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-epoch1-8192
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for OLMoE-1B-7B-0125-Instruct-Distill-bs17k-batch32-epoch1-8192
+
+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-epoch1-8192", 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/h5ipgyj1) 
+
+
+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": 71084393103360.0,
+    "train_loss": 1.2520353261162254,
+    "train_runtime": 7437.5066,
+    "train_samples": 16610,
+    "train_samples_per_second": 1.463,
+    "train_steps_per_second": 0.011
+}

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 sha256:2d4e621d5d6997a455bafb6cbf97a0076848e33d45487ec5d629f35286e69ac1
+size 4997744872

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aad31d681e5ec1829269de2730a13dc65c8308f14c7faa7a4389b705626137e
+size 4997235176

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52ffa301c644f3244371b32e10b484591d5a44f450ba34b438fa1fed29ac485a
+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": 71084393103360.0,
+    "train_loss": 1.2520353261162254,
+    "train_runtime": 7437.5066,
+    "train_samples": 16610,
+    "train_samples_per_second": 1.463,
+    "train_steps_per_second": 0.011
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 85,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.058823529411764705,
+      "grad_norm": 11.891107559204102,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 3.299,
+      "mean_token_accuracy": 0.4547618865966797,
+      "step": 5
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 3.044015884399414,
+      "learning_rate": 1.999145758387301e-05,
+      "loss": 2.3198,
+      "mean_token_accuracy": 0.5092985607683659,
+      "step": 10
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 1.4847815036773682,
+      "learning_rate": 1.9694002659393306e-05,
+      "loss": 1.7828,
+      "mean_token_accuracy": 0.5745997056365013,
+      "step": 15
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 0.9522435069084167,
+      "learning_rate": 1.898390981891979e-05,
+      "loss": 1.4,
+      "mean_token_accuracy": 0.6392715856432915,
+      "step": 20
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.6069338321685791,
+      "learning_rate": 1.789140509396394e-05,
+      "loss": 1.1739,
+      "mean_token_accuracy": 0.6828911945223808,
+      "step": 25
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 0.5275129079818726,
+      "learning_rate": 1.646299237860941e-05,
+      "loss": 1.0771,
+      "mean_token_accuracy": 0.7027453184127808,
+      "step": 30
+    },
+    {
+      "epoch": 0.4117647058823529,
+      "grad_norm": 0.6234576106071472,
+      "learning_rate": 1.4759473930370738e-05,
+      "loss": 1.0115,
+      "mean_token_accuracy": 0.7170437932014465,
+      "step": 35
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.3768845498561859,
+      "learning_rate": 1.2853362242491054e-05,
+      "loss": 0.9793,
+      "mean_token_accuracy": 0.7235300198197365,
+      "step": 40
+    },
+    {
+      "epoch": 0.5294117647058824,
+      "grad_norm": 0.5602439045906067,
+      "learning_rate": 1.0825793454723325e-05,
+      "loss": 0.9547,
+      "mean_token_accuracy": 0.7290156945586205,
+      "step": 45
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 1.601157784461975,
+      "learning_rate": 8.763073687306523e-06,
+      "loss": 0.9258,
+      "mean_token_accuracy": 0.7356743782758712,
+      "step": 50
+    },
+    {
+      "epoch": 0.6470588235294118,
+      "grad_norm": 0.3758750259876251,
+      "learning_rate": 6.7530053079531664e-06,
+      "loss": 0.9166,
+      "mean_token_accuracy": 0.7379220128059387,
+      "step": 55
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.2922804057598114,
+      "learning_rate": 4.881149509103993e-06,
+      "loss": 0.9147,
+      "mean_token_accuracy": 0.7374181285500526,
+      "step": 60
+    },
+    {
+      "epoch": 0.7647058823529411,
+      "grad_norm": 0.322323203086853,
+      "learning_rate": 3.2271842837425917e-06,
+      "loss": 0.9176,
+      "mean_token_accuracy": 0.7366804420948029,
+      "step": 65
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 0.2906600832939148,
+      "learning_rate": 1.861512827298051e-06,
+      "loss": 0.9045,
+      "mean_token_accuracy": 0.7401018545031548,
+      "step": 70
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.33901330828666687,
+      "learning_rate": 8.42266733449425e-07,
+      "loss": 0.8977,
+      "mean_token_accuracy": 0.7416183516383171,
+      "step": 75
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.2457120567560196,
+      "learning_rate": 2.1283154672645522e-07,
+      "loss": 0.9017,
+      "mean_token_accuracy": 0.7403849691152573,
+      "step": 80
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.3804878890514374,
+      "learning_rate": 0.0,
+      "loss": 0.9078,
+      "mean_token_accuracy": 0.7387076124548912,
+      "step": 85
+    },
+    {
+      "epoch": 1.0,
+      "step": 85,
+      "total_flos": 71084393103360.0,
+      "train_loss": 1.2520353261162254,
+      "train_runtime": 7437.5066,
+      "train_samples_per_second": 1.463,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 85,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 71084393103360.0,
+  "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 sha256:4a59eef3c2c972e983e64a5dfba765b9ebfc1a8b833f5e07aca32185cf656653
+size 7544