| { | |
| "best_metric": 0.5628103017807007, | |
| "best_model_checkpoint": "/kaggle/output/checkpoint-600", | |
| "epoch": 1.6528925619834711, | |
| "eval_steps": 50, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 0.6979, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.6723740696907043, | |
| "eval_runtime": 28.903, | |
| "eval_samples_per_second": 40.965, | |
| "eval_steps_per_second": 20.482, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.6272028088569641, | |
| "eval_runtime": 28.756, | |
| "eval_samples_per_second": 41.174, | |
| "eval_steps_per_second": 20.587, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.5726658701896667, | |
| "eval_runtime": 28.7791, | |
| "eval_samples_per_second": 41.141, | |
| "eval_steps_per_second": 20.57, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.5658872723579407, | |
| "eval_runtime": 28.8005, | |
| "eval_samples_per_second": 41.11, | |
| "eval_steps_per_second": 20.555, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.5675005316734314, | |
| "eval_runtime": 28.7479, | |
| "eval_samples_per_second": 41.186, | |
| "eval_steps_per_second": 20.593, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.5632852911949158, | |
| "eval_runtime": 28.807, | |
| "eval_samples_per_second": 41.101, | |
| "eval_steps_per_second": 20.551, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.5931060910224915, | |
| "eval_runtime": 29.0233, | |
| "eval_samples_per_second": 40.795, | |
| "eval_steps_per_second": 20.397, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.5643754005432129, | |
| "eval_runtime": 28.8155, | |
| "eval_samples_per_second": 41.089, | |
| "eval_steps_per_second": 20.545, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.5633080005645752, | |
| "eval_runtime": 29.0501, | |
| "eval_samples_per_second": 40.757, | |
| "eval_steps_per_second": 20.379, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.5926231145858765, | |
| "eval_runtime": 28.7918, | |
| "eval_samples_per_second": 41.123, | |
| "eval_steps_per_second": 20.561, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.5648908019065857, | |
| "eval_runtime": 28.8558, | |
| "eval_samples_per_second": 41.032, | |
| "eval_steps_per_second": 20.516, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.5628103017807007, | |
| "eval_runtime": 28.9143, | |
| "eval_samples_per_second": 40.949, | |
| "eval_steps_per_second": 20.474, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.5630568265914917, | |
| "eval_runtime": 28.8676, | |
| "eval_samples_per_second": 41.015, | |
| "eval_steps_per_second": 20.507, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.5687929391860962, | |
| "eval_runtime": 28.9082, | |
| "eval_samples_per_second": 40.957, | |
| "eval_steps_per_second": 20.479, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.5623889565467834, | |
| "eval_runtime": 28.8406, | |
| "eval_samples_per_second": 41.053, | |
| "eval_steps_per_second": 20.527, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_accuracy": 0.75, | |
| "eval_loss": 0.5629884600639343, | |
| "eval_runtime": 28.8402, | |
| "eval_samples_per_second": 41.054, | |
| "eval_steps_per_second": 20.527, | |
| "step": 800 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 1000, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 2579192374164480.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |