| { | |
| "best_metric": 0.782608695652174, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-ve-U13-b-80b\\checkpoint-117", | |
| "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": 0.13043478260869565, | |
| "eval_loss": 1.385452389717102, | |
| "eval_runtime": 0.715, | |
| "eval_samples_per_second": 64.335, | |
| "eval_steps_per_second": 2.797, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.2916666666666667e-05, | |
| "loss": 1.3852, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.2826086956521739, | |
| "eval_loss": 1.3762171268463135, | |
| "eval_runtime": 0.8255, | |
| "eval_samples_per_second": 55.723, | |
| "eval_steps_per_second": 2.423, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_accuracy": 0.2826086956521739, | |
| "eval_loss": 1.3521002531051636, | |
| "eval_runtime": 0.7696, | |
| "eval_samples_per_second": 59.773, | |
| "eval_steps_per_second": 2.599, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 1.3565, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.34782608695652173, | |
| "eval_loss": 1.250961422920227, | |
| "eval_runtime": 0.7773, | |
| "eval_samples_per_second": 59.179, | |
| "eval_steps_per_second": 2.573, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 5.4276315789473686e-05, | |
| "loss": 1.2024, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_accuracy": 0.34782608695652173, | |
| "eval_loss": 1.1528408527374268, | |
| "eval_runtime": 0.7354, | |
| "eval_samples_per_second": 62.55, | |
| "eval_steps_per_second": 2.72, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.0294172763824463, | |
| "eval_runtime": 0.6853, | |
| "eval_samples_per_second": 67.121, | |
| "eval_steps_per_second": 2.918, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 5.3070175438596496e-05, | |
| "loss": 1.0453, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "eval_accuracy": 0.5217391304347826, | |
| "eval_loss": 0.9608190655708313, | |
| "eval_runtime": 0.7141, | |
| "eval_samples_per_second": 64.421, | |
| "eval_steps_per_second": 2.801, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 5.18640350877193e-05, | |
| "loss": 0.8827, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 0.8800680041313171, | |
| "eval_runtime": 0.7421, | |
| "eval_samples_per_second": 61.99, | |
| "eval_steps_per_second": 2.695, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "eval_accuracy": 0.5652173913043478, | |
| "eval_loss": 0.988355278968811, | |
| "eval_runtime": 0.7152, | |
| "eval_samples_per_second": 64.319, | |
| "eval_steps_per_second": 2.796, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 5.0657894736842104e-05, | |
| "loss": 0.7887, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 0.7927354574203491, | |
| "eval_runtime": 0.7043, | |
| "eval_samples_per_second": 65.311, | |
| "eval_steps_per_second": 2.84, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 4.9451754385964915e-05, | |
| "loss": 0.6795, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 0.7237101793289185, | |
| "eval_runtime": 0.6992, | |
| "eval_samples_per_second": 65.792, | |
| "eval_steps_per_second": 2.861, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.7249867916107178, | |
| "eval_runtime": 0.6943, | |
| "eval_samples_per_second": 66.251, | |
| "eval_steps_per_second": 2.88, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 4.824561403508772e-05, | |
| "loss": 0.5777, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.7140356302261353, | |
| "eval_runtime": 0.6964, | |
| "eval_samples_per_second": 66.052, | |
| "eval_steps_per_second": 2.872, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 13.85, | |
| "learning_rate": 4.703947368421053e-05, | |
| "loss": 0.496, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8013545274734497, | |
| "eval_runtime": 0.7185, | |
| "eval_samples_per_second": 64.019, | |
| "eval_steps_per_second": 2.783, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.8701084852218628, | |
| "eval_runtime": 0.7086, | |
| "eval_samples_per_second": 64.917, | |
| "eval_steps_per_second": 2.822, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.4224, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 0.93837571144104, | |
| "eval_runtime": 0.6717, | |
| "eval_samples_per_second": 68.483, | |
| "eval_steps_per_second": 2.978, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "learning_rate": 4.462719298245614e-05, | |
| "loss": 0.3744, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7593847513198853, | |
| "eval_runtime": 0.8804, | |
| "eval_samples_per_second": 52.248, | |
| "eval_steps_per_second": 2.272, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6122156977653503, | |
| "eval_runtime": 0.7027, | |
| "eval_samples_per_second": 65.461, | |
| "eval_steps_per_second": 2.846, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 4.342105263157895e-05, | |
| "loss": 0.3775, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.814321756362915, | |
| "eval_runtime": 0.7065, | |
| "eval_samples_per_second": 65.112, | |
| "eval_steps_per_second": 2.831, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.221491228070176e-05, | |
| "loss": 0.3275, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 0.9981420040130615, | |
| "eval_runtime": 0.6931, | |
| "eval_samples_per_second": 66.366, | |
| "eval_steps_per_second": 2.885, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8602655529975891, | |
| "eval_runtime": 0.7452, | |
| "eval_samples_per_second": 61.724, | |
| "eval_steps_per_second": 2.684, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 21.54, | |
| "learning_rate": 4.100877192982456e-05, | |
| "loss": 0.3202, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8412013649940491, | |
| "eval_runtime": 0.6933, | |
| "eval_samples_per_second": 66.346, | |
| "eval_steps_per_second": 2.885, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 22.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8653804659843445, | |
| "eval_runtime": 0.7152, | |
| "eval_samples_per_second": 64.32, | |
| "eval_steps_per_second": 2.797, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 3.9802631578947374e-05, | |
| "loss": 0.2849, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.9650171399116516, | |
| "eval_runtime": 0.703, | |
| "eval_samples_per_second": 65.437, | |
| "eval_steps_per_second": 2.845, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 3.859649122807018e-05, | |
| "loss": 0.2518, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 24.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8102234601974487, | |
| "eval_runtime": 0.6748, | |
| "eval_samples_per_second": 68.166, | |
| "eval_steps_per_second": 2.964, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.7203320264816284, | |
| "eval_runtime": 0.6843, | |
| "eval_samples_per_second": 67.221, | |
| "eval_steps_per_second": 2.923, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 26.15, | |
| "learning_rate": 3.739035087719298e-05, | |
| "loss": 0.2467, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9435244798660278, | |
| "eval_runtime": 0.6884, | |
| "eval_samples_per_second": 66.821, | |
| "eval_steps_per_second": 2.905, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "learning_rate": 3.618421052631579e-05, | |
| "loss": 0.2218, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.8905265927314758, | |
| "eval_runtime": 0.7164, | |
| "eval_samples_per_second": 64.207, | |
| "eval_steps_per_second": 2.792, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.0828336477279663, | |
| "eval_runtime": 0.6739, | |
| "eval_samples_per_second": 68.256, | |
| "eval_steps_per_second": 2.968, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 29.23, | |
| "learning_rate": 3.49780701754386e-05, | |
| "loss": 0.2075, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8935770988464355, | |
| "eval_runtime": 0.7007, | |
| "eval_samples_per_second": 65.647, | |
| "eval_steps_per_second": 2.854, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 3.377192982456141e-05, | |
| "loss": 0.1893, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 30.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.8835997581481934, | |
| "eval_runtime": 0.7042, | |
| "eval_samples_per_second": 65.326, | |
| "eval_steps_per_second": 2.84, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9691875576972961, | |
| "eval_runtime": 0.834, | |
| "eval_samples_per_second": 55.158, | |
| "eval_steps_per_second": 2.398, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 32.31, | |
| "learning_rate": 3.256578947368421e-05, | |
| "loss": 0.194, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 32.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 1.039009690284729, | |
| "eval_runtime": 0.7007, | |
| "eval_samples_per_second": 65.651, | |
| "eval_steps_per_second": 2.854, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 33.85, | |
| "learning_rate": 3.1359649122807015e-05, | |
| "loss": 0.1739, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8694977164268494, | |
| "eval_runtime": 0.6645, | |
| "eval_samples_per_second": 69.221, | |
| "eval_steps_per_second": 3.01, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 34.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.1835598945617676, | |
| "eval_runtime": 0.7151, | |
| "eval_samples_per_second": 64.33, | |
| "eval_steps_per_second": 2.797, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 3.0153508771929826e-05, | |
| "loss": 0.1895, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.0130637884140015, | |
| "eval_runtime": 0.7672, | |
| "eval_samples_per_second": 59.96, | |
| "eval_steps_per_second": 2.607, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "learning_rate": 2.894736842105263e-05, | |
| "loss": 0.1428, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.9618039131164551, | |
| "eval_runtime": 0.7041, | |
| "eval_samples_per_second": 65.327, | |
| "eval_steps_per_second": 2.84, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.995048999786377, | |
| "eval_runtime": 0.7508, | |
| "eval_samples_per_second": 61.272, | |
| "eval_steps_per_second": 2.664, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 2.774122807017544e-05, | |
| "loss": 0.1443, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 38.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.9112874865531921, | |
| "eval_runtime": 0.6953, | |
| "eval_samples_per_second": 66.156, | |
| "eval_steps_per_second": 2.876, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 2.6535087719298248e-05, | |
| "loss": 0.1574, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9213477969169617, | |
| "eval_runtime": 0.6866, | |
| "eval_samples_per_second": 67.001, | |
| "eval_steps_per_second": 2.913, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9436842203140259, | |
| "eval_runtime": 0.6962, | |
| "eval_samples_per_second": 66.074, | |
| "eval_steps_per_second": 2.873, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 41.54, | |
| "learning_rate": 2.5328947368421052e-05, | |
| "loss": 0.1442, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.9226171970367432, | |
| "eval_runtime": 0.6819, | |
| "eval_samples_per_second": 67.458, | |
| "eval_steps_per_second": 2.933, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 42.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9430357813835144, | |
| "eval_runtime": 0.6947, | |
| "eval_samples_per_second": 66.212, | |
| "eval_steps_per_second": 2.879, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 43.08, | |
| "learning_rate": 2.412280701754386e-05, | |
| "loss": 0.1186, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.9759092926979065, | |
| "eval_runtime": 0.7192, | |
| "eval_samples_per_second": 63.959, | |
| "eval_steps_per_second": 2.781, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 44.62, | |
| "learning_rate": 2.2916666666666667e-05, | |
| "loss": 0.1135, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 44.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9650900363922119, | |
| "eval_runtime": 0.7171, | |
| "eval_samples_per_second": 64.148, | |
| "eval_steps_per_second": 2.789, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.9536284804344177, | |
| "eval_runtime": 0.7029, | |
| "eval_samples_per_second": 65.444, | |
| "eval_steps_per_second": 2.845, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "learning_rate": 2.1710526315789474e-05, | |
| "loss": 0.1299, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 46.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.9118357300758362, | |
| "eval_runtime": 0.691, | |
| "eval_samples_per_second": 66.567, | |
| "eval_steps_per_second": 2.894, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 47.69, | |
| "learning_rate": 2.050438596491228e-05, | |
| "loss": 0.134, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.9847990274429321, | |
| "eval_runtime": 0.693, | |
| "eval_samples_per_second": 66.381, | |
| "eval_steps_per_second": 2.886, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 48.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.864098072052002, | |
| "eval_runtime": 0.6669, | |
| "eval_samples_per_second": 68.973, | |
| "eval_steps_per_second": 2.999, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 49.23, | |
| "learning_rate": 1.929824561403509e-05, | |
| "loss": 0.1418, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 1.055314064025879, | |
| "eval_runtime": 0.6987, | |
| "eval_samples_per_second": 65.838, | |
| "eval_steps_per_second": 2.863, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 50.77, | |
| "learning_rate": 1.8092105263157896e-05, | |
| "loss": 0.1074, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 50.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.2511317729949951, | |
| "eval_runtime": 0.6763, | |
| "eval_samples_per_second": 68.018, | |
| "eval_steps_per_second": 2.957, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.0186011791229248, | |
| "eval_runtime": 0.6748, | |
| "eval_samples_per_second": 68.173, | |
| "eval_steps_per_second": 2.964, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 52.31, | |
| "learning_rate": 1.6885964912280704e-05, | |
| "loss": 0.1144, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 52.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.0467170476913452, | |
| "eval_runtime": 0.7339, | |
| "eval_samples_per_second": 62.676, | |
| "eval_steps_per_second": 2.725, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 53.85, | |
| "learning_rate": 1.5679824561403508e-05, | |
| "loss": 0.0999, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9897727966308594, | |
| "eval_runtime": 0.724, | |
| "eval_samples_per_second": 63.533, | |
| "eval_steps_per_second": 2.762, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 54.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.1779977083206177, | |
| "eval_runtime": 0.6747, | |
| "eval_samples_per_second": 68.177, | |
| "eval_steps_per_second": 2.964, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 55.38, | |
| "learning_rate": 1.4473684210526315e-05, | |
| "loss": 0.1131, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 1.0015190839767456, | |
| "eval_runtime": 0.6671, | |
| "eval_samples_per_second": 68.953, | |
| "eval_steps_per_second": 2.998, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "learning_rate": 1.3267543859649124e-05, | |
| "loss": 0.1152, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 1.0759129524230957, | |
| "eval_runtime": 0.6833, | |
| "eval_samples_per_second": 67.322, | |
| "eval_steps_per_second": 2.927, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.1293679475784302, | |
| "eval_runtime": 0.7265, | |
| "eval_samples_per_second": 63.317, | |
| "eval_steps_per_second": 2.753, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 58.46, | |
| "learning_rate": 1.206140350877193e-05, | |
| "loss": 0.1012, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 58.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.0893771648406982, | |
| "eval_runtime": 0.7929, | |
| "eval_samples_per_second": 58.015, | |
| "eval_steps_per_second": 2.522, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 1.0855263157894737e-05, | |
| "loss": 0.0938, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.076356291770935, | |
| "eval_runtime": 0.7122, | |
| "eval_samples_per_second": 64.587, | |
| "eval_steps_per_second": 2.808, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.1784361600875854, | |
| "eval_runtime": 0.6759, | |
| "eval_samples_per_second": 68.056, | |
| "eval_steps_per_second": 2.959, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 61.54, | |
| "learning_rate": 9.649122807017545e-06, | |
| "loss": 0.0944, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.158086895942688, | |
| "eval_runtime": 0.6568, | |
| "eval_samples_per_second": 70.035, | |
| "eval_steps_per_second": 3.045, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 62.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.0443789958953857, | |
| "eval_runtime": 0.7668, | |
| "eval_samples_per_second": 59.992, | |
| "eval_steps_per_second": 2.608, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 63.08, | |
| "learning_rate": 8.442982456140352e-06, | |
| "loss": 0.1015, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.0996026992797852, | |
| "eval_runtime": 0.6974, | |
| "eval_samples_per_second": 65.962, | |
| "eval_steps_per_second": 2.868, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 64.62, | |
| "learning_rate": 7.2368421052631575e-06, | |
| "loss": 0.0762, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 64.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 1.1234647035598755, | |
| "eval_runtime": 0.6919, | |
| "eval_samples_per_second": 66.48, | |
| "eval_steps_per_second": 2.89, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.0999064445495605, | |
| "eval_runtime": 0.6675, | |
| "eval_samples_per_second": 68.916, | |
| "eval_steps_per_second": 2.996, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 66.15, | |
| "learning_rate": 6.030701754385965e-06, | |
| "loss": 0.0775, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 66.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.077625036239624, | |
| "eval_runtime": 0.7156, | |
| "eval_samples_per_second": 64.279, | |
| "eval_steps_per_second": 2.795, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 67.69, | |
| "learning_rate": 4.824561403508772e-06, | |
| "loss": 0.0787, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.0878902673721313, | |
| "eval_runtime": 0.8099, | |
| "eval_samples_per_second": 56.794, | |
| "eval_steps_per_second": 2.469, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 68.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.0913468599319458, | |
| "eval_runtime": 0.72, | |
| "eval_samples_per_second": 63.891, | |
| "eval_steps_per_second": 2.778, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 69.23, | |
| "learning_rate": 3.6184210526315788e-06, | |
| "loss": 0.081, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.0558408498764038, | |
| "eval_runtime": 0.6843, | |
| "eval_samples_per_second": 67.219, | |
| "eval_steps_per_second": 2.923, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 70.77, | |
| "learning_rate": 2.412280701754386e-06, | |
| "loss": 0.0749, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 70.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.0401302576065063, | |
| "eval_runtime": 0.6922, | |
| "eval_samples_per_second": 66.457, | |
| "eval_steps_per_second": 2.889, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.0538554191589355, | |
| "eval_runtime": 0.6836, | |
| "eval_samples_per_second": 67.294, | |
| "eval_steps_per_second": 2.926, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 72.31, | |
| "learning_rate": 1.206140350877193e-06, | |
| "loss": 0.0841, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 72.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.0662652254104614, | |
| "eval_runtime": 0.727, | |
| "eval_samples_per_second": 63.271, | |
| "eval_steps_per_second": 2.751, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "learning_rate": 0.0, | |
| "loss": 0.0928, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.0711960792541504, | |
| "eval_runtime": 0.704, | |
| "eval_samples_per_second": 65.342, | |
| "eval_steps_per_second": 2.841, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "step": 480, | |
| "total_flos": 1.5036476561209958e+18, | |
| "train_loss": 0.3110019433001677, | |
| "train_runtime": 594.8679, | |
| "train_samples_per_second": 110.142, | |
| "train_steps_per_second": 0.807 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 480, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 80, | |
| "save_steps": 500, | |
| "total_flos": 1.5036476561209958e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |