| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 50514, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.394, | |
| "step": 16838 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8967889908256881, | |
| "eval_loss": 0.3896108567714691, | |
| "eval_runtime": 19.0439, | |
| "eval_samples_per_second": 45.789, | |
| "eval_steps_per_second": 5.724, | |
| "step": 16838 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.2076, | |
| "step": 33676 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8956422018348624, | |
| "eval_loss": 0.5100129246711731, | |
| "eval_runtime": 19.0123, | |
| "eval_samples_per_second": 45.865, | |
| "eval_steps_per_second": 5.733, | |
| "step": 33676 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.1148, | |
| "step": 50514 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9048165137614679, | |
| "eval_loss": 0.5239545702934265, | |
| "eval_runtime": 18.9842, | |
| "eval_samples_per_second": 45.933, | |
| "eval_steps_per_second": 5.742, | |
| "step": 50514 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 50514, | |
| "total_flos": 1.2640385602092442e+17, | |
| "train_loss": 0.23881868657776187, | |
| "train_runtime": 14505.0544, | |
| "train_samples_per_second": 13.929, | |
| "train_steps_per_second": 3.483 | |
| } | |
| ], | |
| "max_steps": 50514, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.2640385602092442e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |