| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 29.014, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6378, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0803, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0166, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0048, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0037, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0032, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0007, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0011, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0025, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0009, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "eval_loss": 0.1459457278251648, | |
| "eval_runtime": 5.4122, | |
| "eval_samples_per_second": 3.326, | |
| "eval_steps_per_second": 0.924, | |
| "eval_wer": 11.585365853658537, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "step": 1000, | |
| "total_flos": 5.1887996928e+17, | |
| "train_loss": 0.07516751879453659, | |
| "train_runtime": 1282.4235, | |
| "train_samples_per_second": 6.238, | |
| "train_steps_per_second": 0.78 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 5.1887996928e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |