| { | |
| "best_metric": 0.8043478260869565, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-ve-U11-b-60\\checkpoint-156", | |
| "epoch": 55.38461538461539, | |
| "eval_steps": 500, | |
| "global_step": 360, | |
| "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": 1.3858968019485474, | |
| "eval_runtime": 0.5992, | |
| "eval_samples_per_second": 76.77, | |
| "eval_steps_per_second": 3.338, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 1.3858, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.2608695652173913, | |
| "eval_loss": 1.3818036317825317, | |
| "eval_runtime": 0.6188, | |
| "eval_samples_per_second": 74.341, | |
| "eval_steps_per_second": 3.232, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_accuracy": 0.2608695652173913, | |
| "eval_loss": 1.3722529411315918, | |
| "eval_runtime": 0.5891, | |
| "eval_samples_per_second": 78.08, | |
| "eval_steps_per_second": 3.395, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.3747, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.21739130434782608, | |
| "eval_loss": 1.3355135917663574, | |
| "eval_runtime": 0.6036, | |
| "eval_samples_per_second": 76.214, | |
| "eval_steps_per_second": 3.314, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.3001, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_accuracy": 0.3695652173913043, | |
| "eval_loss": 1.2625232934951782, | |
| "eval_runtime": 0.6139, | |
| "eval_samples_per_second": 74.935, | |
| "eval_steps_per_second": 3.258, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.1305873394012451, | |
| "eval_runtime": 0.6404, | |
| "eval_samples_per_second": 71.832, | |
| "eval_steps_per_second": 3.123, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 1.141, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "eval_accuracy": 0.4782608695652174, | |
| "eval_loss": 1.0509722232818604, | |
| "eval_runtime": 0.5953, | |
| "eval_samples_per_second": 77.271, | |
| "eval_steps_per_second": 3.36, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 4.783950617283951e-05, | |
| "loss": 0.9784, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5434782608695652, | |
| "eval_loss": 0.9585281014442444, | |
| "eval_runtime": 0.619, | |
| "eval_samples_per_second": 74.311, | |
| "eval_steps_per_second": 3.231, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "eval_accuracy": 0.4782608695652174, | |
| "eval_loss": 0.9895150661468506, | |
| "eval_runtime": 0.6106, | |
| "eval_samples_per_second": 75.334, | |
| "eval_steps_per_second": 3.275, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.8533, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.951244592666626, | |
| "eval_runtime": 0.5862, | |
| "eval_samples_per_second": 78.472, | |
| "eval_steps_per_second": 3.412, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 4.4753086419753084e-05, | |
| "loss": 0.7564, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "eval_accuracy": 0.5217391304347826, | |
| "eval_loss": 0.9521799683570862, | |
| "eval_runtime": 0.6175, | |
| "eval_samples_per_second": 74.496, | |
| "eval_steps_per_second": 3.239, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 0.9143680930137634, | |
| "eval_runtime": 0.6232, | |
| "eval_samples_per_second": 73.814, | |
| "eval_steps_per_second": 3.209, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 0.6735, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 0.907021701335907, | |
| "eval_runtime": 0.6191, | |
| "eval_samples_per_second": 74.297, | |
| "eval_steps_per_second": 3.23, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 13.85, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.5919, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 0.7915353178977966, | |
| "eval_runtime": 0.6, | |
| "eval_samples_per_second": 76.662, | |
| "eval_steps_per_second": 3.333, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 0.7988886833190918, | |
| "eval_runtime": 0.6334, | |
| "eval_samples_per_second": 72.622, | |
| "eval_steps_per_second": 3.157, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 4.012345679012346e-05, | |
| "loss": 0.504, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 0.9510163068771362, | |
| "eval_runtime": 0.6024, | |
| "eval_samples_per_second": 76.367, | |
| "eval_steps_per_second": 3.32, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "learning_rate": 3.8580246913580246e-05, | |
| "loss": 0.4422, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.8195834159851074, | |
| "eval_runtime": 0.603, | |
| "eval_samples_per_second": 76.291, | |
| "eval_steps_per_second": 3.317, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.6628637909889221, | |
| "eval_runtime": 0.6198, | |
| "eval_samples_per_second": 74.213, | |
| "eval_steps_per_second": 3.227, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.4031, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 0.8767060041427612, | |
| "eval_runtime": 0.6311, | |
| "eval_samples_per_second": 72.889, | |
| "eval_steps_per_second": 3.169, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.5493827160493834e-05, | |
| "loss": 0.3752, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.8252948522567749, | |
| "eval_runtime": 0.5775, | |
| "eval_samples_per_second": 79.655, | |
| "eval_steps_per_second": 3.463, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7182953953742981, | |
| "eval_runtime": 0.653, | |
| "eval_samples_per_second": 70.442, | |
| "eval_steps_per_second": 3.063, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 21.54, | |
| "learning_rate": 3.395061728395062e-05, | |
| "loss": 0.3424, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.88515305519104, | |
| "eval_runtime": 0.6458, | |
| "eval_samples_per_second": 71.225, | |
| "eval_steps_per_second": 3.097, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 22.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7359628081321716, | |
| "eval_runtime": 0.6099, | |
| "eval_samples_per_second": 75.427, | |
| "eval_steps_per_second": 3.279, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.3293, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.7230114340782166, | |
| "eval_runtime": 0.5934, | |
| "eval_samples_per_second": 77.518, | |
| "eval_steps_per_second": 3.37, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.2822, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 24.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8270708918571472, | |
| "eval_runtime": 0.6168, | |
| "eval_samples_per_second": 74.575, | |
| "eval_steps_per_second": 3.242, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.7442592978477478, | |
| "eval_runtime": 0.5915, | |
| "eval_samples_per_second": 77.771, | |
| "eval_steps_per_second": 3.381, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 26.15, | |
| "learning_rate": 2.9320987654320992e-05, | |
| "loss": 0.2623, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9371039271354675, | |
| "eval_runtime": 0.5932, | |
| "eval_samples_per_second": 77.541, | |
| "eval_steps_per_second": 3.371, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.2807, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7391819357872009, | |
| "eval_runtime": 0.5861, | |
| "eval_samples_per_second": 78.483, | |
| "eval_steps_per_second": 3.412, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.8753820657730103, | |
| "eval_runtime": 0.5828, | |
| "eval_samples_per_second": 78.931, | |
| "eval_steps_per_second": 3.432, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 29.23, | |
| "learning_rate": 2.623456790123457e-05, | |
| "loss": 0.223, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.7145875096321106, | |
| "eval_runtime": 0.5811, | |
| "eval_samples_per_second": 79.16, | |
| "eval_steps_per_second": 3.442, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.2185, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 30.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7702176570892334, | |
| "eval_runtime": 0.5879, | |
| "eval_samples_per_second": 78.249, | |
| "eval_steps_per_second": 3.402, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7329592704772949, | |
| "eval_runtime": 0.6173, | |
| "eval_samples_per_second": 74.523, | |
| "eval_steps_per_second": 3.24, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 32.31, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.2157, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 32.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8817254900932312, | |
| "eval_runtime": 0.5926, | |
| "eval_samples_per_second": 77.63, | |
| "eval_steps_per_second": 3.375, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 33.85, | |
| "learning_rate": 2.1604938271604937e-05, | |
| "loss": 0.2011, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7459983229637146, | |
| "eval_runtime": 0.5797, | |
| "eval_samples_per_second": 79.357, | |
| "eval_steps_per_second": 3.45, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 34.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9663064479827881, | |
| "eval_runtime": 0.6007, | |
| "eval_samples_per_second": 76.581, | |
| "eval_steps_per_second": 3.33, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 2.006172839506173e-05, | |
| "loss": 0.2204, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8055830597877502, | |
| "eval_runtime": 0.6033, | |
| "eval_samples_per_second": 76.247, | |
| "eval_steps_per_second": 3.315, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.1856, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7798697352409363, | |
| "eval_runtime": 0.6168, | |
| "eval_samples_per_second": 74.584, | |
| "eval_steps_per_second": 3.243, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8410213589668274, | |
| "eval_runtime": 0.6255, | |
| "eval_samples_per_second": 73.539, | |
| "eval_steps_per_second": 3.197, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 1.697530864197531e-05, | |
| "loss": 0.1678, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 38.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7334251999855042, | |
| "eval_runtime": 0.6096, | |
| "eval_samples_per_second": 75.455, | |
| "eval_steps_per_second": 3.281, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 1.54320987654321e-05, | |
| "loss": 0.1682, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8507670760154724, | |
| "eval_runtime": 0.5939, | |
| "eval_samples_per_second": 77.45, | |
| "eval_steps_per_second": 3.367, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8106131553649902, | |
| "eval_runtime": 0.5922, | |
| "eval_samples_per_second": 77.674, | |
| "eval_steps_per_second": 3.377, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 41.54, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.1638, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8402844071388245, | |
| "eval_runtime": 0.6501, | |
| "eval_samples_per_second": 70.759, | |
| "eval_steps_per_second": 3.076, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 42.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.9157429337501526, | |
| "eval_runtime": 0.6015, | |
| "eval_samples_per_second": 76.475, | |
| "eval_steps_per_second": 3.325, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 43.08, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.1573, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9271051287651062, | |
| "eval_runtime": 0.617, | |
| "eval_samples_per_second": 74.552, | |
| "eval_steps_per_second": 3.241, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 44.62, | |
| "learning_rate": 1.0802469135802469e-05, | |
| "loss": 0.1476, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 44.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9167048335075378, | |
| "eval_runtime": 0.5836, | |
| "eval_samples_per_second": 78.822, | |
| "eval_steps_per_second": 3.427, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9309194684028625, | |
| "eval_runtime": 0.62, | |
| "eval_samples_per_second": 74.197, | |
| "eval_steps_per_second": 3.226, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.1466, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 46.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.8235711455345154, | |
| "eval_runtime": 0.6116, | |
| "eval_samples_per_second": 75.219, | |
| "eval_steps_per_second": 3.27, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 47.69, | |
| "learning_rate": 7.71604938271605e-06, | |
| "loss": 0.1457, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.8834730386734009, | |
| "eval_runtime": 0.6232, | |
| "eval_samples_per_second": 73.809, | |
| "eval_steps_per_second": 3.209, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 48.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9161576628684998, | |
| "eval_runtime": 0.6019, | |
| "eval_samples_per_second": 76.426, | |
| "eval_steps_per_second": 3.323, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 49.23, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.1625, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.8969017267227173, | |
| "eval_runtime": 0.6023, | |
| "eval_samples_per_second": 76.373, | |
| "eval_steps_per_second": 3.321, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 50.77, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.1163, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 50.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9183077812194824, | |
| "eval_runtime": 0.6149, | |
| "eval_samples_per_second": 74.806, | |
| "eval_steps_per_second": 3.252, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9172530770301819, | |
| "eval_runtime": 0.7065, | |
| "eval_samples_per_second": 65.107, | |
| "eval_steps_per_second": 2.831, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 52.31, | |
| "learning_rate": 3.0864197530864196e-06, | |
| "loss": 0.1375, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 52.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8886280655860901, | |
| "eval_runtime": 0.5667, | |
| "eval_samples_per_second": 81.175, | |
| "eval_steps_per_second": 3.529, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 53.85, | |
| "learning_rate": 1.5432098765432098e-06, | |
| "loss": 0.1379, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.877066969871521, | |
| "eval_runtime": 0.6245, | |
| "eval_samples_per_second": 73.66, | |
| "eval_steps_per_second": 3.203, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 54.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.885678231716156, | |
| "eval_runtime": 0.6368, | |
| "eval_samples_per_second": 72.233, | |
| "eval_steps_per_second": 3.141, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 55.38, | |
| "learning_rate": 0.0, | |
| "loss": 0.1321, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 55.38, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.8883605003356934, | |
| "eval_runtime": 0.618, | |
| "eval_samples_per_second": 74.43, | |
| "eval_steps_per_second": 3.236, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 55.38, | |
| "step": 360, | |
| "total_flos": 1.1276549556120576e+18, | |
| "train_loss": 0.4256666488117642, | |
| "train_runtime": 439.4382, | |
| "train_samples_per_second": 111.825, | |
| "train_steps_per_second": 0.819 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 360, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 60, | |
| "save_steps": 500, | |
| "total_flos": 1.1276549556120576e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |