| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.389830508474576, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 4.261892318725586, | |
| "eval_runtime": 94.2977, | |
| "eval_samples_per_second": 22.217, | |
| "eval_steps_per_second": 2.778, | |
| "eval_wer": 0.9999454713997492, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 3.344686508178711, | |
| "eval_runtime": 94.5451, | |
| "eval_samples_per_second": 22.159, | |
| "eval_steps_per_second": 2.771, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 2.064770221710205, | |
| "eval_runtime": 92.8264, | |
| "eval_samples_per_second": 22.569, | |
| "eval_steps_per_second": 2.822, | |
| "eval_wer": 1.0030536016140466, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 1.2480711936950684, | |
| "eval_runtime": 92.4166, | |
| "eval_samples_per_second": 22.669, | |
| "eval_steps_per_second": 2.835, | |
| "eval_wer": 1.0047439882218223, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.000188625, | |
| "loss": 3.7472, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 1.077250361442566, | |
| "eval_runtime": 92.9428, | |
| "eval_samples_per_second": 22.541, | |
| "eval_steps_per_second": 2.819, | |
| "eval_wer": 1.011014777250668, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 0.9297690987586975, | |
| "eval_runtime": 92.8184, | |
| "eval_samples_per_second": 22.571, | |
| "eval_steps_per_second": 2.823, | |
| "eval_wer": 1.0173946234800153, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 0.8263903856277466, | |
| "eval_runtime": 92.5375, | |
| "eval_samples_per_second": 22.639, | |
| "eval_steps_per_second": 2.831, | |
| "eval_wer": 1.0098151480451496, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_loss": 0.7596059441566467, | |
| "eval_runtime": 92.5009, | |
| "eval_samples_per_second": 22.648, | |
| "eval_steps_per_second": 2.832, | |
| "eval_wer": 1.007470418234364, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_loss": 0.7255838513374329, | |
| "eval_runtime": 92.7616, | |
| "eval_samples_per_second": 22.585, | |
| "eval_steps_per_second": 2.824, | |
| "eval_wer": 1.0065979606303506, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 1.1249999999999998e-06, | |
| "loss": 0.4913, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "eval_loss": 0.7122135758399963, | |
| "eval_runtime": 92.98, | |
| "eval_samples_per_second": 22.532, | |
| "eval_steps_per_second": 2.818, | |
| "eval_wer": 1.010687605649163, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "step": 1000, | |
| "total_flos": 2.0204530018974664e+18, | |
| "train_loss": 2.1192366943359375, | |
| "train_runtime": 2559.907, | |
| "train_samples_per_second": 6.25, | |
| "train_steps_per_second": 0.391 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 4, | |
| "total_flos": 2.0204530018974664e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |