| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00047224386673278083, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.722438667327808e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.722438667327808e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 583.464, | |
| "eval_samples_per_second": 15.281, | |
| "eval_steps_per_second": 7.641, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.444877334655616e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00014167316001983425, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014167316001983425, | |
| "eval_loss": NaN, | |
| "eval_runtime": 582.2448, | |
| "eval_samples_per_second": 15.313, | |
| "eval_steps_per_second": 7.657, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00018889754669311232, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00023612193336639041, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002833463200396685, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002833463200396685, | |
| "eval_loss": NaN, | |
| "eval_runtime": 581.9904, | |
| "eval_samples_per_second": 15.32, | |
| "eval_steps_per_second": 7.66, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00033057070671294655, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00037779509338622464, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00042501948005950273, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00042501948005950273, | |
| "eval_loss": NaN, | |
| "eval_runtime": 582.595, | |
| "eval_samples_per_second": 15.304, | |
| "eval_steps_per_second": 7.652, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00047224386673278083, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4104, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "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": 3984672593805312.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |