| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 750.0, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 125.0, | |
| "eval_accuracy": 0.8307210031347962, | |
| "eval_f1": 0.6761904761904761, | |
| "eval_loss": 0.869185745716095, | |
| "eval_precision": 0.6396396396396397, | |
| "eval_recall": 0.7171717171717171, | |
| "eval_runtime": 1.1326, | |
| "eval_samples_per_second": 24.722, | |
| "eval_steps_per_second": 1.766, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 250.0, | |
| "learning_rate": 4e-05, | |
| "loss": 0.2158, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 250.0, | |
| "eval_accuracy": 0.8244514106583072, | |
| "eval_f1": 0.6272727272727273, | |
| "eval_loss": 1.0074251890182495, | |
| "eval_precision": 0.5702479338842975, | |
| "eval_recall": 0.696969696969697, | |
| "eval_runtime": 0.5366, | |
| "eval_samples_per_second": 52.181, | |
| "eval_steps_per_second": 3.727, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 375.0, | |
| "eval_accuracy": 0.8119122257053292, | |
| "eval_f1": 0.6952380952380952, | |
| "eval_loss": 1.3559716939926147, | |
| "eval_precision": 0.6576576576576577, | |
| "eval_recall": 0.7373737373737373, | |
| "eval_runtime": 0.5707, | |
| "eval_samples_per_second": 49.06, | |
| "eval_steps_per_second": 3.504, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 500.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0184, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 500.0, | |
| "eval_accuracy": 0.8056426332288401, | |
| "eval_f1": 0.6507177033492823, | |
| "eval_loss": 1.339294195175171, | |
| "eval_precision": 0.6181818181818182, | |
| "eval_recall": 0.6868686868686869, | |
| "eval_runtime": 0.5948, | |
| "eval_samples_per_second": 47.076, | |
| "eval_steps_per_second": 3.363, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 625.0, | |
| "eval_accuracy": 0.8213166144200627, | |
| "eval_f1": 0.6542056074766355, | |
| "eval_loss": 1.3527517318725586, | |
| "eval_precision": 0.6086956521739131, | |
| "eval_recall": 0.7070707070707071, | |
| "eval_runtime": 0.5373, | |
| "eval_samples_per_second": 52.109, | |
| "eval_steps_per_second": 3.722, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 750.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0175, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 750.0, | |
| "eval_accuracy": 0.8181818181818182, | |
| "eval_f1": 0.660377358490566, | |
| "eval_loss": 1.4282338619232178, | |
| "eval_precision": 0.6194690265486725, | |
| "eval_recall": 0.7070707070707071, | |
| "eval_runtime": 0.5599, | |
| "eval_samples_per_second": 50.01, | |
| "eval_steps_per_second": 3.572, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 750.0, | |
| "step": 3000, | |
| "total_flos": 3253656728250000.0, | |
| "train_loss": 0.0839117234547933, | |
| "train_runtime": 334.6639, | |
| "train_samples_per_second": 573.71, | |
| "train_steps_per_second": 8.964 | |
| } | |
| ], | |
| "max_steps": 3000, | |
| "num_train_epochs": 750, | |
| "total_flos": 3253656728250000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |