| { | |
| "best_metric": 0.44421833753585815, | |
| "best_model_checkpoint": "essayl0/checkpoint-144", | |
| "epoch": 15.0, | |
| "global_step": 1080, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7526132404181185, | |
| "eval_loss": 0.6014369130134583, | |
| "eval_runtime": 8.8226, | |
| "eval_samples_per_second": 32.53, | |
| "eval_steps_per_second": 2.04, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8606271777003485, | |
| "eval_loss": 0.44421833753585815, | |
| "eval_runtime": 8.9292, | |
| "eval_samples_per_second": 32.142, | |
| "eval_steps_per_second": 2.016, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8153310104529616, | |
| "eval_loss": 0.5106114745140076, | |
| "eval_runtime": 9.4286, | |
| "eval_samples_per_second": 30.439, | |
| "eval_steps_per_second": 1.909, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7665505226480837, | |
| "eval_loss": 0.7232147455215454, | |
| "eval_runtime": 8.9358, | |
| "eval_samples_per_second": 32.118, | |
| "eval_steps_per_second": 2.014, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8501742160278746, | |
| "eval_loss": 0.5562837719917297, | |
| "eval_runtime": 8.9194, | |
| "eval_samples_per_second": 32.177, | |
| "eval_steps_per_second": 2.018, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.794425087108014, | |
| "eval_loss": 0.783423125743866, | |
| "eval_runtime": 8.9169, | |
| "eval_samples_per_second": 32.186, | |
| "eval_steps_per_second": 2.019, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 1.0740740740740742e-05, | |
| "loss": 0.2758, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8501742160278746, | |
| "eval_loss": 0.7359230518341064, | |
| "eval_runtime": 8.9, | |
| "eval_samples_per_second": 32.247, | |
| "eval_steps_per_second": 2.022, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8780487804878049, | |
| "eval_loss": 0.6547905802726746, | |
| "eval_runtime": 8.9239, | |
| "eval_samples_per_second": 32.161, | |
| "eval_steps_per_second": 2.017, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8885017421602788, | |
| "eval_loss": 0.6335029602050781, | |
| "eval_runtime": 8.9095, | |
| "eval_samples_per_second": 32.213, | |
| "eval_steps_per_second": 2.02, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7839721254355401, | |
| "eval_loss": 1.1050056219100952, | |
| "eval_runtime": 8.8781, | |
| "eval_samples_per_second": 32.327, | |
| "eval_steps_per_second": 2.027, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.8780487804878049, | |
| "eval_loss": 0.7101187705993652, | |
| "eval_runtime": 8.9338, | |
| "eval_samples_per_second": 32.125, | |
| "eval_steps_per_second": 2.015, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8397212543554007, | |
| "eval_loss": 0.7923139929771423, | |
| "eval_runtime": 8.9267, | |
| "eval_samples_per_second": 32.151, | |
| "eval_steps_per_second": 2.016, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.8432055749128919, | |
| "eval_loss": 0.8634345531463623, | |
| "eval_runtime": 8.9462, | |
| "eval_samples_per_second": 32.081, | |
| "eval_steps_per_second": 2.012, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "learning_rate": 1.4814814814814815e-06, | |
| "loss": 0.0185, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8432055749128919, | |
| "eval_loss": 0.83455491065979, | |
| "eval_runtime": 8.8702, | |
| "eval_samples_per_second": 32.355, | |
| "eval_steps_per_second": 2.029, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.8327526132404182, | |
| "eval_loss": 0.8648095726966858, | |
| "eval_runtime": 8.9204, | |
| "eval_samples_per_second": 32.173, | |
| "eval_steps_per_second": 2.018, | |
| "step": 1080 | |
| } | |
| ], | |
| "max_steps": 1080, | |
| "num_train_epochs": 15, | |
| "total_flos": 4194210824632584.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |