| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9826435246995995, | |
| "eval_steps": 3, | |
| "global_step": 46, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06408544726301736, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.2569, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12817089452603472, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.2421, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.19225634178905207, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.2788, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.25634178905206945, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.2711, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3204272363150868, | |
| "grad_norm": 0.212262362241745, | |
| "learning_rate": 0.001414213562373095, | |
| "loss": 1.212, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.38451268357810414, | |
| "grad_norm": 2.1214916706085205, | |
| "learning_rate": 0.0011547005383792518, | |
| "loss": 1.1966, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 6.387705326080322, | |
| "learning_rate": 0.001, | |
| "loss": 2.1944, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5126835781041389, | |
| "grad_norm": 2.783672332763672, | |
| "learning_rate": 0.0007559289460184544, | |
| "loss": 1.4648, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5767690253671562, | |
| "grad_norm": 0.4924930930137634, | |
| "learning_rate": 0.0006324555320336759, | |
| "loss": 1.1268, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6408544726301736, | |
| "grad_norm": 0.28960251808166504, | |
| "learning_rate": 0.0005547001962252292, | |
| "loss": 0.9747, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7049399198931909, | |
| "grad_norm": 0.2959640920162201, | |
| "learning_rate": 0.0005, | |
| "loss": 0.9345, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7690253671562083, | |
| "grad_norm": 0.2460373342037201, | |
| "learning_rate": 0.0004588314677411235, | |
| "loss": 0.8967, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8331108144192256, | |
| "grad_norm": 0.26428040862083435, | |
| "learning_rate": 0.00042640143271122083, | |
| "loss": 0.898, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.897196261682243, | |
| "grad_norm": 0.2726432681083679, | |
| "learning_rate": 0.0004, | |
| "loss": 0.8521, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9612817089452603, | |
| "grad_norm": 0.2835930287837982, | |
| "learning_rate": 0.0003779644730092272, | |
| "loss": 0.8334, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9826435246995995, | |
| "step": 46, | |
| "total_flos": 4.671973340489974e+17, | |
| "train_loss": 1.1690324233925862, | |
| "train_runtime": 501.1392, | |
| "train_samples_per_second": 11.949, | |
| "train_steps_per_second": 0.092 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 46, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.671973340489974e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |