| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013130898645876077, | |
| "eval_steps": 2, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003282724661469019, | |
| "grad_norm": 1.079748272895813, | |
| "learning_rate": 1e-05, | |
| "loss": 1.5744, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003282724661469019, | |
| "eval_loss": 1.6917016506195068, | |
| "eval_runtime": 67.3584, | |
| "eval_samples_per_second": 7.631, | |
| "eval_steps_per_second": 3.815, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006565449322938038, | |
| "grad_norm": 1.146652340888977, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6875, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006565449322938038, | |
| "eval_loss": 1.6832669973373413, | |
| "eval_runtime": 14.6759, | |
| "eval_samples_per_second": 35.023, | |
| "eval_steps_per_second": 17.512, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009848173984407058, | |
| "grad_norm": 0.9836621284484863, | |
| "learning_rate": 3e-05, | |
| "loss": 1.5016, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013130898645876077, | |
| "grad_norm": 1.1562381982803345, | |
| "learning_rate": 4e-05, | |
| "loss": 1.709, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013130898645876077, | |
| "eval_loss": 1.664827585220337, | |
| "eval_runtime": 14.6498, | |
| "eval_samples_per_second": 35.086, | |
| "eval_steps_per_second": 17.543, | |
| "step": 4 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1113561979944960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |