| { | |
| "best_metric": 0.06124882400035858, | |
| "best_model_checkpoint": "/users/home/elenao23/Models_2/results/elenaovv/model_igc_full/checkpoint-34101", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 45468, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.14601550996303558, | |
| "learning_rate": 9.843747422595384e-07, | |
| "loss": 0.2032, | |
| "step": 11367 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_acc": 0.9787542887305357, | |
| "eval_f1": 0.9787347588271672, | |
| "eval_loss": 0.08981657028198242, | |
| "eval_mcc": 0.971707102962192, | |
| "eval_runtime": 4552.0707, | |
| "eval_samples_per_second": 4.994, | |
| "eval_steps_per_second": 0.312, | |
| "step": 11367 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.00603042496368289, | |
| "learning_rate": 9.68749484519077e-07, | |
| "loss": 0.0839, | |
| "step": 22734 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_acc": 0.9825371689979766, | |
| "eval_f1": 0.9825188346886068, | |
| "eval_loss": 0.08358927816152573, | |
| "eval_mcc": 0.9767754694591899, | |
| "eval_runtime": 4581.7412, | |
| "eval_samples_per_second": 4.962, | |
| "eval_steps_per_second": 0.31, | |
| "step": 22734 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 34.3592414855957, | |
| "learning_rate": 9.531242267786154e-07, | |
| "loss": 0.0602, | |
| "step": 34101 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_acc": 0.9879475675200141, | |
| "eval_f1": 0.9879534397785568, | |
| "eval_loss": 0.06124882400035858, | |
| "eval_mcc": 0.9839390539982584, | |
| "eval_runtime": 4587.1168, | |
| "eval_samples_per_second": 4.956, | |
| "eval_steps_per_second": 0.31, | |
| "step": 34101 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.2689647376537323, | |
| "learning_rate": 9.374989690381538e-07, | |
| "loss": 0.0471, | |
| "step": 45468 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_acc": 0.9893551508753409, | |
| "eval_f1": 0.9893534822467795, | |
| "eval_loss": 0.06302130222320557, | |
| "eval_mcc": 0.9858294150542775, | |
| "eval_runtime": 4574.485, | |
| "eval_samples_per_second": 4.97, | |
| "eval_steps_per_second": 0.311, | |
| "step": 45468 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 45468, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 9.570520762055885e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |