| { | |
| "best_metric": 105.19266433134145, | |
| "best_model_checkpoint": "./another_local/checkpoint-500", | |
| "epoch": 1.5974440894568689, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.2000000000000006e-07, | |
| "loss": 3.5849, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.200000000000001e-07, | |
| "loss": 2.9636, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.42e-06, | |
| "loss": 2.182, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.9200000000000003e-06, | |
| "loss": 1.45, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.42e-06, | |
| "loss": 0.9854, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.92e-06, | |
| "loss": 0.889, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 3.4200000000000007e-06, | |
| "loss": 0.8304, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.920000000000001e-06, | |
| "loss": 0.7477, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.42e-06, | |
| "loss": 0.6921, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.92e-06, | |
| "loss": 0.5867, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5.420000000000001e-06, | |
| "loss": 0.4866, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.92e-06, | |
| "loss": 0.3247, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 6.42e-06, | |
| "loss": 0.2519, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 6.92e-06, | |
| "loss": 0.1937, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 7.420000000000001e-06, | |
| "loss": 0.2031, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 7.92e-06, | |
| "loss": 0.2097, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 8.42e-06, | |
| "loss": 0.1868, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 8.920000000000001e-06, | |
| "loss": 0.1966, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 9.42e-06, | |
| "loss": 0.1949, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.920000000000002e-06, | |
| "loss": 0.1972, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 0.426580011844635, | |
| "eval_runtime": 2503.3967, | |
| "eval_samples_per_second": 0.799, | |
| "eval_steps_per_second": 0.1, | |
| "eval_wer": 105.19266433134145, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 4000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 13, | |
| "save_steps": 500, | |
| "total_flos": 2.30637451935744e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |