| { | |
| "best_metric": 0.8260869565217391, | |
| "best_model_checkpoint": "swiftformer-xs-ve-U13-b-80\\checkpoint-136", | |
| "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": 1.3858562707901, | |
| "eval_runtime": 0.6151, | |
| "eval_samples_per_second": 74.782, | |
| "eval_steps_per_second": 3.251, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.3857, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.2826086956521739, | |
| "eval_loss": 1.383385419845581, | |
| "eval_runtime": 0.5892, | |
| "eval_samples_per_second": 78.066, | |
| "eval_steps_per_second": 3.394, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_accuracy": 0.1956521739130435, | |
| "eval_loss": 1.3788952827453613, | |
| "eval_runtime": 0.6135, | |
| "eval_samples_per_second": 74.979, | |
| "eval_steps_per_second": 3.26, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 1.3767, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.15217391304347827, | |
| "eval_loss": 1.3666234016418457, | |
| "eval_runtime": 0.5852, | |
| "eval_samples_per_second": 78.61, | |
| "eval_steps_per_second": 3.418, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 0.000125, | |
| "loss": 1.3226, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_accuracy": 0.15217391304347827, | |
| "eval_loss": 1.356500506401062, | |
| "eval_runtime": 0.5925, | |
| "eval_samples_per_second": 77.636, | |
| "eval_steps_per_second": 3.375, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 1.3901711702346802, | |
| "eval_runtime": 0.5997, | |
| "eval_samples_per_second": 76.711, | |
| "eval_steps_per_second": 3.335, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 1.1987, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "eval_accuracy": 0.21739130434782608, | |
| "eval_loss": 1.3712323904037476, | |
| "eval_runtime": 0.5757, | |
| "eval_samples_per_second": 79.903, | |
| "eval_steps_per_second": 3.474, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 0.0001990740740740741, | |
| "loss": 1.1075, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.34782608695652173, | |
| "eval_loss": 1.3196704387664795, | |
| "eval_runtime": 0.5987, | |
| "eval_samples_per_second": 76.833, | |
| "eval_steps_per_second": 3.341, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "eval_accuracy": 0.3695652173913043, | |
| "eval_loss": 1.3648946285247803, | |
| "eval_runtime": 0.5855, | |
| "eval_samples_per_second": 78.566, | |
| "eval_steps_per_second": 3.416, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 0.00019444444444444446, | |
| "loss": 0.9988, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.3695652173913043, | |
| "eval_loss": 1.2583398818969727, | |
| "eval_runtime": 0.6118, | |
| "eval_samples_per_second": 75.188, | |
| "eval_steps_per_second": 3.269, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 0.00018981481481481483, | |
| "loss": 0.8863, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "eval_accuracy": 0.3695652173913043, | |
| "eval_loss": 1.2484155893325806, | |
| "eval_runtime": 0.5738, | |
| "eval_samples_per_second": 80.169, | |
| "eval_steps_per_second": 3.486, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.41304347826086957, | |
| "eval_loss": 1.286899447441101, | |
| "eval_runtime": 0.6289, | |
| "eval_samples_per_second": 73.144, | |
| "eval_steps_per_second": 3.18, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 0.0001851851851851852, | |
| "loss": 0.8228, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "eval_accuracy": 0.4782608695652174, | |
| "eval_loss": 1.1677778959274292, | |
| "eval_runtime": 0.5616, | |
| "eval_samples_per_second": 81.902, | |
| "eval_steps_per_second": 3.561, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 13.85, | |
| "learning_rate": 0.00018055555555555557, | |
| "loss": 0.7456, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.0274546146392822, | |
| "eval_runtime": 0.5647, | |
| "eval_samples_per_second": 81.465, | |
| "eval_steps_per_second": 3.542, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9701868891716003, | |
| "eval_runtime": 0.5987, | |
| "eval_samples_per_second": 76.834, | |
| "eval_steps_per_second": 3.341, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 0.00017592592592592595, | |
| "loss": 0.6595, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.9103245139122009, | |
| "eval_runtime": 0.5651, | |
| "eval_samples_per_second": 81.4, | |
| "eval_steps_per_second": 3.539, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "learning_rate": 0.00017129629629629632, | |
| "loss": 0.5995, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.8506172895431519, | |
| "eval_runtime": 0.6113, | |
| "eval_samples_per_second": 75.248, | |
| "eval_steps_per_second": 3.272, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8514139652252197, | |
| "eval_runtime": 0.5699, | |
| "eval_samples_per_second": 80.723, | |
| "eval_steps_per_second": 3.51, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 0.5826, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.8963512182235718, | |
| "eval_runtime": 0.5992, | |
| "eval_samples_per_second": 76.774, | |
| "eval_steps_per_second": 3.338, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.00016203703703703706, | |
| "loss": 0.4818, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8549758195877075, | |
| "eval_runtime": 0.5779, | |
| "eval_samples_per_second": 79.599, | |
| "eval_steps_per_second": 3.461, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7131932973861694, | |
| "eval_runtime": 0.5892, | |
| "eval_samples_per_second": 78.073, | |
| "eval_steps_per_second": 3.394, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 21.54, | |
| "learning_rate": 0.00015740740740740743, | |
| "loss": 0.4553, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6972543597221375, | |
| "eval_runtime": 0.6311, | |
| "eval_samples_per_second": 72.888, | |
| "eval_steps_per_second": 3.169, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 22.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.749606728553772, | |
| "eval_runtime": 0.6069, | |
| "eval_samples_per_second": 75.792, | |
| "eval_steps_per_second": 3.295, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 0.00015277777777777777, | |
| "loss": 0.4276, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.9087320566177368, | |
| "eval_runtime": 0.6537, | |
| "eval_samples_per_second": 70.367, | |
| "eval_steps_per_second": 3.059, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 0.00014814814814814815, | |
| "loss": 0.3375, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 24.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7786810398101807, | |
| "eval_runtime": 0.588, | |
| "eval_samples_per_second": 78.229, | |
| "eval_steps_per_second": 3.401, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.7131972312927246, | |
| "eval_runtime": 0.5899, | |
| "eval_samples_per_second": 77.976, | |
| "eval_steps_per_second": 3.39, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 26.15, | |
| "learning_rate": 0.00014351851851851852, | |
| "loss": 0.3199, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7569522261619568, | |
| "eval_runtime": 0.5879, | |
| "eval_samples_per_second": 78.242, | |
| "eval_steps_per_second": 3.402, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "learning_rate": 0.0001388888888888889, | |
| "loss": 0.2756, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.787326455116272, | |
| "eval_runtime": 0.5846, | |
| "eval_samples_per_second": 78.69, | |
| "eval_steps_per_second": 3.421, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7894624471664429, | |
| "eval_runtime": 0.6067, | |
| "eval_samples_per_second": 75.814, | |
| "eval_steps_per_second": 3.296, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 29.23, | |
| "learning_rate": 0.00013425925925925926, | |
| "loss": 0.2254, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.7443256378173828, | |
| "eval_runtime": 0.6221, | |
| "eval_samples_per_second": 73.946, | |
| "eval_steps_per_second": 3.215, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 0.00012962962962962963, | |
| "loss": 0.2576, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 30.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9623061418533325, | |
| "eval_runtime": 0.6026, | |
| "eval_samples_per_second": 76.332, | |
| "eval_steps_per_second": 3.319, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.7348794341087341, | |
| "eval_runtime": 0.5766, | |
| "eval_samples_per_second": 79.779, | |
| "eval_steps_per_second": 3.469, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 32.31, | |
| "learning_rate": 0.000125, | |
| "loss": 0.2113, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 32.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7886755466461182, | |
| "eval_runtime": 0.6103, | |
| "eval_samples_per_second": 75.378, | |
| "eval_steps_per_second": 3.277, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 33.85, | |
| "learning_rate": 0.00012037037037037037, | |
| "loss": 0.1978, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.8920990228652954, | |
| "eval_runtime": 0.573, | |
| "eval_samples_per_second": 80.278, | |
| "eval_steps_per_second": 3.49, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 34.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.8102229833602905, | |
| "eval_runtime": 0.6072, | |
| "eval_samples_per_second": 75.756, | |
| "eval_steps_per_second": 3.294, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 0.00011574074074074075, | |
| "loss": 0.2455, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.894730269908905, | |
| "eval_runtime": 0.6442, | |
| "eval_samples_per_second": 71.406, | |
| "eval_steps_per_second": 3.105, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 0.1809, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.8143943548202515, | |
| "eval_runtime": 0.5823, | |
| "eval_samples_per_second": 78.995, | |
| "eval_steps_per_second": 3.435, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.829043984413147, | |
| "eval_runtime": 0.573, | |
| "eval_samples_per_second": 80.275, | |
| "eval_steps_per_second": 3.49, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 0.00010648148148148149, | |
| "loss": 0.1967, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 38.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.8135195374488831, | |
| "eval_runtime": 0.5896, | |
| "eval_samples_per_second": 78.014, | |
| "eval_steps_per_second": 3.392, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 0.00010185185185185186, | |
| "loss": 0.1608, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8064969182014465, | |
| "eval_runtime": 0.6144, | |
| "eval_samples_per_second": 74.87, | |
| "eval_steps_per_second": 3.255, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.739860475063324, | |
| "eval_runtime": 0.5769, | |
| "eval_samples_per_second": 79.736, | |
| "eval_steps_per_second": 3.467, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 41.54, | |
| "learning_rate": 9.722222222222223e-05, | |
| "loss": 0.1704, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.7099208235740662, | |
| "eval_runtime": 0.5722, | |
| "eval_samples_per_second": 80.394, | |
| "eval_steps_per_second": 3.495, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 42.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.7569423913955688, | |
| "eval_runtime": 0.5853, | |
| "eval_samples_per_second": 78.596, | |
| "eval_steps_per_second": 3.417, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 43.08, | |
| "learning_rate": 9.25925925925926e-05, | |
| "loss": 0.1682, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.8458698987960815, | |
| "eval_runtime": 0.6104, | |
| "eval_samples_per_second": 75.362, | |
| "eval_steps_per_second": 3.277, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 44.62, | |
| "learning_rate": 8.796296296296297e-05, | |
| "loss": 0.1607, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 44.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7311373353004456, | |
| "eval_runtime": 0.5835, | |
| "eval_samples_per_second": 78.829, | |
| "eval_steps_per_second": 3.427, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.783256471157074, | |
| "eval_runtime": 0.619, | |
| "eval_samples_per_second": 74.311, | |
| "eval_steps_per_second": 3.231, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 0.1589, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 46.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8072806596755981, | |
| "eval_runtime": 0.6425, | |
| "eval_samples_per_second": 71.594, | |
| "eval_steps_per_second": 3.113, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 47.69, | |
| "learning_rate": 7.870370370370372e-05, | |
| "loss": 0.1524, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7472575902938843, | |
| "eval_runtime": 0.6, | |
| "eval_samples_per_second": 76.668, | |
| "eval_steps_per_second": 3.333, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 48.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.6779573559761047, | |
| "eval_runtime": 0.5961, | |
| "eval_samples_per_second": 77.169, | |
| "eval_steps_per_second": 3.355, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 49.23, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 0.1586, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7573379874229431, | |
| "eval_runtime": 0.6092, | |
| "eval_samples_per_second": 75.504, | |
| "eval_steps_per_second": 3.283, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 50.77, | |
| "learning_rate": 6.944444444444444e-05, | |
| "loss": 0.128, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 50.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7614392638206482, | |
| "eval_runtime": 0.5939, | |
| "eval_samples_per_second": 77.451, | |
| "eval_steps_per_second": 3.367, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7338166236877441, | |
| "eval_runtime": 0.6299, | |
| "eval_samples_per_second": 73.033, | |
| "eval_steps_per_second": 3.175, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 52.31, | |
| "learning_rate": 6.481481481481482e-05, | |
| "loss": 0.1254, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 52.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7666023373603821, | |
| "eval_runtime": 0.6065, | |
| "eval_samples_per_second": 75.848, | |
| "eval_steps_per_second": 3.298, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 53.85, | |
| "learning_rate": 6.018518518518519e-05, | |
| "loss": 0.1206, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8433414101600647, | |
| "eval_runtime": 0.6112, | |
| "eval_samples_per_second": 75.257, | |
| "eval_steps_per_second": 3.272, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 54.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8747164011001587, | |
| "eval_runtime": 0.6225, | |
| "eval_samples_per_second": 73.894, | |
| "eval_steps_per_second": 3.213, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 55.38, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 0.1398, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8940105438232422, | |
| "eval_runtime": 0.5972, | |
| "eval_samples_per_second": 77.026, | |
| "eval_steps_per_second": 3.349, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "learning_rate": 5.092592592592593e-05, | |
| "loss": 0.1536, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.7780929803848267, | |
| "eval_runtime": 0.5998, | |
| "eval_samples_per_second": 76.693, | |
| "eval_steps_per_second": 3.334, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7350872159004211, | |
| "eval_runtime": 0.6081, | |
| "eval_samples_per_second": 75.64, | |
| "eval_steps_per_second": 3.289, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 58.46, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.1281, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 58.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7600933313369751, | |
| "eval_runtime": 0.5822, | |
| "eval_samples_per_second": 79.008, | |
| "eval_steps_per_second": 3.435, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.1156, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7990931868553162, | |
| "eval_runtime": 0.6251, | |
| "eval_samples_per_second": 73.589, | |
| "eval_steps_per_second": 3.2, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7775823473930359, | |
| "eval_runtime": 0.5922, | |
| "eval_samples_per_second": 77.678, | |
| "eval_steps_per_second": 3.377, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 61.54, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.0852, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.78378826379776, | |
| "eval_runtime": 0.6126, | |
| "eval_samples_per_second": 75.09, | |
| "eval_steps_per_second": 3.265, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 62.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7752338647842407, | |
| "eval_runtime": 0.594, | |
| "eval_samples_per_second": 77.443, | |
| "eval_steps_per_second": 3.367, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 63.08, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.1106, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7541300058364868, | |
| "eval_runtime": 0.6316, | |
| "eval_samples_per_second": 72.826, | |
| "eval_steps_per_second": 3.166, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 64.62, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0817, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 64.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7536001801490784, | |
| "eval_runtime": 0.6469, | |
| "eval_samples_per_second": 71.106, | |
| "eval_steps_per_second": 3.092, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8129211068153381, | |
| "eval_runtime": 0.5986, | |
| "eval_samples_per_second": 76.844, | |
| "eval_steps_per_second": 3.341, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 66.15, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.1211, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 66.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7883771061897278, | |
| "eval_runtime": 0.6108, | |
| "eval_samples_per_second": 75.306, | |
| "eval_steps_per_second": 3.274, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 67.69, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.0944, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8011212348937988, | |
| "eval_runtime": 0.5979, | |
| "eval_samples_per_second": 76.93, | |
| "eval_steps_per_second": 3.345, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 68.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.806803822517395, | |
| "eval_runtime": 0.5931, | |
| "eval_samples_per_second": 77.56, | |
| "eval_steps_per_second": 3.372, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 69.23, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.1187, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7795934081077576, | |
| "eval_runtime": 0.6317, | |
| "eval_samples_per_second": 72.821, | |
| "eval_steps_per_second": 3.166, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 70.77, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.0935, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 70.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.793422281742096, | |
| "eval_runtime": 0.5934, | |
| "eval_samples_per_second": 77.523, | |
| "eval_steps_per_second": 3.371, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.736743152141571, | |
| "eval_runtime": 0.6082, | |
| "eval_samples_per_second": 75.631, | |
| "eval_steps_per_second": 3.288, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 72.31, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.109, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 72.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7514945268630981, | |
| "eval_runtime": 0.604, | |
| "eval_samples_per_second": 76.157, | |
| "eval_steps_per_second": 3.311, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "learning_rate": 0.0, | |
| "loss": 0.1006, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7887920141220093, | |
| "eval_runtime": 0.613, | |
| "eval_samples_per_second": 75.037, | |
| "eval_steps_per_second": 3.262, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "step": 480, | |
| "total_flos": 1.6581977329862246e+17, | |
| "train_loss": 0.38448232350250083, | |
| "train_runtime": 275.3303, | |
| "train_samples_per_second": 237.969, | |
| "train_steps_per_second": 1.743 | |
| } | |
| ], | |
| "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 | |
| } | |