Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: allenai/OLMoE-1B-7B-0125
+library_name: transformers
+model_name: OLMoE-1B-7B-0125-Distill-bs17k-batch32-epoch5-8192
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for OLMoE-1B-7B-0125-Distill-bs17k-batch32-epoch5-8192
+
+This model is a fine-tuned version of [allenai/OLMoE-1B-7B-0125](https://huggingface.co/allenai/OLMoE-1B-7B-0125).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="Lansechen/OLMoE-1B-7B-0125-Distill-bs17k-batch32-epoch5-8192", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/chenran1995-the-chinese-university-of-hong-kong/huggingface/runs/dzeilrzp) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.16.0.dev0
+- Transformers: 4.49.0
+- Pytorch: 2.5.1+cu121
+- Datasets: 3.3.1
+- Tokenizers: 0.21.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 355840724828160.0,
+    "train_loss": 0.8500821517495548,
+    "train_runtime": 37256.86,
+    "train_samples": 16610,
+    "train_samples_per_second": 1.46,
+    "train_steps_per_second": 0.011
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "allenai/OLMoE-1B-7B-0125",
+  "architectures": [
+    "OlmoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "clip_qkv": null,
+  "eos_token_id": 50279,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 4096,
+  "model_type": "olmoe",
+  "norm_topk_prob": false,
+  "num_attention_heads": 16,
+  "num_experts": 64,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 16,
+  "output_router_logits": false,
+  "pad_token_id": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.01,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 50279,
+  "pad_token_id": 1,
+  "transformers_version": "4.49.0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86053ec32ac70b2fb23f0c8f568e47e071a25e27b373ff481e22db978bf7c318
+size 4997744872

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6339099c7f0b519b4d584bb9f55417a83f456c79f7146f885e8d0663532d7a58
+size 4997235176

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4073cc96d2a6c75372507f803443fb2251abc02cb767579f71ea864cefd9242
+size 3843741912

special_tokens_map.json

@@ -0,0 +1,10 @@
+{
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": null,
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>\n'  + message['content'] + eos_token + '\n' }}{% else %}{{ '<|assistant|>\n'  + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 355840724828160.0,
+    "train_loss": 0.8500821517495548,
+    "train_runtime": 37256.86,
+    "train_samples": 16610,
+    "train_samples_per_second": 1.46,
+    "train_steps_per_second": 0.011
+}

trainer_state.json

@@ -0,0 +1,722 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 100,
+  "global_step": 425,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.058823529411764705,
+      "grad_norm": 9.801055908203125,
+      "learning_rate": 2.3255813953488376e-06,
+      "loss": 2.8838,
+      "mean_token_accuracy": 0.4685125470161438,
+      "step": 5
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 4.448275089263916,
+      "learning_rate": 4.651162790697675e-06,
+      "loss": 2.6682,
+      "mean_token_accuracy": 0.48174361512064934,
+      "step": 10
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 3.506427049636841,
+      "learning_rate": 6.976744186046513e-06,
+      "loss": 2.3047,
+      "mean_token_accuracy": 0.5089653469622135,
+      "step": 15
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 1.942956566810608,
+      "learning_rate": 9.30232558139535e-06,
+      "loss": 1.9878,
+      "mean_token_accuracy": 0.545573990046978,
+      "step": 20
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 1.4031805992126465,
+      "learning_rate": 1.1627906976744187e-05,
+      "loss": 1.6996,
+      "mean_token_accuracy": 0.5859037727117539,
+      "step": 25
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 1.2360728979110718,
+      "learning_rate": 1.3953488372093025e-05,
+      "loss": 1.4437,
+      "mean_token_accuracy": 0.6297813355922699,
+      "step": 30
+    },
+    {
+      "epoch": 0.4117647058823529,
+      "grad_norm": 1.0586236715316772,
+      "learning_rate": 1.6279069767441862e-05,
+      "loss": 1.2465,
+      "mean_token_accuracy": 0.6674090638756752,
+      "step": 35
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 5.732640266418457,
+      "learning_rate": 1.86046511627907e-05,
+      "loss": 1.1191,
+      "mean_token_accuracy": 0.6937173813581466,
+      "step": 40
+    },
+    {
+      "epoch": 0.5294117647058824,
+      "grad_norm": 1.3545150756835938,
+      "learning_rate": 1.9998647325745995e-05,
+      "loss": 1.058,
+      "mean_token_accuracy": 0.7053330481052399,
+      "step": 45
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.5088366866111755,
+      "learning_rate": 1.9983433942731427e-05,
+      "loss": 1.0088,
+      "mean_token_accuracy": 0.7168952524662018,
+      "step": 50
+    },
+    {
+      "epoch": 0.6470588235294118,
+      "grad_norm": 0.5655267834663391,
+      "learning_rate": 1.9951342140049483e-05,
+      "loss": 0.9664,
+      "mean_token_accuracy": 0.7258439436554909,
+      "step": 55
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.38032180070877075,
+      "learning_rate": 1.9902426173471933e-05,
+      "loss": 0.9373,
+      "mean_token_accuracy": 0.7326086208224296,
+      "step": 60
+    },
+    {
+      "epoch": 0.7647058823529411,
+      "grad_norm": 0.3592306673526764,
+      "learning_rate": 1.9836768742420355e-05,
+      "loss": 0.922,
+      "mean_token_accuracy": 0.7359638556838035,
+      "step": 65
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 0.3888241946697235,
+      "learning_rate": 1.975448085015093e-05,
+      "loss": 0.8966,
+      "mean_token_accuracy": 0.7414851307868957,
+      "step": 70
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.4164377748966217,
+      "learning_rate": 1.965570161608762e-05,
+      "loss": 0.8913,
+      "mean_token_accuracy": 0.7422603994607926,
+      "step": 75
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.6885089874267578,
+      "learning_rate": 1.954059804062092e-05,
+      "loss": 0.8714,
+      "mean_token_accuracy": 0.7471662059426307,
+      "step": 80
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4278125464916229,
+      "learning_rate": 1.9409364722769882e-05,
+      "loss": 0.8717,
+      "mean_token_accuracy": 0.746853019297123,
+      "step": 85
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "grad_norm": 0.3752460777759552,
+      "learning_rate": 1.9262223531184678e-05,
+      "loss": 0.8245,
+      "mean_token_accuracy": 0.7577321365475654,
+      "step": 90
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 0.39527037739753723,
+      "learning_rate": 1.9099423229046015e-05,
+      "loss": 0.8363,
+      "mean_token_accuracy": 0.7540760099887848,
+      "step": 95
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.4897399842739105,
+      "learning_rate": 1.8921239053495465e-05,
+      "loss": 0.8341,
+      "mean_token_accuracy": 0.754480054974556,
+      "step": 100
+    },
+    {
+      "epoch": 1.2352941176470589,
+      "grad_norm": 0.6889349818229675,
+      "learning_rate": 1.87279722503078e-05,
+      "loss": 0.8177,
+      "mean_token_accuracy": 0.7585643947124481,
+      "step": 105
+    },
+    {
+      "epoch": 1.2941176470588236,
+      "grad_norm": 0.3268294334411621,
+      "learning_rate": 1.8519949564592047e-05,
+      "loss": 0.8106,
+      "mean_token_accuracy": 0.7604422122240067,
+      "step": 110
+    },
+    {
+      "epoch": 1.3529411764705883,
+      "grad_norm": 0.33755165338516235,
+      "learning_rate": 1.829752268838222e-05,
+      "loss": 0.8065,
+      "mean_token_accuracy": 0.761128132045269,
+      "step": 115
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 0.6083232760429382,
+      "learning_rate": 1.806106766605178e-05,
+      "loss": 0.8108,
+      "mean_token_accuracy": 0.759614397585392,
+      "step": 120
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.3448510766029358,
+      "learning_rate": 1.7810984258556955e-05,
+      "loss": 0.8061,
+      "mean_token_accuracy": 0.7612118363380432,
+      "step": 125
+    },
+    {
+      "epoch": 1.5294117647058822,
+      "grad_norm": 0.32702550292015076,
+      "learning_rate": 1.7547695267583794e-05,
+      "loss": 0.7921,
+      "mean_token_accuracy": 0.7645646795630455,
+      "step": 130
+    },
+    {
+      "epoch": 1.5882352941176472,
+      "grad_norm": 0.5395148396492004,
+      "learning_rate": 1.7271645820741586e-05,
+      "loss": 0.7979,
+      "mean_token_accuracy": 0.7623553887009621,
+      "step": 135
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 0.3668619990348816,
+      "learning_rate": 1.6983302619011125e-05,
+      "loss": 0.8015,
+      "mean_token_accuracy": 0.7612669453024864,
+      "step": 140
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.33199718594551086,
+      "learning_rate": 1.6683153147720098e-05,
+      "loss": 0.7952,
+      "mean_token_accuracy": 0.7631191626191139,
+      "step": 145
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.3427417278289795,
+      "learning_rate": 1.6371704852379587e-05,
+      "loss": 0.7858,
+      "mean_token_accuracy": 0.7653731450438499,
+      "step": 150
+    },
+    {
+      "epoch": 1.8235294117647058,
+      "grad_norm": 0.30648478865623474,
+      "learning_rate": 1.6049484280775012e-05,
+      "loss": 0.7839,
+      "mean_token_accuracy": 0.7659221082925797,
+      "step": 155
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 0.2786785364151001,
+      "learning_rate": 1.571703619276197e-05,
+      "loss": 0.7749,
+      "mean_token_accuracy": 0.7680376842617989,
+      "step": 160
+    },
+    {
+      "epoch": 1.9411764705882353,
+      "grad_norm": 0.37050941586494446,
+      "learning_rate": 1.537492263927196e-05,
+      "loss": 0.7888,
+      "mean_token_accuracy": 0.7642401471734047,
+      "step": 165
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.2998650074005127,
+      "learning_rate": 1.5023722012085098e-05,
+      "loss": 0.7819,
+      "mean_token_accuracy": 0.7661917269229889,
+      "step": 170
+    },
+    {
+      "epoch": 2.0588235294117645,
+      "grad_norm": 0.3789665699005127,
+      "learning_rate": 1.4664028065976245e-05,
+      "loss": 0.7352,
+      "mean_token_accuracy": 0.7768902614712715,
+      "step": 175
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 0.36154264211654663,
+      "learning_rate": 1.4296448914887866e-05,
+      "loss": 0.7354,
+      "mean_token_accuracy": 0.7771928086876869,
+      "step": 180
+    },
+    {
+      "epoch": 2.176470588235294,
+      "grad_norm": 0.28340908885002136,
+      "learning_rate": 1.392160600382663e-05,
+      "loss": 0.7214,
+      "mean_token_accuracy": 0.7810987904667854,
+      "step": 185
+    },
+    {
+      "epoch": 2.235294117647059,
+      "grad_norm": 0.32036685943603516,
+      "learning_rate": 1.3540133058221927e-05,
+      "loss": 0.723,
+      "mean_token_accuracy": 0.7803330168128013,
+      "step": 190
+    },
+    {
+      "epoch": 2.2941176470588234,
+      "grad_norm": 0.32565855979919434,
+      "learning_rate": 1.3152675012522629e-05,
+      "loss": 0.7197,
+      "mean_token_accuracy": 0.7812802106142044,
+      "step": 195
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.3181378245353699,
+      "learning_rate": 1.2759886919843354e-05,
+      "loss": 0.7289,
+      "mean_token_accuracy": 0.7784938037395477,
+      "step": 200
+    },
+    {
+      "epoch": 2.411764705882353,
+      "grad_norm": 0.28247517347335815,
+      "learning_rate": 1.2362432844503725e-05,
+      "loss": 0.7248,
+      "mean_token_accuracy": 0.7791543766856194,
+      "step": 205
+    },
+    {
+      "epoch": 2.4705882352941178,
+      "grad_norm": 0.2911124527454376,
+      "learning_rate": 1.1960984739332851e-05,
+      "loss": 0.7292,
+      "mean_token_accuracy": 0.778170482814312,
+      "step": 210
+    },
+    {
+      "epoch": 2.5294117647058822,
+      "grad_norm": 0.27683931589126587,
+      "learning_rate": 1.1556221309637204e-05,
+      "loss": 0.7237,
+      "mean_token_accuracy": 0.7796448439359664,
+      "step": 215
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 0.33382534980773926,
+      "learning_rate": 1.1148826865752445e-05,
+      "loss": 0.7193,
+      "mean_token_accuracy": 0.7808471828699112,
+      "step": 220
+    },
+    {
+      "epoch": 2.6470588235294117,
+      "grad_norm": 0.4343814253807068,
+      "learning_rate": 1.0739490166119155e-05,
+      "loss": 0.725,
+      "mean_token_accuracy": 0.7788172155618668,
+      "step": 225
+    },
+    {
+      "epoch": 2.7058823529411766,
+      "grad_norm": 0.2904091775417328,
+      "learning_rate": 1.0328903252838415e-05,
+      "loss": 0.7237,
+      "mean_token_accuracy": 0.7795747637748718,
+      "step": 230
+    },
+    {
+      "epoch": 2.764705882352941,
+      "grad_norm": 0.32864418625831604,
+      "learning_rate": 9.917760281675867e-06,
+      "loss": 0.7209,
+      "mean_token_accuracy": 0.7800360411405564,
+      "step": 235
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 0.31458979845046997,
+      "learning_rate": 9.506756348492348e-06,
+      "loss": 0.7159,
+      "mean_token_accuracy": 0.7815931037068367,
+      "step": 240
+    },
+    {
+      "epoch": 2.8823529411764706,
+      "grad_norm": 0.27966296672821045,
+      "learning_rate": 9.096586314085162e-06,
+      "loss": 0.7181,
+      "mean_token_accuracy": 0.781124995648861,
+      "step": 245
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.688630223274231,
+      "learning_rate": 8.687943629426725e-06,
+      "loss": 0.7152,
+      "mean_token_accuracy": 0.7815666347742081,
+      "step": 250
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.28815606236457825,
+      "learning_rate": 8.281519163286772e-06,
+      "loss": 0.7154,
+      "mean_token_accuracy": 0.7819428607821465,
+      "step": 255
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 0.35684919357299805,
+      "learning_rate": 7.878000034220092e-06,
+      "loss": 0.6743,
+      "mean_token_accuracy": 0.792499803006649,
+      "step": 260
+    },
+    {
+      "epoch": 3.1176470588235294,
+      "grad_norm": 0.320491760969162,
+      "learning_rate": 7.478068448894577e-06,
+      "loss": 0.6676,
+      "mean_token_accuracy": 0.793880632519722,
+      "step": 265
+    },
+    {
+      "epoch": 3.176470588235294,
+      "grad_norm": 0.2796066403388977,
+      "learning_rate": 7.082400548723505e-06,
+      "loss": 0.6848,
+      "mean_token_accuracy": 0.789003798365593,
+      "step": 270
+    },
+    {
+      "epoch": 3.235294117647059,
+      "grad_norm": 0.26849114894866943,
+      "learning_rate": 6.6916652667519855e-06,
+      "loss": 0.6713,
+      "mean_token_accuracy": 0.7928505405783653,
+      "step": 275
+    },
+    {
+      "epoch": 3.2941176470588234,
+      "grad_norm": 0.2733159065246582,
+      "learning_rate": 6.3065231967302055e-06,
+      "loss": 0.6738,
+      "mean_token_accuracy": 0.7923304066061974,
+      "step": 280
+    },
+    {
+      "epoch": 3.3529411764705883,
+      "grad_norm": 0.2969025671482086,
+      "learning_rate": 5.927625476285426e-06,
+      "loss": 0.6715,
+      "mean_token_accuracy": 0.7928250879049301,
+      "step": 285
+    },
+    {
+      "epoch": 3.411764705882353,
+      "grad_norm": 0.27059030532836914,
+      "learning_rate": 5.555612686080909e-06,
+      "loss": 0.6763,
+      "mean_token_accuracy": 0.7914069682359696,
+      "step": 290
+    },
+    {
+      "epoch": 3.4705882352941178,
+      "grad_norm": 0.3366273045539856,
+      "learning_rate": 5.191113766822905e-06,
+      "loss": 0.6839,
+      "mean_token_accuracy": 0.7889776557683945,
+      "step": 295
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 0.2921532988548279,
+      "learning_rate": 4.834744955946631e-06,
+      "loss": 0.6736,
+      "mean_token_accuracy": 0.791980504989624,
+      "step": 300
+    },
+    {
+      "epoch": 3.588235294117647,
+      "grad_norm": 0.26477354764938354,
+      "learning_rate": 4.487108745778958e-06,
+      "loss": 0.6752,
+      "mean_token_accuracy": 0.7913888990879059,
+      "step": 305
+    },
+    {
+      "epoch": 3.6470588235294117,
+      "grad_norm": 0.2706132233142853,
+      "learning_rate": 4.148792864939164e-06,
+      "loss": 0.6694,
+      "mean_token_accuracy": 0.793201494216919,
+      "step": 310
+    },
+    {
+      "epoch": 3.7058823529411766,
+      "grad_norm": 0.2624160647392273,
+      "learning_rate": 3.820369284699823e-06,
+      "loss": 0.6774,
+      "mean_token_accuracy": 0.7909433797001839,
+      "step": 315
+    },
+    {
+      "epoch": 3.764705882352941,
+      "grad_norm": 0.24997976422309875,
+      "learning_rate": 3.502393251987776e-06,
+      "loss": 0.6727,
+      "mean_token_accuracy": 0.7921077489852906,
+      "step": 320
+    },
+    {
+      "epoch": 3.8235294117647056,
+      "grad_norm": 0.2666849195957184,
+      "learning_rate": 3.195402350659945e-06,
+      "loss": 0.6673,
+      "mean_token_accuracy": 0.7938370048999787,
+      "step": 325
+    },
+    {
+      "epoch": 3.8823529411764706,
+      "grad_norm": 0.2589641511440277,
+      "learning_rate": 2.8999155926411203e-06,
+      "loss": 0.6756,
+      "mean_token_accuracy": 0.7912636324763298,
+      "step": 330
+    },
+    {
+      "epoch": 3.9411764705882355,
+      "grad_norm": 0.24173301458358765,
+      "learning_rate": 2.616432540460255e-06,
+      "loss": 0.6766,
+      "mean_token_accuracy": 0.790938887000084,
+      "step": 335
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.24843551218509674,
+      "learning_rate": 2.345432462668702e-06,
+      "loss": 0.6766,
+      "mean_token_accuracy": 0.7911555007100105,
+      "step": 340
+    },
+    {
+      "epoch": 4.0588235294117645,
+      "grad_norm": 0.32429039478302,
+      "learning_rate": 2.0873735235683535e-06,
+      "loss": 0.6618,
+      "mean_token_accuracy": 0.7948457077145576,
+      "step": 345
+    },
+    {
+      "epoch": 4.117647058823529,
+      "grad_norm": 0.27062714099884033,
+      "learning_rate": 1.8426920086195065e-06,
+      "loss": 0.653,
+      "mean_token_accuracy": 0.7976298287510872,
+      "step": 350
+    },
+    {
+      "epoch": 4.176470588235294,
+      "grad_norm": 0.26047635078430176,
+      "learning_rate": 1.6118015868380387e-06,
+      "loss": 0.6535,
+      "mean_token_accuracy": 0.797492328286171,
+      "step": 355
+    },
+    {
+      "epoch": 4.235294117647059,
+      "grad_norm": 0.30829542875289917,
+      "learning_rate": 1.395092611428902e-06,
+      "loss": 0.6517,
+      "mean_token_accuracy": 0.7974838793277741,
+      "step": 360
+    },
+    {
+      "epoch": 4.294117647058823,
+      "grad_norm": 0.24258218705654144,
+      "learning_rate": 1.1929314598383423e-06,
+      "loss": 0.6451,
+      "mean_token_accuracy": 0.7996223151683808,
+      "step": 365
+    },
+    {
+      "epoch": 4.352941176470588,
+      "grad_norm": 0.24788279831409454,
+      "learning_rate": 1.0056599143405244e-06,
+      "loss": 0.6513,
+      "mean_token_accuracy": 0.7977980926632882,
+      "step": 370
+    },
+    {
+      "epoch": 4.411764705882353,
+      "grad_norm": 0.29732242226600647,
+      "learning_rate": 8.335945842058524e-07,
+      "loss": 0.645,
+      "mean_token_accuracy": 0.7993328258395195,
+      "step": 375
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 1.655290126800537,
+      "learning_rate": 6.770263704277958e-07,
+      "loss": 0.6472,
+      "mean_token_accuracy": 0.7989670917391777,
+      "step": 380
+    },
+    {
+      "epoch": 4.529411764705882,
+      "grad_norm": 0.28352469205856323,
+      "learning_rate": 5.362199739132656e-07,
+      "loss": 0.6466,
+      "mean_token_accuracy": 0.7991617903113365,
+      "step": 385
+    },
+    {
+      "epoch": 4.588235294117647,
+      "grad_norm": 0.2660938501358032,
+      "learning_rate": 4.114134479679543e-07,
+      "loss": 0.6556,
+      "mean_token_accuracy": 0.7966735288500786,
+      "step": 390
+    },
+    {
+      "epoch": 4.647058823529412,
+      "grad_norm": 0.2790846824645996,
+      "learning_rate": 3.028177958332512e-07,
+      "loss": 0.6489,
+      "mean_token_accuracy": 0.7987425029277802,
+      "step": 395
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 0.2298436462879181,
+      "learning_rate": 2.106166139551602e-07,
+      "loss": 0.64,
+      "mean_token_accuracy": 0.8014952301979065,
+      "step": 400
+    },
+    {
+      "epoch": 4.764705882352941,
+      "grad_norm": 0.29493239521980286,
+      "learning_rate": 1.349657815883032e-07,
+      "loss": 0.6469,
+      "mean_token_accuracy": 0.799544931948185,
+      "step": 405
+    },
+    {
+      "epoch": 4.823529411764706,
+      "grad_norm": 0.23889978229999542,
+      "learning_rate": 7.599319725980047e-08,
+      "loss": 0.655,
+      "mean_token_accuracy": 0.7966993048787117,
+      "step": 410
+    },
+    {
+      "epoch": 4.882352941176471,
+      "grad_norm": 0.23456239700317383,
+      "learning_rate": 3.379856253855951e-08,
+      "loss": 0.662,
+      "mean_token_accuracy": 0.7946143627166748,
+      "step": 415
+    },
+    {
+      "epoch": 4.9411764705882355,
+      "grad_norm": 0.24569636583328247,
+      "learning_rate": 8.453213475543287e-09,
+      "loss": 0.6532,
+      "mean_token_accuracy": 0.7972725719213486,
+      "step": 420
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.2558843195438385,
+      "learning_rate": 0.0,
+      "loss": 0.652,
+      "mean_token_accuracy": 0.7971837684512139,
+      "step": 425
+    },
+    {
+      "epoch": 5.0,
+      "step": 425,
+      "total_flos": 355840724828160.0,
+      "train_loss": 0.8500821517495548,
+      "train_runtime": 37256.86,
+      "train_samples_per_second": 1.46,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 425,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 355840724828160.0,
+  "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:ca4e4995c6916d6a55038fc3783ba2d9f8f96c4d1b5b160ec4db9bb5194921c8
+size 8056