| { | |
| "best_metric": 0.9037830233573914, | |
| "best_model_checkpoint": "./opt_trained3/checkpoint-2643", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2643, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18917896329928113, | |
| "grad_norm": 14.101566314697266, | |
| "learning_rate": 9.784324123011948e-05, | |
| "loss": 0.9633, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.37835792659856227, | |
| "grad_norm": 6.891010761260986, | |
| "learning_rate": 9.14928228350961e-05, | |
| "loss": 0.908, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5675368898978433, | |
| "grad_norm": 11.300192832946777, | |
| "learning_rate": 8.150526293753795e-05, | |
| "loss": 0.9047, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7567158531971245, | |
| "grad_norm": 5.797523021697998, | |
| "learning_rate": 6.875604231051344e-05, | |
| "loss": 0.9013, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9458948164964056, | |
| "grad_norm": 9.209771156311035, | |
| "learning_rate": 5.4362720963179184e-05, | |
| "loss": 0.9028, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.9037830233573914, | |
| "eval_runtime": 1653.9704, | |
| "eval_samples_per_second": 19.886, | |
| "eval_steps_per_second": 4.972, | |
| "step": 2643 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5286, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.0851212666249216e+17, | |
| "train_batch_size": 14, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |