
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.010455120498883346,
+      "learning_rate": 9.74379896070321e-08,
+      "loss": 0.0498,
+      "step": 98
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.009180646694358844,
+      "learning_rate": 2.4366919236169518e-08,
+      "loss": 0.0482,
+      "step": 99
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.010359529273268284,
+      "learning_rate": 0.0,
+      "loss": 0.0513,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "step": 100,
+      "total_flos": 61637279678464.0,
+      "train_loss": 0.07765782132744789,
+      "train_runtime": 680.7019,
+      "train_samples_per_second": 1.175,
+      "train_steps_per_second": 0.147
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "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": 61637279678464.0,
+  "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 sha256:2f3555247801aea5dfe9fa026836212991b4036df8921b7584b4c9cf724d3004
+size 7288