| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 2330, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8702409035670884, | |
| "eval_f1": 0.2995999407319603, | |
| "eval_loss": 0.5389052033424377, | |
| "eval_precision": 0.33331959612610756, | |
| "eval_recall": 0.27207589060450094, | |
| "eval_runtime": 14.1196, | |
| "eval_samples_per_second": 1054.99, | |
| "eval_steps_per_second": 2.125, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9681749946386446, | |
| "eval_f1": 0.8514915583419936, | |
| "eval_loss": 0.12146873772144318, | |
| "eval_precision": 0.8626164998274076, | |
| "eval_recall": 0.8406499142193965, | |
| "eval_runtime": 15.0925, | |
| "eval_samples_per_second": 986.983, | |
| "eval_steps_per_second": 1.988, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 6.25e-06, | |
| "loss": 1.2635, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9790478232897276, | |
| "eval_f1": 0.9141998345125719, | |
| "eval_loss": 0.0771816298365593, | |
| "eval_precision": 0.9178421266784212, | |
| "eval_recall": 0.9105863356544556, | |
| "eval_runtime": 14.0091, | |
| "eval_samples_per_second": 1063.307, | |
| "eval_steps_per_second": 2.141, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.98271141611266, | |
| "eval_f1": 0.9309382867251821, | |
| "eval_loss": 0.06554248929023743, | |
| "eval_precision": 0.9416055882454148, | |
| "eval_recall": 0.9205099740976217, | |
| "eval_runtime": 14.0197, | |
| "eval_samples_per_second": 1062.501, | |
| "eval_steps_per_second": 2.14, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 8.69281045751634e-06, | |
| "loss": 0.0906, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.984880977911216, | |
| "eval_f1": 0.9419223941161552, | |
| "eval_loss": 0.06115253269672394, | |
| "eval_precision": 0.9468692637160921, | |
| "eval_recall": 0.9370269452013321, | |
| "eval_runtime": 14.0288, | |
| "eval_samples_per_second": 1061.817, | |
| "eval_steps_per_second": 2.138, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9843269711916506, | |
| "eval_f1": 0.9446501919062689, | |
| "eval_loss": 0.062205445021390915, | |
| "eval_precision": 0.9454459682582471, | |
| "eval_recall": 0.9438557540283244, | |
| "eval_runtime": 14.4851, | |
| "eval_samples_per_second": 1028.367, | |
| "eval_steps_per_second": 2.071, | |
| "step": 1398 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 5.4248366013071894e-06, | |
| "loss": 0.0429, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9854850239473872, | |
| "eval_f1": 0.9466268938436389, | |
| "eval_loss": 0.06088804826140404, | |
| "eval_precision": 0.9484971293481932, | |
| "eval_recall": 0.9447640192417668, | |
| "eval_runtime": 14.327, | |
| "eval_samples_per_second": 1039.716, | |
| "eval_steps_per_second": 2.094, | |
| "step": 1631 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9853885195510759, | |
| "eval_f1": 0.9475256832068758, | |
| "eval_loss": 0.06388872861862183, | |
| "eval_precision": 0.9456525381135868, | |
| "eval_recall": 0.9494062636660275, | |
| "eval_runtime": 14.5864, | |
| "eval_samples_per_second": 1021.225, | |
| "eval_steps_per_second": 2.057, | |
| "step": 1864 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 2.1568627450980393e-06, | |
| "loss": 0.0265, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9858710415326328, | |
| "eval_f1": 0.9485348353785288, | |
| "eval_loss": 0.06375858187675476, | |
| "eval_precision": 0.9453968253968253, | |
| "eval_recall": 0.9516937464258082, | |
| "eval_runtime": 14.1094, | |
| "eval_samples_per_second": 1055.751, | |
| "eval_steps_per_second": 2.126, | |
| "step": 2097 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9859925655872471, | |
| "eval_f1": 0.949012494961709, | |
| "eval_loss": 0.06480085104703903, | |
| "eval_precision": 0.9475802394607103, | |
| "eval_recall": 0.9504490866888687, | |
| "eval_runtime": 13.7245, | |
| "eval_samples_per_second": 1085.359, | |
| "eval_steps_per_second": 2.186, | |
| "step": 2330 | |
| } | |
| ], | |
| "max_steps": 2330, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.6349634872247114e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |