| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 5.083003563081455, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5562, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.42128339409828186, | |
| "eval_runtime": 16.4858, | |
| "eval_samples_per_second": 21.17, | |
| "eval_steps_per_second": 0.364, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 1.558087322428163, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4266, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.3593507707118988, | |
| "eval_runtime": 16.2917, | |
| "eval_samples_per_second": 21.422, | |
| "eval_steps_per_second": 0.368, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.3076923076923075, | |
| "grad_norm": 0.8119632837482119, | |
| "learning_rate": 5e-06, | |
| "loss": 0.3759, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.33126652240753174, | |
| "eval_runtime": 15.765, | |
| "eval_samples_per_second": 22.138, | |
| "eval_steps_per_second": 0.381, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 39, | |
| "total_flos": 65117072916480.0, | |
| "train_loss": 0.42646326774205917, | |
| "train_runtime": 2905.9313, | |
| "train_samples_per_second": 6.844, | |
| "train_steps_per_second": 0.013 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 39, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 65117072916480.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |