|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 4.787234042553192, |
|
"eval_steps": 300, |
|
"global_step": 900, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 5e-07, |
|
"loss": 1.0874, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 1e-06, |
|
"loss": 0.9487, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 1.5e-06, |
|
"loss": 0.7586, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 2e-06, |
|
"loss": 0.7225, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 2.5e-06, |
|
"loss": 0.7364, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 3e-06, |
|
"loss": 0.7265, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 3.5e-06, |
|
"loss": 0.7267, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 4e-06, |
|
"loss": 0.5697, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 4.5e-06, |
|
"loss": 1.018, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 5e-06, |
|
"loss": 0.7875, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 5.5e-06, |
|
"loss": 0.8242, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 6e-06, |
|
"loss": 0.8034, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 6.5e-06, |
|
"loss": 0.7717, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 7e-06, |
|
"loss": 0.8337, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 7.5e-06, |
|
"loss": 0.6884, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 8e-06, |
|
"loss": 0.9129, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 8.500000000000002e-06, |
|
"loss": 0.5637, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 9e-06, |
|
"loss": 1.0458, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 9.5e-06, |
|
"loss": 0.9414, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 1e-05, |
|
"loss": 0.6379, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 1.0500000000000001e-05, |
|
"loss": 0.9249, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 1.1e-05, |
|
"loss": 0.6944, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 1.15e-05, |
|
"loss": 0.9221, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 1.2e-05, |
|
"loss": 0.6475, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 1.25e-05, |
|
"loss": 0.7748, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 1.3e-05, |
|
"loss": 0.8705, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 1.35e-05, |
|
"loss": 0.7737, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 1.4e-05, |
|
"loss": 0.8643, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 1.4500000000000002e-05, |
|
"loss": 0.8428, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 1.5e-05, |
|
"loss": 0.6785, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"eval_accuracy": 0.7386666666666667, |
|
"eval_combined_score": 0.6626504648943422, |
|
"eval_f1": 0.6276400817995911, |
|
"eval_loss": 0.7930460572242737, |
|
"eval_precision": 0.5456284444444445, |
|
"eval_recall": 0.7386666666666667, |
|
"eval_runtime": 6.0663, |
|
"eval_samples_per_second": 247.266, |
|
"eval_steps_per_second": 7.748, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 1.55e-05, |
|
"loss": 0.6076, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 1.6e-05, |
|
"loss": 0.5963, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 1.65e-05, |
|
"loss": 0.6626, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 1.7000000000000003e-05, |
|
"loss": 0.8379, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 1.7500000000000002e-05, |
|
"loss": 0.8851, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.91, |
|
"learning_rate": 1.8e-05, |
|
"loss": 0.7489, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.97, |
|
"learning_rate": 1.85e-05, |
|
"loss": 0.7573, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 1.9e-05, |
|
"loss": 0.8018, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 2.07, |
|
"learning_rate": 1.95e-05, |
|
"loss": 0.6645, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 2e-05, |
|
"loss": 0.8677, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 2.18, |
|
"learning_rate": 2.05e-05, |
|
"loss": 0.7478, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 2.23, |
|
"learning_rate": 2.1000000000000002e-05, |
|
"loss": 0.8551, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 2.29, |
|
"learning_rate": 2.1499999999999997e-05, |
|
"loss": 0.9323, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 2.34, |
|
"learning_rate": 2.2e-05, |
|
"loss": 0.7536, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 2.39, |
|
"learning_rate": 2.2499999999999998e-05, |
|
"loss": 0.5336, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 2.45, |
|
"learning_rate": 2.3e-05, |
|
"loss": 0.8955, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 2.3500000000000002e-05, |
|
"loss": 0.7926, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 2.55, |
|
"learning_rate": 2.4e-05, |
|
"loss": 0.5713, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 2.4500000000000003e-05, |
|
"loss": 0.8568, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 2.66, |
|
"learning_rate": 2.5e-05, |
|
"loss": 0.6348, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.71, |
|
"learning_rate": 2.55e-05, |
|
"loss": 0.6223, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 2.77, |
|
"learning_rate": 2.6e-05, |
|
"loss": 0.7579, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 2.82, |
|
"learning_rate": 2.65e-05, |
|
"loss": 0.6325, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 2.87, |
|
"learning_rate": 2.7e-05, |
|
"loss": 0.7276, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 2.93, |
|
"learning_rate": 2.75e-05, |
|
"loss": 0.8766, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 2.98, |
|
"learning_rate": 2.8e-05, |
|
"loss": 0.7107, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 3.03, |
|
"learning_rate": 2.85e-05, |
|
"loss": 0.5904, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 3.09, |
|
"learning_rate": 2.9000000000000004e-05, |
|
"loss": 0.7125, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 3.14, |
|
"learning_rate": 2.95e-05, |
|
"loss": 0.755, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 3.19, |
|
"learning_rate": 3e-05, |
|
"loss": 0.5583, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 3.19, |
|
"eval_accuracy": 0.7613333333333333, |
|
"eval_combined_score": 0.7403762607674487, |
|
"eval_f1": 0.7316181693637903, |
|
"eval_loss": 0.6910097599029541, |
|
"eval_precision": 0.7072202070393374, |
|
"eval_recall": 0.7613333333333333, |
|
"eval_runtime": 6.0882, |
|
"eval_samples_per_second": 246.376, |
|
"eval_steps_per_second": 7.72, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 3.24, |
|
"learning_rate": 3.05e-05, |
|
"loss": 0.6527, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 3.3, |
|
"learning_rate": 3.1e-05, |
|
"loss": 0.7676, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 3.35, |
|
"learning_rate": 3.15e-05, |
|
"loss": 0.766, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 3.4, |
|
"learning_rate": 3.2e-05, |
|
"loss": 0.6217, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 3.46, |
|
"learning_rate": 3.2500000000000004e-05, |
|
"loss": 0.5405, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 3.51, |
|
"learning_rate": 3.3e-05, |
|
"loss": 0.7951, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 3.56, |
|
"learning_rate": 3.35e-05, |
|
"loss": 0.552, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 3.62, |
|
"learning_rate": 3.4000000000000007e-05, |
|
"loss": 0.6521, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 3.67, |
|
"learning_rate": 3.4500000000000005e-05, |
|
"loss": 0.6814, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 3.72, |
|
"learning_rate": 3.5000000000000004e-05, |
|
"loss": 0.3992, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 3.78, |
|
"learning_rate": 3.5499999999999996e-05, |
|
"loss": 0.7018, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 3.83, |
|
"learning_rate": 3.6e-05, |
|
"loss": 0.664, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 3.88, |
|
"learning_rate": 3.65e-05, |
|
"loss": 0.6891, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 3.94, |
|
"learning_rate": 3.7e-05, |
|
"loss": 0.6063, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 3.99, |
|
"learning_rate": 3.75e-05, |
|
"loss": 0.6543, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 4.04, |
|
"learning_rate": 3.8e-05, |
|
"loss": 0.5638, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 4.1, |
|
"learning_rate": 3.85e-05, |
|
"loss": 0.6984, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 4.15, |
|
"learning_rate": 3.9e-05, |
|
"loss": 0.7148, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 4.2, |
|
"learning_rate": 3.95e-05, |
|
"loss": 0.4915, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 4.26, |
|
"learning_rate": 4e-05, |
|
"loss": 0.648, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 4.31, |
|
"learning_rate": 4.05e-05, |
|
"loss": 0.4527, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 4.36, |
|
"learning_rate": 4.1e-05, |
|
"loss": 0.551, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 4.41, |
|
"learning_rate": 4.1500000000000006e-05, |
|
"loss": 0.5909, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 4.47, |
|
"learning_rate": 4.2000000000000004e-05, |
|
"loss": 0.603, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 4.52, |
|
"learning_rate": 4.25e-05, |
|
"loss": 1.0745, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 4.57, |
|
"learning_rate": 4.2999999999999995e-05, |
|
"loss": 0.6697, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 4.63, |
|
"learning_rate": 4.35e-05, |
|
"loss": 0.8374, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 4.68, |
|
"learning_rate": 4.4e-05, |
|
"loss": 0.4891, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 4.73, |
|
"learning_rate": 4.45e-05, |
|
"loss": 0.5956, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 4.79, |
|
"learning_rate": 4.4999999999999996e-05, |
|
"loss": 0.7857, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 4.79, |
|
"eval_accuracy": 0.7386666666666667, |
|
"eval_combined_score": 0.6626504648943422, |
|
"eval_f1": 0.6276400817995911, |
|
"eval_loss": 0.6514685153961182, |
|
"eval_precision": 0.5456284444444445, |
|
"eval_recall": 0.7386666666666667, |
|
"eval_runtime": 5.9473, |
|
"eval_samples_per_second": 252.216, |
|
"eval_steps_per_second": 7.903, |
|
"step": 900 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 5640, |
|
"num_train_epochs": 30, |
|
"save_steps": 300, |
|
"total_flos": 1890206726750208.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|