| { | |
| "best_metric": 0.025636129081249237, | |
| "best_model_checkpoint": "logs/google-bert/bert-large-cased_synt_flan_/checkpoint-4204", | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 7357, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.776539146900177, | |
| "learning_rate": 1.900190294957184e-05, | |
| "loss": 0.0605, | |
| "step": 1051 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_MAE": 0.1328457146883011, | |
| "eval_R2": 0.5911350949440748, | |
| "eval_RMSE": 0.18202443420886993, | |
| "eval_loss": 0.033132895827293396, | |
| "eval_runtime": 57.2605, | |
| "eval_samples_per_second": 137.634, | |
| "eval_steps_per_second": 2.305, | |
| "step": 1051 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.3320234417915344, | |
| "learning_rate": 1.800190294957184e-05, | |
| "loss": 0.0315, | |
| "step": 2102 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_MAE": 0.12664468586444855, | |
| "eval_R2": 0.6459152872970175, | |
| "eval_RMSE": 0.1693921983242035, | |
| "eval_loss": 0.02869371511042118, | |
| "eval_runtime": 63.3854, | |
| "eval_samples_per_second": 124.335, | |
| "eval_steps_per_second": 2.082, | |
| "step": 2102 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.6608996391296387, | |
| "learning_rate": 1.7001902949571838e-05, | |
| "loss": 0.0235, | |
| "step": 3153 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_MAE": 0.11449417471885681, | |
| "eval_R2": 0.6718858103880652, | |
| "eval_RMSE": 0.16306181252002716, | |
| "eval_loss": 0.026589158922433853, | |
| "eval_runtime": 63.2127, | |
| "eval_samples_per_second": 124.674, | |
| "eval_steps_per_second": 2.088, | |
| "step": 3153 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.4667591452598572, | |
| "learning_rate": 1.6002854424357757e-05, | |
| "loss": 0.0183, | |
| "step": 4204 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_MAE": 0.11234939843416214, | |
| "eval_R2": 0.6836463521967036, | |
| "eval_RMSE": 0.16011285781860352, | |
| "eval_loss": 0.025636129081249237, | |
| "eval_runtime": 63.8057, | |
| "eval_samples_per_second": 123.516, | |
| "eval_steps_per_second": 2.069, | |
| "step": 4204 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.5772440433502197, | |
| "learning_rate": 1.5002854424357756e-05, | |
| "loss": 0.0146, | |
| "step": 5255 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_MAE": 0.11249976605176926, | |
| "eval_R2": 0.6823521370731253, | |
| "eval_RMSE": 0.16044004261493683, | |
| "eval_loss": 0.025741007179021835, | |
| "eval_runtime": 63.9385, | |
| "eval_samples_per_second": 123.259, | |
| "eval_steps_per_second": 2.064, | |
| "step": 5255 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.5639244914054871, | |
| "learning_rate": 1.4002854424357755e-05, | |
| "loss": 0.012, | |
| "step": 6306 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_MAE": 0.11984019726514816, | |
| "eval_R2": 0.6479695405721535, | |
| "eval_RMSE": 0.16890010237693787, | |
| "eval_loss": 0.02852724678814411, | |
| "eval_runtime": 63.5115, | |
| "eval_samples_per_second": 124.088, | |
| "eval_steps_per_second": 2.078, | |
| "step": 6306 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.34999290108680725, | |
| "learning_rate": 1.3002854424357757e-05, | |
| "loss": 0.0099, | |
| "step": 7357 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_MAE": 0.11679080128669739, | |
| "eval_R2": 0.6535357331636864, | |
| "eval_RMSE": 0.16755947470664978, | |
| "eval_loss": 0.028076183050870895, | |
| "eval_runtime": 63.3285, | |
| "eval_samples_per_second": 124.446, | |
| "eval_steps_per_second": 2.084, | |
| "step": 7357 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 21020, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "total_flos": 2.052312281323627e+17, | |
| "train_batch_size": 30, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |