| { | |
| "best_metric": 0.8695652173913043, | |
| "best_model_checkpoint": "swiftformer-xs-ve-U13-b-80\\checkpoint-175", | |
| "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": 0.10869565217391304, | |
| "eval_loss": 1.4460796117782593, | |
| "eval_runtime": 0.7125, | |
| "eval_samples_per_second": 64.563, | |
| "eval_steps_per_second": 2.807, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.3993, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 1.4435073137283325, | |
| "eval_runtime": 0.6148, | |
| "eval_samples_per_second": 74.823, | |
| "eval_steps_per_second": 3.253, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 1.4388779401779175, | |
| "eval_runtime": 0.6122, | |
| "eval_samples_per_second": 75.137, | |
| "eval_steps_per_second": 3.267, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 1.3849, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 1.4283998012542725, | |
| "eval_runtime": 0.6101, | |
| "eval_samples_per_second": 75.4, | |
| "eval_steps_per_second": 3.278, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 0.000125, | |
| "loss": 1.3287, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_accuracy": 0.13043478260869565, | |
| "eval_loss": 1.4222790002822876, | |
| "eval_runtime": 0.6169, | |
| "eval_samples_per_second": 74.563, | |
| "eval_steps_per_second": 3.242, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 1.4646577835083008, | |
| "eval_runtime": 0.6082, | |
| "eval_samples_per_second": 75.638, | |
| "eval_steps_per_second": 3.289, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 1.2128, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "eval_accuracy": 0.17391304347826086, | |
| "eval_loss": 1.4183566570281982, | |
| "eval_runtime": 0.64, | |
| "eval_samples_per_second": 71.878, | |
| "eval_steps_per_second": 3.125, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 0.0001990740740740741, | |
| "loss": 1.122, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.1956521739130435, | |
| "eval_loss": 1.3262405395507812, | |
| "eval_runtime": 0.6384, | |
| "eval_samples_per_second": 72.055, | |
| "eval_steps_per_second": 3.133, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "eval_accuracy": 0.1956521739130435, | |
| "eval_loss": 1.3297909498214722, | |
| "eval_runtime": 0.5935, | |
| "eval_samples_per_second": 77.507, | |
| "eval_steps_per_second": 3.37, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 0.00019444444444444446, | |
| "loss": 1.0062, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.3695652173913043, | |
| "eval_loss": 1.2035472393035889, | |
| "eval_runtime": 0.5924, | |
| "eval_samples_per_second": 77.654, | |
| "eval_steps_per_second": 3.376, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 0.00018981481481481483, | |
| "loss": 0.872, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "eval_accuracy": 0.32608695652173914, | |
| "eval_loss": 1.3667021989822388, | |
| "eval_runtime": 0.6186, | |
| "eval_samples_per_second": 74.367, | |
| "eval_steps_per_second": 3.233, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.43478260869565216, | |
| "eval_loss": 1.201258897781372, | |
| "eval_runtime": 0.6083, | |
| "eval_samples_per_second": 75.623, | |
| "eval_steps_per_second": 3.288, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 0.0001851851851851852, | |
| "loss": 0.814, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.9996185898780823, | |
| "eval_runtime": 0.6063, | |
| "eval_samples_per_second": 75.874, | |
| "eval_steps_per_second": 3.299, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 13.85, | |
| "learning_rate": 0.00018055555555555557, | |
| "loss": 0.7228, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.9706003069877625, | |
| "eval_runtime": 0.6069, | |
| "eval_samples_per_second": 75.799, | |
| "eval_steps_per_second": 3.296, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9295421242713928, | |
| "eval_runtime": 0.6331, | |
| "eval_samples_per_second": 72.657, | |
| "eval_steps_per_second": 3.159, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 0.00017592592592592595, | |
| "loss": 0.6473, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8987626433372498, | |
| "eval_runtime": 0.607, | |
| "eval_samples_per_second": 75.787, | |
| "eval_steps_per_second": 3.295, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "learning_rate": 0.00017129629629629632, | |
| "loss": 0.5696, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9612070322036743, | |
| "eval_runtime": 0.6266, | |
| "eval_samples_per_second": 73.408, | |
| "eval_steps_per_second": 3.192, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8712936043739319, | |
| "eval_runtime": 0.5923, | |
| "eval_samples_per_second": 77.662, | |
| "eval_steps_per_second": 3.377, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 0.5546, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8049858212471008, | |
| "eval_runtime": 0.6052, | |
| "eval_samples_per_second": 76.002, | |
| "eval_steps_per_second": 3.304, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.00016203703703703706, | |
| "loss": 0.4747, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7724586129188538, | |
| "eval_runtime": 0.5976, | |
| "eval_samples_per_second": 76.969, | |
| "eval_steps_per_second": 3.346, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.7933102250099182, | |
| "eval_runtime": 0.5936, | |
| "eval_samples_per_second": 77.487, | |
| "eval_steps_per_second": 3.369, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 21.54, | |
| "learning_rate": 0.00015740740740740743, | |
| "loss": 0.4393, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.7665086984634399, | |
| "eval_runtime": 0.6062, | |
| "eval_samples_per_second": 75.883, | |
| "eval_steps_per_second": 3.299, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 22.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7885972857475281, | |
| "eval_runtime": 0.644, | |
| "eval_samples_per_second": 71.425, | |
| "eval_steps_per_second": 3.105, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 0.00015277777777777777, | |
| "loss": 0.4077, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7824200391769409, | |
| "eval_runtime": 0.6187, | |
| "eval_samples_per_second": 74.344, | |
| "eval_steps_per_second": 3.232, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 0.00014814814814814815, | |
| "loss": 0.3326, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 24.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7020803689956665, | |
| "eval_runtime": 0.6226, | |
| "eval_samples_per_second": 73.885, | |
| "eval_steps_per_second": 3.212, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6346074342727661, | |
| "eval_runtime": 0.611, | |
| "eval_samples_per_second": 75.283, | |
| "eval_steps_per_second": 3.273, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 26.15, | |
| "learning_rate": 0.00014351851851851852, | |
| "loss": 0.315, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "eval_accuracy": 0.8695652173913043, | |
| "eval_loss": 0.6163212060928345, | |
| "eval_runtime": 0.6094, | |
| "eval_samples_per_second": 75.49, | |
| "eval_steps_per_second": 3.282, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "learning_rate": 0.0001388888888888889, | |
| "loss": 0.2729, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6938338875770569, | |
| "eval_runtime": 0.6252, | |
| "eval_samples_per_second": 73.577, | |
| "eval_steps_per_second": 3.199, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.7417004704475403, | |
| "eval_runtime": 0.6265, | |
| "eval_samples_per_second": 73.429, | |
| "eval_steps_per_second": 3.193, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 29.23, | |
| "learning_rate": 0.00013425925925925926, | |
| "loss": 0.2218, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6668894290924072, | |
| "eval_runtime": 0.6201, | |
| "eval_samples_per_second": 74.182, | |
| "eval_steps_per_second": 3.225, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 0.00012962962962962963, | |
| "loss": 0.2499, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 30.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7111229300498962, | |
| "eval_runtime": 0.6369, | |
| "eval_samples_per_second": 72.225, | |
| "eval_steps_per_second": 3.14, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6729680299758911, | |
| "eval_runtime": 0.6117, | |
| "eval_samples_per_second": 75.197, | |
| "eval_steps_per_second": 3.269, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 32.31, | |
| "learning_rate": 0.000125, | |
| "loss": 0.2218, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 32.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6511849164962769, | |
| "eval_runtime": 0.6114, | |
| "eval_samples_per_second": 75.242, | |
| "eval_steps_per_second": 3.271, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 33.85, | |
| "learning_rate": 0.00012037037037037037, | |
| "loss": 0.2037, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7164542078971863, | |
| "eval_runtime": 0.6112, | |
| "eval_samples_per_second": 75.258, | |
| "eval_steps_per_second": 3.272, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 34.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6299737691879272, | |
| "eval_runtime": 0.6021, | |
| "eval_samples_per_second": 76.406, | |
| "eval_steps_per_second": 3.322, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 0.00011574074074074075, | |
| "loss": 0.2367, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.7421004176139832, | |
| "eval_runtime": 0.6016, | |
| "eval_samples_per_second": 76.464, | |
| "eval_steps_per_second": 3.325, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 0.1835, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6643686294555664, | |
| "eval_runtime": 0.6164, | |
| "eval_samples_per_second": 74.628, | |
| "eval_steps_per_second": 3.245, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6250634789466858, | |
| "eval_runtime": 0.6064, | |
| "eval_samples_per_second": 75.856, | |
| "eval_steps_per_second": 3.298, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.00010648148148148149, | |
| "loss": 0.2073, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 38.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6430649161338806, | |
| "eval_runtime": 0.6133, | |
| "eval_samples_per_second": 75.001, | |
| "eval_steps_per_second": 3.261, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 0.00010185185185185186, | |
| "loss": 0.1643, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.634781539440155, | |
| "eval_runtime": 0.6208, | |
| "eval_samples_per_second": 74.097, | |
| "eval_steps_per_second": 3.222, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6192363500595093, | |
| "eval_runtime": 0.6183, | |
| "eval_samples_per_second": 74.394, | |
| "eval_steps_per_second": 3.235, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 41.54, | |
| "learning_rate": 9.722222222222223e-05, | |
| "loss": 0.1685, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6753482818603516, | |
| "eval_runtime": 0.5997, | |
| "eval_samples_per_second": 76.701, | |
| "eval_steps_per_second": 3.335, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 42.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.7440155148506165, | |
| "eval_runtime": 0.6117, | |
| "eval_samples_per_second": 75.199, | |
| "eval_steps_per_second": 3.27, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 43.08, | |
| "learning_rate": 9.25925925925926e-05, | |
| "loss": 0.1539, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.7504969239234924, | |
| "eval_runtime": 0.6044, | |
| "eval_samples_per_second": 76.107, | |
| "eval_steps_per_second": 3.309, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 44.62, | |
| "learning_rate": 8.796296296296297e-05, | |
| "loss": 0.1658, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 44.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6331078410148621, | |
| "eval_runtime": 0.6101, | |
| "eval_samples_per_second": 75.401, | |
| "eval_steps_per_second": 3.278, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6549533009529114, | |
| "eval_runtime": 0.8345, | |
| "eval_samples_per_second": 55.12, | |
| "eval_steps_per_second": 2.397, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 0.1596, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 46.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6824274063110352, | |
| "eval_runtime": 0.6289, | |
| "eval_samples_per_second": 73.143, | |
| "eval_steps_per_second": 3.18, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 47.69, | |
| "learning_rate": 7.870370370370372e-05, | |
| "loss": 0.1534, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6970986723899841, | |
| "eval_runtime": 0.6878, | |
| "eval_samples_per_second": 66.875, | |
| "eval_steps_per_second": 2.908, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 48.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6347023248672485, | |
| "eval_runtime": 0.6022, | |
| "eval_samples_per_second": 76.388, | |
| "eval_steps_per_second": 3.321, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 49.23, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 0.1677, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6392168998718262, | |
| "eval_runtime": 0.6333, | |
| "eval_samples_per_second": 72.632, | |
| "eval_steps_per_second": 3.158, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 50.77, | |
| "learning_rate": 6.944444444444444e-05, | |
| "loss": 0.1453, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 50.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6368798017501831, | |
| "eval_runtime": 0.6455, | |
| "eval_samples_per_second": 71.262, | |
| "eval_steps_per_second": 3.098, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.623034656047821, | |
| "eval_runtime": 0.7388, | |
| "eval_samples_per_second": 62.259, | |
| "eval_steps_per_second": 2.707, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 52.31, | |
| "learning_rate": 6.481481481481482e-05, | |
| "loss": 0.1385, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 52.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.6432219743728638, | |
| "eval_runtime": 0.6128, | |
| "eval_samples_per_second": 75.06, | |
| "eval_steps_per_second": 3.263, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 53.85, | |
| "learning_rate": 6.018518518518519e-05, | |
| "loss": 0.1221, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.6757408380508423, | |
| "eval_runtime": 0.5947, | |
| "eval_samples_per_second": 77.346, | |
| "eval_steps_per_second": 3.363, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 54.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7383140921592712, | |
| "eval_runtime": 0.6233, | |
| "eval_samples_per_second": 73.805, | |
| "eval_steps_per_second": 3.209, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 55.38, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 0.1433, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7100470066070557, | |
| "eval_runtime": 0.6051, | |
| "eval_samples_per_second": 76.02, | |
| "eval_steps_per_second": 3.305, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "learning_rate": 5.092592592592593e-05, | |
| "loss": 0.1567, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.6861900091171265, | |
| "eval_runtime": 0.6176, | |
| "eval_samples_per_second": 74.482, | |
| "eval_steps_per_second": 3.238, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.6653789281845093, | |
| "eval_runtime": 0.6048, | |
| "eval_samples_per_second": 76.061, | |
| "eval_steps_per_second": 3.307, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 58.46, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.1361, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 58.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.66651451587677, | |
| "eval_runtime": 0.6057, | |
| "eval_samples_per_second": 75.942, | |
| "eval_steps_per_second": 3.302, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.1157, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6439006924629211, | |
| "eval_runtime": 0.6871, | |
| "eval_samples_per_second": 66.95, | |
| "eval_steps_per_second": 2.911, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6306149959564209, | |
| "eval_runtime": 0.6235, | |
| "eval_samples_per_second": 73.782, | |
| "eval_steps_per_second": 3.208, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 61.54, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.0934, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6546051502227783, | |
| "eval_runtime": 0.6648, | |
| "eval_samples_per_second": 69.19, | |
| "eval_steps_per_second": 3.008, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 62.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.665103018283844, | |
| "eval_runtime": 0.6067, | |
| "eval_samples_per_second": 75.824, | |
| "eval_steps_per_second": 3.297, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 63.08, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.1123, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.6568355560302734, | |
| "eval_runtime": 0.6061, | |
| "eval_samples_per_second": 75.896, | |
| "eval_steps_per_second": 3.3, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 64.62, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0855, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 64.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.6506606936454773, | |
| "eval_runtime": 0.6256, | |
| "eval_samples_per_second": 73.528, | |
| "eval_steps_per_second": 3.197, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6667113304138184, | |
| "eval_runtime": 0.6184, | |
| "eval_samples_per_second": 74.384, | |
| "eval_steps_per_second": 3.234, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 66.15, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.1135, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 66.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6515849232673645, | |
| "eval_runtime": 0.6641, | |
| "eval_samples_per_second": 69.267, | |
| "eval_steps_per_second": 3.012, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 67.69, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.0932, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6596114039421082, | |
| "eval_runtime": 0.5982, | |
| "eval_samples_per_second": 76.895, | |
| "eval_steps_per_second": 3.343, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 68.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.677249550819397, | |
| "eval_runtime": 0.6014, | |
| "eval_samples_per_second": 76.488, | |
| "eval_steps_per_second": 3.326, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 69.23, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.1228, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.6525955200195312, | |
| "eval_runtime": 0.6064, | |
| "eval_samples_per_second": 75.857, | |
| "eval_steps_per_second": 3.298, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 70.77, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.0878, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 70.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6731473207473755, | |
| "eval_runtime": 0.6319, | |
| "eval_samples_per_second": 72.794, | |
| "eval_steps_per_second": 3.165, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6350728869438171, | |
| "eval_runtime": 0.626, | |
| "eval_samples_per_second": 73.479, | |
| "eval_steps_per_second": 3.195, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 72.31, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.1073, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 72.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6268617510795593, | |
| "eval_runtime": 0.6109, | |
| "eval_samples_per_second": 75.304, | |
| "eval_steps_per_second": 3.274, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "learning_rate": 0.0, | |
| "loss": 0.1028, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6742560267448425, | |
| "eval_runtime": 0.6109, | |
| "eval_samples_per_second": 75.3, | |
| "eval_steps_per_second": 3.274, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "step": 480, | |
| "total_flos": 1.6581977329862246e+17, | |
| "train_loss": 0.38355133185784024, | |
| "train_runtime": 282.7663, | |
| "train_samples_per_second": 231.711, | |
| "train_steps_per_second": 1.698 | |
| } | |
| ], | |
| "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 | |
| } | |