| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011281906642222535, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022563813284445073, | |
| "grad_norm": 0.028453228995203972, | |
| "learning_rate": 1e-05, | |
| "loss": 10.376, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022563813284445073, | |
| "eval_loss": 10.37138557434082, | |
| "eval_runtime": 12.7862, | |
| "eval_samples_per_second": 58.422, | |
| "eval_steps_per_second": 29.25, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0045127626568890146, | |
| "grad_norm": 0.030275369063019753, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3744, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0045127626568890146, | |
| "eval_loss": 10.371378898620605, | |
| "eval_runtime": 0.932, | |
| "eval_samples_per_second": 801.543, | |
| "eval_steps_per_second": 401.308, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006769143985333521, | |
| "grad_norm": 0.03374136611819267, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3716, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009025525313778029, | |
| "grad_norm": 0.033730849623680115, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3705, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009025525313778029, | |
| "eval_loss": 10.371350288391113, | |
| "eval_runtime": 0.9394, | |
| "eval_samples_per_second": 795.222, | |
| "eval_steps_per_second": 398.143, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011281906642222535, | |
| "grad_norm": 0.03464337810873985, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3729, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 258618163200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |