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 +1,67 @@
+---
+library_name: peft
+license: mit
+base_model: deepseek-ai/Deepseek-R1-Distill-Qwen-32B
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: sft_r1_32b
+  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. -->
+
+# sft_r1_32b
+
+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.
+It achieves the following results on the evaluation set:
+- Loss: 0.2803
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 32
+- 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
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.1054        | 1.0   | 46   | 0.3035          |
+| 0.1192        | 2.0   | 92   | 0.2803          |
+
+
+### 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": 64,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "q_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:ea783ac425340034a542f6f620d65926a76eee83441ecc36fa817fbf743e9e86
+size 1073864104

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 572434188075008.0,
+    "train_loss": 0.16822839941343534,
+    "train_runtime": 1109.5336,
+    "train_samples": 1456,
+    "train_samples_per_second": 2.625,
+    "train_steps_per_second": 0.083
+}

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 sha256:05bcf3f0259d0c68665fbf232d7d8bdfba9a1425cdc555c8df4296024e8b8762
+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｜>'}}{% 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
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 572434188075008.0,
+    "train_loss": 0.16822839941343534,
+    "train_runtime": 1109.5336,
+    "train_samples": 1456,
+    "train_samples_per_second": 2.625,
+    "train_steps_per_second": 0.083
+}

trainer_state.json

@@ -0,0 +1,702 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 92,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.021739130434782608,
+      "grad_norm": 0.05251724104456546,
+      "learning_rate": 5e-06,
+      "loss": 0.3754,
+      "step": 1
+    },
+    {
+      "epoch": 0.043478260869565216,
+      "grad_norm": 0.05573697984543011,
+      "learning_rate": 1e-05,
+      "loss": 0.3931,
+      "step": 2
+    },
+    {
+      "epoch": 0.06521739130434782,
+      "grad_norm": 0.055686020785277644,
+      "learning_rate": 1.5e-05,
+      "loss": 0.3919,
+      "step": 3
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 0.057383370366662766,
+      "learning_rate": 2e-05,
+      "loss": 0.3866,
+      "step": 4
+    },
+    {
+      "epoch": 0.10869565217391304,
+      "grad_norm": 0.056949255113048027,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3698,
+      "step": 5
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "grad_norm": 0.048987512185392136,
+      "learning_rate": 3e-05,
+      "loss": 0.3106,
+      "step": 6
+    },
+    {
+      "epoch": 0.15217391304347827,
+      "grad_norm": 0.08045374073923785,
+      "learning_rate": 3.5e-05,
+      "loss": 0.4882,
+      "step": 7
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 0.06212427796062866,
+      "learning_rate": 4e-05,
+      "loss": 0.3509,
+      "step": 8
+    },
+    {
+      "epoch": 0.1956521739130435,
+      "grad_norm": 0.06930559793460131,
+      "learning_rate": 4.5e-05,
+      "loss": 0.3487,
+      "step": 9
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 0.08479060810374385,
+      "learning_rate": 5e-05,
+      "loss": 0.4164,
+      "step": 10
+    },
+    {
+      "epoch": 0.2391304347826087,
+      "grad_norm": 0.07735060989792922,
+      "learning_rate": 4.998165452627025e-05,
+      "loss": 0.3236,
+      "step": 11
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 0.10035136196658945,
+      "learning_rate": 4.992664502959351e-05,
+      "loss": 0.3669,
+      "step": 12
+    },
+    {
+      "epoch": 0.2826086956521739,
+      "grad_norm": 0.13408793546788408,
+      "learning_rate": 4.9835052243991874e-05,
+      "loss": 0.4156,
+      "step": 13
+    },
+    {
+      "epoch": 0.30434782608695654,
+      "grad_norm": 0.0618863026694214,
+      "learning_rate": 4.970701059450872e-05,
+      "loss": 0.1941,
+      "step": 14
+    },
+    {
+      "epoch": 0.32608695652173914,
+      "grad_norm": 0.08810397229413987,
+      "learning_rate": 4.954270799992138e-05,
+      "loss": 0.2403,
+      "step": 15
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 0.10295433419800738,
+      "learning_rate": 4.934238559694448e-05,
+      "loss": 0.229,
+      "step": 16
+    },
+    {
+      "epoch": 0.3695652173913043,
+      "grad_norm": 0.07858446128053818,
+      "learning_rate": 4.9106337386328524e-05,
+      "loss": 0.1684,
+      "step": 17
+    },
+    {
+      "epoch": 0.391304347826087,
+      "grad_norm": 0.09977779781083818,
+      "learning_rate": 4.8834909801373264e-05,
+      "loss": 0.2317,
+      "step": 18
+    },
+    {
+      "epoch": 0.41304347826086957,
+      "grad_norm": 0.10328996330616422,
+      "learning_rate": 4.852850119948904e-05,
+      "loss": 0.2274,
+      "step": 19
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 0.03556332520397947,
+      "learning_rate": 4.8187561277552374e-05,
+      "loss": 0.1173,
+      "step": 20
+    },
+    {
+      "epoch": 0.45652173913043476,
+      "grad_norm": 0.03661754748416793,
+      "learning_rate": 4.781259041191375e-05,
+      "loss": 0.153,
+      "step": 21
+    },
+    {
+      "epoch": 0.4782608695652174,
+      "grad_norm": 0.03688873582054527,
+      "learning_rate": 4.740413892402639e-05,
+      "loss": 0.2053,
+      "step": 22
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.034331812326829386,
+      "learning_rate": 4.6962806272773564e-05,
+      "loss": 0.1627,
+      "step": 23
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 0.03389755142942411,
+      "learning_rate": 4.648924017468003e-05,
+      "loss": 0.1833,
+      "step": 24
+    },
+    {
+      "epoch": 0.5434782608695652,
+      "grad_norm": 0.025413775146317773,
+      "learning_rate": 4.598413565329875e-05,
+      "loss": 0.1142,
+      "step": 25
+    },
+    {
+      "epoch": 0.5652173913043478,
+      "grad_norm": 0.020890145281436717,
+      "learning_rate": 4.5448234019167945e-05,
+      "loss": 0.1243,
+      "step": 26
+    },
+    {
+      "epoch": 0.5869565217391305,
+      "grad_norm": 0.029530067713524434,
+      "learning_rate": 4.488232178183567e-05,
+      "loss": 0.1787,
+      "step": 27
+    },
+    {
+      "epoch": 0.6086956521739131,
+      "grad_norm": 0.02677272586798852,
+      "learning_rate": 4.428722949554857e-05,
+      "loss": 0.1603,
+      "step": 28
+    },
+    {
+      "epoch": 0.6304347826086957,
+      "grad_norm": 0.029036099883147894,
+      "learning_rate": 4.366383054029906e-05,
+      "loss": 0.145,
+      "step": 29
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 0.0287043462798634,
+      "learning_rate": 4.301303984001967e-05,
+      "loss": 0.1406,
+      "step": 30
+    },
+    {
+      "epoch": 0.6739130434782609,
+      "grad_norm": 0.026695006095735583,
+      "learning_rate": 4.233581251980604e-05,
+      "loss": 0.1596,
+      "step": 31
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 0.022277973287203573,
+      "learning_rate": 4.163314250413913e-05,
+      "loss": 0.1141,
+      "step": 32
+    },
+    {
+      "epoch": 0.717391304347826,
+      "grad_norm": 0.018213338155673494,
+      "learning_rate": 4.0906061058163995e-05,
+      "loss": 0.1104,
+      "step": 33
+    },
+    {
+      "epoch": 0.7391304347826086,
+      "grad_norm": 0.024993298491119125,
+      "learning_rate": 4.015563527416595e-05,
+      "loss": 0.1204,
+      "step": 34
+    },
+    {
+      "epoch": 0.7608695652173914,
+      "grad_norm": 0.024904136966888247,
+      "learning_rate": 3.938296650546552e-05,
+      "loss": 0.1786,
+      "step": 35
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 0.03278423774009264,
+      "learning_rate": 3.858918875003053e-05,
+      "loss": 0.159,
+      "step": 36
+    },
+    {
+      "epoch": 0.8043478260869565,
+      "grad_norm": 0.023360922040722182,
+      "learning_rate": 3.777546698617776e-05,
+      "loss": 0.139,
+      "step": 37
+    },
+    {
+      "epoch": 0.8260869565217391,
+      "grad_norm": 0.019421042176258622,
+      "learning_rate": 3.694299546280657e-05,
+      "loss": 0.123,
+      "step": 38
+    },
+    {
+      "epoch": 0.8478260869565217,
+      "grad_norm": 0.02790250452851226,
+      "learning_rate": 3.6092995946673994e-05,
+      "loss": 0.1455,
+      "step": 39
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.020391123084155874,
+      "learning_rate": 3.5226715929283506e-05,
+      "loss": 0.1075,
+      "step": 40
+    },
+    {
+      "epoch": 0.8913043478260869,
+      "grad_norm": 0.027629714624384374,
+      "learning_rate": 3.434542679601922e-05,
+      "loss": 0.1242,
+      "step": 41
+    },
+    {
+      "epoch": 0.9130434782608695,
+      "grad_norm": 0.028746769789642922,
+      "learning_rate": 3.3450421960212566e-05,
+      "loss": 0.1414,
+      "step": 42
+    },
+    {
+      "epoch": 0.9347826086956522,
+      "grad_norm": 0.028588314627560837,
+      "learning_rate": 3.2543014964879816e-05,
+      "loss": 0.1323,
+      "step": 43
+    },
+    {
+      "epoch": 0.9565217391304348,
+      "grad_norm": 0.028772092036388672,
+      "learning_rate": 3.162453755491655e-05,
+      "loss": 0.1257,
+      "step": 44
+    },
+    {
+      "epoch": 0.9782608695652174,
+      "grad_norm": 0.025144393064489897,
+      "learning_rate": 3.0696337722578444e-05,
+      "loss": 0.1079,
+      "step": 45
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.02669084247428836,
+      "learning_rate": 2.975977772911671e-05,
+      "loss": 0.1054,
+      "step": 46
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.3034745752811432,
+      "eval_runtime": 0.937,
+      "eval_samples_per_second": 1.067,
+      "eval_steps_per_second": 1.067,
+      "step": 46
+    },
+    {
+      "epoch": 1.0217391304347827,
+      "grad_norm": 0.03642257387541599,
+      "learning_rate": 2.8816232105471863e-05,
+      "loss": 0.1522,
+      "step": 47
+    },
+    {
+      "epoch": 1.0434782608695652,
+      "grad_norm": 0.03561836088528626,
+      "learning_rate": 2.7867085634960016e-05,
+      "loss": 0.1074,
+      "step": 48
+    },
+    {
+      "epoch": 1.065217391304348,
+      "grad_norm": 0.05234517691102434,
+      "learning_rate": 2.69137313209124e-05,
+      "loss": 0.1531,
+      "step": 49
+    },
+    {
+      "epoch": 1.0869565217391304,
+      "grad_norm": 0.03637238679653222,
+      "learning_rate": 2.595756834225089e-05,
+      "loss": 0.0994,
+      "step": 50
+    },
+    {
+      "epoch": 1.108695652173913,
+      "grad_norm": 0.055544310311407594,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1557,
+      "step": 51
+    },
+    {
+      "epoch": 1.1304347826086956,
+      "grad_norm": 0.04355397356970732,
+      "learning_rate": 2.4042431657749117e-05,
+      "loss": 0.1182,
+      "step": 52
+    },
+    {
+      "epoch": 1.1521739130434783,
+      "grad_norm": 0.05424064771814464,
+      "learning_rate": 2.3086268679087607e-05,
+      "loss": 0.1394,
+      "step": 53
+    },
+    {
+      "epoch": 1.1739130434782608,
+      "grad_norm": 0.0577161872555808,
+      "learning_rate": 2.2132914365039993e-05,
+      "loss": 0.1479,
+      "step": 54
+    },
+    {
+      "epoch": 1.1956521739130435,
+      "grad_norm": 0.050279613109606325,
+      "learning_rate": 2.1183767894528136e-05,
+      "loss": 0.1098,
+      "step": 55
+    },
+    {
+      "epoch": 1.2173913043478262,
+      "grad_norm": 0.046679735735405535,
+      "learning_rate": 2.0240222270883288e-05,
+      "loss": 0.1278,
+      "step": 56
+    },
+    {
+      "epoch": 1.2391304347826086,
+      "grad_norm": 0.05499379456722616,
+      "learning_rate": 1.9303662277421568e-05,
+      "loss": 0.1165,
+      "step": 57
+    },
+    {
+      "epoch": 1.2608695652173914,
+      "grad_norm": 0.048749222045477394,
+      "learning_rate": 1.8375462445083464e-05,
+      "loss": 0.1179,
+      "step": 58
+    },
+    {
+      "epoch": 1.2826086956521738,
+      "grad_norm": 0.053461827603602095,
+      "learning_rate": 1.7456985035120193e-05,
+      "loss": 0.1106,
+      "step": 59
+    },
+    {
+      "epoch": 1.3043478260869565,
+      "grad_norm": 0.049149472041118754,
+      "learning_rate": 1.6549578039787436e-05,
+      "loss": 0.1217,
+      "step": 60
+    },
+    {
+      "epoch": 1.3260869565217392,
+      "grad_norm": 0.06669872511152387,
+      "learning_rate": 1.5654573203980784e-05,
+      "loss": 0.1521,
+      "step": 61
+    },
+    {
+      "epoch": 1.3478260869565217,
+      "grad_norm": 0.05588607166721095,
+      "learning_rate": 1.4773284070716503e-05,
+      "loss": 0.1305,
+      "step": 62
+    },
+    {
+      "epoch": 1.3695652173913042,
+      "grad_norm": 0.041651128759622034,
+      "learning_rate": 1.3907004053326006e-05,
+      "loss": 0.0844,
+      "step": 63
+    },
+    {
+      "epoch": 1.391304347826087,
+      "grad_norm": 0.04846481547080971,
+      "learning_rate": 1.3057004537193423e-05,
+      "loss": 0.1056,
+      "step": 64
+    },
+    {
+      "epoch": 1.4130434782608696,
+      "grad_norm": 0.05162255952027679,
+      "learning_rate": 1.2224533013822238e-05,
+      "loss": 0.1062,
+      "step": 65
+    },
+    {
+      "epoch": 1.434782608695652,
+      "grad_norm": 0.03899787589566359,
+      "learning_rate": 1.1410811249969475e-05,
+      "loss": 0.0995,
+      "step": 66
+    },
+    {
+      "epoch": 1.4565217391304348,
+      "grad_norm": 0.045147641938472066,
+      "learning_rate": 1.0617033494534486e-05,
+      "loss": 0.114,
+      "step": 67
+    },
+    {
+      "epoch": 1.4782608695652173,
+      "grad_norm": 0.035173380736597745,
+      "learning_rate": 9.844364725834057e-06,
+      "loss": 0.0857,
+      "step": 68
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.04035039972686669,
+      "learning_rate": 9.09393894183601e-06,
+      "loss": 0.134,
+      "step": 69
+    },
+    {
+      "epoch": 1.5217391304347827,
+      "grad_norm": 0.040239271954492645,
+      "learning_rate": 8.36685749586087e-06,
+      "loss": 0.1292,
+      "step": 70
+    },
+    {
+      "epoch": 1.5434782608695652,
+      "grad_norm": 0.04298216736498849,
+      "learning_rate": 7.66418748019396e-06,
+      "loss": 0.1252,
+      "step": 71
+    },
+    {
+      "epoch": 1.5652173913043477,
+      "grad_norm": 0.0377478426245691,
+      "learning_rate": 6.986960159980327e-06,
+      "loss": 0.1182,
+      "step": 72
+    },
+    {
+      "epoch": 1.5869565217391304,
+      "grad_norm": 0.035083658633779165,
+      "learning_rate": 6.336169459700933e-06,
+      "loss": 0.1111,
+      "step": 73
+    },
+    {
+      "epoch": 1.608695652173913,
+      "grad_norm": 0.03549273911531577,
+      "learning_rate": 5.712770504451426e-06,
+      "loss": 0.095,
+      "step": 74
+    },
+    {
+      "epoch": 1.6304347826086958,
+      "grad_norm": 0.038451065120467254,
+      "learning_rate": 5.117678218164338e-06,
+      "loss": 0.1251,
+      "step": 75
+    },
+    {
+      "epoch": 1.6521739130434783,
+      "grad_norm": 0.038832533498611044,
+      "learning_rate": 4.551765980832059e-06,
+      "loss": 0.1242,
+      "step": 76
+    },
+    {
+      "epoch": 1.6739130434782608,
+      "grad_norm": 0.0353230449019216,
+      "learning_rate": 4.015864346701251e-06,
+      "loss": 0.0996,
+      "step": 77
+    },
+    {
+      "epoch": 1.6956521739130435,
+      "grad_norm": 0.0334116561862488,
+      "learning_rate": 3.5107598253199758e-06,
+      "loss": 0.1446,
+      "step": 78
+    },
+    {
+      "epoch": 1.7173913043478262,
+      "grad_norm": 0.039290163251729085,
+      "learning_rate": 3.037193727226445e-06,
+      "loss": 0.1208,
+      "step": 79
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 0.03065338534301958,
+      "learning_rate": 2.595861075973613e-06,
+      "loss": 0.1012,
+      "step": 80
+    },
+    {
+      "epoch": 1.7608695652173914,
+      "grad_norm": 0.03648435286390689,
+      "learning_rate": 2.1874095880862505e-06,
+      "loss": 0.11,
+      "step": 81
+    },
+    {
+      "epoch": 1.7826086956521738,
+      "grad_norm": 0.04312471286254432,
+      "learning_rate": 1.8124387224476347e-06,
+      "loss": 0.1596,
+      "step": 82
+    },
+    {
+      "epoch": 1.8043478260869565,
+      "grad_norm": 0.03977695517913043,
+      "learning_rate": 1.471498800510962e-06,
+      "loss": 0.1443,
+      "step": 83
+    },
+    {
+      "epoch": 1.8260869565217392,
+      "grad_norm": 0.03818913820220683,
+      "learning_rate": 1.1650901986267365e-06,
+      "loss": 0.102,
+      "step": 84
+    },
+    {
+      "epoch": 1.8478260869565217,
+      "grad_norm": 0.0301431900096843,
+      "learning_rate": 8.936626136714754e-07,
+      "loss": 0.089,
+      "step": 85
+    },
+    {
+      "epoch": 1.8695652173913042,
+      "grad_norm": 0.0328482429308812,
+      "learning_rate": 6.576144030555259e-07,
+      "loss": 0.0877,
+      "step": 86
+    },
+    {
+      "epoch": 1.891304347826087,
+      "grad_norm": 0.03569083003459117,
+      "learning_rate": 4.5729200007862683e-07,
+      "loss": 0.1045,
+      "step": 87
+    },
+    {
+      "epoch": 1.9130434782608696,
+      "grad_norm": 0.03653172717728122,
+      "learning_rate": 2.9298940549128964e-07,
+      "loss": 0.1174,
+      "step": 88
+    },
+    {
+      "epoch": 1.9347826086956523,
+      "grad_norm": 0.041464913365954224,
+      "learning_rate": 1.6494775600812417e-07,
+      "loss": 0.1278,
+      "step": 89
+    },
+    {
+      "epoch": 1.9565217391304348,
+      "grad_norm": 0.0331840973132891,
+      "learning_rate": 7.335497040648898e-08,
+      "loss": 0.117,
+      "step": 90
+    },
+    {
+      "epoch": 1.9782608695652173,
+      "grad_norm": 0.034232885328460604,
+      "learning_rate": 1.834547372975004e-08,
+      "loss": 0.1074,
+      "step": 91
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.037882602740239905,
+      "learning_rate": 0.0,
+      "loss": 0.1192,
+      "step": 92
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.2802792489528656,
+      "eval_runtime": 1.6275,
+      "eval_samples_per_second": 0.614,
+      "eval_steps_per_second": 0.614,
+      "step": 92
+    },
+    {
+      "epoch": 2.0,
+      "step": 92,
+      "total_flos": 572434188075008.0,
+      "train_loss": 0.16822839941343534,
+      "train_runtime": 1109.5336,
+      "train_samples_per_second": 2.625,
+      "train_steps_per_second": 0.083
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 92,
+  "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": 572434188075008.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5daff86556339c6cec5cf77fba02220d601a923f24269afbcfb361bfe9f7b161
+size 7224