| { | |
| "best_metric": 0.7684440341259363, | |
| "best_model_checkpoint": "outputs/time_lm_nli/checkpoint-844", | |
| "epoch": 4.0, | |
| "global_step": 844, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.666666666666666e-07, | |
| "loss": 0.5392, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7, | |
| "eval_f1": 0.6998718119161117, | |
| "eval_loss": 0.4048246741294861, | |
| "eval_runtime": 5.0256, | |
| "eval_samples_per_second": 596.939, | |
| "eval_steps_per_second": 74.617, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.333333333333333e-07, | |
| "loss": 0.3725, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.759, | |
| "eval_f1": 0.7583549419422403, | |
| "eval_loss": 0.3489450216293335, | |
| "eval_runtime": 5.103, | |
| "eval_samples_per_second": 587.885, | |
| "eval_steps_per_second": 73.486, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9e-07, | |
| "loss": 0.3158, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7613333333333333, | |
| "eval_f1": 0.7569694772671423, | |
| "eval_loss": 0.3286795914173126, | |
| "eval_runtime": 5.4646, | |
| "eval_samples_per_second": 548.991, | |
| "eval_steps_per_second": 68.624, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.666666666666667e-07, | |
| "loss": 0.289, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.769, | |
| "eval_f1": 0.7684440341259363, | |
| "eval_loss": 0.33065709471702576, | |
| "eval_runtime": 5.2159, | |
| "eval_samples_per_second": 575.162, | |
| "eval_steps_per_second": 71.895, | |
| "step": 844 | |
| } | |
| ], | |
| "max_steps": 6330, | |
| "num_train_epochs": 30, | |
| "total_flos": 5732616477926016.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |