| { | |
| "best_metric": 0.08565760403871536, | |
| "best_model_checkpoint": "BBC_CLS_deberta_v3_large_v2/checkpoint-594", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 660, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 6.6e-06, | |
| "loss": 1.235, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.796420581655481, | |
| "eval_f1": 0.4417921999471439, | |
| "eval_loss": 0.633094072341919, | |
| "eval_precision": 0.4046829607174435, | |
| "eval_recall": 0.4873423547822885, | |
| "eval_runtime": 6.7539, | |
| "eval_samples_per_second": 66.184, | |
| "eval_steps_per_second": 2.073, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.32e-05, | |
| "loss": 0.4336, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8970917225950783, | |
| "eval_f1": 0.6910171764080433, | |
| "eval_loss": 0.22008153796195984, | |
| "eval_precision": 0.6753658536585365, | |
| "eval_recall": 0.7090775277247049, | |
| "eval_runtime": 6.7716, | |
| "eval_samples_per_second": 66.011, | |
| "eval_steps_per_second": 2.067, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.9800000000000004e-05, | |
| "loss": 0.2133, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9776286353467561, | |
| "eval_f1": 0.9601648947616865, | |
| "eval_loss": 0.0990455150604248, | |
| "eval_precision": 0.9476303317535546, | |
| "eval_recall": 0.9785651349741774, | |
| "eval_runtime": 6.7752, | |
| "eval_samples_per_second": 65.976, | |
| "eval_steps_per_second": 2.066, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 2.64e-05, | |
| "loss": 0.1083, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9821029082774049, | |
| "eval_f1": 0.9653218049514888, | |
| "eval_loss": 0.10380033403635025, | |
| "eval_precision": 0.9655642046538242, | |
| "eval_recall": 0.9650874727825403, | |
| "eval_runtime": 6.7715, | |
| "eval_samples_per_second": 66.012, | |
| "eval_steps_per_second": 2.067, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.3e-05, | |
| "loss": 0.0848, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9865771812080537, | |
| "eval_f1": 0.9747350357333067, | |
| "eval_loss": 0.09066177904605865, | |
| "eval_precision": 0.9782430301452915, | |
| "eval_recall": 0.9713632225190546, | |
| "eval_runtime": 6.7664, | |
| "eval_samples_per_second": 66.062, | |
| "eval_steps_per_second": 2.069, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3.960000000000001e-05, | |
| "loss": 0.1087, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9798657718120806, | |
| "eval_f1": 0.9671245324193838, | |
| "eval_loss": 0.12698371708393097, | |
| "eval_precision": 0.9672288359788359, | |
| "eval_recall": 0.9688744042217826, | |
| "eval_runtime": 6.7679, | |
| "eval_samples_per_second": 66.047, | |
| "eval_steps_per_second": 2.069, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.6200000000000005e-05, | |
| "loss": 0.1011, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9753914988814317, | |
| "eval_f1": 0.9666995780164981, | |
| "eval_loss": 0.12892137467861176, | |
| "eval_precision": 0.9676667575151919, | |
| "eval_recall": 0.9659549559260323, | |
| "eval_runtime": 6.7567, | |
| "eval_samples_per_second": 66.157, | |
| "eval_steps_per_second": 2.072, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.125e-05, | |
| "loss": 0.0827, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9798657718120806, | |
| "eval_f1": 0.9631601759286037, | |
| "eval_loss": 0.09904194623231888, | |
| "eval_precision": 0.9818050507874383, | |
| "eval_recall": 0.9479257225190546, | |
| "eval_runtime": 6.7541, | |
| "eval_samples_per_second": 66.182, | |
| "eval_steps_per_second": 2.073, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 2.0625e-05, | |
| "loss": 0.0621, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9865771812080537, | |
| "eval_f1": 0.9750903668573623, | |
| "eval_loss": 0.08565760403871536, | |
| "eval_precision": 0.9722969853754562, | |
| "eval_recall": 0.9780020135988667, | |
| "eval_runtime": 6.7572, | |
| "eval_samples_per_second": 66.152, | |
| "eval_steps_per_second": 2.072, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0444, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9843400447427293, | |
| "eval_f1": 0.9714752151121933, | |
| "eval_loss": 0.10706986486911774, | |
| "eval_precision": 0.9768891875746715, | |
| "eval_recall": 0.9662611817027281, | |
| "eval_runtime": 6.7612, | |
| "eval_samples_per_second": 66.112, | |
| "eval_steps_per_second": 2.071, | |
| "step": 660 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 660, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 9724835143127040.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |