| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6568313021167415, | |
| "eval_steps": 500, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9986295347545738e-05, | |
| "loss": 1.1468, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9945218953682736e-05, | |
| "loss": 1.1476, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 1.1366, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.9510565162951538e-05, | |
| "loss": 1.1232, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 1.1253, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.866025403784439e-05, | |
| "loss": 1.0947, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 1.1062, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.7431448254773943e-05, | |
| "loss": 1.1017, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 1.0888, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.5877852522924733e-05, | |
| "loss": 1.0726, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 1.0734, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.4067366430758004e-05, | |
| "loss": 1.0815, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 1.0628, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.2079116908177592e-05, | |
| "loss": 1.0674, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 1.0667, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1e-05, | |
| "loss": 1.0732, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 8.954715367323468e-06, | |
| "loss": 1.0647, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 7.92088309182241e-06, | |
| "loss": 1.0574, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 1.0483, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 5.932633569242e-06, | |
| "loss": 1.0492, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 1.0498, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.0541661977767944, | |
| "eval_runtime": 1943.1867, | |
| "eval_samples_per_second": 11.893, | |
| "eval_steps_per_second": 0.744, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "step": 40, | |
| "total_flos": 3.680138604408996e+18, | |
| "train_loss": 1.106418876349926, | |
| "train_runtime": 18557.3295, | |
| "train_samples_per_second": 3.36, | |
| "train_steps_per_second": 0.003 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 60, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "total_flos": 3.680138604408996e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |