| { | |
| "best_metric": 0.6684188842773438, | |
| "best_model_checkpoint": "my_awesome_model/checkpoint-12500", | |
| "epoch": 1.0, | |
| "global_step": 12500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 0.6978, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.8400000000000003e-05, | |
| "loss": 0.6951, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.76e-05, | |
| "loss": 0.6948, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 0.6757, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.6541, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5200000000000002e-05, | |
| "loss": 0.7619, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.4400000000000001e-05, | |
| "loss": 0.7755, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.3600000000000002e-05, | |
| "loss": 0.8347, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.2800000000000001e-05, | |
| "loss": 0.7848, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.7772, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.1200000000000001e-05, | |
| "loss": 0.6601, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.04e-05, | |
| "loss": 0.7317, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 0.7202, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 8.8e-06, | |
| "loss": 0.6754, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.7578, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 0.7782, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 0.6967, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.600000000000001e-06, | |
| "loss": 0.6118, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 0.6468, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.64, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 0.7285, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 0.6744, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.6000000000000001e-06, | |
| "loss": 0.7347, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 0.6218, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.7703, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.85048, | |
| "eval_loss": 0.6684188842773438, | |
| "eval_runtime": 256.7866, | |
| "eval_samples_per_second": 97.357, | |
| "eval_steps_per_second": 48.679, | |
| "step": 12500 | |
| } | |
| ], | |
| "max_steps": 12500, | |
| "num_train_epochs": 1, | |
| "total_flos": 506545463743800.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |