| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.19672131147541, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 2.5e-06, | |
| "loss": 3.5867, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5e-06, | |
| "loss": 3.5457, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 7.5e-06, | |
| "loss": 3.4513, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1e-05, | |
| "loss": 3.3432, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.25e-05, | |
| "loss": 3.3533, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 3.2806732654571533, | |
| "eval_runtime": 190.4728, | |
| "eval_samples_per_second": 25.426, | |
| "eval_steps_per_second": 0.798, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.5e-05, | |
| "loss": 3.2217, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.7500000000000002e-05, | |
| "loss": 3.1765, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2e-05, | |
| "loss": 3.1408, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.2499999999999998e-05, | |
| "loss": 3.1165, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 2.5e-05, | |
| "loss": 3.1709, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_loss": 3.1325438022613525, | |
| "eval_runtime": 192.4978, | |
| "eval_samples_per_second": 25.159, | |
| "eval_steps_per_second": 0.79, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| } | |
| ], | |
| "max_steps": 4550, | |
| "num_train_epochs": 50, | |
| "total_flos": 3.115318423228506e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |