| { | |
| "best_metric": 0.6666666666666666, | |
| "best_model_checkpoint": "videomae-base-short-ssv2-finetuned-ct_cpc/checkpoint-47", | |
| "epoch": 48.01913043478261, | |
| "eval_steps": 500, | |
| "global_step": 2300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.347826086956522e-07, | |
| "loss": 2.0243, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8.695652173913044e-07, | |
| "loss": 1.8063, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.3043478260869566e-06, | |
| "loss": 1.6927, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.7391304347826088e-06, | |
| "loss": 1.4832, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.1202621459960938, | |
| "eval_runtime": 7.2119, | |
| "eval_samples_per_second": 8.32, | |
| "eval_steps_per_second": 1.387, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.173913043478261e-06, | |
| "loss": 1.3436, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 2.6086956521739132e-06, | |
| "loss": 1.2714, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.043478260869566e-06, | |
| "loss": 1.1191, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.4782608695652175e-06, | |
| "loss": 0.9807, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.91304347826087e-06, | |
| "loss": 1.32, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.050528645515442, | |
| "eval_runtime": 6.9232, | |
| "eval_samples_per_second": 8.667, | |
| "eval_steps_per_second": 1.444, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.347826086956522e-06, | |
| "loss": 1.0838, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 4.782608695652174e-06, | |
| "loss": 1.1624, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 5.2173913043478265e-06, | |
| "loss": 0.9414, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 5.652173913043479e-06, | |
| "loss": 1.2583, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 6.086956521739132e-06, | |
| "loss": 1.1539, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.0524587631225586, | |
| "eval_runtime": 7.8366, | |
| "eval_samples_per_second": 7.656, | |
| "eval_steps_per_second": 1.276, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 6.521739130434783e-06, | |
| "loss": 1.0695, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 6.956521739130435e-06, | |
| "loss": 0.9282, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 7.391304347826087e-06, | |
| "loss": 0.9621, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 7.82608695652174e-06, | |
| "loss": 1.2399, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.0353821516036987, | |
| "eval_runtime": 7.1279, | |
| "eval_samples_per_second": 8.418, | |
| "eval_steps_per_second": 1.403, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.260869565217392e-06, | |
| "loss": 1.1451, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 8.695652173913044e-06, | |
| "loss": 1.1118, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 9.130434782608697e-06, | |
| "loss": 1.1014, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 9.565217391304349e-06, | |
| "loss": 1.1536, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9928, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.0516277551651, | |
| "eval_runtime": 6.8144, | |
| "eval_samples_per_second": 8.805, | |
| "eval_steps_per_second": 1.467, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 9.95169082125604e-06, | |
| "loss": 1.1887, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 9.903381642512077e-06, | |
| "loss": 1.176, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 9.855072463768118e-06, | |
| "loss": 1.0889, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 9.806763285024155e-06, | |
| "loss": 0.8653, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 9.758454106280194e-06, | |
| "loss": 1.0054, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.0296636819839478, | |
| "eval_runtime": 6.8135, | |
| "eval_samples_per_second": 8.806, | |
| "eval_steps_per_second": 1.468, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 9.710144927536233e-06, | |
| "loss": 1.1702, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 9.66183574879227e-06, | |
| "loss": 1.0608, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 9.61352657004831e-06, | |
| "loss": 1.0026, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 9.565217391304349e-06, | |
| "loss": 1.1166, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.024717092514038, | |
| "eval_runtime": 6.7961, | |
| "eval_samples_per_second": 8.829, | |
| "eval_steps_per_second": 1.471, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 9.516908212560388e-06, | |
| "loss": 1.0851, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 9.468599033816425e-06, | |
| "loss": 0.9748, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 9.420289855072464e-06, | |
| "loss": 1.0743, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 9.371980676328503e-06, | |
| "loss": 0.9153, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 9.323671497584542e-06, | |
| "loss": 1.2715, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.0097945928573608, | |
| "eval_runtime": 6.7899, | |
| "eval_samples_per_second": 8.837, | |
| "eval_steps_per_second": 1.473, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9.275362318840581e-06, | |
| "loss": 0.9517, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 9.227053140096618e-06, | |
| "loss": 0.8985, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 9.178743961352658e-06, | |
| "loss": 1.1341, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 9.130434782608697e-06, | |
| "loss": 1.0505, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 9.082125603864736e-06, | |
| "loss": 1.0317, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.040429949760437, | |
| "eval_runtime": 6.9971, | |
| "eval_samples_per_second": 8.575, | |
| "eval_steps_per_second": 1.429, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 9.033816425120775e-06, | |
| "loss": 1.1947, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 8.985507246376812e-06, | |
| "loss": 0.9361, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 8.937198067632851e-06, | |
| "loss": 0.9432, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 1.0958, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 8.840579710144929e-06, | |
| "loss": 1.1258, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.0053784847259521, | |
| "eval_runtime": 7.1441, | |
| "eval_samples_per_second": 8.399, | |
| "eval_steps_per_second": 1.4, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 8.792270531400966e-06, | |
| "loss": 1.0206, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 8.743961352657005e-06, | |
| "loss": 1.0568, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 8.695652173913044e-06, | |
| "loss": 1.1054, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 8.647342995169082e-06, | |
| "loss": 0.8991, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.0477041006088257, | |
| "eval_runtime": 7.2799, | |
| "eval_samples_per_second": 8.242, | |
| "eval_steps_per_second": 1.374, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 8.599033816425122e-06, | |
| "loss": 1.167, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 8.55072463768116e-06, | |
| "loss": 0.9754, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 8.502415458937199e-06, | |
| "loss": 1.0365, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 8.454106280193238e-06, | |
| "loss": 0.9409, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 8.405797101449275e-06, | |
| "loss": 0.8957, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.0607702732086182, | |
| "eval_runtime": 6.9041, | |
| "eval_samples_per_second": 8.69, | |
| "eval_steps_per_second": 1.448, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 8.357487922705316e-06, | |
| "loss": 0.8378, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 8.309178743961353e-06, | |
| "loss": 0.8314, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 8.260869565217392e-06, | |
| "loss": 1.092, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 8.212560386473431e-06, | |
| "loss": 1.0079, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 8.164251207729469e-06, | |
| "loss": 1.078, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.0165636539459229, | |
| "eval_runtime": 7.648, | |
| "eval_samples_per_second": 7.845, | |
| "eval_steps_per_second": 1.308, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 8.115942028985508e-06, | |
| "loss": 0.8161, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 8.067632850241547e-06, | |
| "loss": 1.2458, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 8.019323671497586e-06, | |
| "loss": 0.9597, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 7.971014492753623e-06, | |
| "loss": 0.9067, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.2110427618026733, | |
| "eval_runtime": 7.2284, | |
| "eval_samples_per_second": 8.301, | |
| "eval_steps_per_second": 1.383, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 7.922705314009662e-06, | |
| "loss": 0.9322, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 7.874396135265701e-06, | |
| "loss": 0.993, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 7.82608695652174e-06, | |
| "loss": 0.7774, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 7.77777777777778e-06, | |
| "loss": 0.9399, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 7.729468599033817e-06, | |
| "loss": 1.0383, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 1.0380301475524902, | |
| "eval_runtime": 6.9013, | |
| "eval_samples_per_second": 8.694, | |
| "eval_steps_per_second": 1.449, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 7.681159420289856e-06, | |
| "loss": 0.7043, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 7.632850241545895e-06, | |
| "loss": 1.0185, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 7.584541062801934e-06, | |
| "loss": 0.9907, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 7.536231884057972e-06, | |
| "loss": 0.8602, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 7.48792270531401e-06, | |
| "loss": 1.2244, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 1.1040699481964111, | |
| "eval_runtime": 7.4605, | |
| "eval_samples_per_second": 8.042, | |
| "eval_steps_per_second": 1.34, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 7.439613526570049e-06, | |
| "loss": 0.9108, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 7.391304347826087e-06, | |
| "loss": 0.8811, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 7.342995169082127e-06, | |
| "loss": 0.8487, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 7.294685990338165e-06, | |
| "loss": 1.0364, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 1.0123381614685059, | |
| "eval_runtime": 6.8033, | |
| "eval_samples_per_second": 8.819, | |
| "eval_steps_per_second": 1.47, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 7.246376811594203e-06, | |
| "loss": 0.8189, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 7.1980676328502416e-06, | |
| "loss": 0.8733, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 7.149758454106281e-06, | |
| "loss": 0.6958, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 7.10144927536232e-06, | |
| "loss": 0.782, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 7.053140096618359e-06, | |
| "loss": 0.9662, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "eval_accuracy": 0.6333333333333333, | |
| "eval_loss": 1.1802695989608765, | |
| "eval_runtime": 7.2583, | |
| "eval_samples_per_second": 8.266, | |
| "eval_steps_per_second": 1.378, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 7.004830917874397e-06, | |
| "loss": 0.9205, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 6.956521739130435e-06, | |
| "loss": 0.8999, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 6.908212560386473e-06, | |
| "loss": 0.6096, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 6.859903381642513e-06, | |
| "loss": 0.79, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 6.811594202898551e-06, | |
| "loss": 0.9299, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "eval_accuracy": 0.6333333333333333, | |
| "eval_loss": 1.0910345315933228, | |
| "eval_runtime": 6.9398, | |
| "eval_samples_per_second": 8.646, | |
| "eval_steps_per_second": 1.441, | |
| "step": 893 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 6.76328502415459e-06, | |
| "loss": 0.8715, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 6.7149758454106285e-06, | |
| "loss": 0.8882, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.8562, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 6.6183574879227065e-06, | |
| "loss": 0.9704, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 6.570048309178745e-06, | |
| "loss": 0.877, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "eval_accuracy": 0.65, | |
| "eval_loss": 1.0182613134384155, | |
| "eval_runtime": 7.0493, | |
| "eval_samples_per_second": 8.511, | |
| "eval_steps_per_second": 1.419, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 6.521739130434783e-06, | |
| "loss": 0.8358, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 6.473429951690822e-06, | |
| "loss": 0.7785, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 6.42512077294686e-06, | |
| "loss": 0.7644, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "learning_rate": 6.376811594202898e-06, | |
| "loss": 0.8649, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_loss": 1.1414852142333984, | |
| "eval_runtime": 7.0701, | |
| "eval_samples_per_second": 8.486, | |
| "eval_steps_per_second": 1.414, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 6.328502415458938e-06, | |
| "loss": 0.8795, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 6.280193236714976e-06, | |
| "loss": 0.7464, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 6.2318840579710145e-06, | |
| "loss": 0.7973, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 6.1835748792270535e-06, | |
| "loss": 0.9681, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 6.135265700483092e-06, | |
| "loss": 0.8841, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "eval_accuracy": 0.6333333333333333, | |
| "eval_loss": 1.0975487232208252, | |
| "eval_runtime": 7.726, | |
| "eval_samples_per_second": 7.766, | |
| "eval_steps_per_second": 1.294, | |
| "step": 1034 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 6.086956521739132e-06, | |
| "loss": 0.6596, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 6.03864734299517e-06, | |
| "loss": 0.7252, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 5.990338164251208e-06, | |
| "loss": 0.7564, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "learning_rate": 5.942028985507247e-06, | |
| "loss": 0.7406, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "learning_rate": 5.893719806763285e-06, | |
| "loss": 0.6276, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 1.072813868522644, | |
| "eval_runtime": 7.252, | |
| "eval_samples_per_second": 8.274, | |
| "eval_steps_per_second": 1.379, | |
| "step": 1081 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 5.845410628019324e-06, | |
| "loss": 0.7456, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 5.797101449275363e-06, | |
| "loss": 0.5497, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 5.748792270531401e-06, | |
| "loss": 0.875, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "learning_rate": 5.70048309178744e-06, | |
| "loss": 0.7974, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.1675584316253662, | |
| "eval_runtime": 6.8242, | |
| "eval_samples_per_second": 8.792, | |
| "eval_steps_per_second": 1.465, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 5.652173913043479e-06, | |
| "loss": 0.8186, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 5.603864734299518e-06, | |
| "loss": 0.7628, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 0.4592, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 5.507246376811595e-06, | |
| "loss": 0.6761, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "learning_rate": 5.458937198067633e-06, | |
| "loss": 0.7381, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "eval_accuracy": 0.55, | |
| "eval_loss": 1.1623855829238892, | |
| "eval_runtime": 6.815, | |
| "eval_samples_per_second": 8.804, | |
| "eval_steps_per_second": 1.467, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 5.410628019323671e-06, | |
| "loss": 0.8723, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 5.362318840579711e-06, | |
| "loss": 0.6832, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 5.314009661835749e-06, | |
| "loss": 0.7768, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "learning_rate": 5.265700483091788e-06, | |
| "loss": 0.6568, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "learning_rate": 5.2173913043478265e-06, | |
| "loss": 0.4807, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "eval_accuracy": 0.55, | |
| "eval_loss": 1.1929564476013184, | |
| "eval_runtime": 6.8394, | |
| "eval_samples_per_second": 8.773, | |
| "eval_steps_per_second": 1.462, | |
| "step": 1222 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 5.169082125603865e-06, | |
| "loss": 0.7603, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 5.1207729468599045e-06, | |
| "loss": 0.647, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 5.072463768115943e-06, | |
| "loss": 0.67, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "learning_rate": 5.024154589371981e-06, | |
| "loss": 0.6812, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 1.1511147022247314, | |
| "eval_runtime": 7.0933, | |
| "eval_samples_per_second": 8.459, | |
| "eval_steps_per_second": 1.41, | |
| "step": 1269 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 4.97584541062802e-06, | |
| "loss": 0.6945, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 4.927536231884059e-06, | |
| "loss": 0.6031, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 4.879227053140097e-06, | |
| "loss": 0.659, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 4.830917874396135e-06, | |
| "loss": 0.659, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 4.782608695652174e-06, | |
| "loss": 0.5802, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_loss": 1.2314832210540771, | |
| "eval_runtime": 7.5214, | |
| "eval_samples_per_second": 7.977, | |
| "eval_steps_per_second": 1.33, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 4.7342995169082125e-06, | |
| "loss": 0.5988, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "learning_rate": 4.6859903381642516e-06, | |
| "loss": 0.6461, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "learning_rate": 4.637681159420291e-06, | |
| "loss": 0.729, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "learning_rate": 4.589371980676329e-06, | |
| "loss": 0.5582, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "learning_rate": 4.541062801932368e-06, | |
| "loss": 0.5943, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_loss": 1.1640959978103638, | |
| "eval_runtime": 7.4811, | |
| "eval_samples_per_second": 8.02, | |
| "eval_steps_per_second": 1.337, | |
| "step": 1363 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 4.492753623188406e-06, | |
| "loss": 0.4759, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 0.7748, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 4.396135265700483e-06, | |
| "loss": 0.5033, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 4.347826086956522e-06, | |
| "loss": 0.8771, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 4.299516908212561e-06, | |
| "loss": 0.5416, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 1.0962903499603271, | |
| "eval_runtime": 7.0002, | |
| "eval_samples_per_second": 8.571, | |
| "eval_steps_per_second": 1.429, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 4.251207729468599e-06, | |
| "loss": 0.6134, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 4.202898550724638e-06, | |
| "loss": 0.5366, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 4.154589371980677e-06, | |
| "loss": 0.5575, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "learning_rate": 4.106280193236716e-06, | |
| "loss": 0.6676, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_loss": 1.1130536794662476, | |
| "eval_runtime": 7.3167, | |
| "eval_samples_per_second": 8.2, | |
| "eval_steps_per_second": 1.367, | |
| "step": 1457 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 4.057971014492754e-06, | |
| "loss": 0.5169, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 4.009661835748793e-06, | |
| "loss": 0.5593, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 3.961352657004831e-06, | |
| "loss": 0.7655, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 3.91304347826087e-06, | |
| "loss": 0.6803, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 31.02, | |
| "learning_rate": 3.864734299516908e-06, | |
| "loss": 0.4085, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 31.02, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.2947934865951538, | |
| "eval_runtime": 6.9055, | |
| "eval_samples_per_second": 8.689, | |
| "eval_steps_per_second": 1.448, | |
| "step": 1504 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 3.816425120772947e-06, | |
| "loss": 0.7962, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 3.768115942028986e-06, | |
| "loss": 0.742, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 3.7198067632850245e-06, | |
| "loss": 0.4275, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 32.02, | |
| "learning_rate": 3.6714975845410635e-06, | |
| "loss": 0.6044, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 32.02, | |
| "learning_rate": 3.6231884057971017e-06, | |
| "loss": 0.4548, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 32.02, | |
| "eval_accuracy": 0.6333333333333333, | |
| "eval_loss": 1.2788442373275757, | |
| "eval_runtime": 6.7575, | |
| "eval_samples_per_second": 8.879, | |
| "eval_steps_per_second": 1.48, | |
| "step": 1551 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 3.5748792270531403e-06, | |
| "loss": 0.7688, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "learning_rate": 3.5265700483091793e-06, | |
| "loss": 0.489, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "learning_rate": 3.4782608695652175e-06, | |
| "loss": 0.545, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "learning_rate": 3.4299516908212565e-06, | |
| "loss": 0.4351, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_loss": 1.1921883821487427, | |
| "eval_runtime": 6.9013, | |
| "eval_samples_per_second": 8.694, | |
| "eval_steps_per_second": 1.449, | |
| "step": 1598 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 3.381642512077295e-06, | |
| "loss": 0.5118, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.5212, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 3.2850241545893724e-06, | |
| "loss": 0.3797, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 3.236714975845411e-06, | |
| "loss": 0.5177, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 34.02, | |
| "learning_rate": 3.188405797101449e-06, | |
| "loss": 0.5641, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 34.02, | |
| "eval_accuracy": 0.55, | |
| "eval_loss": 1.267711877822876, | |
| "eval_runtime": 7.3036, | |
| "eval_samples_per_second": 8.215, | |
| "eval_steps_per_second": 1.369, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 3.140096618357488e-06, | |
| "loss": 0.3153, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 3.0917874396135268e-06, | |
| "loss": 0.4103, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 3.043478260869566e-06, | |
| "loss": 0.503, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 35.02, | |
| "learning_rate": 2.995169082125604e-06, | |
| "loss": 0.5921, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 35.02, | |
| "learning_rate": 2.9468599033816426e-06, | |
| "loss": 0.4471, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 35.02, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_loss": 1.2765668630599976, | |
| "eval_runtime": 7.0911, | |
| "eval_samples_per_second": 8.461, | |
| "eval_steps_per_second": 1.41, | |
| "step": 1692 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 2.8985507246376816e-06, | |
| "loss": 0.4534, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 2.85024154589372e-06, | |
| "loss": 0.4072, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 2.801932367149759e-06, | |
| "loss": 0.4057, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 36.02, | |
| "learning_rate": 2.7536231884057974e-06, | |
| "loss": 0.361, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 36.02, | |
| "eval_accuracy": 0.55, | |
| "eval_loss": 1.2524678707122803, | |
| "eval_runtime": 7.3291, | |
| "eval_samples_per_second": 8.187, | |
| "eval_steps_per_second": 1.364, | |
| "step": 1739 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "learning_rate": 2.7053140096618356e-06, | |
| "loss": 0.5294, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "learning_rate": 2.6570048309178746e-06, | |
| "loss": 0.4, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 2.6086956521739132e-06, | |
| "loss": 0.4891, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 2.5603864734299523e-06, | |
| "loss": 0.3458, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "learning_rate": 2.5120772946859904e-06, | |
| "loss": 0.5668, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "eval_accuracy": 0.55, | |
| "eval_loss": 1.292838454246521, | |
| "eval_runtime": 7.1147, | |
| "eval_samples_per_second": 8.433, | |
| "eval_steps_per_second": 1.406, | |
| "step": 1786 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 2.4637681159420295e-06, | |
| "loss": 0.4136, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 2.4154589371980677e-06, | |
| "loss": 0.6028, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 2.3671497584541063e-06, | |
| "loss": 0.4004, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 2.3188405797101453e-06, | |
| "loss": 0.4186, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "learning_rate": 2.270531400966184e-06, | |
| "loss": 0.5262, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "eval_accuracy": 0.6333333333333333, | |
| "eval_loss": 1.2428669929504395, | |
| "eval_runtime": 7.0978, | |
| "eval_samples_per_second": 8.453, | |
| "eval_steps_per_second": 1.409, | |
| "step": 1833 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 0.4642, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 2.173913043478261e-06, | |
| "loss": 0.485, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 2.1256038647342997e-06, | |
| "loss": 0.3757, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "learning_rate": 2.0772946859903383e-06, | |
| "loss": 0.5197, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "learning_rate": 2.028985507246377e-06, | |
| "loss": 0.4901, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "eval_accuracy": 0.5666666666666667, | |
| "eval_loss": 1.1457266807556152, | |
| "eval_runtime": 7.0788, | |
| "eval_samples_per_second": 8.476, | |
| "eval_steps_per_second": 1.413, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 1.9806763285024155e-06, | |
| "loss": 0.432, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "learning_rate": 1.932367149758454e-06, | |
| "loss": 0.3237, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "learning_rate": 1.884057971014493e-06, | |
| "loss": 0.3166, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 40.02, | |
| "learning_rate": 1.8357487922705318e-06, | |
| "loss": 0.481, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 40.02, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.213700771331787, | |
| "eval_runtime": 7.0464, | |
| "eval_samples_per_second": 8.515, | |
| "eval_steps_per_second": 1.419, | |
| "step": 1927 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "learning_rate": 1.7874396135265702e-06, | |
| "loss": 0.3313, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 1.7391304347826088e-06, | |
| "loss": 0.4095, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 1.6908212560386476e-06, | |
| "loss": 0.4013, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 1.6425120772946862e-06, | |
| "loss": 0.453, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 41.02, | |
| "learning_rate": 1.5942028985507246e-06, | |
| "loss": 0.3566, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 41.02, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_loss": 1.1829572916030884, | |
| "eval_runtime": 7.0773, | |
| "eval_samples_per_second": 8.478, | |
| "eval_steps_per_second": 1.413, | |
| "step": 1974 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 1.5458937198067634e-06, | |
| "loss": 0.342, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 1.497584541062802e-06, | |
| "loss": 0.2666, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 1.4492753623188408e-06, | |
| "loss": 0.4153, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 42.02, | |
| "learning_rate": 1.4009661835748794e-06, | |
| "loss": 0.3853, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 42.02, | |
| "learning_rate": 1.3526570048309178e-06, | |
| "loss": 0.5147, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 42.02, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 1.1628528833389282, | |
| "eval_runtime": 6.9693, | |
| "eval_samples_per_second": 8.609, | |
| "eval_steps_per_second": 1.435, | |
| "step": 2021 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 1.3043478260869566e-06, | |
| "loss": 0.5075, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 1.2560386473429952e-06, | |
| "loss": 0.3599, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 1.2077294685990338e-06, | |
| "loss": 0.3602, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "learning_rate": 1.1594202898550726e-06, | |
| "loss": 0.4013, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 1.2734596729278564, | |
| "eval_runtime": 7.5005, | |
| "eval_samples_per_second": 8.0, | |
| "eval_steps_per_second": 1.333, | |
| "step": 2068 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 1.111111111111111e-06, | |
| "loss": 0.1829, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 1.0628019323671499e-06, | |
| "loss": 0.3784, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 1.0144927536231885e-06, | |
| "loss": 0.3492, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 9.66183574879227e-07, | |
| "loss": 0.3413, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 44.02, | |
| "learning_rate": 9.178743961352659e-07, | |
| "loss": 0.3895, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 44.02, | |
| "eval_accuracy": 0.6166666666666667, | |
| "eval_loss": 1.275781273841858, | |
| "eval_runtime": 7.0795, | |
| "eval_samples_per_second": 8.475, | |
| "eval_steps_per_second": 1.413, | |
| "step": 2115 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 8.695652173913044e-07, | |
| "loss": 0.2765, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "learning_rate": 8.212560386473431e-07, | |
| "loss": 0.3307, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "learning_rate": 7.729468599033817e-07, | |
| "loss": 0.4263, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 45.02, | |
| "learning_rate": 7.246376811594204e-07, | |
| "loss": 0.2821, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 45.02, | |
| "learning_rate": 6.763285024154589e-07, | |
| "loss": 0.3727, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 45.02, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.251878023147583, | |
| "eval_runtime": 6.9821, | |
| "eval_samples_per_second": 8.593, | |
| "eval_steps_per_second": 1.432, | |
| "step": 2162 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 6.280193236714976e-07, | |
| "loss": 0.2848, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 5.797101449275363e-07, | |
| "loss": 0.3064, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 5.314009661835749e-07, | |
| "loss": 0.2802, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 46.02, | |
| "learning_rate": 4.830917874396135e-07, | |
| "loss": 0.2379, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 46.02, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.2318103313446045, | |
| "eval_runtime": 7.4568, | |
| "eval_samples_per_second": 8.046, | |
| "eval_steps_per_second": 1.341, | |
| "step": 2209 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "learning_rate": 4.347826086956522e-07, | |
| "loss": 0.3444, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "learning_rate": 3.8647342995169085e-07, | |
| "loss": 0.3964, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 3.3816425120772945e-07, | |
| "loss": 0.218, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 2.8985507246376816e-07, | |
| "loss": 0.4576, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "learning_rate": 2.4154589371980677e-07, | |
| "loss": 0.2985, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.2594045400619507, | |
| "eval_runtime": 6.9353, | |
| "eval_samples_per_second": 8.651, | |
| "eval_steps_per_second": 1.442, | |
| "step": 2256 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 1.9323671497584542e-07, | |
| "loss": 0.359, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "learning_rate": 1.4492753623188408e-07, | |
| "loss": 0.3572, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "learning_rate": 9.661835748792271e-08, | |
| "loss": 0.4208, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "learning_rate": 4.8309178743961356e-08, | |
| "loss": 0.3265, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "learning_rate": 0.0, | |
| "loss": 0.2991, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "eval_accuracy": 0.5833333333333334, | |
| "eval_loss": 1.2510361671447754, | |
| "eval_runtime": 6.9183, | |
| "eval_samples_per_second": 8.673, | |
| "eval_steps_per_second": 1.445, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "step": 2300, | |
| "total_flos": 1.7136338694977618e+19, | |
| "train_loss": 0.7374556654950847, | |
| "train_runtime": 3025.2001, | |
| "train_samples_per_second": 4.562, | |
| "train_steps_per_second": 0.76 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "eval_accuracy": 0.6507936507936508, | |
| "eval_loss": 1.1547213792800903, | |
| "eval_runtime": 9.0552, | |
| "eval_samples_per_second": 6.957, | |
| "eval_steps_per_second": 1.215, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "eval_accuracy": 0.6507936507936508, | |
| "eval_loss": 1.1547214984893799, | |
| "eval_runtime": 7.9277, | |
| "eval_samples_per_second": 7.947, | |
| "eval_steps_per_second": 1.388, | |
| "step": 2300 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2300, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 1.7136338694977618e+19, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |