| { | |
| "best_metric": 0.8913043478260869, | |
| "best_model_checkpoint": "vit-base-patch16-224-ve-U11-b-80\\checkpoint-357", | |
| "epoch": 73.84615384615384, | |
| "eval_steps": 500, | |
| "global_step": 480, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.3695652173913043, | |
| "eval_loss": 1.3848360776901245, | |
| "eval_runtime": 0.7009, | |
| "eval_samples_per_second": 65.626, | |
| "eval_steps_per_second": 2.853, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.2916666666666667e-05, | |
| "loss": 1.3848, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5217391304347826, | |
| "eval_loss": 1.3691749572753906, | |
| "eval_runtime": 0.7095, | |
| "eval_samples_per_second": 64.836, | |
| "eval_steps_per_second": 2.819, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_accuracy": 0.5434782608695652, | |
| "eval_loss": 1.3196941614151, | |
| "eval_runtime": 0.7166, | |
| "eval_samples_per_second": 64.193, | |
| "eval_steps_per_second": 2.791, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 1.3517, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.226363182067871, | |
| "eval_runtime": 0.7199, | |
| "eval_samples_per_second": 63.894, | |
| "eval_steps_per_second": 2.778, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 5.4276315789473686e-05, | |
| "loss": 1.2334, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_accuracy": 0.43478260869565216, | |
| "eval_loss": 1.1280030012130737, | |
| "eval_runtime": 0.7001, | |
| "eval_samples_per_second": 65.707, | |
| "eval_steps_per_second": 2.857, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5434782608695652, | |
| "eval_loss": 1.043665885925293, | |
| "eval_runtime": 0.6942, | |
| "eval_samples_per_second": 66.267, | |
| "eval_steps_per_second": 2.881, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 5.3070175438596496e-05, | |
| "loss": 1.073, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "eval_accuracy": 0.5869565217391305, | |
| "eval_loss": 0.977077841758728, | |
| "eval_runtime": 0.7166, | |
| "eval_samples_per_second": 64.193, | |
| "eval_steps_per_second": 2.791, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 5.18640350877193e-05, | |
| "loss": 0.9358, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9469745755195618, | |
| "eval_runtime": 0.716, | |
| "eval_samples_per_second": 64.245, | |
| "eval_steps_per_second": 2.793, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.8527599573135376, | |
| "eval_runtime": 0.7068, | |
| "eval_samples_per_second": 65.083, | |
| "eval_steps_per_second": 2.83, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 5.0657894736842104e-05, | |
| "loss": 0.7955, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7838979959487915, | |
| "eval_runtime": 0.7095, | |
| "eval_samples_per_second": 64.83, | |
| "eval_steps_per_second": 2.819, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 4.9451754385964915e-05, | |
| "loss": 0.6429, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.762014627456665, | |
| "eval_runtime": 0.7297, | |
| "eval_samples_per_second": 63.039, | |
| "eval_steps_per_second": 2.741, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6466214656829834, | |
| "eval_runtime": 0.7269, | |
| "eval_samples_per_second": 63.282, | |
| "eval_steps_per_second": 2.751, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 4.824561403508772e-05, | |
| "loss": 0.5096, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7395678162574768, | |
| "eval_runtime": 0.7173, | |
| "eval_samples_per_second": 64.127, | |
| "eval_steps_per_second": 2.788, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 13.85, | |
| "learning_rate": 4.703947368421053e-05, | |
| "loss": 0.4086, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7334679961204529, | |
| "eval_runtime": 0.7, | |
| "eval_samples_per_second": 65.717, | |
| "eval_steps_per_second": 2.857, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.6472949981689453, | |
| "eval_runtime": 0.7003, | |
| "eval_samples_per_second": 65.683, | |
| "eval_steps_per_second": 2.856, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.3355, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.6019440293312073, | |
| "eval_runtime": 0.7173, | |
| "eval_samples_per_second": 64.128, | |
| "eval_steps_per_second": 2.788, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "learning_rate": 4.462719298245614e-05, | |
| "loss": 0.2511, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.5275207757949829, | |
| "eval_runtime": 0.7323, | |
| "eval_samples_per_second": 62.817, | |
| "eval_steps_per_second": 2.731, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.606886088848114, | |
| "eval_runtime": 0.7178, | |
| "eval_samples_per_second": 64.088, | |
| "eval_steps_per_second": 2.786, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 4.342105263157895e-05, | |
| "loss": 0.1925, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6446670293807983, | |
| "eval_runtime": 0.7505, | |
| "eval_samples_per_second": 61.289, | |
| "eval_steps_per_second": 2.665, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.221491228070176e-05, | |
| "loss": 0.2121, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.5044350028038025, | |
| "eval_runtime": 0.697, | |
| "eval_samples_per_second": 65.993, | |
| "eval_steps_per_second": 2.869, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.48049649596214294, | |
| "eval_runtime": 0.683, | |
| "eval_samples_per_second": 67.347, | |
| "eval_steps_per_second": 2.928, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 21.54, | |
| "learning_rate": 4.100877192982456e-05, | |
| "loss": 0.1883, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6722545623779297, | |
| "eval_runtime": 0.7334, | |
| "eval_samples_per_second": 62.717, | |
| "eval_steps_per_second": 2.727, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 22.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7729943990707397, | |
| "eval_runtime": 0.7005, | |
| "eval_samples_per_second": 65.672, | |
| "eval_steps_per_second": 2.855, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 3.9802631578947374e-05, | |
| "loss": 0.1693, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.6573545336723328, | |
| "eval_runtime": 0.7181, | |
| "eval_samples_per_second": 64.055, | |
| "eval_steps_per_second": 2.785, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 3.859649122807018e-05, | |
| "loss": 0.1252, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 24.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.8191500902175903, | |
| "eval_runtime": 0.7167, | |
| "eval_samples_per_second": 64.183, | |
| "eval_steps_per_second": 2.791, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.598371148109436, | |
| "eval_runtime": 0.7198, | |
| "eval_samples_per_second": 63.906, | |
| "eval_steps_per_second": 2.779, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 26.15, | |
| "learning_rate": 3.739035087719298e-05, | |
| "loss": 0.1439, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.7632927298545837, | |
| "eval_runtime": 0.7166, | |
| "eval_samples_per_second": 64.19, | |
| "eval_steps_per_second": 2.791, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "learning_rate": 3.618421052631579e-05, | |
| "loss": 0.137, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.6566154956817627, | |
| "eval_runtime": 0.7333, | |
| "eval_samples_per_second": 62.732, | |
| "eval_steps_per_second": 2.727, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6550094485282898, | |
| "eval_runtime": 0.7171, | |
| "eval_samples_per_second": 64.147, | |
| "eval_steps_per_second": 2.789, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 29.23, | |
| "learning_rate": 3.49780701754386e-05, | |
| "loss": 0.1316, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7162931561470032, | |
| "eval_runtime": 0.7253, | |
| "eval_samples_per_second": 63.42, | |
| "eval_steps_per_second": 2.757, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 3.377192982456141e-05, | |
| "loss": 0.1101, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 30.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6240657567977905, | |
| "eval_runtime": 0.7, | |
| "eval_samples_per_second": 65.714, | |
| "eval_steps_per_second": 2.857, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.6359685659408569, | |
| "eval_runtime": 0.7141, | |
| "eval_samples_per_second": 64.418, | |
| "eval_steps_per_second": 2.801, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 32.31, | |
| "learning_rate": 3.256578947368421e-05, | |
| "loss": 0.0947, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 32.92, | |
| "eval_accuracy": 0.8695652173913043, | |
| "eval_loss": 0.5272877216339111, | |
| "eval_runtime": 0.7338, | |
| "eval_samples_per_second": 62.69, | |
| "eval_steps_per_second": 2.726, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 33.85, | |
| "learning_rate": 3.1359649122807015e-05, | |
| "loss": 0.0885, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.657907247543335, | |
| "eval_runtime": 0.6973, | |
| "eval_samples_per_second": 65.972, | |
| "eval_steps_per_second": 2.868, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 34.92, | |
| "eval_accuracy": 0.8695652173913043, | |
| "eval_loss": 0.5920112133026123, | |
| "eval_runtime": 0.7176, | |
| "eval_samples_per_second": 64.106, | |
| "eval_steps_per_second": 2.787, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 3.0153508771929826e-05, | |
| "loss": 0.0967, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6778892278671265, | |
| "eval_runtime": 0.7072, | |
| "eval_samples_per_second": 65.043, | |
| "eval_steps_per_second": 2.828, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "learning_rate": 2.894736842105263e-05, | |
| "loss": 0.0812, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.7354278564453125, | |
| "eval_runtime": 0.7011, | |
| "eval_samples_per_second": 65.61, | |
| "eval_steps_per_second": 2.853, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.68247389793396, | |
| "eval_runtime": 0.704, | |
| "eval_samples_per_second": 65.342, | |
| "eval_steps_per_second": 2.841, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 2.774122807017544e-05, | |
| "loss": 0.0752, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 38.92, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.6347822546958923, | |
| "eval_runtime": 0.7005, | |
| "eval_samples_per_second": 65.672, | |
| "eval_steps_per_second": 2.855, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 2.6535087719298248e-05, | |
| "loss": 0.0757, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.7726355791091919, | |
| "eval_runtime": 0.7169, | |
| "eval_samples_per_second": 64.165, | |
| "eval_steps_per_second": 2.79, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6737184524536133, | |
| "eval_runtime": 0.7008, | |
| "eval_samples_per_second": 65.637, | |
| "eval_steps_per_second": 2.854, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 41.54, | |
| "learning_rate": 2.5328947368421052e-05, | |
| "loss": 0.086, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6738055348396301, | |
| "eval_runtime": 0.71, | |
| "eval_samples_per_second": 64.791, | |
| "eval_steps_per_second": 2.817, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 42.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7295153141021729, | |
| "eval_runtime": 0.7, | |
| "eval_samples_per_second": 65.716, | |
| "eval_steps_per_second": 2.857, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 43.08, | |
| "learning_rate": 2.412280701754386e-05, | |
| "loss": 0.0533, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6896860599517822, | |
| "eval_runtime": 0.7158, | |
| "eval_samples_per_second": 64.267, | |
| "eval_steps_per_second": 2.794, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 44.62, | |
| "learning_rate": 2.2916666666666667e-05, | |
| "loss": 0.0574, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 44.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6426982879638672, | |
| "eval_runtime": 0.692, | |
| "eval_samples_per_second": 66.474, | |
| "eval_steps_per_second": 2.89, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.647143542766571, | |
| "eval_runtime": 0.7047, | |
| "eval_samples_per_second": 65.273, | |
| "eval_steps_per_second": 2.838, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "learning_rate": 2.1710526315789474e-05, | |
| "loss": 0.0739, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 46.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6645414233207703, | |
| "eval_runtime": 0.7034, | |
| "eval_samples_per_second": 65.395, | |
| "eval_steps_per_second": 2.843, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 47.69, | |
| "learning_rate": 2.050438596491228e-05, | |
| "loss": 0.0849, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6857832074165344, | |
| "eval_runtime": 0.7532, | |
| "eval_samples_per_second": 61.074, | |
| "eval_steps_per_second": 2.655, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 48.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.747519314289093, | |
| "eval_runtime": 0.7003, | |
| "eval_samples_per_second": 65.687, | |
| "eval_steps_per_second": 2.856, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 49.23, | |
| "learning_rate": 1.929824561403509e-05, | |
| "loss": 0.0719, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6734511256217957, | |
| "eval_runtime": 0.6961, | |
| "eval_samples_per_second": 66.08, | |
| "eval_steps_per_second": 2.873, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 50.77, | |
| "learning_rate": 1.8092105263157896e-05, | |
| "loss": 0.0434, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 50.92, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.6892310380935669, | |
| "eval_runtime": 0.7085, | |
| "eval_samples_per_second": 64.925, | |
| "eval_steps_per_second": 2.823, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.6820205450057983, | |
| "eval_runtime": 0.7093, | |
| "eval_samples_per_second": 64.852, | |
| "eval_steps_per_second": 2.82, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 52.31, | |
| "learning_rate": 1.6885964912280704e-05, | |
| "loss": 0.0564, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 52.92, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.6677300930023193, | |
| "eval_runtime": 0.7015, | |
| "eval_samples_per_second": 65.573, | |
| "eval_steps_per_second": 2.851, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 53.85, | |
| "learning_rate": 1.5679824561403508e-05, | |
| "loss": 0.0408, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.7379003763198853, | |
| "eval_runtime": 0.7059, | |
| "eval_samples_per_second": 65.163, | |
| "eval_steps_per_second": 2.833, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 54.92, | |
| "eval_accuracy": 0.8913043478260869, | |
| "eval_loss": 0.5455520749092102, | |
| "eval_runtime": 0.7176, | |
| "eval_samples_per_second": 64.104, | |
| "eval_steps_per_second": 2.787, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 55.38, | |
| "learning_rate": 1.4473684210526315e-05, | |
| "loss": 0.0464, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.7951130270957947, | |
| "eval_runtime": 0.7275, | |
| "eval_samples_per_second": 63.232, | |
| "eval_steps_per_second": 2.749, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "learning_rate": 1.3267543859649124e-05, | |
| "loss": 0.0463, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.6356358528137207, | |
| "eval_runtime": 0.6997, | |
| "eval_samples_per_second": 65.74, | |
| "eval_steps_per_second": 2.858, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7528730630874634, | |
| "eval_runtime": 0.7044, | |
| "eval_samples_per_second": 65.303, | |
| "eval_steps_per_second": 2.839, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 58.46, | |
| "learning_rate": 1.206140350877193e-05, | |
| "loss": 0.0361, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 58.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.8016931414604187, | |
| "eval_runtime": 0.7001, | |
| "eval_samples_per_second": 65.709, | |
| "eval_steps_per_second": 2.857, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 1.0855263157894737e-05, | |
| "loss": 0.0457, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.7876579165458679, | |
| "eval_runtime": 0.712, | |
| "eval_samples_per_second": 64.605, | |
| "eval_steps_per_second": 2.809, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.8018705248832703, | |
| "eval_runtime": 0.7111, | |
| "eval_samples_per_second": 64.689, | |
| "eval_steps_per_second": 2.813, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 61.54, | |
| "learning_rate": 9.649122807017545e-06, | |
| "loss": 0.0371, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.8015215396881104, | |
| "eval_runtime": 0.7026, | |
| "eval_samples_per_second": 65.472, | |
| "eval_steps_per_second": 2.847, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 62.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.8487241268157959, | |
| "eval_runtime": 0.7173, | |
| "eval_samples_per_second": 64.132, | |
| "eval_steps_per_second": 2.788, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 63.08, | |
| "learning_rate": 8.442982456140352e-06, | |
| "loss": 0.0452, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.9400689601898193, | |
| "eval_runtime": 0.7216, | |
| "eval_samples_per_second": 63.751, | |
| "eval_steps_per_second": 2.772, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 64.62, | |
| "learning_rate": 7.2368421052631575e-06, | |
| "loss": 0.0455, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 64.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.9647494554519653, | |
| "eval_runtime": 0.7173, | |
| "eval_samples_per_second": 64.126, | |
| "eval_steps_per_second": 2.788, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8957914113998413, | |
| "eval_runtime": 0.704, | |
| "eval_samples_per_second": 65.338, | |
| "eval_steps_per_second": 2.841, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 66.15, | |
| "learning_rate": 6.030701754385965e-06, | |
| "loss": 0.0408, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 66.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.8531116247177124, | |
| "eval_runtime": 0.6999, | |
| "eval_samples_per_second": 65.72, | |
| "eval_steps_per_second": 2.857, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 67.69, | |
| "learning_rate": 4.824561403508772e-06, | |
| "loss": 0.0418, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.8205869197845459, | |
| "eval_runtime": 0.715, | |
| "eval_samples_per_second": 64.335, | |
| "eval_steps_per_second": 2.797, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 68.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.8044800758361816, | |
| "eval_runtime": 0.7334, | |
| "eval_samples_per_second": 62.721, | |
| "eval_steps_per_second": 2.727, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 69.23, | |
| "learning_rate": 3.6184210526315788e-06, | |
| "loss": 0.0424, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.8089639544487, | |
| "eval_runtime": 0.7207, | |
| "eval_samples_per_second": 63.826, | |
| "eval_steps_per_second": 2.775, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 70.77, | |
| "learning_rate": 2.412280701754386e-06, | |
| "loss": 0.038, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 70.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.7901564836502075, | |
| "eval_runtime": 0.7, | |
| "eval_samples_per_second": 65.711, | |
| "eval_steps_per_second": 2.857, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.8007910251617432, | |
| "eval_runtime": 0.7273, | |
| "eval_samples_per_second": 63.251, | |
| "eval_steps_per_second": 2.75, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 72.31, | |
| "learning_rate": 1.206140350877193e-06, | |
| "loss": 0.0401, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 72.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.8121515512466431, | |
| "eval_runtime": 0.7164, | |
| "eval_samples_per_second": 64.206, | |
| "eval_steps_per_second": 2.792, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "learning_rate": 0.0, | |
| "loss": 0.0347, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.8161138296127319, | |
| "eval_runtime": 0.7385, | |
| "eval_samples_per_second": 62.291, | |
| "eval_steps_per_second": 2.708, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "step": 480, | |
| "total_flos": 4.687651970153865e+18, | |
| "train_loss": 0.24899903287490208, | |
| "train_runtime": 1004.3941, | |
| "train_samples_per_second": 65.233, | |
| "train_steps_per_second": 0.478 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 480, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 80, | |
| "save_steps": 500, | |
| "total_flos": 4.687651970153865e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |