| { | |
| "best_metric": 0.6521739130434783, | |
| "best_model_checkpoint": "swiftformer-xs-ve-U13-b-80b\\checkpoint-429", | |
| "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": 0.21739130434782608, | |
| "eval_loss": 1.3861862421035767, | |
| "eval_runtime": 0.8414, | |
| "eval_samples_per_second": 54.668, | |
| "eval_steps_per_second": 2.377, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 1.3862, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.3855926990509033, | |
| "eval_runtime": 0.6123, | |
| "eval_samples_per_second": 75.124, | |
| "eval_steps_per_second": 3.266, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_accuracy": 0.2826086956521739, | |
| "eval_loss": 1.3848732709884644, | |
| "eval_runtime": 0.825, | |
| "eval_samples_per_second": 55.755, | |
| "eval_steps_per_second": 2.424, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 1.3848, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.2608695652173913, | |
| "eval_loss": 1.382991075515747, | |
| "eval_runtime": 0.6325, | |
| "eval_samples_per_second": 72.728, | |
| "eval_steps_per_second": 3.162, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 3.125e-05, | |
| "loss": 1.3806, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_accuracy": 0.17391304347826086, | |
| "eval_loss": 1.3804432153701782, | |
| "eval_runtime": 0.6066, | |
| "eval_samples_per_second": 75.828, | |
| "eval_steps_per_second": 3.297, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.1956521739130435, | |
| "eval_loss": 1.3757747411727905, | |
| "eval_runtime": 0.6385, | |
| "eval_samples_per_second": 72.045, | |
| "eval_steps_per_second": 3.132, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.3662, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "eval_accuracy": 0.17391304347826086, | |
| "eval_loss": 1.3700366020202637, | |
| "eval_runtime": 0.6079, | |
| "eval_samples_per_second": 75.673, | |
| "eval_steps_per_second": 3.29, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 4.976851851851852e-05, | |
| "loss": 1.3261, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.17391304347826086, | |
| "eval_loss": 1.3651779890060425, | |
| "eval_runtime": 0.6421, | |
| "eval_samples_per_second": 71.635, | |
| "eval_steps_per_second": 3.115, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "eval_accuracy": 0.15217391304347827, | |
| "eval_loss": 1.3624860048294067, | |
| "eval_runtime": 0.6404, | |
| "eval_samples_per_second": 71.835, | |
| "eval_steps_per_second": 3.123, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 1.2588, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.13043478260869565, | |
| "eval_loss": 1.362892985343933, | |
| "eval_runtime": 0.6225, | |
| "eval_samples_per_second": 73.894, | |
| "eval_steps_per_second": 3.213, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 4.745370370370371e-05, | |
| "loss": 1.1972, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "eval_accuracy": 0.13043478260869565, | |
| "eval_loss": 1.3591643571853638, | |
| "eval_runtime": 0.6092, | |
| "eval_samples_per_second": 75.509, | |
| "eval_steps_per_second": 3.283, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.21739130434782608, | |
| "eval_loss": 1.3570374250411987, | |
| "eval_runtime": 0.6841, | |
| "eval_samples_per_second": 67.244, | |
| "eval_steps_per_second": 2.924, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 1.1578, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "eval_accuracy": 0.1956521739130435, | |
| "eval_loss": 1.3590192794799805, | |
| "eval_runtime": 0.5819, | |
| "eval_samples_per_second": 79.051, | |
| "eval_steps_per_second": 3.437, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 13.85, | |
| "learning_rate": 4.5138888888888894e-05, | |
| "loss": 1.124, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.21739130434782608, | |
| "eval_loss": 1.3730636835098267, | |
| "eval_runtime": 0.6272, | |
| "eval_samples_per_second": 73.336, | |
| "eval_steps_per_second": 3.189, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "eval_accuracy": 0.15217391304347827, | |
| "eval_loss": 1.3718194961547852, | |
| "eval_runtime": 0.5953, | |
| "eval_samples_per_second": 77.274, | |
| "eval_steps_per_second": 3.36, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 4.3981481481481486e-05, | |
| "loss": 1.1045, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.17391304347826086, | |
| "eval_loss": 1.3736342191696167, | |
| "eval_runtime": 0.6132, | |
| "eval_samples_per_second": 75.018, | |
| "eval_steps_per_second": 3.262, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "learning_rate": 4.282407407407408e-05, | |
| "loss": 1.0703, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "eval_accuracy": 0.21739130434782608, | |
| "eval_loss": 1.4983274936676025, | |
| "eval_runtime": 0.5972, | |
| "eval_samples_per_second": 77.024, | |
| "eval_steps_per_second": 3.349, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.17391304347826086, | |
| "eval_loss": 1.5455262660980225, | |
| "eval_runtime": 0.6497, | |
| "eval_samples_per_second": 70.799, | |
| "eval_steps_per_second": 3.078, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.0663, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "eval_accuracy": 0.17391304347826086, | |
| "eval_loss": 1.4473291635513306, | |
| "eval_runtime": 0.6179, | |
| "eval_samples_per_second": 74.447, | |
| "eval_steps_per_second": 3.237, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.0509259259259265e-05, | |
| "loss": 1.01, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.2608695652173913, | |
| "eval_loss": 1.4010741710662842, | |
| "eval_runtime": 0.6583, | |
| "eval_samples_per_second": 69.876, | |
| "eval_steps_per_second": 3.038, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "eval_accuracy": 0.2826086956521739, | |
| "eval_loss": 1.405311107635498, | |
| "eval_runtime": 0.6711, | |
| "eval_samples_per_second": 68.548, | |
| "eval_steps_per_second": 2.98, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 21.54, | |
| "learning_rate": 3.935185185185186e-05, | |
| "loss": 0.9961, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.21739130434782608, | |
| "eval_loss": 1.4185727834701538, | |
| "eval_runtime": 0.6066, | |
| "eval_samples_per_second": 75.831, | |
| "eval_steps_per_second": 3.297, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 22.92, | |
| "eval_accuracy": 0.2608695652173913, | |
| "eval_loss": 1.5167733430862427, | |
| "eval_runtime": 0.5944, | |
| "eval_samples_per_second": 77.394, | |
| "eval_steps_per_second": 3.365, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 3.8194444444444444e-05, | |
| "loss": 0.9754, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.2826086956521739, | |
| "eval_loss": 1.3872967958450317, | |
| "eval_runtime": 0.6424, | |
| "eval_samples_per_second": 71.611, | |
| "eval_steps_per_second": 3.114, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.9417, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 24.92, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.465644121170044, | |
| "eval_runtime": 0.6234, | |
| "eval_samples_per_second": 73.783, | |
| "eval_steps_per_second": 3.208, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.2608695652173913, | |
| "eval_loss": 1.349937081336975, | |
| "eval_runtime": 0.6013, | |
| "eval_samples_per_second": 76.503, | |
| "eval_steps_per_second": 3.326, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 26.15, | |
| "learning_rate": 3.587962962962963e-05, | |
| "loss": 0.9286, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "eval_accuracy": 0.30434782608695654, | |
| "eval_loss": 1.3902080059051514, | |
| "eval_runtime": 0.5952, | |
| "eval_samples_per_second": 77.279, | |
| "eval_steps_per_second": 3.36, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.9216, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.481874704360962, | |
| "eval_runtime": 0.627, | |
| "eval_samples_per_second": 73.362, | |
| "eval_steps_per_second": 3.19, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "eval_accuracy": 0.30434782608695654, | |
| "eval_loss": 1.413346290588379, | |
| "eval_runtime": 0.6049, | |
| "eval_samples_per_second": 76.05, | |
| "eval_steps_per_second": 3.307, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 29.23, | |
| "learning_rate": 3.3564814814814815e-05, | |
| "loss": 0.8868, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.41304347826086957, | |
| "eval_loss": 1.4124078750610352, | |
| "eval_runtime": 0.6224, | |
| "eval_samples_per_second": 73.908, | |
| "eval_steps_per_second": 3.213, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.8908, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 30.92, | |
| "eval_accuracy": 0.34782608695652173, | |
| "eval_loss": 1.442051649093628, | |
| "eval_runtime": 0.631, | |
| "eval_samples_per_second": 72.897, | |
| "eval_steps_per_second": 3.169, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.30434782608695654, | |
| "eval_loss": 1.508549690246582, | |
| "eval_runtime": 0.6317, | |
| "eval_samples_per_second": 72.816, | |
| "eval_steps_per_second": 3.166, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 32.31, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.8729, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 32.92, | |
| "eval_accuracy": 0.34782608695652173, | |
| "eval_loss": 1.3853687047958374, | |
| "eval_runtime": 0.6089, | |
| "eval_samples_per_second": 75.544, | |
| "eval_steps_per_second": 3.285, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 33.85, | |
| "learning_rate": 3.0092592592592593e-05, | |
| "loss": 0.8685, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.30434782608695654, | |
| "eval_loss": 1.3264027833938599, | |
| "eval_runtime": 0.6425, | |
| "eval_samples_per_second": 71.592, | |
| "eval_steps_per_second": 3.113, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 34.92, | |
| "eval_accuracy": 0.30434782608695654, | |
| "eval_loss": 1.3947439193725586, | |
| "eval_runtime": 0.6548, | |
| "eval_samples_per_second": 70.247, | |
| "eval_steps_per_second": 3.054, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 2.8935185185185186e-05, | |
| "loss": 0.8739, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.391304347826087, | |
| "eval_loss": 1.3455146551132202, | |
| "eval_runtime": 0.6498, | |
| "eval_samples_per_second": 70.786, | |
| "eval_steps_per_second": 3.078, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.8288, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "eval_accuracy": 0.391304347826087, | |
| "eval_loss": 1.3620754480361938, | |
| "eval_runtime": 0.6234, | |
| "eval_samples_per_second": 73.794, | |
| "eval_steps_per_second": 3.208, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.391304347826087, | |
| "eval_loss": 1.3875010013580322, | |
| "eval_runtime": 0.6978, | |
| "eval_samples_per_second": 65.925, | |
| "eval_steps_per_second": 2.866, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 2.6620370370370372e-05, | |
| "loss": 0.8369, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 38.92, | |
| "eval_accuracy": 0.3695652173913043, | |
| "eval_loss": 1.427413821220398, | |
| "eval_runtime": 0.6031, | |
| "eval_samples_per_second": 76.27, | |
| "eval_steps_per_second": 3.316, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 2.5462962962962965e-05, | |
| "loss": 0.8101, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.3251171112060547, | |
| "eval_runtime": 0.6452, | |
| "eval_samples_per_second": 71.293, | |
| "eval_steps_per_second": 3.1, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.92, | |
| "eval_accuracy": 0.4782608695652174, | |
| "eval_loss": 1.3038846254348755, | |
| "eval_runtime": 0.6153, | |
| "eval_samples_per_second": 74.765, | |
| "eval_steps_per_second": 3.251, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 41.54, | |
| "learning_rate": 2.4305555555555558e-05, | |
| "loss": 0.8126, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.5434782608695652, | |
| "eval_loss": 1.2522791624069214, | |
| "eval_runtime": 0.6343, | |
| "eval_samples_per_second": 72.516, | |
| "eval_steps_per_second": 3.153, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 42.92, | |
| "eval_accuracy": 0.5217391304347826, | |
| "eval_loss": 1.305979609489441, | |
| "eval_runtime": 0.6243, | |
| "eval_samples_per_second": 73.687, | |
| "eval_steps_per_second": 3.204, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 43.08, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.7971, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.5217391304347826, | |
| "eval_loss": 1.2678192853927612, | |
| "eval_runtime": 0.623, | |
| "eval_samples_per_second": 73.834, | |
| "eval_steps_per_second": 3.21, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 44.62, | |
| "learning_rate": 2.1990740740740743e-05, | |
| "loss": 0.7806, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 44.92, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.333229422569275, | |
| "eval_runtime": 0.6201, | |
| "eval_samples_per_second": 74.182, | |
| "eval_steps_per_second": 3.225, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.5652173913043478, | |
| "eval_loss": 1.2550207376480103, | |
| "eval_runtime": 0.6483, | |
| "eval_samples_per_second": 70.953, | |
| "eval_steps_per_second": 3.085, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.7899, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 46.92, | |
| "eval_accuracy": 0.5869565217391305, | |
| "eval_loss": 1.2517149448394775, | |
| "eval_runtime": 0.6424, | |
| "eval_samples_per_second": 71.608, | |
| "eval_steps_per_second": 3.113, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 47.69, | |
| "learning_rate": 1.967592592592593e-05, | |
| "loss": 0.7602, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.5869565217391305, | |
| "eval_loss": 1.262738823890686, | |
| "eval_runtime": 0.6343, | |
| "eval_samples_per_second": 72.521, | |
| "eval_steps_per_second": 3.153, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 48.92, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 1.2619768381118774, | |
| "eval_runtime": 0.6074, | |
| "eval_samples_per_second": 75.729, | |
| "eval_steps_per_second": 3.293, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 49.23, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.7748, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.5652173913043478, | |
| "eval_loss": 1.2286384105682373, | |
| "eval_runtime": 0.6688, | |
| "eval_samples_per_second": 68.782, | |
| "eval_steps_per_second": 2.991, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 50.77, | |
| "learning_rate": 1.736111111111111e-05, | |
| "loss": 0.7613, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 50.92, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 1.1996554136276245, | |
| "eval_runtime": 0.6038, | |
| "eval_samples_per_second": 76.18, | |
| "eval_steps_per_second": 3.312, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.5869565217391305, | |
| "eval_loss": 1.2353354692459106, | |
| "eval_runtime": 0.6194, | |
| "eval_samples_per_second": 74.263, | |
| "eval_steps_per_second": 3.229, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 52.31, | |
| "learning_rate": 1.6203703703703704e-05, | |
| "loss": 0.7514, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 52.92, | |
| "eval_accuracy": 0.5869565217391305, | |
| "eval_loss": 1.2466143369674683, | |
| "eval_runtime": 0.621, | |
| "eval_samples_per_second": 74.069, | |
| "eval_steps_per_second": 3.22, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 53.85, | |
| "learning_rate": 1.5046296296296297e-05, | |
| "loss": 0.7581, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.5869565217391305, | |
| "eval_loss": 1.2161446809768677, | |
| "eval_runtime": 0.6054, | |
| "eval_samples_per_second": 75.982, | |
| "eval_steps_per_second": 3.304, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 54.92, | |
| "eval_accuracy": 0.5434782608695652, | |
| "eval_loss": 1.2395505905151367, | |
| "eval_runtime": 0.6151, | |
| "eval_samples_per_second": 74.788, | |
| "eval_steps_per_second": 3.252, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 55.38, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.7401, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 1.1859078407287598, | |
| "eval_runtime": 0.6189, | |
| "eval_samples_per_second": 74.326, | |
| "eval_steps_per_second": 3.232, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "learning_rate": 1.2731481481481482e-05, | |
| "loss": 0.7421, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 1.175710916519165, | |
| "eval_runtime": 0.5963, | |
| "eval_samples_per_second": 77.144, | |
| "eval_steps_per_second": 3.354, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.5869565217391305, | |
| "eval_loss": 1.1754209995269775, | |
| "eval_runtime": 0.6029, | |
| "eval_samples_per_second": 76.301, | |
| "eval_steps_per_second": 3.317, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 58.46, | |
| "learning_rate": 1.1574074074074075e-05, | |
| "loss": 0.7261, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 58.92, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 1.163039207458496, | |
| "eval_runtime": 0.6158, | |
| "eval_samples_per_second": 74.694, | |
| "eval_steps_per_second": 3.248, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 0.709, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.5869565217391305, | |
| "eval_loss": 1.2156723737716675, | |
| "eval_runtime": 0.6211, | |
| "eval_samples_per_second": 74.063, | |
| "eval_steps_per_second": 3.22, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.92, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 1.2124063968658447, | |
| "eval_runtime": 0.6248, | |
| "eval_samples_per_second": 73.62, | |
| "eval_steps_per_second": 3.201, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 61.54, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.7075, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 1.2095441818237305, | |
| "eval_runtime": 0.6782, | |
| "eval_samples_per_second": 67.83, | |
| "eval_steps_per_second": 2.949, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 62.92, | |
| "eval_accuracy": 0.5652173913043478, | |
| "eval_loss": 1.2543033361434937, | |
| "eval_runtime": 0.6232, | |
| "eval_samples_per_second": 73.813, | |
| "eval_steps_per_second": 3.209, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 63.08, | |
| "learning_rate": 8.101851851851852e-06, | |
| "loss": 0.7141, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 1.2210296392440796, | |
| "eval_runtime": 0.6158, | |
| "eval_samples_per_second": 74.702, | |
| "eval_steps_per_second": 3.248, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 64.62, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.6907, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 64.92, | |
| "eval_accuracy": 0.5434782608695652, | |
| "eval_loss": 1.318984031677246, | |
| "eval_runtime": 0.6081, | |
| "eval_samples_per_second": 75.645, | |
| "eval_steps_per_second": 3.289, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 1.2197457551956177, | |
| "eval_runtime": 0.6159, | |
| "eval_samples_per_second": 74.683, | |
| "eval_steps_per_second": 3.247, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 66.15, | |
| "learning_rate": 5.787037037037038e-06, | |
| "loss": 0.7237, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 66.92, | |
| "eval_accuracy": 0.5652173913043478, | |
| "eval_loss": 1.2365007400512695, | |
| "eval_runtime": 0.6167, | |
| "eval_samples_per_second": 74.585, | |
| "eval_steps_per_second": 3.243, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 67.69, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.6918, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 1.157048225402832, | |
| "eval_runtime": 0.6163, | |
| "eval_samples_per_second": 74.638, | |
| "eval_steps_per_second": 3.245, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 68.92, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 1.1790133714675903, | |
| "eval_runtime": 0.6063, | |
| "eval_samples_per_second": 75.866, | |
| "eval_steps_per_second": 3.299, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 69.23, | |
| "learning_rate": 3.4722222222222224e-06, | |
| "loss": 0.7137, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 1.196757197380066, | |
| "eval_runtime": 0.6046, | |
| "eval_samples_per_second": 76.087, | |
| "eval_steps_per_second": 3.308, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 70.77, | |
| "learning_rate": 2.3148148148148148e-06, | |
| "loss": 0.6954, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 70.92, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 1.195902943611145, | |
| "eval_runtime": 0.6061, | |
| "eval_samples_per_second": 75.891, | |
| "eval_steps_per_second": 3.3, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 1.1782379150390625, | |
| "eval_runtime": 0.6167, | |
| "eval_samples_per_second": 74.59, | |
| "eval_steps_per_second": 3.243, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 72.31, | |
| "learning_rate": 1.1574074074074074e-06, | |
| "loss": 0.6961, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 72.92, | |
| "eval_accuracy": 0.5652173913043478, | |
| "eval_loss": 1.1934988498687744, | |
| "eval_runtime": 0.63, | |
| "eval_samples_per_second": 73.022, | |
| "eval_steps_per_second": 3.175, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "learning_rate": 0.0, | |
| "loss": 0.6889, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 1.1834712028503418, | |
| "eval_runtime": 0.6088, | |
| "eval_samples_per_second": 75.554, | |
| "eval_steps_per_second": 3.285, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "step": 480, | |
| "total_flos": 1.6581977329862246e+17, | |
| "train_loss": 0.9102102994918824, | |
| "train_runtime": 281.4413, | |
| "train_samples_per_second": 232.802, | |
| "train_steps_per_second": 1.706 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 480, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 80, | |
| "save_steps": 500, | |
| "total_flos": 1.6581977329862246e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |