| { | |
| "best_metric": 0.09872297197580338, | |
| "best_model_checkpoint": "saves/LLaMA3-8B/lora/train_1/checkpoint-60", | |
| "epoch": 2.918918918918919, | |
| "eval_steps": 10, | |
| "global_step": 81, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.36036036036036034, | |
| "grad_norm": 0.16021642088890076, | |
| "learning_rate": 0.00028885859539033357, | |
| "loss": 0.3349, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.36036036036036034, | |
| "eval_loss": 0.127897709608078, | |
| "eval_runtime": 93.3043, | |
| "eval_samples_per_second": 15.691, | |
| "eval_steps_per_second": 1.961, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7207207207207207, | |
| "grad_norm": 0.18659265339374542, | |
| "learning_rate": 0.00025708946018368484, | |
| "loss": 0.1057, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7207207207207207, | |
| "eval_loss": 0.11239976435899734, | |
| "eval_runtime": 93.2473, | |
| "eval_samples_per_second": 15.7, | |
| "eval_steps_per_second": 1.963, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0810810810810811, | |
| "grad_norm": 0.17047131061553955, | |
| "learning_rate": 0.0002094119649058735, | |
| "loss": 0.0941, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0810810810810811, | |
| "eval_loss": 0.10465721040964127, | |
| "eval_runtime": 93.2208, | |
| "eval_samples_per_second": 15.705, | |
| "eval_steps_per_second": 1.963, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4414414414414414, | |
| "grad_norm": 0.1429479867219925, | |
| "learning_rate": 0.00015290869976577364, | |
| "loss": 0.0853, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4414414414414414, | |
| "eval_loss": 0.09956511110067368, | |
| "eval_runtime": 93.1814, | |
| "eval_samples_per_second": 15.711, | |
| "eval_steps_per_second": 1.964, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.8018018018018018, | |
| "grad_norm": 0.2423897683620453, | |
| "learning_rate": 9.597334127929346e-05, | |
| "loss": 0.0793, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8018018018018018, | |
| "eval_loss": 0.09926876425743103, | |
| "eval_runtime": 93.2398, | |
| "eval_samples_per_second": 15.701, | |
| "eval_steps_per_second": 1.963, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.1621621621621623, | |
| "grad_norm": 0.14185480773448944, | |
| "learning_rate": 4.706375431968997e-05, | |
| "loss": 0.0768, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.1621621621621623, | |
| "eval_loss": 0.09872297197580338, | |
| "eval_runtime": 93.2225, | |
| "eval_samples_per_second": 15.704, | |
| "eval_steps_per_second": 1.963, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.5225225225225225, | |
| "grad_norm": 0.16820678114891052, | |
| "learning_rate": 1.3445558855078014e-05, | |
| "loss": 0.0688, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.5225225225225225, | |
| "eval_loss": 0.10358671098947525, | |
| "eval_runtime": 93.1923, | |
| "eval_samples_per_second": 15.709, | |
| "eval_steps_per_second": 1.964, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8828828828828827, | |
| "grad_norm": 0.19234561920166016, | |
| "learning_rate": 1.1280712436549378e-07, | |
| "loss": 0.072, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.8828828828828827, | |
| "eval_loss": 0.10096894949674606, | |
| "eval_runtime": 93.213, | |
| "eval_samples_per_second": 15.706, | |
| "eval_steps_per_second": 1.963, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.918918918918919, | |
| "step": 81, | |
| "total_flos": 1.3175616566919168e+17, | |
| "train_loss": 0.11416268514262305, | |
| "train_runtime": 3957.6024, | |
| "train_samples_per_second": 5.384, | |
| "train_steps_per_second": 0.02 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 81, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3175616566919168e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |