| { | |
| "best_metric": 0.2647058823529412, | |
| "best_model_checkpoint": "videomae-large-finetuned-kinetics-finetuned-engine-subset-R2-K400-20230418_3/checkpoint-550", | |
| "epoch": 49.00185185185185, | |
| "global_step": 2700, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 2.5889, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 2.6177, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 2.6425, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 2.5758, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 2.5562, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.022058823529411766, | |
| "eval_loss": 2.5746004581451416, | |
| "eval_runtime": 18.5226, | |
| "eval_samples_per_second": 7.342, | |
| "eval_steps_per_second": 1.242, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 2.5636, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 2.4418, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 2.5013, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 2.4885, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 2.5236, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 2.4543, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_accuracy": 0.09558823529411764, | |
| "eval_loss": 2.5524215698242188, | |
| "eval_runtime": 18.7327, | |
| "eval_samples_per_second": 7.26, | |
| "eval_steps_per_second": 1.228, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 2.283, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 2.3757, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 2.2946, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 2.3668, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 2.1443, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_accuracy": 0.11029411764705882, | |
| "eval_loss": 2.5213658809661865, | |
| "eval_runtime": 19.2865, | |
| "eval_samples_per_second": 7.052, | |
| "eval_steps_per_second": 1.193, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 2.0635, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.063, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 2.0232, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 1.8032, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 1.669, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 1.6604, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "eval_accuracy": 0.13970588235294118, | |
| "eval_loss": 2.6414613723754883, | |
| "eval_runtime": 19.2083, | |
| "eval_samples_per_second": 7.08, | |
| "eval_steps_per_second": 1.197, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 1.3638, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.3303, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 1.6113, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 1.3732, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5847, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "eval_accuracy": 0.07352941176470588, | |
| "eval_loss": 2.9843006134033203, | |
| "eval_runtime": 19.283, | |
| "eval_samples_per_second": 7.053, | |
| "eval_steps_per_second": 1.193, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.9794238683127575e-05, | |
| "loss": 1.404, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 4.958847736625515e-05, | |
| "loss": 1.2842, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 1.4568, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 4.9176954732510286e-05, | |
| "loss": 1.1628, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 4.8971193415637865e-05, | |
| "loss": 1.3066, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 4.876543209876544e-05, | |
| "loss": 1.4657, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "eval_accuracy": 0.14705882352941177, | |
| "eval_loss": 2.747610092163086, | |
| "eval_runtime": 18.9644, | |
| "eval_samples_per_second": 7.171, | |
| "eval_steps_per_second": 1.213, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.855967078189301e-05, | |
| "loss": 1.1392, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 4.835390946502058e-05, | |
| "loss": 1.0831, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 1.1938, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 4.794238683127572e-05, | |
| "loss": 1.1915, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 4.773662551440329e-05, | |
| "loss": 1.0823, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "eval_accuracy": 0.14705882352941177, | |
| "eval_loss": 3.0872228145599365, | |
| "eval_runtime": 19.2681, | |
| "eval_samples_per_second": 7.058, | |
| "eval_steps_per_second": 1.194, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.7530864197530866e-05, | |
| "loss": 1.3142, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 4.732510288065844e-05, | |
| "loss": 0.8276, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 4.711934156378601e-05, | |
| "loss": 1.2421, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 4.691358024691358e-05, | |
| "loss": 0.7453, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 4.6707818930041156e-05, | |
| "loss": 0.8762, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 4.650205761316873e-05, | |
| "loss": 1.0672, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "eval_accuracy": 0.22058823529411764, | |
| "eval_loss": 2.9539241790771484, | |
| "eval_runtime": 19.7255, | |
| "eval_samples_per_second": 6.895, | |
| "eval_steps_per_second": 1.166, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.7333, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 4.609053497942387e-05, | |
| "loss": 0.7281, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 4.5884773662551446e-05, | |
| "loss": 0.7749, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 4.567901234567901e-05, | |
| "loss": 1.0116, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 4.5473251028806584e-05, | |
| "loss": 0.7241, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "eval_accuracy": 0.11029411764705882, | |
| "eval_loss": 3.536442995071411, | |
| "eval_runtime": 19.1835, | |
| "eval_samples_per_second": 7.089, | |
| "eval_steps_per_second": 1.199, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.5267489711934157e-05, | |
| "loss": 0.7966, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.506172839506173e-05, | |
| "loss": 0.6068, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.48559670781893e-05, | |
| "loss": 0.5489, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 4.4650205761316874e-05, | |
| "loss": 0.6817, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.6598, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 4.423868312757202e-05, | |
| "loss": 0.6532, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "eval_accuracy": 0.2647058823529412, | |
| "eval_loss": 3.1971516609191895, | |
| "eval_runtime": 19.3537, | |
| "eval_samples_per_second": 7.027, | |
| "eval_steps_per_second": 1.188, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4.403292181069959e-05, | |
| "loss": 0.3489, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 4.3827160493827164e-05, | |
| "loss": 0.3966, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 4.3621399176954737e-05, | |
| "loss": 0.4513, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 4.341563786008231e-05, | |
| "loss": 0.69, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 0.6476, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "eval_accuracy": 0.07352941176470588, | |
| "eval_loss": 4.128897666931152, | |
| "eval_runtime": 18.8991, | |
| "eval_samples_per_second": 7.196, | |
| "eval_steps_per_second": 1.217, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.300411522633745e-05, | |
| "loss": 0.5848, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 4.279835390946502e-05, | |
| "loss": 0.5367, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 0.5262, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 4.2386831275720165e-05, | |
| "loss": 0.6052, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 4.2181069958847744e-05, | |
| "loss": 0.5266, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 4.197530864197531e-05, | |
| "loss": 0.3725, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "eval_accuracy": 0.058823529411764705, | |
| "eval_loss": 4.470974922180176, | |
| "eval_runtime": 19.5333, | |
| "eval_samples_per_second": 6.962, | |
| "eval_steps_per_second": 1.177, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.176954732510288e-05, | |
| "loss": 0.5395, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 4.1563786008230455e-05, | |
| "loss": 0.3467, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 4.135802469135803e-05, | |
| "loss": 0.4811, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 4.11522633744856e-05, | |
| "loss": 0.2319, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 4.094650205761317e-05, | |
| "loss": 0.7363, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "eval_accuracy": 0.0661764705882353, | |
| "eval_loss": 4.924136161804199, | |
| "eval_runtime": 18.8618, | |
| "eval_samples_per_second": 7.21, | |
| "eval_steps_per_second": 1.219, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.3512, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 4.053497942386831e-05, | |
| "loss": 0.4679, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 4.032921810699588e-05, | |
| "loss": 0.2977, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 4.012345679012346e-05, | |
| "loss": 0.4135, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 3.9917695473251035e-05, | |
| "loss": 0.5098, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 3.971193415637861e-05, | |
| "loss": 0.3136, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "eval_accuracy": 0.11764705882352941, | |
| "eval_loss": 4.821662425994873, | |
| "eval_runtime": 19.3838, | |
| "eval_samples_per_second": 7.016, | |
| "eval_steps_per_second": 1.187, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 3.950617283950617e-05, | |
| "loss": 0.2163, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 3.9300411522633746e-05, | |
| "loss": 0.4752, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 3.909465020576132e-05, | |
| "loss": 0.5568, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.3797, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 3.868312757201646e-05, | |
| "loss": 0.3154, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "eval_accuracy": 0.18382352941176472, | |
| "eval_loss": 4.271665573120117, | |
| "eval_runtime": 19.5325, | |
| "eval_samples_per_second": 6.963, | |
| "eval_steps_per_second": 1.178, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 3.8477366255144036e-05, | |
| "loss": 0.3158, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 3.82716049382716e-05, | |
| "loss": 0.3185, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 3.806584362139918e-05, | |
| "loss": 0.3665, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 3.786008230452675e-05, | |
| "loss": 0.246, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 3.7654320987654326e-05, | |
| "loss": 0.5252, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 3.74485596707819e-05, | |
| "loss": 0.309, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "eval_accuracy": 0.058823529411764705, | |
| "eval_loss": 4.946552276611328, | |
| "eval_runtime": 18.5475, | |
| "eval_samples_per_second": 7.333, | |
| "eval_steps_per_second": 1.24, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.724279835390947e-05, | |
| "loss": 0.294, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.4016, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 3.683127572016461e-05, | |
| "loss": 0.2915, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 3.662551440329218e-05, | |
| "loss": 0.2268, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 3.6419753086419754e-05, | |
| "loss": 0.3094, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "eval_accuracy": 0.014705882352941176, | |
| "eval_loss": 5.539356708526611, | |
| "eval_runtime": 18.4844, | |
| "eval_samples_per_second": 7.358, | |
| "eval_steps_per_second": 1.244, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 3.6213991769547327e-05, | |
| "loss": 0.4337, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 3.60082304526749e-05, | |
| "loss": 0.4705, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 3.580246913580247e-05, | |
| "loss": 0.3836, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 3.5596707818930044e-05, | |
| "loss": 0.2243, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 3.539094650205762e-05, | |
| "loss": 0.29, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.3333, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "eval_accuracy": 0.09558823529411764, | |
| "eval_loss": 5.0939555168151855, | |
| "eval_runtime": 19.0139, | |
| "eval_samples_per_second": 7.153, | |
| "eval_steps_per_second": 1.21, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 3.497942386831276e-05, | |
| "loss": 0.1621, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 3.4773662551440334e-05, | |
| "loss": 0.2036, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 3.45679012345679e-05, | |
| "loss": 0.1649, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 3.436213991769547e-05, | |
| "loss": 0.2498, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 3.4156378600823045e-05, | |
| "loss": 0.2299, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "eval_accuracy": 0.007352941176470588, | |
| "eval_loss": 6.314783096313477, | |
| "eval_runtime": 18.7617, | |
| "eval_samples_per_second": 7.249, | |
| "eval_steps_per_second": 1.226, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 3.395061728395062e-05, | |
| "loss": 0.3375, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 3.374485596707819e-05, | |
| "loss": 0.376, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 3.353909465020576e-05, | |
| "loss": 0.2132, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.2873, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 3.312757201646091e-05, | |
| "loss": 0.1696, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 3.292181069958848e-05, | |
| "loss": 0.2257, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "eval_accuracy": 0.058823529411764705, | |
| "eval_loss": 5.386910915374756, | |
| "eval_runtime": 19.037, | |
| "eval_samples_per_second": 7.144, | |
| "eval_steps_per_second": 1.208, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.271604938271605e-05, | |
| "loss": 0.262, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 3.2510288065843625e-05, | |
| "loss": 0.2932, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 3.230452674897119e-05, | |
| "loss": 0.17, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 3.209876543209876e-05, | |
| "loss": 0.2872, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "learning_rate": 3.1893004115226336e-05, | |
| "loss": 0.255, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "eval_accuracy": 0.014705882352941176, | |
| "eval_loss": 6.413440704345703, | |
| "eval_runtime": 19.1203, | |
| "eval_samples_per_second": 7.113, | |
| "eval_steps_per_second": 1.203, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 3.168724279835391e-05, | |
| "loss": 0.173, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.2732, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 3.127572016460906e-05, | |
| "loss": 0.175, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 3.1069958847736626e-05, | |
| "loss": 0.2022, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.2273, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 3.065843621399177e-05, | |
| "loss": 0.2335, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "eval_accuracy": 0.04411764705882353, | |
| "eval_loss": 6.141349792480469, | |
| "eval_runtime": 19.4239, | |
| "eval_samples_per_second": 7.002, | |
| "eval_steps_per_second": 1.184, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 3.0452674897119343e-05, | |
| "loss": 0.223, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 3.0246913580246916e-05, | |
| "loss": 0.226, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 3.0041152263374488e-05, | |
| "loss": 0.3511, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 2.9835390946502057e-05, | |
| "loss": 0.1201, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.3507, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "eval_accuracy": 0.007352941176470588, | |
| "eval_loss": 6.291131973266602, | |
| "eval_runtime": 18.6286, | |
| "eval_samples_per_second": 7.301, | |
| "eval_steps_per_second": 1.235, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 2.9423868312757202e-05, | |
| "loss": 0.3065, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 2.9218106995884775e-05, | |
| "loss": 0.119, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 2.9012345679012347e-05, | |
| "loss": 0.31, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 2.880658436213992e-05, | |
| "loss": 0.3629, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "learning_rate": 2.860082304526749e-05, | |
| "loss": 0.1736, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "learning_rate": 2.839506172839506e-05, | |
| "loss": 0.1463, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "eval_accuracy": 0.007352941176470588, | |
| "eval_loss": 6.527339935302734, | |
| "eval_runtime": 19.3595, | |
| "eval_samples_per_second": 7.025, | |
| "eval_steps_per_second": 1.188, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 2.8189300411522634e-05, | |
| "loss": 0.1214, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 2.7983539094650207e-05, | |
| "loss": 0.2213, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.1491, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 2.757201646090535e-05, | |
| "loss": 0.1312, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "learning_rate": 2.736625514403292e-05, | |
| "loss": 0.193, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "eval_accuracy": 0.007352941176470588, | |
| "eval_loss": 6.6533203125, | |
| "eval_runtime": 19.6174, | |
| "eval_samples_per_second": 6.933, | |
| "eval_steps_per_second": 1.172, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 2.7160493827160493e-05, | |
| "loss": 0.2329, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 2.6954732510288066e-05, | |
| "loss": 0.2651, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 2.6748971193415638e-05, | |
| "loss": 0.2483, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 2.654320987654321e-05, | |
| "loss": 0.0754, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "learning_rate": 2.6337448559670787e-05, | |
| "loss": 0.1554, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "learning_rate": 2.6131687242798352e-05, | |
| "loss": 0.1167, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 6.809352874755859, | |
| "eval_runtime": 18.9052, | |
| "eval_samples_per_second": 7.194, | |
| "eval_steps_per_second": 1.217, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.1468, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 2.5720164609053497e-05, | |
| "loss": 0.1028, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 2.551440329218107e-05, | |
| "loss": 0.2864, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 2.5308641975308646e-05, | |
| "loss": 0.1794, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "learning_rate": 2.510288065843622e-05, | |
| "loss": 0.1168, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 6.763158321380615, | |
| "eval_runtime": 19.2445, | |
| "eval_samples_per_second": 7.067, | |
| "eval_steps_per_second": 1.195, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 2.4897119341563787e-05, | |
| "loss": 0.153, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.1269, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 2.4485596707818932e-05, | |
| "loss": 0.1475, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 2.4279835390946505e-05, | |
| "loss": 0.3628, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 0.1292, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 2.3868312757201647e-05, | |
| "loss": 0.0511, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "eval_accuracy": 0.007352941176470588, | |
| "eval_loss": 7.004645824432373, | |
| "eval_runtime": 18.9657, | |
| "eval_samples_per_second": 7.171, | |
| "eval_steps_per_second": 1.213, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 2.366255144032922e-05, | |
| "loss": 0.1885, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "learning_rate": 2.345679012345679e-05, | |
| "loss": 0.1131, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "learning_rate": 2.3251028806584364e-05, | |
| "loss": 0.1701, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "learning_rate": 2.3045267489711937e-05, | |
| "loss": 0.0717, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "learning_rate": 2.2839506172839506e-05, | |
| "loss": 0.1336, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 7.287693023681641, | |
| "eval_runtime": 18.4974, | |
| "eval_samples_per_second": 7.352, | |
| "eval_steps_per_second": 1.243, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 2.2633744855967078e-05, | |
| "loss": 0.3002, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 2.242798353909465e-05, | |
| "loss": 0.1882, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.1417, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 2.2016460905349796e-05, | |
| "loss": 0.053, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 2.1810699588477368e-05, | |
| "loss": 0.1451, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 2.1604938271604937e-05, | |
| "loss": 0.1518, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 7.310234069824219, | |
| "eval_runtime": 18.7122, | |
| "eval_samples_per_second": 7.268, | |
| "eval_steps_per_second": 1.229, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 2.139917695473251e-05, | |
| "loss": 0.0757, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 2.1193415637860082e-05, | |
| "loss": 0.119, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 2.0987654320987655e-05, | |
| "loss": 0.2, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 2.0781893004115227e-05, | |
| "loss": 0.1005, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "learning_rate": 2.05761316872428e-05, | |
| "loss": 0.1972, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 7.163204669952393, | |
| "eval_runtime": 18.8868, | |
| "eval_samples_per_second": 7.201, | |
| "eval_steps_per_second": 1.218, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 0.3282, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 2.016460905349794e-05, | |
| "loss": 0.1741, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 1.9958847736625517e-05, | |
| "loss": 0.1258, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 1.9753086419753087e-05, | |
| "loss": 0.1061, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 31.02, | |
| "learning_rate": 1.954732510288066e-05, | |
| "loss": 0.1131, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 31.02, | |
| "learning_rate": 1.934156378600823e-05, | |
| "loss": 0.0605, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 31.02, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 7.296962738037109, | |
| "eval_runtime": 19.2119, | |
| "eval_samples_per_second": 7.079, | |
| "eval_steps_per_second": 1.197, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 1.91358024691358e-05, | |
| "loss": 0.1463, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 1.8930041152263377e-05, | |
| "loss": 0.1264, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 1.872427983539095e-05, | |
| "loss": 0.1558, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.2069, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 32.02, | |
| "learning_rate": 1.831275720164609e-05, | |
| "loss": 0.1633, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 32.02, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 7.34273099899292, | |
| "eval_runtime": 19.2376, | |
| "eval_samples_per_second": 7.069, | |
| "eval_steps_per_second": 1.196, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 1.8106995884773663e-05, | |
| "loss": 0.1313, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "learning_rate": 1.7901234567901236e-05, | |
| "loss": 0.1187, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "learning_rate": 1.769547325102881e-05, | |
| "loss": 0.1455, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "learning_rate": 1.748971193415638e-05, | |
| "loss": 0.0554, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "learning_rate": 1.728395061728395e-05, | |
| "loss": 0.1677, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "learning_rate": 1.7078189300411522e-05, | |
| "loss": 0.1902, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 7.409451484680176, | |
| "eval_runtime": 19.5055, | |
| "eval_samples_per_second": 6.972, | |
| "eval_steps_per_second": 1.179, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 1.6872427983539095e-05, | |
| "loss": 0.2543, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.1069, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 1.646090534979424e-05, | |
| "loss": 0.1131, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 1.6255144032921812e-05, | |
| "loss": 0.0825, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 34.02, | |
| "learning_rate": 1.604938271604938e-05, | |
| "loss": 0.132, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 34.02, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 7.31688928604126, | |
| "eval_runtime": 19.5592, | |
| "eval_samples_per_second": 6.953, | |
| "eval_steps_per_second": 1.176, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 1.5843621399176954e-05, | |
| "loss": 0.168, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 1.563786008230453e-05, | |
| "loss": 0.1214, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 1.54320987654321e-05, | |
| "loss": 0.0863, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 1.5226337448559672e-05, | |
| "loss": 0.1013, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 35.02, | |
| "learning_rate": 1.5020576131687244e-05, | |
| "loss": 0.0962, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 35.02, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.1226, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 35.02, | |
| "eval_accuracy": 0.007352941176470588, | |
| "eval_loss": 7.419619560241699, | |
| "eval_runtime": 19.4051, | |
| "eval_samples_per_second": 7.008, | |
| "eval_steps_per_second": 1.185, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 1.4609053497942387e-05, | |
| "loss": 0.0864, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 1.440329218106996e-05, | |
| "loss": 0.1085, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 1.419753086419753e-05, | |
| "loss": 0.105, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 1.3991769547325103e-05, | |
| "loss": 0.1557, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 36.02, | |
| "learning_rate": 1.3786008230452676e-05, | |
| "loss": 0.115, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 36.02, | |
| "eval_accuracy": 0.007352941176470588, | |
| "eval_loss": 7.324816703796387, | |
| "eval_runtime": 19.4998, | |
| "eval_samples_per_second": 6.974, | |
| "eval_steps_per_second": 1.18, | |
| "step": 2035 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "learning_rate": 1.3580246913580247e-05, | |
| "loss": 0.1213, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 1.3374485596707819e-05, | |
| "loss": 0.1438, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 1.3168724279835393e-05, | |
| "loss": 0.0898, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.0357, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "learning_rate": 1.2757201646090535e-05, | |
| "loss": 0.1411, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "learning_rate": 1.255144032921811e-05, | |
| "loss": 0.1348, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 7.131798267364502, | |
| "eval_runtime": 19.3599, | |
| "eval_samples_per_second": 7.025, | |
| "eval_steps_per_second": 1.188, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.079, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 1.2139917695473252e-05, | |
| "loss": 0.1512, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 1.1934156378600823e-05, | |
| "loss": 0.0962, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 1.1728395061728396e-05, | |
| "loss": 0.1232, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "learning_rate": 1.1522633744855968e-05, | |
| "loss": 0.1684, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 7.648235321044922, | |
| "eval_runtime": 19.5601, | |
| "eval_samples_per_second": 6.953, | |
| "eval_steps_per_second": 1.176, | |
| "step": 2145 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "learning_rate": 1.1316872427983539e-05, | |
| "loss": 0.1614, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0955, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 1.0905349794238684e-05, | |
| "loss": 0.1675, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 1.0699588477366255e-05, | |
| "loss": 0.1518, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "learning_rate": 1.0493827160493827e-05, | |
| "loss": 0.1098, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "learning_rate": 1.02880658436214e-05, | |
| "loss": 0.0722, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "eval_accuracy": 0.007352941176470588, | |
| "eval_loss": 7.594442844390869, | |
| "eval_runtime": 19.5713, | |
| "eval_samples_per_second": 6.949, | |
| "eval_steps_per_second": 1.175, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 1.008230452674897e-05, | |
| "loss": 0.1132, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "learning_rate": 9.876543209876543e-06, | |
| "loss": 0.127, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "learning_rate": 9.670781893004116e-06, | |
| "loss": 0.0605, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "learning_rate": 9.465020576131688e-06, | |
| "loss": 0.1263, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 40.02, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.1155, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 40.02, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 7.561499118804932, | |
| "eval_runtime": 19.559, | |
| "eval_samples_per_second": 6.953, | |
| "eval_steps_per_second": 1.176, | |
| "step": 2255 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "learning_rate": 9.053497942386832e-06, | |
| "loss": 0.1481, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 8.847736625514404e-06, | |
| "loss": 0.1293, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 8.641975308641975e-06, | |
| "loss": 0.102, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 8.436213991769547e-06, | |
| "loss": 0.1447, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 41.02, | |
| "learning_rate": 8.23045267489712e-06, | |
| "loss": 0.0593, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 41.02, | |
| "learning_rate": 8.02469135802469e-06, | |
| "loss": 0.1425, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 41.02, | |
| "eval_accuracy": 0.007352941176470588, | |
| "eval_loss": 7.645389556884766, | |
| "eval_runtime": 19.1466, | |
| "eval_samples_per_second": 7.103, | |
| "eval_steps_per_second": 1.201, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 7.818930041152265e-06, | |
| "loss": 0.0842, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 7.613168724279836e-06, | |
| "loss": 0.0962, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.1109, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 7.20164609053498e-06, | |
| "loss": 0.0989, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 42.02, | |
| "learning_rate": 6.995884773662552e-06, | |
| "loss": 0.1552, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 42.02, | |
| "eval_accuracy": 0.007352941176470588, | |
| "eval_loss": 7.477428436279297, | |
| "eval_runtime": 19.4448, | |
| "eval_samples_per_second": 6.994, | |
| "eval_steps_per_second": 1.183, | |
| "step": 2365 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 6.790123456790123e-06, | |
| "loss": 0.1492, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 6.584362139917697e-06, | |
| "loss": 0.095, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 6.3786008230452675e-06, | |
| "loss": 0.0934, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.1175, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "learning_rate": 5.967078189300412e-06, | |
| "loss": 0.1298, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "learning_rate": 5.761316872427984e-06, | |
| "loss": 0.1078, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "eval_accuracy": 0.007352941176470588, | |
| "eval_loss": 7.3990559577941895, | |
| "eval_runtime": 19.5393, | |
| "eval_samples_per_second": 6.96, | |
| "eval_steps_per_second": 1.177, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.1088, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 5.3497942386831275e-06, | |
| "loss": 0.1179, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 5.1440329218107e-06, | |
| "loss": 0.1019, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 4.938271604938272e-06, | |
| "loss": 0.0844, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 44.02, | |
| "learning_rate": 4.732510288065844e-06, | |
| "loss": 0.1169, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 44.02, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 7.32404899597168, | |
| "eval_runtime": 19.4463, | |
| "eval_samples_per_second": 6.994, | |
| "eval_steps_per_second": 1.183, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 4.526748971193416e-06, | |
| "loss": 0.1361, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "learning_rate": 4.3209876543209875e-06, | |
| "loss": 0.1422, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "learning_rate": 4.11522633744856e-06, | |
| "loss": 0.0732, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "learning_rate": 3.9094650205761325e-06, | |
| "loss": 0.0721, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 45.02, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.1091, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 45.02, | |
| "learning_rate": 3.497942386831276e-06, | |
| "loss": 0.1438, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 45.02, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 7.413323402404785, | |
| "eval_runtime": 19.5353, | |
| "eval_samples_per_second": 6.962, | |
| "eval_steps_per_second": 1.177, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 3.2921810699588483e-06, | |
| "loss": 0.0717, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 3.0864197530864196e-06, | |
| "loss": 0.1297, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 2.880658436213992e-06, | |
| "loss": 0.1206, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 2.6748971193415637e-06, | |
| "loss": 0.1094, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 46.02, | |
| "learning_rate": 2.469135802469136e-06, | |
| "loss": 0.1227, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 46.02, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 7.459200859069824, | |
| "eval_runtime": 19.303, | |
| "eval_samples_per_second": 7.046, | |
| "eval_steps_per_second": 1.192, | |
| "step": 2585 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "learning_rate": 2.263374485596708e-06, | |
| "loss": 0.1153, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 2.05761316872428e-06, | |
| "loss": 0.176, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.1049, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 1.6460905349794242e-06, | |
| "loss": 0.1194, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "learning_rate": 1.440329218106996e-06, | |
| "loss": 0.0728, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "learning_rate": 1.234567901234568e-06, | |
| "loss": 0.0716, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 7.55896520614624, | |
| "eval_runtime": 19.0159, | |
| "eval_samples_per_second": 7.152, | |
| "eval_steps_per_second": 1.21, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 1.02880658436214e-06, | |
| "loss": 0.0481, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "learning_rate": 8.230452674897121e-07, | |
| "loss": 0.1184, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "learning_rate": 6.17283950617284e-07, | |
| "loss": 0.1099, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "learning_rate": 4.1152263374485604e-07, | |
| "loss": 0.116, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "learning_rate": 2.0576131687242802e-07, | |
| "loss": 0.2077, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 7.570817947387695, | |
| "eval_runtime": 18.7229, | |
| "eval_samples_per_second": 7.264, | |
| "eval_steps_per_second": 1.228, | |
| "step": 2695 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0731, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.0, | |
| "eval_loss": 7.571016311645508, | |
| "eval_runtime": 18.9447, | |
| "eval_samples_per_second": 7.179, | |
| "eval_steps_per_second": 1.214, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "step": 2700, | |
| "total_flos": 2.0005037147340177e+19, | |
| "train_loss": 0.48081808435696144, | |
| "train_runtime": 9221.8295, | |
| "train_samples_per_second": 1.757, | |
| "train_steps_per_second": 0.293 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.2647058823529412, | |
| "eval_loss": 3.1971516609191895, | |
| "eval_runtime": 19.2309, | |
| "eval_samples_per_second": 7.072, | |
| "eval_steps_per_second": 1.196, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.2647058823529412, | |
| "eval_loss": 3.1971516609191895, | |
| "eval_runtime": 19.408, | |
| "eval_samples_per_second": 7.007, | |
| "eval_steps_per_second": 1.185, | |
| "step": 2700 | |
| } | |
| ], | |
| "max_steps": 2700, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 2.0005037147340177e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |