| { | |
| "best_metric": 0.9318278600753288, | |
| "best_model_checkpoint": "/home/felix/kubhist2-testing/SuperLim-2-Testing/results/trainer_output/run-ae28d_00003/checkpoint-1512", | |
| "epoch": 7.0, | |
| "eval_steps": 500, | |
| "global_step": 1512, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.768, | |
| "eval_krippendorff_nominal": 0.6462532075451226, | |
| "eval_loss": 0.5996153354644775, | |
| "eval_runtime": 1.6255, | |
| "eval_samples_per_second": 461.404, | |
| "eval_steps_per_second": 7.382, | |
| "learning_rate": 3.8364532019704435e-05, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8813333333333333, | |
| "eval_krippendorff_nominal": 0.8182421349202457, | |
| "eval_loss": 0.33796122670173645, | |
| "eval_runtime": 0.9435, | |
| "eval_samples_per_second": 794.882, | |
| "eval_steps_per_second": 12.718, | |
| "learning_rate": 3.412807881773399e-05, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 3.2788177339901483e-05, | |
| "loss": 0.6653, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9186666666666666, | |
| "eval_krippendorff_nominal": 0.875072922743562, | |
| "eval_loss": 0.2410804033279419, | |
| "eval_runtime": 1.6215, | |
| "eval_samples_per_second": 462.531, | |
| "eval_steps_per_second": 7.4, | |
| "learning_rate": 2.9871921182266012e-05, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.952, | |
| "eval_krippendorff_nominal": 0.9257691117301146, | |
| "eval_loss": 0.24171602725982666, | |
| "eval_runtime": 0.8034, | |
| "eval_samples_per_second": 933.562, | |
| "eval_steps_per_second": 14.937, | |
| "learning_rate": 2.561576354679803e-05, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 2.2935960591133007e-05, | |
| "loss": 0.1402, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.956, | |
| "eval_krippendorff_nominal": 0.9315953885277389, | |
| "eval_loss": 0.2816691994667053, | |
| "eval_runtime": 0.7016, | |
| "eval_samples_per_second": 1068.993, | |
| "eval_steps_per_second": 17.104, | |
| "learning_rate": 2.135960591133005e-05, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9533333333333334, | |
| "eval_krippendorff_nominal": 0.9278546008591717, | |
| "eval_loss": 0.32500791549682617, | |
| "eval_runtime": 0.7136, | |
| "eval_samples_per_second": 1051.007, | |
| "eval_steps_per_second": 16.816, | |
| "learning_rate": 1.710344827586207e-05, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 1.3083743842364534e-05, | |
| "loss": 0.0263, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.956, | |
| "eval_krippendorff_nominal": 0.9318278600753288, | |
| "eval_loss": 0.341027170419693, | |
| "eval_runtime": 0.9282, | |
| "eval_samples_per_second": 808.008, | |
| "eval_steps_per_second": 12.928, | |
| "learning_rate": 1.284729064039409e-05, | |
| "step": 1512 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2160, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 984537519960960.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 4e-05, | |
| "per_device_train_batch_size": 16 | |
| } | |
| } | |