| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "vit-base-patch16-224-Trial007-YEL_STEM4/checkpoint-13", | |
| "epoch": 44.44444444444444, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8105, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8588, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.48148148148148145, | |
| "eval_loss": 0.7925114035606384, | |
| "eval_runtime": 0.2695, | |
| "eval_samples_per_second": 200.403, | |
| "eval_steps_per_second": 3.711, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.8, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7235, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_accuracy": 0.6851851851851852, | |
| "eval_loss": 0.6471065282821655, | |
| "eval_runtime": 0.2654, | |
| "eval_samples_per_second": 203.498, | |
| "eval_steps_per_second": 3.768, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.624, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3e-05, | |
| "loss": 0.6009, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_accuracy": 0.7222222222222222, | |
| "eval_loss": 0.5245712399482727, | |
| "eval_runtime": 0.2719, | |
| "eval_samples_per_second": 198.634, | |
| "eval_steps_per_second": 3.678, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.5091, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5349, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.4196, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9074074074074074, | |
| "eval_loss": 0.3422330617904663, | |
| "eval_runtime": 0.2687, | |
| "eval_samples_per_second": 200.971, | |
| "eval_steps_per_second": 3.722, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4408, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 4.9444444444444446e-05, | |
| "loss": 0.4022, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "eval_accuracy": 0.9259259259259259, | |
| "eval_loss": 0.3213180601596832, | |
| "eval_runtime": 0.2605, | |
| "eval_samples_per_second": 207.264, | |
| "eval_steps_per_second": 3.838, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 0.3015, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 4.8333333333333334e-05, | |
| "loss": 0.3531, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.19483274221420288, | |
| "eval_runtime": 0.2633, | |
| "eval_samples_per_second": 205.079, | |
| "eval_steps_per_second": 3.798, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 4.7777777777777784e-05, | |
| "loss": 0.2652, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.3095, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.11961700022220612, | |
| "eval_runtime": 0.2623, | |
| "eval_samples_per_second": 205.894, | |
| "eval_steps_per_second": 3.813, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.2041, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 4.6111111111111115e-05, | |
| "loss": 0.2782, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.555555555555556e-05, | |
| "loss": 0.283, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.06661991775035858, | |
| "eval_runtime": 0.2844, | |
| "eval_samples_per_second": 189.904, | |
| "eval_steps_per_second": 3.517, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.1837, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.1607, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.04014136642217636, | |
| "eval_runtime": 0.2662, | |
| "eval_samples_per_second": 202.872, | |
| "eval_steps_per_second": 3.757, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 4.388888888888889e-05, | |
| "loss": 0.427, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.1459, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.03019571676850319, | |
| "eval_runtime": 0.2627, | |
| "eval_samples_per_second": 205.591, | |
| "eval_steps_per_second": 3.807, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 4.277777777777778e-05, | |
| "loss": 0.1214, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "learning_rate": 4.222222222222222e-05, | |
| "loss": 0.1325, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.022280599921941757, | |
| "eval_runtime": 0.2634, | |
| "eval_samples_per_second": 205.012, | |
| "eval_steps_per_second": 3.797, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.0976, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 11.56, | |
| "learning_rate": 4.111111111111111e-05, | |
| "loss": 0.1322, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.055555555555556e-05, | |
| "loss": 0.1362, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.020502379164099693, | |
| "eval_runtime": 0.264, | |
| "eval_samples_per_second": 204.523, | |
| "eval_steps_per_second": 3.787, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0831, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 12.89, | |
| "learning_rate": 3.944444444444445e-05, | |
| "loss": 0.1623, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 12.89, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.00942131970077753, | |
| "eval_runtime": 0.2683, | |
| "eval_samples_per_second": 201.286, | |
| "eval_steps_per_second": 3.728, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.1171, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 13.78, | |
| "learning_rate": 3.8333333333333334e-05, | |
| "loss": 0.0974, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 13.78, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.004605439025908709, | |
| "eval_runtime": 0.2648, | |
| "eval_samples_per_second": 203.94, | |
| "eval_steps_per_second": 3.777, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 14.22, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 0.0738, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 14.67, | |
| "learning_rate": 3.722222222222222e-05, | |
| "loss": 0.1077, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 14.67, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.005409094505012035, | |
| "eval_runtime": 0.2623, | |
| "eval_samples_per_second": 205.903, | |
| "eval_steps_per_second": 3.813, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 0.0845, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 15.56, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.1003, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 0.0742, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.003965036477893591, | |
| "eval_runtime": 0.2673, | |
| "eval_samples_per_second": 202.006, | |
| "eval_steps_per_second": 3.741, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 16.44, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0894, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "learning_rate": 3.444444444444445e-05, | |
| "loss": 0.1468, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0029907028656452894, | |
| "eval_runtime": 0.2635, | |
| "eval_samples_per_second": 204.948, | |
| "eval_steps_per_second": 3.795, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 17.33, | |
| "learning_rate": 3.388888888888889e-05, | |
| "loss": 0.0892, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 17.78, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.077, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 17.78, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.004134837072342634, | |
| "eval_runtime": 0.2684, | |
| "eval_samples_per_second": 201.225, | |
| "eval_steps_per_second": 3.726, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 18.22, | |
| "learning_rate": 3.277777777777778e-05, | |
| "loss": 0.0557, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 18.67, | |
| "learning_rate": 3.222222222222223e-05, | |
| "loss": 0.0907, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 18.67, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.010868255980312824, | |
| "eval_runtime": 0.2644, | |
| "eval_samples_per_second": 204.245, | |
| "eval_steps_per_second": 3.782, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 19.11, | |
| "learning_rate": 3.1666666666666666e-05, | |
| "loss": 0.0606, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 19.56, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 0.0898, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.0363, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0022966607939451933, | |
| "eval_runtime": 0.2667, | |
| "eval_samples_per_second": 202.454, | |
| "eval_steps_per_second": 3.749, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 20.44, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0661, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 20.89, | |
| "learning_rate": 2.9444444444444448e-05, | |
| "loss": 0.0519, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 20.89, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0016263651195913553, | |
| "eval_runtime": 0.2632, | |
| "eval_samples_per_second": 205.141, | |
| "eval_steps_per_second": 3.799, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 21.33, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 0.0675, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 21.78, | |
| "learning_rate": 2.8333333333333335e-05, | |
| "loss": 0.0672, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 21.78, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0014932247577235103, | |
| "eval_runtime": 0.2829, | |
| "eval_samples_per_second": 190.887, | |
| "eval_steps_per_second": 3.535, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.072, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 22.67, | |
| "learning_rate": 2.7222222222222223e-05, | |
| "loss": 0.0894, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 22.67, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0020148803014308214, | |
| "eval_runtime": 0.2666, | |
| "eval_samples_per_second": 202.549, | |
| "eval_steps_per_second": 3.751, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 23.11, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.0508, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 23.56, | |
| "learning_rate": 2.6111111111111114e-05, | |
| "loss": 0.0838, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 2.5555555555555554e-05, | |
| "loss": 0.0267, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0019541929941624403, | |
| "eval_runtime": 0.2644, | |
| "eval_samples_per_second": 204.256, | |
| "eval_steps_per_second": 3.783, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 24.44, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0468, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 0.0639, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0019170470768585801, | |
| "eval_runtime": 0.2753, | |
| "eval_samples_per_second": 196.133, | |
| "eval_steps_per_second": 3.632, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 25.33, | |
| "learning_rate": 2.3888888888888892e-05, | |
| "loss": 0.0601, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 25.78, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.0675, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 25.78, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0023251723032444715, | |
| "eval_runtime": 0.2637, | |
| "eval_samples_per_second": 204.786, | |
| "eval_steps_per_second": 3.792, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 26.22, | |
| "learning_rate": 2.277777777777778e-05, | |
| "loss": 0.1053, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 26.67, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0508, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 26.67, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0019600405357778072, | |
| "eval_runtime": 0.2632, | |
| "eval_samples_per_second": 205.143, | |
| "eval_steps_per_second": 3.799, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 27.11, | |
| "learning_rate": 2.1666666666666667e-05, | |
| "loss": 0.0574, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 27.56, | |
| "learning_rate": 2.111111111111111e-05, | |
| "loss": 0.0738, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 2.0555555555555555e-05, | |
| "loss": 0.0509, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0014345721574500203, | |
| "eval_runtime": 0.264, | |
| "eval_samples_per_second": 204.556, | |
| "eval_steps_per_second": 3.788, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 28.44, | |
| "learning_rate": 2e-05, | |
| "loss": 0.073, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 28.89, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.0573, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 28.89, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0018337038345634937, | |
| "eval_runtime": 0.2658, | |
| "eval_samples_per_second": 203.143, | |
| "eval_steps_per_second": 3.762, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 29.33, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 0.0369, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 29.78, | |
| "learning_rate": 1.8333333333333333e-05, | |
| "loss": 0.0584, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 29.78, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0013740634312853217, | |
| "eval_runtime": 0.2689, | |
| "eval_samples_per_second": 200.843, | |
| "eval_steps_per_second": 3.719, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 30.22, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 0.1127, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 30.67, | |
| "learning_rate": 1.7222222222222224e-05, | |
| "loss": 0.0657, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 30.67, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0011925003491342068, | |
| "eval_runtime": 0.2655, | |
| "eval_samples_per_second": 203.376, | |
| "eval_steps_per_second": 3.766, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 31.11, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0286, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 31.56, | |
| "learning_rate": 1.6111111111111115e-05, | |
| "loss": 0.0655, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 1.5555555555555555e-05, | |
| "loss": 0.0635, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0008685937500558794, | |
| "eval_runtime": 0.2664, | |
| "eval_samples_per_second": 202.738, | |
| "eval_steps_per_second": 3.754, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 32.44, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0897, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 32.89, | |
| "learning_rate": 1.4444444444444444e-05, | |
| "loss": 0.0617, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 32.89, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.000824602844659239, | |
| "eval_runtime": 0.2666, | |
| "eval_samples_per_second": 202.534, | |
| "eval_steps_per_second": 3.751, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.1261, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 33.78, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.0614, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 33.78, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0008151546935550869, | |
| "eval_runtime": 0.2757, | |
| "eval_samples_per_second": 195.883, | |
| "eval_steps_per_second": 3.627, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 34.22, | |
| "learning_rate": 1.2777777777777777e-05, | |
| "loss": 0.0437, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 34.67, | |
| "learning_rate": 1.2222222222222222e-05, | |
| "loss": 0.0614, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 34.67, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0008515185909345746, | |
| "eval_runtime": 0.2867, | |
| "eval_samples_per_second": 188.348, | |
| "eval_steps_per_second": 3.488, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 35.11, | |
| "learning_rate": 1.1666666666666668e-05, | |
| "loss": 0.4154, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 35.56, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0741, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 1.0555555555555555e-05, | |
| "loss": 0.0618, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0008116821409203112, | |
| "eval_runtime": 0.2688, | |
| "eval_samples_per_second": 200.888, | |
| "eval_steps_per_second": 3.72, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 36.44, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0478, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 36.89, | |
| "learning_rate": 9.444444444444445e-06, | |
| "loss": 0.0384, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 36.89, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0007847616798244417, | |
| "eval_runtime": 0.2653, | |
| "eval_samples_per_second": 203.518, | |
| "eval_steps_per_second": 3.769, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 37.33, | |
| "learning_rate": 8.88888888888889e-06, | |
| "loss": 0.0435, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 37.78, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.0565, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 37.78, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0007751730154268444, | |
| "eval_runtime": 0.2683, | |
| "eval_samples_per_second": 201.275, | |
| "eval_steps_per_second": 3.727, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 38.22, | |
| "learning_rate": 7.777777777777777e-06, | |
| "loss": 0.0791, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 38.67, | |
| "learning_rate": 7.222222222222222e-06, | |
| "loss": 0.0784, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 38.67, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0007627953891642392, | |
| "eval_runtime": 0.2764, | |
| "eval_samples_per_second": 195.336, | |
| "eval_steps_per_second": 3.617, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 39.11, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.0511, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 39.56, | |
| "learning_rate": 6.111111111111111e-06, | |
| "loss": 0.0758, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0313, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0007455433369614184, | |
| "eval_runtime": 0.2654, | |
| "eval_samples_per_second": 203.503, | |
| "eval_steps_per_second": 3.769, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 40.44, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0486, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 40.89, | |
| "learning_rate": 4.444444444444445e-06, | |
| "loss": 0.0496, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 40.89, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0007441618363372982, | |
| "eval_runtime": 0.262, | |
| "eval_samples_per_second": 206.068, | |
| "eval_steps_per_second": 3.816, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 41.33, | |
| "learning_rate": 3.888888888888889e-06, | |
| "loss": 0.0519, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 41.78, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.0273, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 41.78, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0007541766972281039, | |
| "eval_runtime": 0.2661, | |
| "eval_samples_per_second": 202.899, | |
| "eval_steps_per_second": 3.757, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 42.22, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.0432, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 42.67, | |
| "learning_rate": 2.2222222222222225e-06, | |
| "loss": 0.0448, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 42.67, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0007555445190519094, | |
| "eval_runtime": 0.2674, | |
| "eval_samples_per_second": 201.916, | |
| "eval_steps_per_second": 3.739, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 43.11, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 0.0526, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 43.56, | |
| "learning_rate": 1.1111111111111112e-06, | |
| "loss": 0.0518, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 5.555555555555556e-07, | |
| "loss": 0.0948, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0007408310775645077, | |
| "eval_runtime": 0.2652, | |
| "eval_samples_per_second": 203.585, | |
| "eval_steps_per_second": 3.77, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 44.44, | |
| "learning_rate": 0.0, | |
| "loss": 0.0371, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 44.44, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0007394535932689905, | |
| "eval_runtime": 0.2915, | |
| "eval_samples_per_second": 185.274, | |
| "eval_steps_per_second": 3.431, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 44.44, | |
| "step": 100, | |
| "total_flos": 1.6586385457107272e+18, | |
| "train_loss": 0.1560394330881536, | |
| "train_runtime": 688.8603, | |
| "train_samples_per_second": 34.913, | |
| "train_steps_per_second": 0.145 | |
| } | |
| ], | |
| "max_steps": 100, | |
| "num_train_epochs": 50, | |
| "total_flos": 1.6586385457107272e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |