| { | |
| "best_metric": 0.5987107026018142, | |
| "best_model_checkpoint": "./bert-base-uncased/fine_tuned_models/checkpoint-1608", | |
| "epoch": 10.0, | |
| "global_step": 2680, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5408, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.44839417934417725, | |
| "eval_matthews_correlation": 0.5101050627100728, | |
| "eval_runtime": 4.5316, | |
| "eval_samples_per_second": 230.162, | |
| "eval_steps_per_second": 28.908, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.7777777777777777e-05, | |
| "loss": 0.358, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.41765275597572327, | |
| "eval_matthews_correlation": 0.557314902649449, | |
| "eval_runtime": 4.6251, | |
| "eval_samples_per_second": 225.509, | |
| "eval_steps_per_second": 28.324, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.555555555555556e-05, | |
| "loss": 0.2138, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.4441712200641632, | |
| "eval_matthews_correlation": 0.5633929042001022, | |
| "eval_runtime": 4.7653, | |
| "eval_samples_per_second": 218.876, | |
| "eval_steps_per_second": 27.491, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.1417, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.5438293218612671, | |
| "eval_matthews_correlation": 0.5630684232854489, | |
| "eval_runtime": 4.757, | |
| "eval_samples_per_second": 219.256, | |
| "eval_steps_per_second": 27.538, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 1.1111111111111113e-05, | |
| "loss": 0.1024, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.6504286527633667, | |
| "eval_matthews_correlation": 0.5802214485707464, | |
| "eval_runtime": 4.795, | |
| "eval_samples_per_second": 217.52, | |
| "eval_steps_per_second": 27.32, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 0.0729, | |
| "step": 1608 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.7044526934623718, | |
| "eval_matthews_correlation": 0.5987107026018142, | |
| "eval_runtime": 4.7948, | |
| "eval_samples_per_second": 217.526, | |
| "eval_steps_per_second": 27.321, | |
| "step": 1608 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.0495, | |
| "step": 1876 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.8482019901275635, | |
| "eval_matthews_correlation": 0.5687360893544328, | |
| "eval_runtime": 4.7991, | |
| "eval_samples_per_second": 217.333, | |
| "eval_steps_per_second": 27.297, | |
| "step": 1876 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 0.0396, | |
| "step": 2144 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.9315766096115112, | |
| "eval_matthews_correlation": 0.570213836374093, | |
| "eval_runtime": 4.789, | |
| "eval_samples_per_second": 217.791, | |
| "eval_steps_per_second": 27.354, | |
| "step": 2144 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 0.0291, | |
| "step": 2412 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.0078035593032837, | |
| "eval_matthews_correlation": 0.5719840023272299, | |
| "eval_runtime": 4.8055, | |
| "eval_samples_per_second": 217.045, | |
| "eval_steps_per_second": 27.261, | |
| "step": 2412 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0202, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.0447075366973877, | |
| "eval_matthews_correlation": 0.5730766020227869, | |
| "eval_runtime": 4.754, | |
| "eval_samples_per_second": 219.396, | |
| "eval_steps_per_second": 27.556, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 2680, | |
| "total_flos": 3594991817003520.0, | |
| "train_loss": 0.15679735123221553, | |
| "train_runtime": 1165.9542, | |
| "train_samples_per_second": 73.339, | |
| "train_steps_per_second": 2.299 | |
| } | |
| ], | |
| "max_steps": 2680, | |
| "num_train_epochs": 10, | |
| "total_flos": 3594991817003520.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |