"best_metric": 0.4796141982078552,
"best_model_checkpoint": "/content/output_dir/checkpoint-268",
"epoch": 10.0,
"global_step": 2680,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"max_steps": 2680,
"num_train_epochs": 10,
"total_flos": 7113018526540800.0,
"trial_name": null,
"trial_params": null
epoch eval_loss eval_matthews_correlation eval_runtime eval_samples_per_second eval_steps_per_second step learning_rate loss
1 0.4796141982078552 0.5351033849356494 8.8067 118.433 14.875 268 0.000018067415730337083 0.4913
2 0.5334435701370239 0.5178799252679331 8.9439 116.616 14.647 536 0.00001605992509363296 0.2872
3 0.5544090270996094 0.5649788851042796 8.9467 116.58 14.642 804 0.000014052434456928841 0.1777
4 0.5754779577255249 0.6105374636148787 8.8982 117.215 14.722 1072 0.000012044943820224718 0.1263
5 0.7263916730880737 0.5807606001872874 8.9705 116.27 14.603 1340 0.000010037453183520601 0.0905
6 0.8121512532234192 0.5651092792103851 8.9924 115.987 14.568 1608 0.00000802996254681648 0.0692
7 0.941014289855957 0.5632084517291658 8.9583 116.428 14.623 1876 0.000006022471910112359 0.0413
8 1.0095174312591553 0.5856531698367675 9.0029 115.851 14.551 2144 0.00000401498127340824 0.0327
9 1.0425965785980225 0.5941395545037332 8.9217 116.906 14.683 2412 0.00000200749063670412 0.0202
10 1.0782166719436646 0.5956649094312695 8.9472 116.572 14.641 2680 0 0.0104