| { | |
| "best_metric": 0.667660908939119, | |
| "best_model_checkpoint": "/content/output_dir/checkpoint-2412", | |
| "epoch": 9.0, | |
| "global_step": 2412, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.280492497114274e-05, | |
| "loss": 0.4622, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.5115634202957153, | |
| "eval_matthews_correlation": 0.5385290213636863, | |
| "eval_runtime": 7.985, | |
| "eval_samples_per_second": 130.62, | |
| "eval_steps_per_second": 16.406, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.249326664101577e-05, | |
| "loss": 0.2823, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.4201788902282715, | |
| "eval_matthews_correlation": 0.6035894895952164, | |
| "eval_runtime": 8.0283, | |
| "eval_samples_per_second": 129.916, | |
| "eval_steps_per_second": 16.317, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.218160831088881e-05, | |
| "loss": 0.1804, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.580650806427002, | |
| "eval_matthews_correlation": 0.5574138665741355, | |
| "eval_runtime": 8.1314, | |
| "eval_samples_per_second": 128.268, | |
| "eval_steps_per_second": 16.11, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.186994998076183e-05, | |
| "loss": 0.1357, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.4439031779766083, | |
| "eval_matthews_correlation": 0.6557697896854868, | |
| "eval_runtime": 8.1435, | |
| "eval_samples_per_second": 128.078, | |
| "eval_steps_per_second": 16.087, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.155829165063486e-05, | |
| "loss": 0.0913, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.5736830830574036, | |
| "eval_matthews_correlation": 0.6249925495853809, | |
| "eval_runtime": 8.0533, | |
| "eval_samples_per_second": 129.512, | |
| "eval_steps_per_second": 16.267, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.1246633320507885e-05, | |
| "loss": 0.065, | |
| "step": 1608 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.7729296684265137, | |
| "eval_matthews_correlation": 0.6188970025554703, | |
| "eval_runtime": 8.081, | |
| "eval_samples_per_second": 129.068, | |
| "eval_steps_per_second": 16.211, | |
| "step": 1608 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.093497499038092e-05, | |
| "loss": 0.0433, | |
| "step": 1876 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.7351673245429993, | |
| "eval_matthews_correlation": 0.6405767700619004, | |
| "eval_runtime": 8.1372, | |
| "eval_samples_per_second": 128.176, | |
| "eval_steps_per_second": 16.099, | |
| "step": 1876 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.0623316660253942e-05, | |
| "loss": 0.0199, | |
| "step": 2144 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.7900031208992004, | |
| "eval_matthews_correlation": 0.6565021466238845, | |
| "eval_runtime": 8.1095, | |
| "eval_samples_per_second": 128.615, | |
| "eval_steps_per_second": 16.154, | |
| "step": 2144 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.0311658330126971e-05, | |
| "loss": 0.0114, | |
| "step": 2412 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.8539554476737976, | |
| "eval_matthews_correlation": 0.667660908939119, | |
| "eval_runtime": 8.1204, | |
| "eval_samples_per_second": 128.442, | |
| "eval_steps_per_second": 16.132, | |
| "step": 2412 | |
| } | |
| ], | |
| "max_steps": 2680, | |
| "num_train_epochs": 10, | |
| "total_flos": 6470985270606336.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |