| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.025023459493274947, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005004691898654989, | |
| "grad_norm": 62.33938217163086, | |
| "learning_rate": 1e-05, | |
| "loss": 211.9681, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005004691898654989, | |
| "eval_loss": 12.967564582824707, | |
| "eval_runtime": 97.8171, | |
| "eval_samples_per_second": 3.445, | |
| "eval_steps_per_second": 1.728, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010009383797309979, | |
| "grad_norm": 66.62974548339844, | |
| "learning_rate": 2e-05, | |
| "loss": 212.8376, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010009383797309979, | |
| "eval_loss": 12.773856163024902, | |
| "eval_runtime": 74.9182, | |
| "eval_samples_per_second": 4.498, | |
| "eval_steps_per_second": 2.256, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.015014075695964968, | |
| "grad_norm": 61.90747833251953, | |
| "learning_rate": 3e-05, | |
| "loss": 208.4903, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.020018767594619957, | |
| "grad_norm": 64.7207260131836, | |
| "learning_rate": 4e-05, | |
| "loss": 212.0192, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.020018767594619957, | |
| "eval_loss": 12.617764472961426, | |
| "eval_runtime": 73.6294, | |
| "eval_samples_per_second": 4.577, | |
| "eval_steps_per_second": 2.295, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.025023459493274947, | |
| "grad_norm": 66.44071197509766, | |
| "learning_rate": 5e-05, | |
| "loss": 211.7811, | |
| "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": 6332408345395200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |