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_3k_forcing_022225_step1
+  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_3k_forcing_022225_step1
+
+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: 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": [
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_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:ea4d2168dfedc3289cf46029ac56859e7a1a3f71f0753cee35aaa61b8642a654
+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 sha256:3c11a6ac886e89a098471690b6ced3af1fbd2cdfd12722f5d9b47d3d1327018d
+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": 0.009637037334106903,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1715,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.010363472738535676,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.1824,
+      "step": 2
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.009281759914882096,
+      "learning_rate": 2.4e-05,
+      "loss": 0.1755,
+      "step": 3
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.009379315837523864,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.1754,
+      "step": 4
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.009689818422011673,
+      "learning_rate": 4e-05,
+      "loss": 0.1852,
+      "step": 5
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.01079412055265657,
+      "learning_rate": 4.8e-05,
+      "loss": 0.1798,
+      "step": 6
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.012725094867351431,
+      "learning_rate": 5.6e-05,
+      "loss": 0.1751,
+      "step": 7
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.01328392294717579,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.1757,
+      "step": 8
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.015145006915557084,
+      "learning_rate": 7.2e-05,
+      "loss": 0.1692,
+      "step": 9
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.014214264328987642,
+      "learning_rate": 8e-05,
+      "loss": 0.1706,
+      "step": 10
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.0117747274010397,
+      "learning_rate": 7.997563308076384e-05,
+      "loss": 0.1708,
+      "step": 11
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.010091753251280325,
+      "learning_rate": 7.990256201039297e-05,
+      "loss": 0.1531,
+      "step": 12
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.012645092248136579,
+      "learning_rate": 7.978087581473094e-05,
+      "loss": 0.1671,
+      "step": 13
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.015268244393923469,
+      "learning_rate": 7.961072274966282e-05,
+      "loss": 0.1491,
+      "step": 14
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.017465888150194103,
+      "learning_rate": 7.939231012048833e-05,
+      "loss": 0.1515,
+      "step": 15
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.01782819697407518,
+      "learning_rate": 7.912590402935223e-05,
+      "loss": 0.148,
+      "step": 16
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.013186487241659864,
+      "learning_rate": 7.881182905103986e-05,
+      "loss": 0.1445,
+      "step": 17
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.016720647392397203,
+      "learning_rate": 7.845046783753276e-05,
+      "loss": 0.1292,
+      "step": 18
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.011224205233150252,
+      "learning_rate": 7.804226065180615e-05,
+      "loss": 0.1392,
+      "step": 19
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.010617910894874901,
+      "learning_rate": 7.758770483143634e-05,
+      "loss": 0.1269,
+      "step": 20
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.010715577784169017,
+      "learning_rate": 7.70873541826715e-05,
+      "loss": 0.1231,
+      "step": 21
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.010471813302226756,
+      "learning_rate": 7.654181830570404e-05,
+      "loss": 0.1187,
+      "step": 22
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.010383002437875545,
+      "learning_rate": 7.595176185196669e-05,
+      "loss": 0.1113,
+      "step": 23
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.010586134489056574,
+      "learning_rate": 7.531790371435709e-05,
+      "loss": 0.1234,
+      "step": 24
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.010888260652938336,
+      "learning_rate": 7.464101615137756e-05,
+      "loss": 0.1059,
+      "step": 25
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.010911898967532585,
+      "learning_rate": 7.392192384625704e-05,
+      "loss": 0.1141,
+      "step": 26
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.011539276901662144,
+      "learning_rate": 7.316150290220167e-05,
+      "loss": 0.0931,
+      "step": 27
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.009852319145659155,
+      "learning_rate": 7.236067977499791e-05,
+      "loss": 0.0931,
+      "step": 28
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.009251316792835406,
+      "learning_rate": 7.152043014426888e-05,
+      "loss": 0.0905,
+      "step": 29
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.00933612139727198,
+      "learning_rate": 7.064177772475912e-05,
+      "loss": 0.0881,
+      "step": 30
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.007931619300729838,
+      "learning_rate": 6.972579301909577e-05,
+      "loss": 0.0936,
+      "step": 31
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.008282605911657226,
+      "learning_rate": 6.877359201354606e-05,
+      "loss": 0.0947,
+      "step": 32
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.008696825388038025,
+      "learning_rate": 6.778633481835989e-05,
+      "loss": 0.0974,
+      "step": 33
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.010160185809561427,
+      "learning_rate": 6.676522425435433e-05,
+      "loss": 0.0833,
+      "step": 34
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.009725043660608746,
+      "learning_rate": 6.571150438746157e-05,
+      "loss": 0.091,
+      "step": 35
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.00915870516192456,
+      "learning_rate": 6.462645901302633e-05,
+      "loss": 0.0906,
+      "step": 36
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.00949942001461252,
+      "learning_rate": 6.351141009169893e-05,
+      "loss": 0.0737,
+      "step": 37
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.00963074300361407,
+      "learning_rate": 6.236771613882987e-05,
+      "loss": 0.0808,
+      "step": 38
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.008964309208790133,
+      "learning_rate": 6.11967705693282e-05,
+      "loss": 0.0798,
+      "step": 39
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.010847454918205806,
+      "learning_rate": 6.000000000000001e-05,
+      "loss": 0.0804,
+      "step": 40
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.011408515319016313,
+      "learning_rate": 5.877886251143564e-05,
+      "loss": 0.0802,
+      "step": 41
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.009455272778473722,
+      "learning_rate": 5.75348458715631e-05,
+      "loss": 0.0694,
+      "step": 42
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.009422000569229901,
+      "learning_rate": 5.626946572303202e-05,
+      "loss": 0.0725,
+      "step": 43
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.009392794636835294,
+      "learning_rate": 5.4984263736636494e-05,
+      "loss": 0.0681,
+      "step": 44
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.010717279887046228,
+      "learning_rate": 5.368080573302676e-05,
+      "loss": 0.0606,
+      "step": 45
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.011543751880120315,
+      "learning_rate": 5.23606797749979e-05,
+      "loss": 0.0746,
+      "step": 46
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.00974296442052676,
+      "learning_rate": 5.102549423267997e-05,
+      "loss": 0.0743,
+      "step": 47
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.011092943847511937,
+      "learning_rate": 4.967687582398671e-05,
+      "loss": 0.0639,
+      "step": 48
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.010114698995140116,
+      "learning_rate": 4.831646763271037e-05,
+      "loss": 0.0557,
+      "step": 49
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.010762376254563907,
+      "learning_rate": 4.694592710667723e-05,
+      "loss": 0.0746,
+      "step": 50
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.010667834567782971,
+      "learning_rate": 4.556692403840262e-05,
+      "loss": 0.0639,
+      "step": 51
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.01151367197208969,
+      "learning_rate": 4.418113853070614e-05,
+      "loss": 0.064,
+      "step": 52
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.009860056383718526,
+      "learning_rate": 4.2790258949765014e-05,
+      "loss": 0.063,
+      "step": 53
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.012541225926420095,
+      "learning_rate": 4.139597986810005e-05,
+      "loss": 0.0596,
+      "step": 54
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.009521476670088416,
+      "learning_rate": 4e-05,
+      "loss": 0.0671,
+      "step": 55
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.009542523244632242,
+      "learning_rate": 3.860402013189998e-05,
+      "loss": 0.0556,
+      "step": 56
+    },
+    {
+      "epoch": 1.1400000000000001,
+      "grad_norm": 0.011878302307403495,
+      "learning_rate": 3.720974105023499e-05,
+      "loss": 0.0656,
+      "step": 57
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.010454526692007589,
+      "learning_rate": 3.581886146929387e-05,
+      "loss": 0.0548,
+      "step": 58
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.009345662853487318,
+      "learning_rate": 3.44330759615974e-05,
+      "loss": 0.0569,
+      "step": 59
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.007827806039224647,
+      "learning_rate": 3.305407289332279e-05,
+      "loss": 0.0765,
+      "step": 60
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.009649781285302035,
+      "learning_rate": 3.168353236728964e-05,
+      "loss": 0.0506,
+      "step": 61
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.008286751994014904,
+      "learning_rate": 3.0323124176013297e-05,
+      "loss": 0.063,
+      "step": 62
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.06655073893981245,
+      "learning_rate": 2.8974505767320037e-05,
+      "loss": 0.0575,
+      "step": 63
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.007836975850936692,
+      "learning_rate": 2.7639320225002108e-05,
+      "loss": 0.0565,
+      "step": 64
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.007383922106306936,
+      "learning_rate": 2.6319194266973256e-05,
+      "loss": 0.0621,
+      "step": 65
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.009229854315503655,
+      "learning_rate": 2.501573626336352e-05,
+      "loss": 0.058,
+      "step": 66
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.008287035866375275,
+      "learning_rate": 2.3730534276968e-05,
+      "loss": 0.0556,
+      "step": 67
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.007495725344916213,
+      "learning_rate": 2.24651541284369e-05,
+      "loss": 0.0631,
+      "step": 68
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.006754595847272537,
+      "learning_rate": 2.122113748856438e-05,
+      "loss": 0.0606,
+      "step": 69
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.006929010051776861,
+      "learning_rate": 2.0000000000000012e-05,
+      "loss": 0.0561,
+      "step": 70
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.006736592433187392,
+      "learning_rate": 1.880322943067181e-05,
+      "loss": 0.062,
+      "step": 71
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.007182482865872722,
+      "learning_rate": 1.7632283861170135e-05,
+      "loss": 0.0635,
+      "step": 72
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.006904910945379308,
+      "learning_rate": 1.648858990830108e-05,
+      "loss": 0.0681,
+      "step": 73
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.0067574401332377056,
+      "learning_rate": 1.537354098697367e-05,
+      "loss": 0.0624,
+      "step": 74
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.008832621099426353,
+      "learning_rate": 1.4288495612538427e-05,
+      "loss": 0.0535,
+      "step": 75
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.006117317016948899,
+      "learning_rate": 1.3234775745645684e-05,
+      "loss": 0.0652,
+      "step": 76
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.0066094648348674016,
+      "learning_rate": 1.2213665181640106e-05,
+      "loss": 0.0598,
+      "step": 77
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.00623976002166191,
+      "learning_rate": 1.1226407986453963e-05,
+      "loss": 0.0624,
+      "step": 78
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.006987672701303646,
+      "learning_rate": 1.0274206980904226e-05,
+      "loss": 0.0593,
+      "step": 79
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.012589601873003389,
+      "learning_rate": 9.358222275240884e-06,
+      "loss": 0.0568,
+      "step": 80
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.006470591696598215,
+      "learning_rate": 8.479569855731125e-06,
+      "loss": 0.0614,
+      "step": 81
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.0063493059376758,
+      "learning_rate": 7.639320225002106e-06,
+      "loss": 0.0632,
+      "step": 82
+    },
+    {
+      "epoch": 1.6600000000000001,
+      "grad_norm": 0.006760934543182845,
+      "learning_rate": 6.838497097798336e-06,
+      "loss": 0.0531,
+      "step": 83
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.006284261758909252,
+      "learning_rate": 6.078076153742962e-06,
+      "loss": 0.06,
+      "step": 84
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.006244910460154182,
+      "learning_rate": 5.358983848622452e-06,
+      "loss": 0.0553,
+      "step": 85
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.006874931862320411,
+      "learning_rate": 4.6820962856429205e-06,
+      "loss": 0.0603,
+      "step": 86
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.006108098451612518,
+      "learning_rate": 4.048238148033328e-06,
+      "loss": 0.0649,
+      "step": 87
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.006139066593709117,
+      "learning_rate": 3.458181694295961e-06,
+      "loss": 0.0612,
+      "step": 88
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.0064314090852090324,
+      "learning_rate": 2.9126458173285077e-06,
+      "loss": 0.0538,
+      "step": 89
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.006473633645701588,
+      "learning_rate": 2.4122951685636674e-06,
+      "loss": 0.0508,
+      "step": 90
+    },
+    {
+      "epoch": 1.8199999999999998,
+      "grad_norm": 0.006069288699200219,
+      "learning_rate": 1.957739348193859e-06,
+      "loss": 0.0594,
+      "step": 91
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.006342799495160182,
+      "learning_rate": 1.5495321624672443e-06,
+      "loss": 0.0604,
+      "step": 92
+    },
+    {
+      "epoch": 1.8599999999999999,
+      "grad_norm": 0.006508582185322709,
+      "learning_rate": 1.1881709489601413e-06,
+      "loss": 0.0619,
+      "step": 93
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.006406562832602666,
+      "learning_rate": 8.740959706477725e-07,
+      "loss": 0.0715,
+      "step": 94
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.006419751800132748,
+      "learning_rate": 6.076898795116792e-07,
+      "loss": 0.0602,
+      "step": 95
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.006577037827020311,
+      "learning_rate": 3.8927725033718553e-07,
+      "loss": 0.0516,
+      "step": 96
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.006468345159494065,
+      "learning_rate": 2.1912418526906841e-07,
+      "loss": 0.0635,
+      "step": 97
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.007306372789184797,
+      "learning_rate": 9.74379896070321e-08,
+      "loss": 0.0576,
+      "step": 98
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.006748891809751133,
+      "learning_rate": 2.4366919236169518e-08,
+      "loss": 0.0638,
+      "step": 99
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.00654742251498959,
+      "learning_rate": 0.0,
+      "loss": 0.0572,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "step": 100,
+      "total_flos": 75312582098944.0,
+      "train_loss": 0.08874193653464317,
+      "train_runtime": 868.9432,
+      "train_samples_per_second": 0.921,
+      "train_steps_per_second": 0.115
+    }
+  ],
+  "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": 75312582098944.0,
+  "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 sha256:68c312adfaaf54b419adc1e84288ccaa01e053e895731715993e5837345488c2
+size 7288