The uploaded model is from epoch 9 with Matthews Correlation of 66.77
"best_metric": 0.667660908939119,
"best_model_checkpoint": "/content/output_dir/checkpoint-2412",
"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": 7189983634007040.0,
"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 | 0.5115634202957153 | 0.5385290213636863 | 7.985 | 130.62 | 16.406 | 268 | 0.00009280492497114274 | 0.4622 |
| 2 | 0.4201788902282715 | 0.6035894895952164 | 8.0283 | 129.916 | 16.317 | 536 | 0.00008249326664101577 | 0.2823 |
| 3 | 0.580650806427002 | 0.5574138665741355 | 8.1314 | 128.268 | 16.11 | 804 | 0.00007218160831088881 | 0.1804 |
| 4 | 0.4439031779766083 | 0.6557697896854868 | 8.1435 | 128.078 | 16.087 | 1072 | 0.00006186994998076183 | 0.1357 |
| 5 | 0.5736830830574036 | 0.6249925495853809 | 8.0533 | 129.512 | 16.267 | 1340 | 0.00005155829165063486 | 0.0913 |
| 6 | 0.7729296684265137 | 0.6188970025554703 | 8.081 | 129.068 | 16.211 | 1608 | 0.000041246633320507885 | 0.065 |
| 7 | 0.7351673245429993 | 0.6405767700619004 | 8.1372 | 128.176 | 16.099 | 1876 | 0.00003093497499038092 | 0.0433 |
| 8 | 0.7900031208992004 | 0.6565021466238845 | 8.1095 | 128.615 | 16.154 | 2144 | 0.000020623316660253942 | 0.0199 |
| 9 | 0.8539554476737976 | 0.667660908939119 | 8.1204 | 128.442 | 16.132 | 2412 | 0.000010311658330126971 | 0.0114 |
| 10 | 0.9261117577552795 | 0.660301076782038 | 8.0088 | 130.231 | 16.357 | 2680 | 0 | 0.0066 |