| { | |
| "best_metric": 0.8478260869565217, | |
| "best_model_checkpoint": "swiftformer-xs-ve-U13-b-80e\\checkpoint-169", | |
| "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": 0.2391304347826087, | |
| "eval_loss": 1.3858561515808105, | |
| "eval_runtime": 0.6465, | |
| "eval_samples_per_second": 71.154, | |
| "eval_steps_per_second": 3.094, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 4.1666666666666665e-05, | |
| "loss": 1.3857, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.383376121520996, | |
| "eval_runtime": 0.6231, | |
| "eval_samples_per_second": 73.828, | |
| "eval_steps_per_second": 3.21, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_accuracy": 0.1956521739130435, | |
| "eval_loss": 1.378893256187439, | |
| "eval_runtime": 0.5859, | |
| "eval_samples_per_second": 78.518, | |
| "eval_steps_per_second": 3.414, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 8.333333333333333e-05, | |
| "loss": 1.3767, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.17391304347826086, | |
| "eval_loss": 1.366553544998169, | |
| "eval_runtime": 0.5917, | |
| "eval_samples_per_second": 77.74, | |
| "eval_steps_per_second": 3.38, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 0.000125, | |
| "loss": 1.3227, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_accuracy": 0.15217391304347827, | |
| "eval_loss": 1.356503963470459, | |
| "eval_runtime": 0.6244, | |
| "eval_samples_per_second": 73.672, | |
| "eval_steps_per_second": 3.203, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 1.3886877298355103, | |
| "eval_runtime": 0.5987, | |
| "eval_samples_per_second": 76.83, | |
| "eval_steps_per_second": 3.34, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 0.00016666666666666666, | |
| "loss": 1.1987, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "eval_accuracy": 0.21739130434782608, | |
| "eval_loss": 1.3718664646148682, | |
| "eval_runtime": 0.6257, | |
| "eval_samples_per_second": 73.514, | |
| "eval_steps_per_second": 3.196, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 0.00020833333333333332, | |
| "loss": 1.1071, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.30434782608695654, | |
| "eval_loss": 1.3271123170852661, | |
| "eval_runtime": 0.6134, | |
| "eval_samples_per_second": 74.99, | |
| "eval_steps_per_second": 3.26, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "eval_accuracy": 0.2608695652173913, | |
| "eval_loss": 1.356224536895752, | |
| "eval_runtime": 0.6427, | |
| "eval_samples_per_second": 71.579, | |
| "eval_steps_per_second": 3.112, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 0.00025, | |
| "loss": 0.9926, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.41304347826086957, | |
| "eval_loss": 1.2305893898010254, | |
| "eval_runtime": 0.6037, | |
| "eval_samples_per_second": 76.203, | |
| "eval_steps_per_second": 3.313, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 0.00029166666666666664, | |
| "loss": 0.8721, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.1952728033065796, | |
| "eval_runtime": 0.6138, | |
| "eval_samples_per_second": 74.943, | |
| "eval_steps_per_second": 3.258, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5652173913043478, | |
| "eval_loss": 1.0754497051239014, | |
| "eval_runtime": 0.6016, | |
| "eval_samples_per_second": 76.465, | |
| "eval_steps_per_second": 3.325, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 0.0002941176470588235, | |
| "loss": 0.7746, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9931479096412659, | |
| "eval_runtime": 0.596, | |
| "eval_samples_per_second": 77.175, | |
| "eval_steps_per_second": 3.355, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 13.85, | |
| "learning_rate": 0.00028676470588235296, | |
| "loss": 0.6859, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9978837370872498, | |
| "eval_runtime": 0.6322, | |
| "eval_samples_per_second": 72.759, | |
| "eval_steps_per_second": 3.163, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8964032530784607, | |
| "eval_runtime": 0.6041, | |
| "eval_samples_per_second": 76.144, | |
| "eval_steps_per_second": 3.311, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 0.00027941176470588236, | |
| "loss": 0.5777, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 0.918592631816864, | |
| "eval_runtime": 0.6311, | |
| "eval_samples_per_second": 72.89, | |
| "eval_steps_per_second": 3.169, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "learning_rate": 0.00027205882352941175, | |
| "loss": 0.5136, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7949799299240112, | |
| "eval_runtime": 0.6157, | |
| "eval_samples_per_second": 74.714, | |
| "eval_steps_per_second": 3.248, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7793933153152466, | |
| "eval_runtime": 0.6552, | |
| "eval_samples_per_second": 70.208, | |
| "eval_steps_per_second": 3.053, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 0.00026470588235294115, | |
| "loss": 0.5019, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8644534945487976, | |
| "eval_runtime": 0.6093, | |
| "eval_samples_per_second": 75.502, | |
| "eval_steps_per_second": 3.283, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.00025735294117647055, | |
| "loss": 0.3879, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8773152828216553, | |
| "eval_runtime": 0.6121, | |
| "eval_samples_per_second": 75.146, | |
| "eval_steps_per_second": 3.267, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7303956747055054, | |
| "eval_runtime": 0.6736, | |
| "eval_samples_per_second": 68.293, | |
| "eval_steps_per_second": 2.969, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 21.54, | |
| "learning_rate": 0.00025, | |
| "loss": 0.3532, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.6918480396270752, | |
| "eval_runtime": 0.6237, | |
| "eval_samples_per_second": 73.758, | |
| "eval_steps_per_second": 3.207, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 22.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7881707549095154, | |
| "eval_runtime": 0.63, | |
| "eval_samples_per_second": 73.014, | |
| "eval_steps_per_second": 3.175, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 0.0002426470588235294, | |
| "loss": 0.3288, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7132053375244141, | |
| "eval_runtime": 0.607, | |
| "eval_samples_per_second": 75.781, | |
| "eval_steps_per_second": 3.295, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 0.0002352941176470588, | |
| "loss": 0.2573, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 24.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6645399332046509, | |
| "eval_runtime": 0.5984, | |
| "eval_samples_per_second": 76.877, | |
| "eval_steps_per_second": 3.342, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.6617594361305237, | |
| "eval_runtime": 0.6083, | |
| "eval_samples_per_second": 75.626, | |
| "eval_steps_per_second": 3.288, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 26.15, | |
| "learning_rate": 0.0002279411764705882, | |
| "loss": 0.239, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6779818534851074, | |
| "eval_runtime": 0.6084, | |
| "eval_samples_per_second": 75.608, | |
| "eval_steps_per_second": 3.287, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "learning_rate": 0.00022058823529411765, | |
| "loss": 0.2018, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8137790560722351, | |
| "eval_runtime": 0.6252, | |
| "eval_samples_per_second": 73.571, | |
| "eval_steps_per_second": 3.199, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8797154426574707, | |
| "eval_runtime": 0.6147, | |
| "eval_samples_per_second": 74.836, | |
| "eval_steps_per_second": 3.254, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 29.23, | |
| "learning_rate": 0.00021323529411764705, | |
| "loss": 0.1961, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8602275848388672, | |
| "eval_runtime": 0.606, | |
| "eval_samples_per_second": 75.907, | |
| "eval_steps_per_second": 3.3, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 0.00020588235294117645, | |
| "loss": 0.214, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 30.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.8187522888183594, | |
| "eval_runtime": 0.6148, | |
| "eval_samples_per_second": 74.818, | |
| "eval_steps_per_second": 3.253, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.6955972909927368, | |
| "eval_runtime": 0.6018, | |
| "eval_samples_per_second": 76.431, | |
| "eval_steps_per_second": 3.323, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 32.31, | |
| "learning_rate": 0.00019852941176470585, | |
| "loss": 0.1596, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 32.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7980555891990662, | |
| "eval_runtime": 0.5918, | |
| "eval_samples_per_second": 77.731, | |
| "eval_steps_per_second": 3.38, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 33.85, | |
| "learning_rate": 0.00019117647058823528, | |
| "loss": 0.172, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.6845263838768005, | |
| "eval_runtime": 0.6133, | |
| "eval_samples_per_second": 75.008, | |
| "eval_steps_per_second": 3.261, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 34.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9340136051177979, | |
| "eval_runtime": 0.5942, | |
| "eval_samples_per_second": 77.416, | |
| "eval_steps_per_second": 3.366, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 0.0001838235294117647, | |
| "loss": 0.1852, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 0.9547532200813293, | |
| "eval_runtime": 0.7213, | |
| "eval_samples_per_second": 63.775, | |
| "eval_steps_per_second": 2.773, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "learning_rate": 0.0001764705882352941, | |
| "loss": 0.1492, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.774700403213501, | |
| "eval_runtime": 0.6442, | |
| "eval_samples_per_second": 71.401, | |
| "eval_steps_per_second": 3.104, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 0.9906997680664062, | |
| "eval_runtime": 0.5977, | |
| "eval_samples_per_second": 76.967, | |
| "eval_steps_per_second": 3.346, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.0001691176470588235, | |
| "loss": 0.1735, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 38.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8040443062782288, | |
| "eval_runtime": 0.6235, | |
| "eval_samples_per_second": 73.773, | |
| "eval_steps_per_second": 3.208, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 0.00016176470588235293, | |
| "loss": 0.1405, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.6945919990539551, | |
| "eval_runtime": 0.6077, | |
| "eval_samples_per_second": 75.694, | |
| "eval_steps_per_second": 3.291, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7019456624984741, | |
| "eval_runtime": 0.6269, | |
| "eval_samples_per_second": 73.381, | |
| "eval_steps_per_second": 3.19, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 41.54, | |
| "learning_rate": 0.00015441176470588233, | |
| "loss": 0.1269, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.824578583240509, | |
| "eval_runtime": 0.6131, | |
| "eval_samples_per_second": 75.023, | |
| "eval_steps_per_second": 3.262, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 42.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9238297939300537, | |
| "eval_runtime": 0.6079, | |
| "eval_samples_per_second": 75.675, | |
| "eval_steps_per_second": 3.29, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 43.08, | |
| "learning_rate": 0.00014705882352941175, | |
| "loss": 0.1237, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.9354200959205627, | |
| "eval_runtime": 0.6235, | |
| "eval_samples_per_second": 73.772, | |
| "eval_steps_per_second": 3.207, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 44.62, | |
| "learning_rate": 0.00013970588235294118, | |
| "loss": 0.1201, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 44.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7543055415153503, | |
| "eval_runtime": 0.6059, | |
| "eval_samples_per_second": 75.924, | |
| "eval_steps_per_second": 3.301, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7151233553886414, | |
| "eval_runtime": 0.6316, | |
| "eval_samples_per_second": 72.834, | |
| "eval_steps_per_second": 3.167, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "learning_rate": 0.00013235294117647058, | |
| "loss": 0.1134, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 46.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7283941507339478, | |
| "eval_runtime": 0.6109, | |
| "eval_samples_per_second": 75.305, | |
| "eval_steps_per_second": 3.274, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 47.69, | |
| "learning_rate": 0.000125, | |
| "loss": 0.1141, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7790563702583313, | |
| "eval_runtime": 0.6549, | |
| "eval_samples_per_second": 70.245, | |
| "eval_steps_per_second": 3.054, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 48.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7823971509933472, | |
| "eval_runtime": 0.5941, | |
| "eval_samples_per_second": 77.431, | |
| "eval_steps_per_second": 3.367, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 49.23, | |
| "learning_rate": 0.0001176470588235294, | |
| "loss": 0.1253, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7318633794784546, | |
| "eval_runtime": 0.6139, | |
| "eval_samples_per_second": 74.933, | |
| "eval_steps_per_second": 3.258, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 50.77, | |
| "learning_rate": 0.00011029411764705883, | |
| "loss": 0.0968, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 50.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.715053379535675, | |
| "eval_runtime": 0.6106, | |
| "eval_samples_per_second": 75.337, | |
| "eval_steps_per_second": 3.276, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7661868333816528, | |
| "eval_runtime": 0.672, | |
| "eval_samples_per_second": 68.453, | |
| "eval_steps_per_second": 2.976, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 52.31, | |
| "learning_rate": 0.00010294117647058823, | |
| "loss": 0.0996, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 52.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.8085704445838928, | |
| "eval_runtime": 0.6284, | |
| "eval_samples_per_second": 73.205, | |
| "eval_steps_per_second": 3.183, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 53.85, | |
| "learning_rate": 9.558823529411764e-05, | |
| "loss": 0.0844, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.892122209072113, | |
| "eval_runtime": 0.6018, | |
| "eval_samples_per_second": 76.432, | |
| "eval_steps_per_second": 3.323, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 54.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8782345056533813, | |
| "eval_runtime": 0.5936, | |
| "eval_samples_per_second": 77.489, | |
| "eval_steps_per_second": 3.369, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 55.38, | |
| "learning_rate": 8.823529411764705e-05, | |
| "loss": 0.1141, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7863830327987671, | |
| "eval_runtime": 0.6193, | |
| "eval_samples_per_second": 74.279, | |
| "eval_steps_per_second": 3.23, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "learning_rate": 8.088235294117646e-05, | |
| "loss": 0.1263, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7125386595726013, | |
| "eval_runtime": 0.6664, | |
| "eval_samples_per_second": 69.025, | |
| "eval_steps_per_second": 3.001, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.6758188605308533, | |
| "eval_runtime": 0.6415, | |
| "eval_samples_per_second": 71.704, | |
| "eval_steps_per_second": 3.118, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 58.46, | |
| "learning_rate": 7.352941176470588e-05, | |
| "loss": 0.0966, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 58.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7242967486381531, | |
| "eval_runtime": 0.6256, | |
| "eval_samples_per_second": 73.526, | |
| "eval_steps_per_second": 3.197, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 6.617647058823529e-05, | |
| "loss": 0.0771, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7089547514915466, | |
| "eval_runtime": 0.6119, | |
| "eval_samples_per_second": 75.172, | |
| "eval_steps_per_second": 3.268, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7157294154167175, | |
| "eval_runtime": 0.6426, | |
| "eval_samples_per_second": 71.584, | |
| "eval_steps_per_second": 3.112, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 61.54, | |
| "learning_rate": 5.88235294117647e-05, | |
| "loss": 0.0497, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7549222707748413, | |
| "eval_runtime": 0.6404, | |
| "eval_samples_per_second": 71.829, | |
| "eval_steps_per_second": 3.123, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 62.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7805795073509216, | |
| "eval_runtime": 0.5971, | |
| "eval_samples_per_second": 77.034, | |
| "eval_steps_per_second": 3.349, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 63.08, | |
| "learning_rate": 5.147058823529411e-05, | |
| "loss": 0.0848, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7902293801307678, | |
| "eval_runtime": 0.6284, | |
| "eval_samples_per_second": 73.207, | |
| "eval_steps_per_second": 3.183, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 64.62, | |
| "learning_rate": 4.4117647058823526e-05, | |
| "loss": 0.0477, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 64.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7683706879615784, | |
| "eval_runtime": 0.6332, | |
| "eval_samples_per_second": 72.646, | |
| "eval_steps_per_second": 3.159, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8037605881690979, | |
| "eval_runtime": 0.6154, | |
| "eval_samples_per_second": 74.747, | |
| "eval_steps_per_second": 3.25, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 66.15, | |
| "learning_rate": 3.676470588235294e-05, | |
| "loss": 0.0823, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 66.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.7502751350402832, | |
| "eval_runtime": 0.619, | |
| "eval_samples_per_second": 74.309, | |
| "eval_steps_per_second": 3.231, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 67.69, | |
| "learning_rate": 2.941176470588235e-05, | |
| "loss": 0.0726, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7634245753288269, | |
| "eval_runtime": 0.5953, | |
| "eval_samples_per_second": 77.278, | |
| "eval_steps_per_second": 3.36, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 68.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.7860420346260071, | |
| "eval_runtime": 0.6305, | |
| "eval_samples_per_second": 72.962, | |
| "eval_steps_per_second": 3.172, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 69.23, | |
| "learning_rate": 2.2058823529411763e-05, | |
| "loss": 0.0799, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7629542350769043, | |
| "eval_runtime": 0.6052, | |
| "eval_samples_per_second": 76.009, | |
| "eval_steps_per_second": 3.305, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 70.77, | |
| "learning_rate": 1.4705882352941175e-05, | |
| "loss": 0.067, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 70.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.809410035610199, | |
| "eval_runtime": 0.6232, | |
| "eval_samples_per_second": 73.811, | |
| "eval_steps_per_second": 3.209, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.751130998134613, | |
| "eval_runtime": 0.6317, | |
| "eval_samples_per_second": 72.822, | |
| "eval_steps_per_second": 3.166, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 72.31, | |
| "learning_rate": 7.352941176470588e-06, | |
| "loss": 0.0893, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 72.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7738297581672668, | |
| "eval_runtime": 0.6364, | |
| "eval_samples_per_second": 72.286, | |
| "eval_steps_per_second": 3.143, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "learning_rate": 0.0, | |
| "loss": 0.0738, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.797092080116272, | |
| "eval_runtime": 0.6138, | |
| "eval_samples_per_second": 74.941, | |
| "eval_steps_per_second": 3.258, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "step": 480, | |
| "total_flos": 1.6581977329862246e+17, | |
| "train_loss": 0.3444344773267706, | |
| "train_runtime": 276.4072, | |
| "train_samples_per_second": 237.042, | |
| "train_steps_per_second": 1.737 | |
| } | |
| ], | |
| "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 | |
| } | |