Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: allenai/OLMoE-1B-7B-0125-Instruct
+library_name: transformers
+model_name: OLMoE-1B-7B-0125-Instruct-Distill-bs17k-batch32-epoch5-8192
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for OLMoE-1B-7B-0125-Instruct-Distill-bs17k-batch32-epoch5-8192
+
+This model is a fine-tuned version of [allenai/OLMoE-1B-7B-0125-Instruct](https://huggingface.co/allenai/OLMoE-1B-7B-0125-Instruct).
+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-Instruct-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/2do20nag) 
+
+
+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": 0.8547473980398739,
+    "train_runtime": 36760.1561,
+    "train_samples": 16610,
+    "train_samples_per_second": 1.48,
+    "train_steps_per_second": 0.012
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "allenai/OLMoE-1B-7B-0125-Instruct",
+  "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:aee437e402a9e37b3d993d535f5e13c9f33137a818287d08e934dcdf5a807ab3
+size 4997744872

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca13bcb004af737846be15ad9938ba5ec296d8b6983324a6ca0b3ee5403b8272
+size 4997235176

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e92e63b97dd2f2aca01d2a5b2ceb9f597c5cf2a1870385a9f16dbb1a16fc9b
+size 3843741912

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "|||IP_ADDRESS|||",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "|||IP_ADDRESS|||",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "|||IP_ADDRESS|||"
+}

tokenizer_config.json

@@ -0,0 +1,248 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50280": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "|||IP_ADDRESS|||",
+  "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": false,
+  "eos_token": "|||IP_ADDRESS|||",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "|||IP_ADDRESS|||",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 355840724828160.0,
+    "train_loss": 0.8547473980398739,
+    "train_runtime": 36760.1561,
+    "train_samples": 16610,
+    "train_samples_per_second": 1.48,
+    "train_steps_per_second": 0.012
+}

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": 21.04814338684082,
+      "learning_rate": 2.3255813953488376e-06,
+      "loss": 3.4185,
+      "mean_token_accuracy": 0.4514082193374634,
+      "step": 5
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 6.334374904632568,
+      "learning_rate": 4.651162790697675e-06,
+      "loss": 3.0621,
+      "mean_token_accuracy": 0.4611593335866928,
+      "step": 10
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 3.551992416381836,
+      "learning_rate": 6.976744186046513e-06,
+      "loss": 2.4392,
+      "mean_token_accuracy": 0.4970729276537895,
+      "step": 15
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 2.2272236347198486,
+      "learning_rate": 9.30232558139535e-06,
+      "loss": 2.0849,
+      "mean_token_accuracy": 0.5340504199266434,
+      "step": 20
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 1.518161416053772,
+      "learning_rate": 1.1627906976744187e-05,
+      "loss": 1.7753,
+      "mean_token_accuracy": 0.575017799437046,
+      "step": 25
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 1.348536491394043,
+      "learning_rate": 1.3953488372093025e-05,
+      "loss": 1.5121,
+      "mean_token_accuracy": 0.6183966279029847,
+      "step": 30
+    },
+    {
+      "epoch": 0.4117647058823529,
+      "grad_norm": 0.8599673509597778,
+      "learning_rate": 1.6279069767441862e-05,
+      "loss": 1.273,
+      "mean_token_accuracy": 0.6627080455422402,
+      "step": 35
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.5608036518096924,
+      "learning_rate": 1.86046511627907e-05,
+      "loss": 1.1304,
+      "mean_token_accuracy": 0.6911454066634178,
+      "step": 40
+    },
+    {
+      "epoch": 0.5294117647058824,
+      "grad_norm": 0.6153124570846558,
+      "learning_rate": 1.9998647325745995e-05,
+      "loss": 1.0442,
+      "mean_token_accuracy": 0.7094879731535911,
+      "step": 45
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.39213573932647705,
+      "learning_rate": 1.9983433942731427e-05,
+      "loss": 0.9779,
+      "mean_token_accuracy": 0.7240924999117851,
+      "step": 50
+    },
+    {
+      "epoch": 0.6470588235294118,
+      "grad_norm": 0.4305499494075775,
+      "learning_rate": 1.9951342140049483e-05,
+      "loss": 0.9446,
+      "mean_token_accuracy": 0.7315783813595772,
+      "step": 55
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.3433878719806671,
+      "learning_rate": 1.9902426173471933e-05,
+      "loss": 0.9255,
+      "mean_token_accuracy": 0.7349760130047798,
+      "step": 60
+    },
+    {
+      "epoch": 0.7647058823529411,
+      "grad_norm": 0.3223603367805481,
+      "learning_rate": 1.9836768742420355e-05,
+      "loss": 0.9154,
+      "mean_token_accuracy": 0.7370613440871239,
+      "step": 65
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 0.37942802906036377,
+      "learning_rate": 1.975448085015093e-05,
+      "loss": 0.8909,
+      "mean_token_accuracy": 0.7428933218121528,
+      "step": 70
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.307282954454422,
+      "learning_rate": 1.965570161608762e-05,
+      "loss": 0.874,
+      "mean_token_accuracy": 0.7465408593416214,
+      "step": 75
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.2984541952610016,
+      "learning_rate": 1.954059804062092e-05,
+      "loss": 0.8687,
+      "mean_token_accuracy": 0.7473416522145271,
+      "step": 80
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.3891313672065735,
+      "learning_rate": 1.9409364722769882e-05,
+      "loss": 0.866,
+      "mean_token_accuracy": 0.7474386006593704,
+      "step": 85
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "grad_norm": 0.3219473659992218,
+      "learning_rate": 1.9262223531184678e-05,
+      "loss": 0.8262,
+      "mean_token_accuracy": 0.7569629773497581,
+      "step": 90
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 0.3140917122364044,
+      "learning_rate": 1.9099423229046015e-05,
+      "loss": 0.8145,
+      "mean_token_accuracy": 0.7599107891321182,
+      "step": 95
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.40147674083709717,
+      "learning_rate": 1.8921239053495465e-05,
+      "loss": 0.8059,
+      "mean_token_accuracy": 0.7613397642970086,
+      "step": 100
+    },
+    {
+      "epoch": 1.2352941176470589,
+      "grad_norm": 0.3681145906448364,
+      "learning_rate": 1.87279722503078e-05,
+      "loss": 0.8088,
+      "mean_token_accuracy": 0.7605203837156296,
+      "step": 105
+    },
+    {
+      "epoch": 1.2941176470588236,
+      "grad_norm": 0.3510204553604126,
+      "learning_rate": 1.8519949564592047e-05,
+      "loss": 0.7982,
+      "mean_token_accuracy": 0.7630930453538894,
+      "step": 110
+    },
+    {
+      "epoch": 1.3529411764705883,
+      "grad_norm": 0.320533812046051,
+      "learning_rate": 1.829752268838222e-05,
+      "loss": 0.802,
+      "mean_token_accuracy": 0.7621062293648719,
+      "step": 115
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 0.31711480021476746,
+      "learning_rate": 1.806106766605178e-05,
+      "loss": 0.7907,
+      "mean_token_accuracy": 0.7650755509734154,
+      "step": 120
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.5543116927146912,
+      "learning_rate": 1.7810984258556955e-05,
+      "loss": 0.7947,
+      "mean_token_accuracy": 0.7635570585727691,
+      "step": 125
+    },
+    {
+      "epoch": 1.5294117647058822,
+      "grad_norm": 0.3128114342689514,
+      "learning_rate": 1.7547695267583794e-05,
+      "loss": 0.7872,
+      "mean_token_accuracy": 0.7655140712857247,
+      "step": 130
+    },
+    {
+      "epoch": 1.5882352941176472,
+      "grad_norm": 0.3138386607170105,
+      "learning_rate": 1.7271645820741586e-05,
+      "loss": 0.7769,
+      "mean_token_accuracy": 0.767977848649025,
+      "step": 135
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 0.3568255603313446,
+      "learning_rate": 1.6983302619011125e-05,
+      "loss": 0.7853,
+      "mean_token_accuracy": 0.7654600262641906,
+      "step": 140
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.2793898284435272,
+      "learning_rate": 1.6683153147720098e-05,
+      "loss": 0.7807,
+      "mean_token_accuracy": 0.7674098491668702,
+      "step": 145
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.27672550082206726,
+      "learning_rate": 1.6371704852379587e-05,
+      "loss": 0.7779,
+      "mean_token_accuracy": 0.7671994060277939,
+      "step": 150
+    },
+    {
+      "epoch": 1.8235294117647058,
+      "grad_norm": 0.2928065061569214,
+      "learning_rate": 1.6049484280775012e-05,
+      "loss": 0.7858,
+      "mean_token_accuracy": 0.7647877380251884,
+      "step": 155
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 0.33357909321784973,
+      "learning_rate": 1.571703619276197e-05,
+      "loss": 0.7778,
+      "mean_token_accuracy": 0.7669166877865792,
+      "step": 160
+    },
+    {
+      "epoch": 1.9411764705882353,
+      "grad_norm": 0.4173744022846222,
+      "learning_rate": 1.537492263927196e-05,
+      "loss": 0.7695,
+      "mean_token_accuracy": 0.7690707325935364,
+      "step": 165
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.28684037923812866,
+      "learning_rate": 1.5023722012085098e-05,
+      "loss": 0.7614,
+      "mean_token_accuracy": 0.7713808581233025,
+      "step": 170
+    },
+    {
+      "epoch": 2.0588235294117645,
+      "grad_norm": 0.32347068190574646,
+      "learning_rate": 1.4664028065976245e-05,
+      "loss": 0.7215,
+      "mean_token_accuracy": 0.7805892318487168,
+      "step": 175
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 0.3120904266834259,
+      "learning_rate": 1.4296448914887866e-05,
+      "loss": 0.7207,
+      "mean_token_accuracy": 0.7809153541922569,
+      "step": 180
+    },
+    {
+      "epoch": 2.176470588235294,
+      "grad_norm": 0.27011847496032715,
+      "learning_rate": 1.392160600382663e-05,
+      "loss": 0.7137,
+      "mean_token_accuracy": 0.7821896791458129,
+      "step": 185
+    },
+    {
+      "epoch": 2.235294117647059,
+      "grad_norm": 0.2704910933971405,
+      "learning_rate": 1.3540133058221927e-05,
+      "loss": 0.7079,
+      "mean_token_accuracy": 0.7843272894620895,
+      "step": 190
+    },
+    {
+      "epoch": 2.2941176470588234,
+      "grad_norm": 0.26255378127098083,
+      "learning_rate": 1.3152675012522629e-05,
+      "loss": 0.7096,
+      "mean_token_accuracy": 0.7832606792449951,
+      "step": 195
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.24626174569129944,
+      "learning_rate": 1.2759886919843354e-05,
+      "loss": 0.7145,
+      "mean_token_accuracy": 0.7819388702511787,
+      "step": 200
+    },
+    {
+      "epoch": 2.411764705882353,
+      "grad_norm": 0.25306323170661926,
+      "learning_rate": 1.2362432844503725e-05,
+      "loss": 0.7146,
+      "mean_token_accuracy": 0.7821550950407982,
+      "step": 205
+    },
+    {
+      "epoch": 2.4705882352941178,
+      "grad_norm": 0.25537386536598206,
+      "learning_rate": 1.1960984739332851e-05,
+      "loss": 0.7193,
+      "mean_token_accuracy": 0.7801969021558761,
+      "step": 210
+    },
+    {
+      "epoch": 2.5294117647058822,
+      "grad_norm": 0.2627454400062561,
+      "learning_rate": 1.1556221309637204e-05,
+      "loss": 0.7044,
+      "mean_token_accuracy": 0.7845285147428512,
+      "step": 215
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 0.25752195715904236,
+      "learning_rate": 1.1148826865752445e-05,
+      "loss": 0.7086,
+      "mean_token_accuracy": 0.7835307970643044,
+      "step": 220
+    },
+    {
+      "epoch": 2.6470588235294117,
+      "grad_norm": 0.25302332639694214,
+      "learning_rate": 1.0739490166119155e-05,
+      "loss": 0.7099,
+      "mean_token_accuracy": 0.7831782385706901,
+      "step": 225
+    },
+    {
+      "epoch": 2.7058823529411766,
+      "grad_norm": 0.25182807445526123,
+      "learning_rate": 1.0328903252838415e-05,
+      "loss": 0.7103,
+      "mean_token_accuracy": 0.783260951936245,
+      "step": 230
+    },
+    {
+      "epoch": 2.764705882352941,
+      "grad_norm": 0.24797865748405457,
+      "learning_rate": 9.917760281675867e-06,
+      "loss": 0.7101,
+      "mean_token_accuracy": 0.7828504905104637,
+      "step": 235
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 0.2946624755859375,
+      "learning_rate": 9.506756348492348e-06,
+      "loss": 0.708,
+      "mean_token_accuracy": 0.7837049275636673,
+      "step": 240
+    },
+    {
+      "epoch": 2.8823529411764706,
+      "grad_norm": 0.3295968770980835,
+      "learning_rate": 9.096586314085162e-06,
+      "loss": 0.7069,
+      "mean_token_accuracy": 0.7832710444927216,
+      "step": 245
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.2471035271883011,
+      "learning_rate": 8.687943629426725e-06,
+      "loss": 0.709,
+      "mean_token_accuracy": 0.7834857434034348,
+      "step": 250
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.24563513696193695,
+      "learning_rate": 8.281519163286772e-06,
+      "loss": 0.7071,
+      "mean_token_accuracy": 0.7836518883705139,
+      "step": 255
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 0.2883757948875427,
+      "learning_rate": 7.878000034220092e-06,
+      "loss": 0.6674,
+      "mean_token_accuracy": 0.7938904002308845,
+      "step": 260
+    },
+    {
+      "epoch": 3.1176470588235294,
+      "grad_norm": 0.27395448088645935,
+      "learning_rate": 7.478068448894577e-06,
+      "loss": 0.6634,
+      "mean_token_accuracy": 0.7947225421667099,
+      "step": 265
+    },
+    {
+      "epoch": 3.176470588235294,
+      "grad_norm": 0.26141196489334106,
+      "learning_rate": 7.082400548723505e-06,
+      "loss": 0.6639,
+      "mean_token_accuracy": 0.7947093069553375,
+      "step": 270
+    },
+    {
+      "epoch": 3.235294117647059,
+      "grad_norm": 0.255613774061203,
+      "learning_rate": 6.6916652667519855e-06,
+      "loss": 0.6595,
+      "mean_token_accuracy": 0.7959247648715972,
+      "step": 275
+    },
+    {
+      "epoch": 3.2941176470588234,
+      "grad_norm": 0.24434104561805725,
+      "learning_rate": 6.3065231967302055e-06,
+      "loss": 0.6628,
+      "mean_token_accuracy": 0.7947000727057457,
+      "step": 280
+    },
+    {
+      "epoch": 3.3529411764705883,
+      "grad_norm": 0.2408313900232315,
+      "learning_rate": 5.927625476285426e-06,
+      "loss": 0.6596,
+      "mean_token_accuracy": 0.7956547513604164,
+      "step": 285
+    },
+    {
+      "epoch": 3.411764705882353,
+      "grad_norm": 0.2657158374786377,
+      "learning_rate": 5.555612686080909e-06,
+      "loss": 0.656,
+      "mean_token_accuracy": 0.7964748367667198,
+      "step": 290
+    },
+    {
+      "epoch": 3.4705882352941178,
+      "grad_norm": 0.5136517882347107,
+      "learning_rate": 5.191113766822905e-06,
+      "loss": 0.6581,
+      "mean_token_accuracy": 0.7958363279700279,
+      "step": 295
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 0.23569130897521973,
+      "learning_rate": 4.834744955946631e-06,
+      "loss": 0.6763,
+      "mean_token_accuracy": 0.7909138843417167,
+      "step": 300
+    },
+    {
+      "epoch": 3.588235294117647,
+      "grad_norm": 0.23169729113578796,
+      "learning_rate": 4.487108745778958e-06,
+      "loss": 0.6614,
+      "mean_token_accuracy": 0.7953535467386246,
+      "step": 305
+    },
+    {
+      "epoch": 3.6470588235294117,
+      "grad_norm": 0.260445237159729,
+      "learning_rate": 4.148792864939164e-06,
+      "loss": 0.6689,
+      "mean_token_accuracy": 0.792862094938755,
+      "step": 310
+    },
+    {
+      "epoch": 3.7058823529411766,
+      "grad_norm": 0.23310521245002747,
+      "learning_rate": 3.820369284699823e-06,
+      "loss": 0.6603,
+      "mean_token_accuracy": 0.7954040706157685,
+      "step": 315
+    },
+    {
+      "epoch": 3.764705882352941,
+      "grad_norm": 0.2321671098470688,
+      "learning_rate": 3.502393251987776e-06,
+      "loss": 0.6556,
+      "mean_token_accuracy": 0.7969529747962951,
+      "step": 320
+    },
+    {
+      "epoch": 3.8235294117647056,
+      "grad_norm": 0.23052778840065002,
+      "learning_rate": 3.195402350659945e-06,
+      "loss": 0.6638,
+      "mean_token_accuracy": 0.7944248780608177,
+      "step": 325
+    },
+    {
+      "epoch": 3.8823529411764706,
+      "grad_norm": 0.2269795835018158,
+      "learning_rate": 2.8999155926411203e-06,
+      "loss": 0.6532,
+      "mean_token_accuracy": 0.7974555715918541,
+      "step": 330
+    },
+    {
+      "epoch": 3.9411764705882355,
+      "grad_norm": 0.26359397172927856,
+      "learning_rate": 2.616432540460255e-06,
+      "loss": 0.658,
+      "mean_token_accuracy": 0.796060574054718,
+      "step": 335
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.2300868183374405,
+      "learning_rate": 2.345432462668702e-06,
+      "loss": 0.6696,
+      "mean_token_accuracy": 0.7929902136325836,
+      "step": 340
+    },
+    {
+      "epoch": 4.0588235294117645,
+      "grad_norm": 0.2431250661611557,
+      "learning_rate": 2.0873735235683535e-06,
+      "loss": 0.6374,
+      "mean_token_accuracy": 0.8019135504961014,
+      "step": 345
+    },
+    {
+      "epoch": 4.117647058823529,
+      "grad_norm": 0.2521369755268097,
+      "learning_rate": 1.8426920086195065e-06,
+      "loss": 0.6449,
+      "mean_token_accuracy": 0.7989285483956337,
+      "step": 350
+    },
+    {
+      "epoch": 4.176470588235294,
+      "grad_norm": 0.2348567396402359,
+      "learning_rate": 1.6118015868380387e-06,
+      "loss": 0.639,
+      "mean_token_accuracy": 0.8011548355221748,
+      "step": 355
+    },
+    {
+      "epoch": 4.235294117647059,
+      "grad_norm": 0.2301347851753235,
+      "learning_rate": 1.395092611428902e-06,
+      "loss": 0.638,
+      "mean_token_accuracy": 0.8016765296459198,
+      "step": 360
+    },
+    {
+      "epoch": 4.294117647058823,
+      "grad_norm": 0.22677163779735565,
+      "learning_rate": 1.1929314598383423e-06,
+      "loss": 0.6395,
+      "mean_token_accuracy": 0.8011483311653137,
+      "step": 365
+    },
+    {
+      "epoch": 4.352941176470588,
+      "grad_norm": 0.3107834458351135,
+      "learning_rate": 1.0056599143405244e-06,
+      "loss": 0.6366,
+      "mean_token_accuracy": 0.8016634568572044,
+      "step": 370
+    },
+    {
+      "epoch": 4.411764705882353,
+      "grad_norm": 0.22472035884857178,
+      "learning_rate": 8.335945842058524e-07,
+      "loss": 0.6374,
+      "mean_token_accuracy": 0.8015297800302505,
+      "step": 375
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 0.22342084348201752,
+      "learning_rate": 6.770263704277958e-07,
+      "loss": 0.6428,
+      "mean_token_accuracy": 0.7997823596000672,
+      "step": 380
+    },
+    {
+      "epoch": 4.529411764705882,
+      "grad_norm": 0.2275530993938446,
+      "learning_rate": 5.362199739132656e-07,
+      "loss": 0.6386,
+      "mean_token_accuracy": 0.800740472972393,
+      "step": 385
+    },
+    {
+      "epoch": 4.588235294117647,
+      "grad_norm": 0.2201569676399231,
+      "learning_rate": 4.114134479679543e-07,
+      "loss": 0.6375,
+      "mean_token_accuracy": 0.801284721493721,
+      "step": 390
+    },
+    {
+      "epoch": 4.647058823529412,
+      "grad_norm": 0.461182564496994,
+      "learning_rate": 3.028177958332512e-07,
+      "loss": 0.6447,
+      "mean_token_accuracy": 0.7993519201874733,
+      "step": 395
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 0.2319057285785675,
+      "learning_rate": 2.106166139551602e-07,
+      "loss": 0.6333,
+      "mean_token_accuracy": 0.802707064151764,
+      "step": 400
+    },
+    {
+      "epoch": 4.764705882352941,
+      "grad_norm": 0.22582513093948364,
+      "learning_rate": 1.349657815883032e-07,
+      "loss": 0.6323,
+      "mean_token_accuracy": 0.8026360154151917,
+      "step": 405
+    },
+    {
+      "epoch": 4.823529411764706,
+      "grad_norm": 0.2295258790254593,
+      "learning_rate": 7.599319725980047e-08,
+      "loss": 0.6358,
+      "mean_token_accuracy": 0.801770193874836,
+      "step": 410
+    },
+    {
+      "epoch": 4.882352941176471,
+      "grad_norm": 0.21853575110435486,
+      "learning_rate": 3.379856253855951e-08,
+      "loss": 0.6377,
+      "mean_token_accuracy": 0.8013792619109154,
+      "step": 415
+    },
+    {
+      "epoch": 4.9411764705882355,
+      "grad_norm": 0.21868692338466644,
+      "learning_rate": 8.453213475543287e-09,
+      "loss": 0.6354,
+      "mean_token_accuracy": 0.8020963743329048,
+      "step": 420
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.2259187251329422,
+      "learning_rate": 0.0,
+      "loss": 0.6423,
+      "mean_token_accuracy": 0.800124317407608,
+      "step": 425
+    },
+    {
+      "epoch": 5.0,
+      "step": 425,
+      "total_flos": 355840724828160.0,
+      "train_loss": 0.8547473980398739,
+      "train_runtime": 36760.1561,
+      "train_samples_per_second": 1.48,
+      "train_steps_per_second": 0.012
+    }
+  ],
+  "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 sha256:14d1d37d8de7246cbbe098ed078a4fc76239817e2b27ea2efee61eb8c57ce29b
+size 7544