| { | |
| "best_metric": 0.16990411281585693, | |
| "best_model_checkpoint": "BERT-AJGT/checkpoint-30", | |
| "epoch": 6.0, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.9e-05, | |
| "loss": 0.5804, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8703703703703703, | |
| "eval_f1": 0.864516129032258, | |
| "eval_loss": 0.436138391494751, | |
| "eval_precision": 0.9054054054054054, | |
| "eval_recall": 0.8271604938271605, | |
| "eval_runtime": 0.0502, | |
| "eval_samples_per_second": 3228.319, | |
| "eval_steps_per_second": 19.928, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.3676, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9135802469135802, | |
| "eval_f1": 0.9135802469135802, | |
| "eval_loss": 0.279801607131958, | |
| "eval_precision": 0.9135802469135802, | |
| "eval_recall": 0.9135802469135802, | |
| "eval_runtime": 0.0493, | |
| "eval_samples_per_second": 3288.154, | |
| "eval_steps_per_second": 20.297, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.7e-05, | |
| "loss": 0.2252, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9320987654320988, | |
| "eval_f1": 0.9325153374233128, | |
| "eval_loss": 0.20178434252738953, | |
| "eval_precision": 0.926829268292683, | |
| "eval_recall": 0.9382716049382716, | |
| "eval_runtime": 0.0509, | |
| "eval_samples_per_second": 3184.457, | |
| "eval_steps_per_second": 19.657, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.138, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9382716049382716, | |
| "eval_f1": 0.9390243902439024, | |
| "eval_loss": 0.17006997764110565, | |
| "eval_precision": 0.927710843373494, | |
| "eval_recall": 0.9506172839506173, | |
| "eval_runtime": 0.0494, | |
| "eval_samples_per_second": 3277.401, | |
| "eval_steps_per_second": 20.231, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.0975, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9444444444444444, | |
| "eval_f1": 0.9454545454545454, | |
| "eval_loss": 0.16990411281585693, | |
| "eval_precision": 0.9285714285714286, | |
| "eval_recall": 0.9629629629629629, | |
| "eval_runtime": 0.0525, | |
| "eval_samples_per_second": 3084.733, | |
| "eval_steps_per_second": 19.042, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.0679, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9567901234567902, | |
| "eval_f1": 0.9575757575757574, | |
| "eval_loss": 0.17372706532478333, | |
| "eval_precision": 0.9404761904761905, | |
| "eval_recall": 0.9753086419753086, | |
| "eval_runtime": 0.0501, | |
| "eval_samples_per_second": 3232.281, | |
| "eval_steps_per_second": 19.952, | |
| "step": 36 | |
| } | |
| ], | |
| "max_steps": 120, | |
| "num_train_epochs": 20, | |
| "total_flos": 420675008084580.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |