| 05/08/2024 19:50:37 - INFO - transformers.tokenization_utils_base - loading file tokenizer.model from cache at /root/.cache/huggingface/hub/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/tokenizer.model | |
| 05/08/2024 19:50:37 - INFO - transformers.tokenization_utils_base - loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/tokenizer.json | |
| 05/08/2024 19:50:37 - INFO - transformers.tokenization_utils_base - loading file added_tokens.json from cache at /root/.cache/huggingface/hub/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/added_tokens.json | |
| 05/08/2024 19:50:37 - INFO - transformers.tokenization_utils_base - loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/special_tokens_map.json | |
| 05/08/2024 19:50:37 - INFO - transformers.tokenization_utils_base - loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/tokenizer_config.json | |
| 05/08/2024 19:50:38 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. | |
| 05/08/2024 19:50:38 - INFO - llmtuner.data.loader - Loading dataset realign_no_robots.jsonl... | |
| 05/08/2024 19:50:39 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/config.json | |
| 05/08/2024 19:50:39 - INFO - transformers.configuration_utils - Model config MistralConfig { | |
| "_name_or_path": "chujiezheng/Starling-LM-7B-alpha-ExPO", | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 32000, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 8192, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.40.1", | |
| "use_cache": true, | |
| "vocab_size": 32002 | |
| } | |
| 05/08/2024 19:50:39 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/config.json | |
| 05/08/2024 19:50:39 - INFO - transformers.configuration_utils - Model config MistralConfig { | |
| "_name_or_path": "chujiezheng/Starling-LM-7B-alpha-ExPO", | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 32000, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 8192, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.40.1", | |
| "use_cache": true, | |
| "vocab_size": 32002 | |
| } | |
| 05/08/2024 19:50:39 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/config.json | |
| 05/08/2024 19:50:39 - INFO - transformers.configuration_utils - Model config MistralConfig { | |
| "_name_or_path": "chujiezheng/Starling-LM-7B-alpha-ExPO", | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 32000, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 8192, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.40.1", | |
| "use_cache": true, | |
| "vocab_size": 32002 | |
| } | |
| 05/08/2024 19:50:40 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/config.json | |
| 05/08/2024 19:50:40 - INFO - transformers.configuration_utils - Model config MistralConfig { | |
| "_name_or_path": "chujiezheng/Starling-LM-7B-alpha-ExPO", | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 32000, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 8192, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.40.1", | |
| "use_cache": true, | |
| "vocab_size": 32002 | |
| } | |
| 05/08/2024 19:50:40 - INFO - transformers.modeling_utils - loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/model.safetensors.index.json | |
| 05/08/2024 19:50:40 - INFO - transformers.modeling_utils - Instantiating MistralForCausalLM model under default dtype torch.float16. | |
| 05/08/2024 19:50:40 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig { | |
| "bos_token_id": 1, | |
| "eos_token_id": 32000 | |
| } | |
| 05/08/2024 19:51:52 - INFO - transformers.modeling_utils - All model checkpoint weights were used when initializing MistralForCausalLM. | |
| 05/08/2024 19:51:52 - INFO - transformers.modeling_utils - All the weights of MistralForCausalLM were initialized from the model checkpoint at chujiezheng/Starling-LM-7B-alpha-ExPO. | |
| If your task is similar to the task the model of the checkpoint was trained on, you can already use MistralForCausalLM for predictions without further training. | |
| 05/08/2024 19:51:52 - INFO - transformers.generation.configuration_utils - loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/generation_config.json | |
| 05/08/2024 19:51:52 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig { | |
| "bos_token_id": 1, | |
| "do_sample": true, | |
| "eos_token_id": 32000, | |
| "max_length": 8192, | |
| "pad_token_id": 0, | |
| "temperature": 0.5 | |
| } | |
| 05/08/2024 19:51:52 - INFO - transformers.tokenization_utils_base - loading file tokenizer.model from cache at huggingface_tokenizers_cache/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/tokenizer.model | |
| 05/08/2024 19:51:52 - INFO - transformers.tokenization_utils_base - loading file added_tokens.json from cache at huggingface_tokenizers_cache/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/added_tokens.json | |
| 05/08/2024 19:51:52 - INFO - transformers.tokenization_utils_base - loading file special_tokens_map.json from cache at huggingface_tokenizers_cache/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/special_tokens_map.json | |
| 05/08/2024 19:51:52 - INFO - transformers.tokenization_utils_base - loading file tokenizer_config.json from cache at huggingface_tokenizers_cache/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/tokenizer_config.json | |
| 05/08/2024 19:51:52 - INFO - transformers.tokenization_utils_base - loading file tokenizer.json from cache at huggingface_tokenizers_cache/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/tokenizer.json | |
| 05/08/2024 19:51:52 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. | |
| 05/08/2024 19:51:53 - INFO - transformers.tokenization_utils_base - loading file tokenizer.model from cache at huggingface_tokenizers_cache/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/tokenizer.model | |
| 05/08/2024 19:51:53 - INFO - transformers.tokenization_utils_base - loading file tokenizer.json from cache at huggingface_tokenizers_cache/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/tokenizer.json | |
| 05/08/2024 19:51:53 - INFO - transformers.tokenization_utils_base - loading file added_tokens.json from cache at huggingface_tokenizers_cache/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/added_tokens.json | |
| 05/08/2024 19:51:53 - INFO - transformers.tokenization_utils_base - loading file special_tokens_map.json from cache at huggingface_tokenizers_cache/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/special_tokens_map.json | |
| 05/08/2024 19:51:53 - INFO - transformers.tokenization_utils_base - loading file tokenizer_config.json from cache at huggingface_tokenizers_cache/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/tokenizer_config.json | |
| 05/08/2024 19:51:53 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. | |
| 05/08/2024 19:51:53 - WARNING - transformers.models.llama.modeling_llama - chujiezheng/Starling-LM-7B-alpha-ExPO does not have a padding token! Will use pad_token = <unk>. | |
| 05/08/2024 19:51:54 - INFO - llmtuner.model.utils.checkpointing - Gradient checkpointing enabled. | |
| 05/08/2024 19:51:54 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA | |
| 05/08/2024 19:51:54 - WARNING - transformers.models.llama.modeling_llama - Unsloth cannot patch MLP layers with our manual autograd engine since either LoRA adapters | |
| are not enabled or a bias term (like in Qwen) is used. | |
| 05/08/2024 19:51:54 - WARNING - transformers.models.llama.modeling_llama - Unsloth cannot patch Attention layers with our manual autograd engine since either LoRA adapters | |
| are not enabled or a bias term (like in Qwen) is used. | |
| 05/08/2024 19:51:54 - WARNING - transformers.models.llama.modeling_llama - Unsloth cannot patch O projection layer with our manual autograd engine since either LoRA adapters | |
| are not enabled or a bias term (like in Qwen) is used. | |
| 05/08/2024 19:51:54 - WARNING - transformers.models.llama.modeling_llama - Unsloth 2024.4 patched 32 layers with 0 QKV layers, 0 O layers and 0 MLP layers. | |
| 05/08/2024 19:51:54 - INFO - llmtuner.model.loader - trainable params: 3407872 || all params: 7245156352 || trainable%: 0.0470 | |
| 05/08/2024 19:51:54 - INFO - transformers.trainer - Using auto half precision backend | |
| 05/08/2024 19:51:54 - WARNING - transformers.trainer - ==((====))== Unsloth - 2x faster free finetuning | Num GPUs = 1 | |
| \\ /| Num examples = 9,500 | Num Epochs = 1 | |
| O^O/ \_/ \ Batch size per device = 2 | Gradient Accumulation steps = 8 | |
| \ / Total batch size = 16 | Total steps = 60 | |
| "-____-" Number of trainable parameters = 3,407,872 | |
| 05/08/2024 19:53:17 - INFO - llmtuner.extras.callbacks - {'loss': 1.8162, 'learning_rate': 4.9148e-05, 'epoch': 0.01} | |
| 05/08/2024 19:54:37 - INFO - llmtuner.extras.callbacks - {'loss': 1.7065, 'learning_rate': 4.6651e-05, 'epoch': 0.02} | |
| 05/08/2024 19:55:55 - INFO - llmtuner.extras.callbacks - {'loss': 1.6809, 'learning_rate': 4.2678e-05, 'epoch': 0.03} | |
| 05/08/2024 19:57:22 - INFO - llmtuner.extras.callbacks - {'loss': 1.7278, 'learning_rate': 3.7500e-05, 'epoch': 0.03} | |
| 05/08/2024 19:58:49 - INFO - llmtuner.extras.callbacks - {'loss': 1.5573, 'learning_rate': 3.1470e-05, 'epoch': 0.04} | |
| 05/08/2024 20:00:11 - INFO - llmtuner.extras.callbacks - {'loss': 1.5858, 'learning_rate': 2.5000e-05, 'epoch': 0.05} | |
| 05/08/2024 20:01:39 - INFO - llmtuner.extras.callbacks - {'loss': 1.4219, 'learning_rate': 1.8530e-05, 'epoch': 0.06} | |
| 05/08/2024 20:02:51 - INFO - llmtuner.extras.callbacks - {'loss': 1.6545, 'learning_rate': 1.2500e-05, 'epoch': 0.07} | |
| 05/08/2024 20:04:11 - INFO - llmtuner.extras.callbacks - {'loss': 1.5896, 'learning_rate': 7.3223e-06, 'epoch': 0.08} | |
| 05/08/2024 20:05:24 - INFO - llmtuner.extras.callbacks - {'loss': 1.4727, 'learning_rate': 3.3494e-06, 'epoch': 0.08} | |
| 05/08/2024 20:06:42 - INFO - llmtuner.extras.callbacks - {'loss': 1.6785, 'learning_rate': 8.5185e-07, 'epoch': 0.09} | |
| 05/08/2024 20:08:03 - INFO - llmtuner.extras.callbacks - {'loss': 1.6034, 'learning_rate': 0.0000e+00, 'epoch': 0.10} | |
| 05/08/2024 20:08:03 - INFO - transformers.trainer - | |
| Training completed. Do not forget to share your model on huggingface.co/models =) | |
| 05/08/2024 20:08:03 - INFO - transformers.trainer - Saving model checkpoint to saves/OpenChat3.5-7B-Chat/lora/train_2024-05-08-19-49-29 | |
| 05/08/2024 20:08:03 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--chujiezheng--Starling-LM-7B-alpha-ExPO/snapshots/fc53fe6883ff3ea00a89be453a6cc586b3c369c3/config.json | |
| 05/08/2024 20:08:03 - INFO - transformers.configuration_utils - Model config MistralConfig { | |
| "_name_or_path": "openchat/openchat_3.5", | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 32000, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 8192, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.40.1", | |
| "use_cache": true, | |
| "vocab_size": 32002 | |
| } | |
| 05/08/2024 20:08:03 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves/OpenChat3.5-7B-Chat/lora/train_2024-05-08-19-49-29/tokenizer_config.json | |
| 05/08/2024 20:08:03 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves/OpenChat3.5-7B-Chat/lora/train_2024-05-08-19-49-29/special_tokens_map.json | |
| 05/08/2024 20:08:03 - INFO - transformers.modelcard - Dropping the following result as it does not have all the necessary fields: | |
| {'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}} | |