| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 80.0, | |
| "global_step": 27200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5203761755485894, | |
| "eval_loss": 0.7313023209571838, | |
| "eval_runtime": 10.3291, | |
| "eval_samples_per_second": 61.767, | |
| "eval_steps_per_second": 7.745, | |
| "step": 340 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5203761755485894, | |
| "epoch": 1.0, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.000294485294117647, | |
| "loss": 0.7523, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.7285043001174927, | |
| "eval_runtime": 10.3914, | |
| "eval_samples_per_second": 61.397, | |
| "eval_steps_per_second": 7.699, | |
| "step": 680 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5203761755485894, | |
| "epoch": 2.0, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.00028897058823529407, | |
| "loss": 0.7461, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5062695924764891, | |
| "eval_loss": 0.7228550314903259, | |
| "eval_runtime": 10.386, | |
| "eval_samples_per_second": 61.429, | |
| "eval_steps_per_second": 7.703, | |
| "step": 1020 | |
| }, | |
| { | |
| "best_epoch": 0, | |
| "best_eval_accuracy": 0.5203761755485894, | |
| "epoch": 3.0, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5783699059561128, | |
| "eval_loss": 0.706242561340332, | |
| "eval_runtime": 10.3842, | |
| "eval_samples_per_second": 61.44, | |
| "eval_steps_per_second": 7.704, | |
| "step": 1360 | |
| }, | |
| { | |
| "best_epoch": 3, | |
| "best_eval_accuracy": 0.5783699059561128, | |
| "epoch": 4.0, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 0.00028345588235294115, | |
| "loss": 0.7318, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.603448275862069, | |
| "eval_loss": 0.779592752456665, | |
| "eval_runtime": 10.4186, | |
| "eval_samples_per_second": 61.237, | |
| "eval_steps_per_second": 7.679, | |
| "step": 1700 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 5.0, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 0.0002779411764705882, | |
| "loss": 0.7057, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5830721003134797, | |
| "eval_loss": 0.819421648979187, | |
| "eval_runtime": 10.3891, | |
| "eval_samples_per_second": 61.41, | |
| "eval_steps_per_second": 7.7, | |
| "step": 2040 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 6.0, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.7296625971794128, | |
| "eval_runtime": 10.3494, | |
| "eval_samples_per_second": 61.646, | |
| "eval_steps_per_second": 7.73, | |
| "step": 2380 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 7.0, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 0.00027242647058823525, | |
| "loss": 0.7178, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.7423174381256104, | |
| "eval_runtime": 10.3479, | |
| "eval_samples_per_second": 61.655, | |
| "eval_steps_per_second": 7.731, | |
| "step": 2720 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 8.0, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 0.0002669117647058823, | |
| "loss": 0.7417, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.7279828786849976, | |
| "eval_runtime": 10.3545, | |
| "eval_samples_per_second": 61.615, | |
| "eval_steps_per_second": 7.726, | |
| "step": 3060 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 9.0, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5015673981191222, | |
| "eval_loss": 0.7606477737426758, | |
| "eval_runtime": 10.346, | |
| "eval_samples_per_second": 61.666, | |
| "eval_steps_per_second": 7.732, | |
| "step": 3400 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 10.0, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 10.29, | |
| "learning_rate": 0.0002613970588235294, | |
| "loss": 0.7399, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.5172413793103449, | |
| "eval_loss": 0.7346045970916748, | |
| "eval_runtime": 10.3459, | |
| "eval_samples_per_second": 61.667, | |
| "eval_steps_per_second": 7.733, | |
| "step": 3740 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 11.0, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "learning_rate": 0.0002558823529411764, | |
| "loss": 0.7334, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.7410521507263184, | |
| "eval_runtime": 10.3526, | |
| "eval_samples_per_second": 61.627, | |
| "eval_steps_per_second": 7.728, | |
| "step": 4080 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 12.0, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.7588055729866028, | |
| "eval_runtime": 10.341, | |
| "eval_samples_per_second": 61.696, | |
| "eval_steps_per_second": 7.736, | |
| "step": 4420 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 13.0, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 13.24, | |
| "learning_rate": 0.0002503676470588235, | |
| "loss": 0.7332, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.4717868338557994, | |
| "eval_loss": 0.7427398562431335, | |
| "eval_runtime": 10.356, | |
| "eval_samples_per_second": 61.607, | |
| "eval_steps_per_second": 7.725, | |
| "step": 4760 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 14.0, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 14.71, | |
| "learning_rate": 0.0002448529411764706, | |
| "loss": 0.7345, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.5047021943573667, | |
| "eval_loss": 0.7316854596138, | |
| "eval_runtime": 10.3543, | |
| "eval_samples_per_second": 61.617, | |
| "eval_steps_per_second": 7.726, | |
| "step": 5100 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 15.0, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5031347962382445, | |
| "eval_loss": 0.7394306063652039, | |
| "eval_runtime": 10.3304, | |
| "eval_samples_per_second": 61.759, | |
| "eval_steps_per_second": 7.744, | |
| "step": 5440 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 16.0, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 16.18, | |
| "learning_rate": 0.00023933823529411765, | |
| "loss": 0.7308, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.744519054889679, | |
| "eval_runtime": 10.3255, | |
| "eval_samples_per_second": 61.789, | |
| "eval_steps_per_second": 7.748, | |
| "step": 5780 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 17.0, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 17.65, | |
| "learning_rate": 0.0002338235294117647, | |
| "loss": 0.7295, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.4717868338557994, | |
| "eval_loss": 0.7516658902168274, | |
| "eval_runtime": 10.338, | |
| "eval_samples_per_second": 61.714, | |
| "eval_steps_per_second": 7.738, | |
| "step": 6120 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 18.0, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.5015673981191222, | |
| "eval_loss": 0.7323266267776489, | |
| "eval_runtime": 10.3388, | |
| "eval_samples_per_second": 61.709, | |
| "eval_steps_per_second": 7.738, | |
| "step": 6460 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 19.0, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 19.12, | |
| "learning_rate": 0.00022830882352941172, | |
| "loss": 0.728, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.5156739811912225, | |
| "eval_loss": 0.7320307493209839, | |
| "eval_runtime": 10.3718, | |
| "eval_samples_per_second": 61.513, | |
| "eval_steps_per_second": 7.713, | |
| "step": 6800 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 20.0, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 20.59, | |
| "learning_rate": 0.00022279411764705882, | |
| "loss": 0.73, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.5172413793103449, | |
| "eval_loss": 0.730900228023529, | |
| "eval_runtime": 10.3696, | |
| "eval_samples_per_second": 61.526, | |
| "eval_steps_per_second": 7.715, | |
| "step": 7140 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 21.0, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.49843260188087773, | |
| "eval_loss": 0.7434073686599731, | |
| "eval_runtime": 10.3764, | |
| "eval_samples_per_second": 61.486, | |
| "eval_steps_per_second": 7.71, | |
| "step": 7480 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 22.0, | |
| "step": 7480 | |
| }, | |
| { | |
| "epoch": 22.06, | |
| "learning_rate": 0.00021727941176470585, | |
| "loss": 0.7304, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.5094043887147336, | |
| "eval_loss": 0.7365709543228149, | |
| "eval_runtime": 10.371, | |
| "eval_samples_per_second": 61.518, | |
| "eval_steps_per_second": 7.714, | |
| "step": 7820 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 23.0, | |
| "step": 7820 | |
| }, | |
| { | |
| "epoch": 23.53, | |
| "learning_rate": 0.00021176470588235295, | |
| "loss": 0.7298, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.7333634495735168, | |
| "eval_runtime": 10.3649, | |
| "eval_samples_per_second": 61.554, | |
| "eval_steps_per_second": 7.718, | |
| "step": 8160 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 24.0, | |
| "step": 8160 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 0.00020624999999999997, | |
| "loss": 0.7283, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.512539184952978, | |
| "eval_loss": 0.7341791391372681, | |
| "eval_runtime": 10.3671, | |
| "eval_samples_per_second": 61.541, | |
| "eval_steps_per_second": 7.717, | |
| "step": 8500 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 25.0, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.5047021943573667, | |
| "eval_loss": 0.7310704588890076, | |
| "eval_runtime": 10.3754, | |
| "eval_samples_per_second": 61.491, | |
| "eval_steps_per_second": 7.711, | |
| "step": 8840 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 26.0, | |
| "step": 8840 | |
| }, | |
| { | |
| "epoch": 26.47, | |
| "learning_rate": 0.00020073529411764702, | |
| "loss": 0.7291, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.4702194357366771, | |
| "eval_loss": 0.7565436363220215, | |
| "eval_runtime": 10.384, | |
| "eval_samples_per_second": 61.441, | |
| "eval_steps_per_second": 7.704, | |
| "step": 9180 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 27.0, | |
| "step": 9180 | |
| }, | |
| { | |
| "epoch": 27.94, | |
| "learning_rate": 0.0001952205882352941, | |
| "loss": 0.7292, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5031347962382445, | |
| "eval_loss": 0.7282286286354065, | |
| "eval_runtime": 10.3869, | |
| "eval_samples_per_second": 61.424, | |
| "eval_steps_per_second": 7.702, | |
| "step": 9520 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 28.0, | |
| "step": 9520 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.5015673981191222, | |
| "eval_loss": 0.7332981824874878, | |
| "eval_runtime": 10.3776, | |
| "eval_samples_per_second": 61.478, | |
| "eval_steps_per_second": 7.709, | |
| "step": 9860 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 29.0, | |
| "step": 9860 | |
| }, | |
| { | |
| "epoch": 29.41, | |
| "learning_rate": 0.00018970588235294115, | |
| "loss": 0.7261, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.512539184952978, | |
| "eval_loss": 0.7328195571899414, | |
| "eval_runtime": 10.3898, | |
| "eval_samples_per_second": 61.406, | |
| "eval_steps_per_second": 7.7, | |
| "step": 10200 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 30.0, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 30.88, | |
| "learning_rate": 0.00018419117647058822, | |
| "loss": 0.7279, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.512539184952978, | |
| "eval_loss": 0.7348790764808655, | |
| "eval_runtime": 10.3887, | |
| "eval_samples_per_second": 61.413, | |
| "eval_steps_per_second": 7.701, | |
| "step": 10540 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 31.0, | |
| "step": 10540 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.4702194357366771, | |
| "eval_loss": 0.7592222690582275, | |
| "eval_runtime": 10.3874, | |
| "eval_samples_per_second": 61.421, | |
| "eval_steps_per_second": 7.702, | |
| "step": 10880 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 32.0, | |
| "step": 10880 | |
| }, | |
| { | |
| "epoch": 32.35, | |
| "learning_rate": 0.00017867647058823527, | |
| "loss": 0.7252, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.5094043887147336, | |
| "eval_loss": 0.7393137812614441, | |
| "eval_runtime": 10.3855, | |
| "eval_samples_per_second": 61.432, | |
| "eval_steps_per_second": 7.703, | |
| "step": 11220 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 33.0, | |
| "step": 11220 | |
| }, | |
| { | |
| "epoch": 33.82, | |
| "learning_rate": 0.00017316176470588232, | |
| "loss": 0.7263, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.5047021943573667, | |
| "eval_loss": 0.7394311428070068, | |
| "eval_runtime": 10.3899, | |
| "eval_samples_per_second": 61.406, | |
| "eval_steps_per_second": 7.7, | |
| "step": 11560 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 34.0, | |
| "step": 11560 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.5015673981191222, | |
| "eval_loss": 0.7465404272079468, | |
| "eval_runtime": 10.3834, | |
| "eval_samples_per_second": 61.444, | |
| "eval_steps_per_second": 7.705, | |
| "step": 11900 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 35.0, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 35.29, | |
| "learning_rate": 0.0001676470588235294, | |
| "loss": 0.7269, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.5141065830721003, | |
| "eval_loss": 0.7349045872688293, | |
| "eval_runtime": 10.4039, | |
| "eval_samples_per_second": 61.323, | |
| "eval_steps_per_second": 7.689, | |
| "step": 12240 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 36.0, | |
| "step": 12240 | |
| }, | |
| { | |
| "epoch": 36.76, | |
| "learning_rate": 0.00016213235294117645, | |
| "loss": 0.7263, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.5047021943573667, | |
| "eval_loss": 0.7295121550559998, | |
| "eval_runtime": 10.3882, | |
| "eval_samples_per_second": 61.416, | |
| "eval_steps_per_second": 7.701, | |
| "step": 12580 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 37.0, | |
| "step": 12580 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.5172413793103449, | |
| "eval_loss": 0.7328969836235046, | |
| "eval_runtime": 10.391, | |
| "eval_samples_per_second": 61.399, | |
| "eval_steps_per_second": 7.699, | |
| "step": 12920 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 38.0, | |
| "step": 12920 | |
| }, | |
| { | |
| "epoch": 38.24, | |
| "learning_rate": 0.00015661764705882352, | |
| "loss": 0.728, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.7401482462882996, | |
| "eval_runtime": 10.401, | |
| "eval_samples_per_second": 61.34, | |
| "eval_steps_per_second": 7.692, | |
| "step": 13260 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 39.0, | |
| "step": 13260 | |
| }, | |
| { | |
| "epoch": 39.71, | |
| "learning_rate": 0.00015110294117647057, | |
| "loss": 0.7254, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.5156739811912225, | |
| "eval_loss": 0.7330672144889832, | |
| "eval_runtime": 10.4053, | |
| "eval_samples_per_second": 61.315, | |
| "eval_steps_per_second": 7.688, | |
| "step": 13600 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 40.0, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.5172413793103449, | |
| "eval_loss": 0.7308171391487122, | |
| "eval_runtime": 10.3936, | |
| "eval_samples_per_second": 61.384, | |
| "eval_steps_per_second": 7.697, | |
| "step": 13940 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 41.0, | |
| "step": 13940 | |
| }, | |
| { | |
| "epoch": 41.18, | |
| "learning_rate": 0.00014558823529411762, | |
| "loss": 0.7265, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.5172413793103449, | |
| "eval_loss": 0.7311594486236572, | |
| "eval_runtime": 10.4029, | |
| "eval_samples_per_second": 61.329, | |
| "eval_steps_per_second": 7.69, | |
| "step": 14280 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 42.0, | |
| "step": 14280 | |
| }, | |
| { | |
| "epoch": 42.65, | |
| "learning_rate": 0.0001400735294117647, | |
| "loss": 0.7234, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.7393350005149841, | |
| "eval_runtime": 10.3921, | |
| "eval_samples_per_second": 61.393, | |
| "eval_steps_per_second": 7.698, | |
| "step": 14620 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 43.0, | |
| "step": 14620 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.7391661405563354, | |
| "eval_runtime": 10.415, | |
| "eval_samples_per_second": 61.258, | |
| "eval_steps_per_second": 7.681, | |
| "step": 14960 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 44.0, | |
| "step": 14960 | |
| }, | |
| { | |
| "epoch": 44.12, | |
| "learning_rate": 0.00013455882352941175, | |
| "loss": 0.7254, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.7389068007469177, | |
| "eval_runtime": 10.4123, | |
| "eval_samples_per_second": 61.274, | |
| "eval_steps_per_second": 7.683, | |
| "step": 15300 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 45.0, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 45.59, | |
| "learning_rate": 0.00012904411764705882, | |
| "loss": 0.7225, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.5156739811912225, | |
| "eval_loss": 0.731235921382904, | |
| "eval_runtime": 10.4254, | |
| "eval_samples_per_second": 61.197, | |
| "eval_steps_per_second": 7.674, | |
| "step": 15640 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 46.0, | |
| "step": 15640 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.7334668636322021, | |
| "eval_runtime": 10.3994, | |
| "eval_samples_per_second": 61.35, | |
| "eval_steps_per_second": 7.693, | |
| "step": 15980 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 47.0, | |
| "step": 15980 | |
| }, | |
| { | |
| "epoch": 47.06, | |
| "learning_rate": 0.00012352941176470587, | |
| "loss": 0.7268, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.5015673981191222, | |
| "eval_loss": 0.7363240122795105, | |
| "eval_runtime": 10.4221, | |
| "eval_samples_per_second": 61.216, | |
| "eval_steps_per_second": 7.676, | |
| "step": 16320 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 48.0, | |
| "step": 16320 | |
| }, | |
| { | |
| "epoch": 48.53, | |
| "learning_rate": 0.00011801470588235293, | |
| "loss": 0.7258, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.5031347962382445, | |
| "eval_loss": 0.7393150329589844, | |
| "eval_runtime": 10.4224, | |
| "eval_samples_per_second": 61.214, | |
| "eval_steps_per_second": 7.676, | |
| "step": 16660 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 49.0, | |
| "step": 16660 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 0.0001125, | |
| "loss": 0.7253, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.5047021943573667, | |
| "eval_loss": 0.7305631041526794, | |
| "eval_runtime": 10.4154, | |
| "eval_samples_per_second": 61.256, | |
| "eval_steps_per_second": 7.681, | |
| "step": 17000 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 50.0, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.5094043887147336, | |
| "eval_loss": 0.7371691465377808, | |
| "eval_runtime": 10.429, | |
| "eval_samples_per_second": 61.175, | |
| "eval_steps_per_second": 7.671, | |
| "step": 17340 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 51.0, | |
| "step": 17340 | |
| }, | |
| { | |
| "epoch": 51.47, | |
| "learning_rate": 0.00010698529411764705, | |
| "loss": 0.7247, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.7402310371398926, | |
| "eval_runtime": 10.4194, | |
| "eval_samples_per_second": 61.232, | |
| "eval_steps_per_second": 7.678, | |
| "step": 17680 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 52.0, | |
| "step": 17680 | |
| }, | |
| { | |
| "epoch": 52.94, | |
| "learning_rate": 0.00010147058823529411, | |
| "loss": 0.7248, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.5141065830721003, | |
| "eval_loss": 0.7354699969291687, | |
| "eval_runtime": 10.4291, | |
| "eval_samples_per_second": 61.175, | |
| "eval_steps_per_second": 7.671, | |
| "step": 18020 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 53.0, | |
| "step": 18020 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.5156739811912225, | |
| "eval_loss": 0.7369323372840881, | |
| "eval_runtime": 10.4219, | |
| "eval_samples_per_second": 61.217, | |
| "eval_steps_per_second": 7.676, | |
| "step": 18360 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 54.0, | |
| "step": 18360 | |
| }, | |
| { | |
| "epoch": 54.41, | |
| "learning_rate": 9.595588235294116e-05, | |
| "loss": 0.7237, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.5141065830721003, | |
| "eval_loss": 0.7319989800453186, | |
| "eval_runtime": 10.4292, | |
| "eval_samples_per_second": 61.174, | |
| "eval_steps_per_second": 7.671, | |
| "step": 18700 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 55.0, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 55.88, | |
| "learning_rate": 9.044117647058822e-05, | |
| "loss": 0.7226, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.5172413793103449, | |
| "eval_loss": 0.7365678548812866, | |
| "eval_runtime": 10.4179, | |
| "eval_samples_per_second": 61.241, | |
| "eval_steps_per_second": 7.679, | |
| "step": 19040 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 56.0, | |
| "step": 19040 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.5172413793103449, | |
| "eval_loss": 0.7315055131912231, | |
| "eval_runtime": 10.4146, | |
| "eval_samples_per_second": 61.26, | |
| "eval_steps_per_second": 7.682, | |
| "step": 19380 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 57.0, | |
| "step": 19380 | |
| }, | |
| { | |
| "epoch": 57.35, | |
| "learning_rate": 8.492647058823528e-05, | |
| "loss": 0.7238, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.5015673981191222, | |
| "eval_loss": 0.73880934715271, | |
| "eval_runtime": 10.4223, | |
| "eval_samples_per_second": 61.215, | |
| "eval_steps_per_second": 7.676, | |
| "step": 19720 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 58.0, | |
| "step": 19720 | |
| }, | |
| { | |
| "epoch": 58.82, | |
| "learning_rate": 7.941176470588235e-05, | |
| "loss": 0.7228, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.5047021943573667, | |
| "eval_loss": 0.7347163558006287, | |
| "eval_runtime": 10.4154, | |
| "eval_samples_per_second": 61.256, | |
| "eval_steps_per_second": 7.681, | |
| "step": 20060 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 59.0, | |
| "step": 20060 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.5141065830721003, | |
| "eval_loss": 0.7313491106033325, | |
| "eval_runtime": 10.4505, | |
| "eval_samples_per_second": 61.05, | |
| "eval_steps_per_second": 7.655, | |
| "step": 20400 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 60.0, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 60.29, | |
| "learning_rate": 7.389705882352941e-05, | |
| "loss": 0.7245, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.5141065830721003, | |
| "eval_loss": 0.7329691052436829, | |
| "eval_runtime": 10.4244, | |
| "eval_samples_per_second": 61.203, | |
| "eval_steps_per_second": 7.674, | |
| "step": 20740 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 61.0, | |
| "step": 20740 | |
| }, | |
| { | |
| "epoch": 61.76, | |
| "learning_rate": 6.838235294117646e-05, | |
| "loss": 0.7222, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.5141065830721003, | |
| "eval_loss": 0.7349640130996704, | |
| "eval_runtime": 10.4114, | |
| "eval_samples_per_second": 61.279, | |
| "eval_steps_per_second": 7.684, | |
| "step": 21080 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 62.0, | |
| "step": 21080 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.5156739811912225, | |
| "eval_loss": 0.7314162254333496, | |
| "eval_runtime": 10.4097, | |
| "eval_samples_per_second": 61.289, | |
| "eval_steps_per_second": 7.685, | |
| "step": 21420 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 63.0, | |
| "step": 21420 | |
| }, | |
| { | |
| "epoch": 63.24, | |
| "learning_rate": 6.286764705882352e-05, | |
| "loss": 0.724, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.5141065830721003, | |
| "eval_loss": 0.7327254414558411, | |
| "eval_runtime": 10.4103, | |
| "eval_samples_per_second": 61.285, | |
| "eval_steps_per_second": 7.685, | |
| "step": 21760 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 64.0, | |
| "step": 21760 | |
| }, | |
| { | |
| "epoch": 64.71, | |
| "learning_rate": 5.7352941176470576e-05, | |
| "loss": 0.7236, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.5172413793103449, | |
| "eval_loss": 0.7306498289108276, | |
| "eval_runtime": 10.404, | |
| "eval_samples_per_second": 61.323, | |
| "eval_steps_per_second": 7.689, | |
| "step": 22100 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 65.0, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.5141065830721003, | |
| "eval_loss": 0.7351139783859253, | |
| "eval_runtime": 10.4141, | |
| "eval_samples_per_second": 61.263, | |
| "eval_steps_per_second": 7.682, | |
| "step": 22440 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 66.0, | |
| "step": 22440 | |
| }, | |
| { | |
| "epoch": 66.18, | |
| "learning_rate": 5.183823529411764e-05, | |
| "loss": 0.7205, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.512539184952978, | |
| "eval_loss": 0.7343327403068542, | |
| "eval_runtime": 10.4158, | |
| "eval_samples_per_second": 61.253, | |
| "eval_steps_per_second": 7.681, | |
| "step": 22780 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 67.0, | |
| "step": 22780 | |
| }, | |
| { | |
| "epoch": 67.65, | |
| "learning_rate": 4.63235294117647e-05, | |
| "loss": 0.7236, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.5156739811912225, | |
| "eval_loss": 0.7313010096549988, | |
| "eval_runtime": 10.4192, | |
| "eval_samples_per_second": 61.233, | |
| "eval_steps_per_second": 7.678, | |
| "step": 23120 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 68.0, | |
| "step": 23120 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.5172413793103449, | |
| "eval_loss": 0.7338398694992065, | |
| "eval_runtime": 10.4173, | |
| "eval_samples_per_second": 61.244, | |
| "eval_steps_per_second": 7.68, | |
| "step": 23460 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 69.0, | |
| "step": 23460 | |
| }, | |
| { | |
| "epoch": 69.12, | |
| "learning_rate": 4.080882352941176e-05, | |
| "loss": 0.7221, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.5156739811912225, | |
| "eval_loss": 0.7317362427711487, | |
| "eval_runtime": 10.4144, | |
| "eval_samples_per_second": 61.262, | |
| "eval_steps_per_second": 7.682, | |
| "step": 23800 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 70.0, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 70.59, | |
| "learning_rate": 3.529411764705882e-05, | |
| "loss": 0.7226, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.5141065830721003, | |
| "eval_loss": 0.7343974113464355, | |
| "eval_runtime": 10.418, | |
| "eval_samples_per_second": 61.24, | |
| "eval_steps_per_second": 7.679, | |
| "step": 24140 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 71.0, | |
| "step": 24140 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.5156739811912225, | |
| "eval_loss": 0.7342385649681091, | |
| "eval_runtime": 10.4188, | |
| "eval_samples_per_second": 61.235, | |
| "eval_steps_per_second": 7.678, | |
| "step": 24480 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 72.0, | |
| "step": 24480 | |
| }, | |
| { | |
| "epoch": 72.06, | |
| "learning_rate": 2.9779411764705876e-05, | |
| "loss": 0.7209, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.5156739811912225, | |
| "eval_loss": 0.7333251237869263, | |
| "eval_runtime": 10.4209, | |
| "eval_samples_per_second": 61.223, | |
| "eval_steps_per_second": 7.677, | |
| "step": 24820 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 73.0, | |
| "step": 24820 | |
| }, | |
| { | |
| "epoch": 73.53, | |
| "learning_rate": 2.426470588235294e-05, | |
| "loss": 0.7229, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.5141065830721003, | |
| "eval_loss": 0.7358043789863586, | |
| "eval_runtime": 10.4307, | |
| "eval_samples_per_second": 61.166, | |
| "eval_steps_per_second": 7.67, | |
| "step": 25160 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 74.0, | |
| "step": 25160 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "learning_rate": 1.875e-05, | |
| "loss": 0.7204, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.5156739811912225, | |
| "eval_loss": 0.7342051863670349, | |
| "eval_runtime": 10.4227, | |
| "eval_samples_per_second": 61.212, | |
| "eval_steps_per_second": 7.676, | |
| "step": 25500 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 75.0, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.5156739811912225, | |
| "eval_loss": 0.7328677773475647, | |
| "eval_runtime": 10.4246, | |
| "eval_samples_per_second": 61.201, | |
| "eval_steps_per_second": 7.674, | |
| "step": 25840 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 76.0, | |
| "step": 25840 | |
| }, | |
| { | |
| "epoch": 76.47, | |
| "learning_rate": 1.323529411764706e-05, | |
| "loss": 0.7213, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.5141065830721003, | |
| "eval_loss": 0.7333688139915466, | |
| "eval_runtime": 10.429, | |
| "eval_samples_per_second": 61.176, | |
| "eval_steps_per_second": 7.671, | |
| "step": 26180 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 77.0, | |
| "step": 26180 | |
| }, | |
| { | |
| "epoch": 77.94, | |
| "learning_rate": 7.720588235294117e-06, | |
| "loss": 0.7208, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.5141065830721003, | |
| "eval_loss": 0.7335054278373718, | |
| "eval_runtime": 10.4223, | |
| "eval_samples_per_second": 61.215, | |
| "eval_steps_per_second": 7.676, | |
| "step": 26520 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 78.0, | |
| "step": 26520 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.5141065830721003, | |
| "eval_loss": 0.7329541444778442, | |
| "eval_runtime": 10.431, | |
| "eval_samples_per_second": 61.164, | |
| "eval_steps_per_second": 7.669, | |
| "step": 26860 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 79.0, | |
| "step": 26860 | |
| }, | |
| { | |
| "epoch": 79.41, | |
| "learning_rate": 2.2058823529411763e-06, | |
| "loss": 0.7203, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.5141065830721003, | |
| "eval_loss": 0.73334801197052, | |
| "eval_runtime": 10.4229, | |
| "eval_samples_per_second": 61.212, | |
| "eval_steps_per_second": 7.675, | |
| "step": 27200 | |
| }, | |
| { | |
| "best_epoch": 4, | |
| "best_eval_accuracy": 0.603448275862069, | |
| "epoch": 80.0, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "step": 27200, | |
| "total_flos": 2.19509178753024e+17, | |
| "train_loss": 0.726637606901281, | |
| "train_runtime": 10977.5099, | |
| "train_samples_per_second": 39.557, | |
| "train_steps_per_second": 2.478 | |
| } | |
| ], | |
| "max_steps": 27200, | |
| "num_train_epochs": 80, | |
| "total_flos": 2.19509178753024e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |