| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 1830, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 47.84418869018555, | |
| "eval_runtime": 186.8063, | |
| "eval_samples_per_second": 19.587, | |
| "eval_steps_per_second": 1.226, | |
| "eval_wer": 1.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 6.310945510864258, | |
| "eval_runtime": 163.2985, | |
| "eval_samples_per_second": 22.407, | |
| "eval_steps_per_second": 1.402, | |
| "eval_wer": 1.0, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.00029699999999999996, | |
| "loss": 41.8902, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 6.239192008972168, | |
| "eval_runtime": 163.0201, | |
| "eval_samples_per_second": 22.445, | |
| "eval_steps_per_second": 1.405, | |
| "eval_wer": 1.0, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 5.973925590515137, | |
| "eval_runtime": 163.0214, | |
| "eval_samples_per_second": 22.445, | |
| "eval_steps_per_second": 1.405, | |
| "eval_wer": 1.1123227917121048, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 4.901411056518555, | |
| "eval_runtime": 162.8715, | |
| "eval_samples_per_second": 22.466, | |
| "eval_steps_per_second": 1.406, | |
| "eval_wer": 1.9473827699018538, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 0.00018834586466165413, | |
| "loss": 5.5817, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 3.9892334938049316, | |
| "eval_runtime": 163.2053, | |
| "eval_samples_per_second": 22.42, | |
| "eval_steps_per_second": 1.403, | |
| "eval_wer": 1.0188113413304254, | |
| "step": 1098 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 3.5080456733703613, | |
| "eval_runtime": 162.7362, | |
| "eval_samples_per_second": 22.484, | |
| "eval_steps_per_second": 1.407, | |
| "eval_wer": 1.0103598691384952, | |
| "step": 1281 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 3.0796852111816406, | |
| "eval_runtime": 164.2666, | |
| "eval_samples_per_second": 22.275, | |
| "eval_steps_per_second": 1.394, | |
| "eval_wer": 0.9904580152671756, | |
| "step": 1464 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 7.556390977443609e-05, | |
| "loss": 3.5579, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 2.8110806941986084, | |
| "eval_runtime": 168.541, | |
| "eval_samples_per_second": 21.71, | |
| "eval_steps_per_second": 1.359, | |
| "eval_wer": 0.9836423118865867, | |
| "step": 1647 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 2.67260479927063, | |
| "eval_runtime": 165.7448, | |
| "eval_samples_per_second": 22.076, | |
| "eval_steps_per_second": 1.382, | |
| "eval_wer": 0.9814612868047983, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1830, | |
| "total_flos": 1.3577354977100892e+19, | |
| "train_loss": 14.438921352032104, | |
| "train_runtime": 7245.592, | |
| "train_samples_per_second": 16.128, | |
| "train_steps_per_second": 0.253 | |
| } | |
| ], | |
| "max_steps": 1830, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.3577354977100892e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |