| [WARNING|2025-01-21 12:42:54] logging.py:162 >> `ddp_find_unused_parameters` needs to be set as False for LoRA in DDP training. | |
| [INFO|2025-01-21 12:42:54] parser.py:359 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16 | |
| [INFO|2025-01-21 12:42:54] configuration_utils.py:679 >> loading configuration file config.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/config.json | |
| [INFO|2025-01-21 12:42:54] configuration_utils.py:746 >> Model config MistralConfig { | |
| "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2", | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.1", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |
| [INFO|2025-01-21 12:42:54] tokenization_utils_base.py:2211 >> loading file tokenizer.model from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/tokenizer.model | |
| [INFO|2025-01-21 12:42:54] parser.py:359 >> Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16 | |
| [INFO|2025-01-21 12:42:54] parser.py:359 >> Process rank: 4, device: cuda:4, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16 | |
| [INFO|2025-01-21 12:42:54] parser.py:359 >> Process rank: 5, device: cuda:5, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16 | |
| [INFO|2025-01-21 12:42:54] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/tokenizer.json | |
| [INFO|2025-01-21 12:42:54] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at None | |
| [INFO|2025-01-21 12:42:54] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/special_tokens_map.json | |
| [INFO|2025-01-21 12:42:54] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/tokenizer_config.json | |
| [INFO|2025-01-21 12:42:55] configuration_utils.py:679 >> loading configuration file config.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/config.json | |
| [INFO|2025-01-21 12:42:55] configuration_utils.py:746 >> Model config MistralConfig { | |
| "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2", | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.1", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |
| [INFO|2025-01-21 12:42:55] tokenization_utils_base.py:2211 >> loading file tokenizer.model from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/tokenizer.model | |
| [INFO|2025-01-21 12:42:55] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/tokenizer.json | |
| [INFO|2025-01-21 12:42:55] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at None | |
| [INFO|2025-01-21 12:42:55] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/special_tokens_map.json | |
| [INFO|2025-01-21 12:42:55] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/tokenizer_config.json | |
| [INFO|2025-01-21 12:42:55] logging.py:157 >> Add pad token: </s> | |
| [INFO|2025-01-21 12:42:55] logging.py:157 >> Loading dataset followir_advanced_1.json... | |
| [INFO|2025-01-21 12:42:58] configuration_utils.py:679 >> loading configuration file config.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/config.json | |
| [INFO|2025-01-21 12:42:58] configuration_utils.py:746 >> Model config MistralConfig { | |
| "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2", | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.1", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |
| [INFO|2025-01-21 12:42:58] modeling_utils.py:3937 >> loading weights file model.safetensors from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/model.safetensors.index.json | |
| [INFO|2025-01-21 12:42:58] modeling_utils.py:1670 >> Instantiating MistralForCausalLM model under default dtype torch.bfloat16. | |
| [INFO|2025-01-21 12:42:58] configuration_utils.py:1096 >> Generate config GenerationConfig { | |
| "bos_token_id": 1, | |
| "eos_token_id": 2 | |
| } | |
| [INFO|2025-01-21 12:43:04] modeling_utils.py:4800 >> All model checkpoint weights were used when initializing MistralForCausalLM. | |
| [INFO|2025-01-21 12:43:04] modeling_utils.py:4808 >> All the weights of MistralForCausalLM were initialized from the model checkpoint at mistralai/Mistral-7B-Instruct-v0.2. | |
| 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. | |
| [INFO|2025-01-21 12:43:04] configuration_utils.py:1051 >> loading configuration file generation_config.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/generation_config.json | |
| [INFO|2025-01-21 12:43:04] configuration_utils.py:1096 >> Generate config GenerationConfig { | |
| "bos_token_id": 1, | |
| "eos_token_id": 2 | |
| } | |
| [INFO|2025-01-21 12:43:04] logging.py:157 >> Gradient checkpointing enabled. | |
| [INFO|2025-01-21 12:43:04] logging.py:157 >> Using torch SDPA for faster training and inference. | |
| [INFO|2025-01-21 12:43:04] logging.py:157 >> Upcasting trainable params to float32. | |
| [INFO|2025-01-21 12:43:04] logging.py:157 >> Fine-tuning method: LoRA | |
| [INFO|2025-01-21 12:43:05] logging.py:157 >> trainable params: 6,815,744 || all params: 7,248,547,840 || trainable%: 0.0940 | |
| [INFO|2025-01-21 12:43:05] trainer.py:698 >> Using auto half precision backend | |
| [INFO|2025-01-21 12:43:06] trainer.py:2313 >> ***** Running training ***** | |
| [INFO|2025-01-21 12:43:06] trainer.py:2314 >> Num examples = 1,776 | |
| [INFO|2025-01-21 12:43:06] trainer.py:2315 >> Num Epochs = 8 | |
| [INFO|2025-01-21 12:43:06] trainer.py:2316 >> Instantaneous batch size per device = 4 | |
| [INFO|2025-01-21 12:43:06] trainer.py:2319 >> Total train batch size (w. parallel, distributed & accumulation) = 768 | |
| [INFO|2025-01-21 12:43:06] trainer.py:2320 >> Gradient Accumulation steps = 32 | |
| [INFO|2025-01-21 12:43:06] trainer.py:2321 >> Total optimization steps = 16 | |
| [INFO|2025-01-21 12:43:06] trainer.py:2322 >> Number of trainable parameters = 6,815,744 | |
| [INFO|2025-01-21 13:40:59] logging.py:157 >> {'loss': 5.5456, 'learning_rate': 2.3334e-05, 'epoch': 2.16} | |
| [INFO|2025-01-21 14:38:30] logging.py:157 >> {'loss': 1.1889, 'learning_rate': 9.2597e-06, 'epoch': 4.32} | |
| [INFO|2025-01-21 15:36:25] logging.py:157 >> {'loss': 0.3610, 'learning_rate': 2.8822e-07, 'epoch': 6.49} | |
| [INFO|2025-01-21 15:47:57] trainer.py:3801 >> Saving model checkpoint to saves/Mistral-7B-Instruct-v0.2/lora/train_2025-01-21-12-40-17/checkpoint-16 | |
| [INFO|2025-01-21 15:47:57] configuration_utils.py:679 >> loading configuration file config.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/config.json | |
| [INFO|2025-01-21 15:47:57] configuration_utils.py:746 >> Model config MistralConfig { | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.1", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |
| [INFO|2025-01-21 15:47:57] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Mistral-7B-Instruct-v0.2/lora/train_2025-01-21-12-40-17/checkpoint-16/tokenizer_config.json | |
| [INFO|2025-01-21 15:47:57] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Mistral-7B-Instruct-v0.2/lora/train_2025-01-21-12-40-17/checkpoint-16/special_tokens_map.json | |
| [INFO|2025-01-21 15:47:58] trainer.py:2584 >> | |
| Training completed. Do not forget to share your model on huggingface.co/models =) | |
| [INFO|2025-01-21 15:47:58] trainer.py:3801 >> Saving model checkpoint to saves/Mistral-7B-Instruct-v0.2/lora/train_2025-01-21-12-40-17 | |
| [INFO|2025-01-21 15:47:58] configuration_utils.py:679 >> loading configuration file config.json from cache at /nethome/atrinh31/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.2/snapshots/3ad372fc79158a2148299e3318516c786aeded6c/config.json | |
| [INFO|2025-01-21 15:47:58] configuration_utils.py:746 >> Model config MistralConfig { | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.1", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |
| [INFO|2025-01-21 15:47:58] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Mistral-7B-Instruct-v0.2/lora/train_2025-01-21-12-40-17/tokenizer_config.json | |
| [INFO|2025-01-21 15:47:58] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Mistral-7B-Instruct-v0.2/lora/train_2025-01-21-12-40-17/special_tokens_map.json | |
| [WARNING|2025-01-21 15:47:58] logging.py:162 >> No metric eval_loss to plot. | |
| [WARNING|2025-01-21 15:47:58] logging.py:162 >> No metric eval_accuracy to plot. | |
| [INFO|2025-01-21 15:47:58] modelcard.py:449 >> Dropping the following result as it does not have all the necessary fields: | |
| {'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}} | |