| { | |
| "best_metric": 0.8478260869565217, | |
| "best_model_checkpoint": "beit-base-patch16-224-ve-U13-b-80b\\checkpoint-312", | |
| "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": 0.45652173913043476, | |
| "eval_loss": 1.3181706666946411, | |
| "eval_runtime": 0.8174, | |
| "eval_samples_per_second": 56.274, | |
| "eval_steps_per_second": 2.447, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 1.6182, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.3055709600448608, | |
| "eval_runtime": 0.8052, | |
| "eval_samples_per_second": 57.127, | |
| "eval_steps_per_second": 2.484, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2883871793746948, | |
| "eval_runtime": 0.8141, | |
| "eval_samples_per_second": 56.505, | |
| "eval_steps_per_second": 2.457, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 1.592, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.280716061592102, | |
| "eval_runtime": 0.844, | |
| "eval_samples_per_second": 54.501, | |
| "eval_steps_per_second": 2.37, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 3.125e-05, | |
| "loss": 1.4756, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2991440296173096, | |
| "eval_runtime": 0.9835, | |
| "eval_samples_per_second": 46.77, | |
| "eval_steps_per_second": 2.033, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.2451491355895996, | |
| "eval_runtime": 0.8204, | |
| "eval_samples_per_second": 56.071, | |
| "eval_steps_per_second": 2.438, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.352, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "eval_accuracy": 0.5217391304347826, | |
| "eval_loss": 1.1844638586044312, | |
| "eval_runtime": 0.7995, | |
| "eval_samples_per_second": 57.535, | |
| "eval_steps_per_second": 2.502, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 4.976851851851852e-05, | |
| "loss": 1.2143, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 1.0315006971359253, | |
| "eval_runtime": 0.8068, | |
| "eval_samples_per_second": 57.014, | |
| "eval_steps_per_second": 2.479, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "eval_accuracy": 0.5434782608695652, | |
| "eval_loss": 0.9288709759712219, | |
| "eval_runtime": 0.8497, | |
| "eval_samples_per_second": 54.135, | |
| "eval_steps_per_second": 2.354, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 1.0327, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5434782608695652, | |
| "eval_loss": 0.8924712538719177, | |
| "eval_runtime": 0.8251, | |
| "eval_samples_per_second": 55.751, | |
| "eval_steps_per_second": 2.424, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 4.745370370370371e-05, | |
| "loss": 0.8878, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "eval_accuracy": 0.5652173913043478, | |
| "eval_loss": 0.8632795214653015, | |
| "eval_runtime": 0.8493, | |
| "eval_samples_per_second": 54.163, | |
| "eval_steps_per_second": 2.355, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 0.7565776705741882, | |
| "eval_runtime": 0.8341, | |
| "eval_samples_per_second": 55.152, | |
| "eval_steps_per_second": 2.398, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.7712, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7668902277946472, | |
| "eval_runtime": 0.8109, | |
| "eval_samples_per_second": 56.725, | |
| "eval_steps_per_second": 2.466, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 13.85, | |
| "learning_rate": 4.5138888888888894e-05, | |
| "loss": 0.6808, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.763481616973877, | |
| "eval_runtime": 0.8235, | |
| "eval_samples_per_second": 55.861, | |
| "eval_steps_per_second": 2.429, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 0.865291953086853, | |
| "eval_runtime": 0.8503, | |
| "eval_samples_per_second": 54.099, | |
| "eval_steps_per_second": 2.352, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 4.3981481481481486e-05, | |
| "loss": 0.5844, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7192845344543457, | |
| "eval_runtime": 0.8184, | |
| "eval_samples_per_second": 56.204, | |
| "eval_steps_per_second": 2.444, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "learning_rate": 4.282407407407408e-05, | |
| "loss": 0.4332, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6186434626579285, | |
| "eval_runtime": 0.8325, | |
| "eval_samples_per_second": 55.254, | |
| "eval_steps_per_second": 2.402, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.0295032262802124, | |
| "eval_runtime": 0.8366, | |
| "eval_samples_per_second": 54.987, | |
| "eval_steps_per_second": 2.391, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.3607, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8007151484489441, | |
| "eval_runtime": 0.8163, | |
| "eval_samples_per_second": 56.352, | |
| "eval_steps_per_second": 2.45, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.0509259259259265e-05, | |
| "loss": 0.3134, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.679006814956665, | |
| "eval_runtime": 0.817, | |
| "eval_samples_per_second": 56.305, | |
| "eval_steps_per_second": 2.448, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.801273763179779, | |
| "eval_runtime": 0.8163, | |
| "eval_samples_per_second": 56.35, | |
| "eval_steps_per_second": 2.45, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 21.54, | |
| "learning_rate": 3.935185185185186e-05, | |
| "loss": 0.2988, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7480794787406921, | |
| "eval_runtime": 0.8337, | |
| "eval_samples_per_second": 55.173, | |
| "eval_steps_per_second": 2.399, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 22.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9279541373252869, | |
| "eval_runtime": 0.8048, | |
| "eval_samples_per_second": 57.157, | |
| "eval_steps_per_second": 2.485, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 3.8194444444444444e-05, | |
| "loss": 0.2487, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.6541624665260315, | |
| "eval_runtime": 0.7972, | |
| "eval_samples_per_second": 57.704, | |
| "eval_steps_per_second": 2.509, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.1912, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 24.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7133772373199463, | |
| "eval_runtime": 0.8524, | |
| "eval_samples_per_second": 53.966, | |
| "eval_steps_per_second": 2.346, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8421454429626465, | |
| "eval_runtime": 0.8221, | |
| "eval_samples_per_second": 55.956, | |
| "eval_steps_per_second": 2.433, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 26.15, | |
| "learning_rate": 3.587962962962963e-05, | |
| "loss": 0.1946, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7283844947814941, | |
| "eval_runtime": 0.8187, | |
| "eval_samples_per_second": 56.184, | |
| "eval_steps_per_second": 2.443, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.1685, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7506698369979858, | |
| "eval_runtime": 0.8254, | |
| "eval_samples_per_second": 55.732, | |
| "eval_steps_per_second": 2.423, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.761018693447113, | |
| "eval_runtime": 0.9254, | |
| "eval_samples_per_second": 49.709, | |
| "eval_steps_per_second": 2.161, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 29.23, | |
| "learning_rate": 3.3564814814814815e-05, | |
| "loss": 0.1646, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.8012712001800537, | |
| "eval_runtime": 0.8337, | |
| "eval_samples_per_second": 55.178, | |
| "eval_steps_per_second": 2.399, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.166, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 30.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.8803007006645203, | |
| "eval_runtime": 0.9377, | |
| "eval_samples_per_second": 49.054, | |
| "eval_steps_per_second": 2.133, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7894579172134399, | |
| "eval_runtime": 0.8269, | |
| "eval_samples_per_second": 55.629, | |
| "eval_steps_per_second": 2.419, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 32.31, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.1372, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 32.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7760207056999207, | |
| "eval_runtime": 0.8341, | |
| "eval_samples_per_second": 55.149, | |
| "eval_steps_per_second": 2.398, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 33.85, | |
| "learning_rate": 3.0092592592592593e-05, | |
| "loss": 0.1424, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9389709830284119, | |
| "eval_runtime": 0.8316, | |
| "eval_samples_per_second": 55.318, | |
| "eval_steps_per_second": 2.405, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 34.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.7839226722717285, | |
| "eval_runtime": 0.8199, | |
| "eval_samples_per_second": 56.103, | |
| "eval_steps_per_second": 2.439, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 2.8935185185185186e-05, | |
| "loss": 0.1399, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.9422168135643005, | |
| "eval_runtime": 0.8523, | |
| "eval_samples_per_second": 53.975, | |
| "eval_steps_per_second": 2.347, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.1238, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8710301518440247, | |
| "eval_runtime": 0.817, | |
| "eval_samples_per_second": 56.3, | |
| "eval_steps_per_second": 2.448, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.8683509230613708, | |
| "eval_runtime": 0.8145, | |
| "eval_samples_per_second": 56.475, | |
| "eval_steps_per_second": 2.455, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 2.6620370370370372e-05, | |
| "loss": 0.123, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 38.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8193817138671875, | |
| "eval_runtime": 0.8004, | |
| "eval_samples_per_second": 57.472, | |
| "eval_steps_per_second": 2.499, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 2.5462962962962965e-05, | |
| "loss": 0.1381, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9698395133018494, | |
| "eval_runtime": 0.8139, | |
| "eval_samples_per_second": 56.515, | |
| "eval_steps_per_second": 2.457, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8545413017272949, | |
| "eval_runtime": 0.8323, | |
| "eval_samples_per_second": 55.266, | |
| "eval_steps_per_second": 2.403, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 41.54, | |
| "learning_rate": 2.4305555555555558e-05, | |
| "loss": 0.1081, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9924511313438416, | |
| "eval_runtime": 0.8284, | |
| "eval_samples_per_second": 55.531, | |
| "eval_steps_per_second": 2.414, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 42.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.9319804906845093, | |
| "eval_runtime": 0.818, | |
| "eval_samples_per_second": 56.235, | |
| "eval_steps_per_second": 2.445, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 43.08, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.0929, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 1.0241632461547852, | |
| "eval_runtime": 0.8281, | |
| "eval_samples_per_second": 55.549, | |
| "eval_steps_per_second": 2.415, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 44.62, | |
| "learning_rate": 2.1990740740740743e-05, | |
| "loss": 0.0898, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 44.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.9411269426345825, | |
| "eval_runtime": 0.8388, | |
| "eval_samples_per_second": 54.838, | |
| "eval_steps_per_second": 2.384, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8995408415794373, | |
| "eval_runtime": 0.8513, | |
| "eval_samples_per_second": 54.038, | |
| "eval_steps_per_second": 2.349, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.12, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 46.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.774114191532135, | |
| "eval_runtime": 0.8167, | |
| "eval_samples_per_second": 56.327, | |
| "eval_steps_per_second": 2.449, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 47.69, | |
| "learning_rate": 1.967592592592593e-05, | |
| "loss": 0.1126, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.7122377157211304, | |
| "eval_runtime": 0.8146, | |
| "eval_samples_per_second": 56.469, | |
| "eval_steps_per_second": 2.455, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 48.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.9098690152168274, | |
| "eval_runtime": 0.8003, | |
| "eval_samples_per_second": 57.477, | |
| "eval_steps_per_second": 2.499, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 49.23, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.1088, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.114755630493164, | |
| "eval_runtime": 0.8219, | |
| "eval_samples_per_second": 55.97, | |
| "eval_steps_per_second": 2.433, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 50.77, | |
| "learning_rate": 1.736111111111111e-05, | |
| "loss": 0.0851, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 50.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.9296599626541138, | |
| "eval_runtime": 0.8335, | |
| "eval_samples_per_second": 55.191, | |
| "eval_steps_per_second": 2.4, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.8800845742225647, | |
| "eval_runtime": 0.8362, | |
| "eval_samples_per_second": 55.008, | |
| "eval_steps_per_second": 2.392, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 52.31, | |
| "learning_rate": 1.6203703703703704e-05, | |
| "loss": 0.1001, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 52.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.8427883386611938, | |
| "eval_runtime": 0.8167, | |
| "eval_samples_per_second": 56.324, | |
| "eval_steps_per_second": 2.449, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 53.85, | |
| "learning_rate": 1.5046296296296297e-05, | |
| "loss": 0.0718, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.9720932245254517, | |
| "eval_runtime": 0.8541, | |
| "eval_samples_per_second": 53.859, | |
| "eval_steps_per_second": 2.342, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 54.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.8770763278007507, | |
| "eval_runtime": 0.884, | |
| "eval_samples_per_second": 52.036, | |
| "eval_steps_per_second": 2.262, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 55.38, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.0842, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.9981948137283325, | |
| "eval_runtime": 0.8228, | |
| "eval_samples_per_second": 55.903, | |
| "eval_steps_per_second": 2.431, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "learning_rate": 1.2731481481481482e-05, | |
| "loss": 0.1069, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 1.1083166599273682, | |
| "eval_runtime": 0.8167, | |
| "eval_samples_per_second": 56.321, | |
| "eval_steps_per_second": 2.449, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.9071816205978394, | |
| "eval_runtime": 0.8396, | |
| "eval_samples_per_second": 54.785, | |
| "eval_steps_per_second": 2.382, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 58.46, | |
| "learning_rate": 1.1574074074074075e-05, | |
| "loss": 0.0803, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 58.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7978565096855164, | |
| "eval_runtime": 0.8347, | |
| "eval_samples_per_second": 55.108, | |
| "eval_steps_per_second": 2.396, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 0.0752, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.7488988041877747, | |
| "eval_runtime": 0.8278, | |
| "eval_samples_per_second": 55.57, | |
| "eval_steps_per_second": 2.416, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.802253246307373, | |
| "eval_runtime": 0.8336, | |
| "eval_samples_per_second": 55.183, | |
| "eval_steps_per_second": 2.399, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 61.54, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.0646, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.802682101726532, | |
| "eval_runtime": 1.0467, | |
| "eval_samples_per_second": 43.949, | |
| "eval_steps_per_second": 1.911, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 62.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.8274930119514465, | |
| "eval_runtime": 0.8068, | |
| "eval_samples_per_second": 57.017, | |
| "eval_steps_per_second": 2.479, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 63.08, | |
| "learning_rate": 8.101851851851852e-06, | |
| "loss": 0.0829, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.8587205410003662, | |
| "eval_runtime": 0.8175, | |
| "eval_samples_per_second": 56.27, | |
| "eval_steps_per_second": 2.447, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 64.62, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.0616, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 64.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.8869741559028625, | |
| "eval_runtime": 0.8172, | |
| "eval_samples_per_second": 56.29, | |
| "eval_steps_per_second": 2.447, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.8927735090255737, | |
| "eval_runtime": 0.8177, | |
| "eval_samples_per_second": 56.255, | |
| "eval_steps_per_second": 2.446, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 66.15, | |
| "learning_rate": 5.787037037037038e-06, | |
| "loss": 0.0693, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 66.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.9289346933364868, | |
| "eval_runtime": 0.9088, | |
| "eval_samples_per_second": 50.618, | |
| "eval_steps_per_second": 2.201, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 67.69, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.0657, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.9603818655014038, | |
| "eval_runtime": 0.8139, | |
| "eval_samples_per_second": 56.517, | |
| "eval_steps_per_second": 2.457, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 68.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.9559684991836548, | |
| "eval_runtime": 0.8119, | |
| "eval_samples_per_second": 56.658, | |
| "eval_steps_per_second": 2.463, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 69.23, | |
| "learning_rate": 3.4722222222222224e-06, | |
| "loss": 0.0588, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.9543905854225159, | |
| "eval_runtime": 0.8184, | |
| "eval_samples_per_second": 56.206, | |
| "eval_steps_per_second": 2.444, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 70.77, | |
| "learning_rate": 2.3148148148148148e-06, | |
| "loss": 0.0578, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 70.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.9418670535087585, | |
| "eval_runtime": 0.8002, | |
| "eval_samples_per_second": 57.489, | |
| "eval_steps_per_second": 2.5, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.9473724961280823, | |
| "eval_runtime": 0.814, | |
| "eval_samples_per_second": 56.514, | |
| "eval_steps_per_second": 2.457, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 72.31, | |
| "learning_rate": 1.1574074074074074e-06, | |
| "loss": 0.0638, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 72.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.953983724117279, | |
| "eval_runtime": 0.8002, | |
| "eval_samples_per_second": 57.487, | |
| "eval_steps_per_second": 2.499, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "learning_rate": 0.0, | |
| "loss": 0.0592, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.9548673033714294, | |
| "eval_runtime": 0.8156, | |
| "eval_samples_per_second": 56.403, | |
| "eval_steps_per_second": 2.452, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "step": 480, | |
| "total_flos": 4.685648449140449e+18, | |
| "train_loss": 0.3410949035237233, | |
| "train_runtime": 1069.8093, | |
| "train_samples_per_second": 61.245, | |
| "train_steps_per_second": 0.449 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 480, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 80, | |
| "save_steps": 500, | |
| "total_flos": 4.685648449140449e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |