| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.415584415584416, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.828125e-06, | |
| "loss": 15.104, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 7.6953125e-06, | |
| "loss": 12.2149, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 1.16015625e-05, | |
| "loss": 4.9885, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 1.55078125e-05, | |
| "loss": 3.3788, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 1.94140625e-05, | |
| "loss": 3.1705, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 2.3320312499999995e-05, | |
| "loss": 3.11, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "learning_rate": 2.72265625e-05, | |
| "loss": 3.0526, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 3.11328125e-05, | |
| "loss": 3.0113, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 3.5039062499999995e-05, | |
| "loss": 2.9601, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "learning_rate": 3.89453125e-05, | |
| "loss": 2.9099, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "eval_loss": 2.8369038105010986, | |
| "eval_runtime": 198.5866, | |
| "eval_samples_per_second": 25.405, | |
| "eval_steps_per_second": 0.796, | |
| "eval_wer": 1.0, | |
| "step": 1000 | |
| } | |
| ], | |
| "max_steps": 9600, | |
| "num_train_epochs": 100, | |
| "total_flos": 1.5571160176119996e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |