| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 7.5e-05, | |
| "loss": 18.7839, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 32.55470657348633, | |
| "eval_runtime": 5.5933, | |
| "eval_samples_per_second": 22.884, | |
| "eval_steps_per_second": 0.358, | |
| "eval_wer": 1.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.5e-05, | |
| "loss": 19.4045, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 32.55470657348633, | |
| "eval_runtime": 5.6123, | |
| "eval_samples_per_second": 22.807, | |
| "eval_steps_per_second": 0.356, | |
| "eval_wer": 1.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 6.75e-05, | |
| "loss": 19.6279, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 31.884950637817383, | |
| "eval_runtime": 5.4543, | |
| "eval_samples_per_second": 23.468, | |
| "eval_steps_per_second": 0.367, | |
| "eval_wer": 1.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 17.7216, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 31.10820960998535, | |
| "eval_runtime": 5.4982, | |
| "eval_samples_per_second": 23.28, | |
| "eval_steps_per_second": 0.364, | |
| "eval_wer": 1.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 17.3103, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 31.10820960998535, | |
| "eval_runtime": 5.9789, | |
| "eval_samples_per_second": 21.409, | |
| "eval_steps_per_second": 0.335, | |
| "eval_wer": 1.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 5.2499999999999995e-05, | |
| "loss": 17.2026, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 29.966575622558594, | |
| "eval_runtime": 5.3861, | |
| "eval_samples_per_second": 23.765, | |
| "eval_steps_per_second": 0.371, | |
| "eval_wer": 1.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 4.4999999999999996e-05, | |
| "loss": 16.7911, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "eval_loss": 28.54442596435547, | |
| "eval_runtime": 5.434, | |
| "eval_samples_per_second": 23.555, | |
| "eval_steps_per_second": 0.368, | |
| "eval_wer": 1.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.75e-05, | |
| "loss": 13.7364, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 25.79315185546875, | |
| "eval_runtime": 5.4455, | |
| "eval_samples_per_second": 23.506, | |
| "eval_steps_per_second": 0.367, | |
| "eval_wer": 1.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 13.1602, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "eval_loss": 23.46338653564453, | |
| "eval_runtime": 5.3714, | |
| "eval_samples_per_second": 23.83, | |
| "eval_steps_per_second": 0.372, | |
| "eval_wer": 1.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 2.2499999999999998e-05, | |
| "loss": 12.9439, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 21.93878936767578, | |
| "eval_runtime": 5.4116, | |
| "eval_samples_per_second": 23.653, | |
| "eval_steps_per_second": 0.37, | |
| "eval_wer": 1.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 10, | |
| "total_flos": 1.3476444758728704e+17, | |
| "train_loss": 16.66825189590454, | |
| "train_runtime": 91.9274, | |
| "train_samples_per_second": 6.962, | |
| "train_steps_per_second": 0.109 | |
| } | |
| ], | |
| "max_steps": 10, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.3476444758728704e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |