| { | |
| "best_metric": 0.9846153846153847, | |
| "best_model_checkpoint": "delivery_truck_classification/checkpoint-104", | |
| "epoch": 59.8421052631579, | |
| "global_step": 240, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.84, | |
| "eval_accuracy": 0.3230769230769231, | |
| "eval_loss": 1.819914698600769, | |
| "eval_runtime": 4.4893, | |
| "eval_samples_per_second": 14.479, | |
| "eval_steps_per_second": 0.668, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_accuracy": 0.4153846153846154, | |
| "eval_loss": 1.7274595499038696, | |
| "eval_runtime": 5.1038, | |
| "eval_samples_per_second": 12.736, | |
| "eval_steps_per_second": 0.588, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "eval_accuracy": 0.46153846153846156, | |
| "eval_loss": 1.628129005432129, | |
| "eval_runtime": 4.4017, | |
| "eval_samples_per_second": 14.767, | |
| "eval_steps_per_second": 0.682, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "eval_accuracy": 0.46153846153846156, | |
| "eval_loss": 1.5271515846252441, | |
| "eval_runtime": 4.7528, | |
| "eval_samples_per_second": 13.676, | |
| "eval_steps_per_second": 0.631, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.9537, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "eval_accuracy": 0.5076923076923077, | |
| "eval_loss": 1.3667770624160767, | |
| "eval_runtime": 4.3866, | |
| "eval_samples_per_second": 14.818, | |
| "eval_steps_per_second": 0.684, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 1.0963521003723145, | |
| "eval_runtime": 4.7064, | |
| "eval_samples_per_second": 13.811, | |
| "eval_steps_per_second": 0.637, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "eval_accuracy": 0.7846153846153846, | |
| "eval_loss": 0.7691364884376526, | |
| "eval_runtime": 4.2153, | |
| "eval_samples_per_second": 15.42, | |
| "eval_steps_per_second": 0.712, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "eval_accuracy": 0.8307692307692308, | |
| "eval_loss": 0.6369762420654297, | |
| "eval_runtime": 4.7258, | |
| "eval_samples_per_second": 13.754, | |
| "eval_steps_per_second": 0.635, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "eval_accuracy": 0.9076923076923077, | |
| "eval_loss": 0.4328678548336029, | |
| "eval_runtime": 4.7157, | |
| "eval_samples_per_second": 13.784, | |
| "eval_steps_per_second": 0.636, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 1.0682, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "eval_accuracy": 0.9076923076923077, | |
| "eval_loss": 0.3517535626888275, | |
| "eval_runtime": 4.7127, | |
| "eval_samples_per_second": 13.792, | |
| "eval_steps_per_second": 0.637, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 10.84, | |
| "eval_accuracy": 0.8923076923076924, | |
| "eval_loss": 0.3229323625564575, | |
| "eval_runtime": 4.2434, | |
| "eval_samples_per_second": 15.318, | |
| "eval_steps_per_second": 0.707, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "eval_accuracy": 0.9384615384615385, | |
| "eval_loss": 0.2324085831642151, | |
| "eval_runtime": 4.734, | |
| "eval_samples_per_second": 13.731, | |
| "eval_steps_per_second": 0.634, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 12.84, | |
| "eval_accuracy": 0.9384615384615385, | |
| "eval_loss": 0.23686641454696655, | |
| "eval_runtime": 4.3354, | |
| "eval_samples_per_second": 14.993, | |
| "eval_steps_per_second": 0.692, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 13.84, | |
| "eval_accuracy": 0.9384615384615385, | |
| "eval_loss": 0.21190524101257324, | |
| "eval_runtime": 4.793, | |
| "eval_samples_per_second": 13.561, | |
| "eval_steps_per_second": 0.626, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.6335, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "eval_accuracy": 0.9384615384615385, | |
| "eval_loss": 0.18046662211418152, | |
| "eval_runtime": 4.2602, | |
| "eval_samples_per_second": 15.257, | |
| "eval_steps_per_second": 0.704, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 15.84, | |
| "eval_accuracy": 0.9076923076923077, | |
| "eval_loss": 0.21350829303264618, | |
| "eval_runtime": 4.7427, | |
| "eval_samples_per_second": 13.705, | |
| "eval_steps_per_second": 0.633, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 16.84, | |
| "eval_accuracy": 0.9230769230769231, | |
| "eval_loss": 0.1889328807592392, | |
| "eval_runtime": 4.2616, | |
| "eval_samples_per_second": 15.253, | |
| "eval_steps_per_second": 0.704, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 17.84, | |
| "eval_accuracy": 0.9538461538461539, | |
| "eval_loss": 0.16009008884429932, | |
| "eval_runtime": 4.7629, | |
| "eval_samples_per_second": 13.647, | |
| "eval_steps_per_second": 0.63, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 18.84, | |
| "eval_accuracy": 0.9692307692307692, | |
| "eval_loss": 0.14124387502670288, | |
| "eval_runtime": 4.3251, | |
| "eval_samples_per_second": 15.029, | |
| "eval_steps_per_second": 0.694, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.5133, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "eval_accuracy": 0.9538461538461539, | |
| "eval_loss": 0.14968368411064148, | |
| "eval_runtime": 4.7085, | |
| "eval_samples_per_second": 13.805, | |
| "eval_steps_per_second": 0.637, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 20.84, | |
| "eval_accuracy": 0.9538461538461539, | |
| "eval_loss": 0.15449711680412292, | |
| "eval_runtime": 4.2803, | |
| "eval_samples_per_second": 15.186, | |
| "eval_steps_per_second": 0.701, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 21.84, | |
| "eval_accuracy": 0.9538461538461539, | |
| "eval_loss": 0.12975920736789703, | |
| "eval_runtime": 6.2107, | |
| "eval_samples_per_second": 10.466, | |
| "eval_steps_per_second": 0.483, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 22.84, | |
| "eval_accuracy": 0.9538461538461539, | |
| "eval_loss": 0.14153267443180084, | |
| "eval_runtime": 4.2538, | |
| "eval_samples_per_second": 15.28, | |
| "eval_steps_per_second": 0.705, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 23.84, | |
| "eval_accuracy": 0.9230769230769231, | |
| "eval_loss": 0.16845214366912842, | |
| "eval_runtime": 4.6805, | |
| "eval_samples_per_second": 13.888, | |
| "eval_steps_per_second": 0.641, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 24.84, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.4383, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 24.84, | |
| "eval_accuracy": 0.9384615384615385, | |
| "eval_loss": 0.13808518648147583, | |
| "eval_runtime": 4.2829, | |
| "eval_samples_per_second": 15.177, | |
| "eval_steps_per_second": 0.7, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 25.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.1295621246099472, | |
| "eval_runtime": 4.717, | |
| "eval_samples_per_second": 13.78, | |
| "eval_steps_per_second": 0.636, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 26.84, | |
| "eval_accuracy": 0.9538461538461539, | |
| "eval_loss": 0.1106828972697258, | |
| "eval_runtime": 4.4246, | |
| "eval_samples_per_second": 14.691, | |
| "eval_steps_per_second": 0.678, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "eval_accuracy": 0.9384615384615385, | |
| "eval_loss": 0.12369797378778458, | |
| "eval_runtime": 4.7653, | |
| "eval_samples_per_second": 13.64, | |
| "eval_steps_per_second": 0.63, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 28.84, | |
| "eval_accuracy": 0.9538461538461539, | |
| "eval_loss": 0.1366400122642517, | |
| "eval_runtime": 4.3203, | |
| "eval_samples_per_second": 15.045, | |
| "eval_steps_per_second": 0.694, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 29.84, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.4149, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 29.84, | |
| "eval_accuracy": 0.9692307692307692, | |
| "eval_loss": 0.13494354486465454, | |
| "eval_runtime": 4.6686, | |
| "eval_samples_per_second": 13.923, | |
| "eval_steps_per_second": 0.643, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 30.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.10458508133888245, | |
| "eval_runtime": 4.2843, | |
| "eval_samples_per_second": 15.172, | |
| "eval_steps_per_second": 0.7, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 31.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.0881725624203682, | |
| "eval_runtime": 4.7053, | |
| "eval_samples_per_second": 13.814, | |
| "eval_steps_per_second": 0.638, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 32.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.10219049453735352, | |
| "eval_runtime": 4.3211, | |
| "eval_samples_per_second": 15.042, | |
| "eval_steps_per_second": 0.694, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 33.84, | |
| "eval_accuracy": 0.9692307692307692, | |
| "eval_loss": 0.12066025286912918, | |
| "eval_runtime": 4.8023, | |
| "eval_samples_per_second": 13.535, | |
| "eval_steps_per_second": 0.625, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 34.84, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.3657, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 34.84, | |
| "eval_accuracy": 0.9538461538461539, | |
| "eval_loss": 0.11678420007228851, | |
| "eval_runtime": 4.4027, | |
| "eval_samples_per_second": 14.764, | |
| "eval_steps_per_second": 0.681, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 35.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.09219826757907867, | |
| "eval_runtime": 6.9593, | |
| "eval_samples_per_second": 9.34, | |
| "eval_steps_per_second": 0.431, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 36.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.09314019978046417, | |
| "eval_runtime": 4.3, | |
| "eval_samples_per_second": 15.116, | |
| "eval_steps_per_second": 0.698, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 37.84, | |
| "eval_accuracy": 0.9692307692307692, | |
| "eval_loss": 0.10055378824472427, | |
| "eval_runtime": 4.7227, | |
| "eval_samples_per_second": 13.763, | |
| "eval_steps_per_second": 0.635, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 38.84, | |
| "eval_accuracy": 0.9692307692307692, | |
| "eval_loss": 0.09866410493850708, | |
| "eval_runtime": 4.3725, | |
| "eval_samples_per_second": 14.866, | |
| "eval_steps_per_second": 0.686, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 39.84, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.3294, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 39.84, | |
| "eval_accuracy": 0.9692307692307692, | |
| "eval_loss": 0.11275947839021683, | |
| "eval_runtime": 4.6903, | |
| "eval_samples_per_second": 13.858, | |
| "eval_steps_per_second": 0.64, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 40.84, | |
| "eval_accuracy": 0.9538461538461539, | |
| "eval_loss": 0.11520560085773468, | |
| "eval_runtime": 4.3303, | |
| "eval_samples_per_second": 15.01, | |
| "eval_steps_per_second": 0.693, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 41.84, | |
| "eval_accuracy": 0.9538461538461539, | |
| "eval_loss": 0.09974207729101181, | |
| "eval_runtime": 4.7259, | |
| "eval_samples_per_second": 13.754, | |
| "eval_steps_per_second": 0.635, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 42.84, | |
| "eval_accuracy": 0.9692307692307692, | |
| "eval_loss": 0.09684933722019196, | |
| "eval_runtime": 4.3525, | |
| "eval_samples_per_second": 14.934, | |
| "eval_steps_per_second": 0.689, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 43.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.08187751471996307, | |
| "eval_runtime": 4.6538, | |
| "eval_samples_per_second": 13.967, | |
| "eval_steps_per_second": 0.645, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 44.84, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.3198, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 44.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.07292691618204117, | |
| "eval_runtime": 4.3483, | |
| "eval_samples_per_second": 14.948, | |
| "eval_steps_per_second": 0.69, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 45.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.07438476383686066, | |
| "eval_runtime": 4.8323, | |
| "eval_samples_per_second": 13.451, | |
| "eval_steps_per_second": 0.621, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 46.84, | |
| "eval_accuracy": 0.9692307692307692, | |
| "eval_loss": 0.09510225057601929, | |
| "eval_runtime": 4.3498, | |
| "eval_samples_per_second": 14.943, | |
| "eval_steps_per_second": 0.69, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 47.84, | |
| "eval_accuracy": 0.9692307692307692, | |
| "eval_loss": 0.09657642990350723, | |
| "eval_runtime": 4.7293, | |
| "eval_samples_per_second": 13.744, | |
| "eval_steps_per_second": 0.634, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 48.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.08329986035823822, | |
| "eval_runtime": 4.2989, | |
| "eval_samples_per_second": 15.12, | |
| "eval_steps_per_second": 0.698, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 49.84, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.2936, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 49.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.06941184401512146, | |
| "eval_runtime": 4.7066, | |
| "eval_samples_per_second": 13.811, | |
| "eval_steps_per_second": 0.637, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 50.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.06908843666315079, | |
| "eval_runtime": 4.3338, | |
| "eval_samples_per_second": 14.999, | |
| "eval_steps_per_second": 0.692, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 51.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.0735919326543808, | |
| "eval_runtime": 4.7155, | |
| "eval_samples_per_second": 13.784, | |
| "eval_steps_per_second": 0.636, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 52.84, | |
| "eval_accuracy": 0.9692307692307692, | |
| "eval_loss": 0.08048100024461746, | |
| "eval_runtime": 4.337, | |
| "eval_samples_per_second": 14.987, | |
| "eval_steps_per_second": 0.692, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 53.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.08007017523050308, | |
| "eval_runtime": 4.765, | |
| "eval_samples_per_second": 13.641, | |
| "eval_steps_per_second": 0.63, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 54.84, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.3127, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 54.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.0826273187994957, | |
| "eval_runtime": 4.2934, | |
| "eval_samples_per_second": 15.139, | |
| "eval_steps_per_second": 0.699, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 55.84, | |
| "eval_accuracy": 0.9692307692307692, | |
| "eval_loss": 0.08565446734428406, | |
| "eval_runtime": 4.7099, | |
| "eval_samples_per_second": 13.801, | |
| "eval_steps_per_second": 0.637, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 56.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.0864274650812149, | |
| "eval_runtime": 4.246, | |
| "eval_samples_per_second": 15.309, | |
| "eval_steps_per_second": 0.707, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 57.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.08776658028364182, | |
| "eval_runtime": 4.758, | |
| "eval_samples_per_second": 13.661, | |
| "eval_steps_per_second": 0.631, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 58.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.08772400766611099, | |
| "eval_runtime": 4.2874, | |
| "eval_samples_per_second": 15.161, | |
| "eval_steps_per_second": 0.7, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 59.84, | |
| "learning_rate": 0.0, | |
| "loss": 0.285, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 59.84, | |
| "eval_accuracy": 0.9846153846153847, | |
| "eval_loss": 0.08735792338848114, | |
| "eval_runtime": 4.7501, | |
| "eval_samples_per_second": 13.684, | |
| "eval_steps_per_second": 0.632, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 59.84, | |
| "step": 240, | |
| "total_flos": 8.648855308501955e+17, | |
| "train_loss": 0.577343902985255, | |
| "train_runtime": 4213.9216, | |
| "train_samples_per_second": 8.273, | |
| "train_steps_per_second": 0.057 | |
| } | |
| ], | |
| "max_steps": 240, | |
| "num_train_epochs": 60, | |
| "total_flos": 8.648855308501955e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |