| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 6414, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.5533, | |
| "step": 2138 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.794291079044342, | |
| "eval_matthews_correlation": 0.44394615350761574, | |
| "eval_runtime": 33.9254, | |
| "eval_samples_per_second": 30.744, | |
| "eval_steps_per_second": 3.861, | |
| "step": 2138 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.5004, | |
| "step": 4276 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.7272064685821533, | |
| "eval_matthews_correlation": 0.5678267214677118, | |
| "eval_runtime": 33.839, | |
| "eval_samples_per_second": 30.822, | |
| "eval_steps_per_second": 3.871, | |
| "step": 4276 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.2865, | |
| "step": 6414 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.8384876251220703, | |
| "eval_matthews_correlation": 0.5957317644481708, | |
| "eval_runtime": 33.7835, | |
| "eval_samples_per_second": 30.873, | |
| "eval_steps_per_second": 3.878, | |
| "step": 6414 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 6414, | |
| "total_flos": 2.3906835263453184e+16, | |
| "train_loss": 0.0, | |
| "train_runtime": 0.0244, | |
| "train_samples_per_second": 1051774.003, | |
| "train_steps_per_second": 262974.251 | |
| } | |
| ], | |
| "max_steps": 6414, | |
| "num_train_epochs": 3, | |
| "total_flos": 2.3906835263453184e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |