| { | |
| "best_metric": 0.84, | |
| "best_model_checkpoint": "MAE-CT-CPC-Dicotomized-v6-Day1/checkpoint-896", | |
| "epoch": 49.00218181818182, | |
| "eval_steps": 500, | |
| "global_step": 2750, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.6363636363636366e-07, | |
| "loss": 0.7109, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.272727272727273e-07, | |
| "loss": 0.6964, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.090909090909091e-06, | |
| "loss": 0.6618, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.4545454545454546e-06, | |
| "loss": 0.6946, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.8181818181818183e-06, | |
| "loss": 0.638, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_accuracy": 0.64, | |
| "eval_loss": 0.6488345265388489, | |
| "eval_runtime": 5.4784, | |
| "eval_samples_per_second": 4.563, | |
| "eval_steps_per_second": 1.278, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.181818181818182e-06, | |
| "loss": 0.6898, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 2.5454545454545456e-06, | |
| "loss": 0.6249, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 2.9090909090909093e-06, | |
| "loss": 0.5873, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.272727272727273e-06, | |
| "loss": 0.6824, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.6363636363636366e-06, | |
| "loss": 0.5355, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.7032, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_accuracy": 0.64, | |
| "eval_loss": 0.6394311785697937, | |
| "eval_runtime": 5.0835, | |
| "eval_samples_per_second": 4.918, | |
| "eval_steps_per_second": 1.377, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.363636363636364e-06, | |
| "loss": 0.6825, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 4.727272727272728e-06, | |
| "loss": 0.5733, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 5.090909090909091e-06, | |
| "loss": 0.6115, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 5.4545454545454545e-06, | |
| "loss": 0.5805, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 5.8181818181818185e-06, | |
| "loss": 0.6243, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_accuracy": 0.64, | |
| "eval_loss": 0.5943312048912048, | |
| "eval_runtime": 5.0387, | |
| "eval_samples_per_second": 4.962, | |
| "eval_steps_per_second": 1.389, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 6.181818181818182e-06, | |
| "loss": 0.6231, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 6.545454545454546e-06, | |
| "loss": 0.5273, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 6.90909090909091e-06, | |
| "loss": 0.4817, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 7.272727272727273e-06, | |
| "loss": 0.647, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 7.636363636363638e-06, | |
| "loss": 0.5636, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.6339, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "eval_accuracy": 0.6, | |
| "eval_loss": 0.6504328846931458, | |
| "eval_runtime": 4.8576, | |
| "eval_samples_per_second": 5.147, | |
| "eval_steps_per_second": 1.441, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.363636363636365e-06, | |
| "loss": 0.5425, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 8.727272727272728e-06, | |
| "loss": 0.5086, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 0.5566, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 9.454545454545456e-06, | |
| "loss": 0.7499, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 9.81818181818182e-06, | |
| "loss": 0.524, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 9.97979797979798e-06, | |
| "loss": 0.6566, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "eval_accuracy": 0.64, | |
| "eval_loss": 0.6404885649681091, | |
| "eval_runtime": 4.8837, | |
| "eval_samples_per_second": 5.119, | |
| "eval_steps_per_second": 1.433, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 9.939393939393939e-06, | |
| "loss": 0.5201, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 9.8989898989899e-06, | |
| "loss": 0.6411, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 9.85858585858586e-06, | |
| "loss": 0.4865, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 9.81818181818182e-06, | |
| "loss": 0.5733, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 9.777777777777779e-06, | |
| "loss": 0.4056, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "eval_accuracy": 0.64, | |
| "eval_loss": 0.6274449825286865, | |
| "eval_runtime": 5.0813, | |
| "eval_samples_per_second": 4.92, | |
| "eval_steps_per_second": 1.378, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 9.737373737373738e-06, | |
| "loss": 0.7089, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 9.696969696969698e-06, | |
| "loss": 0.5468, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 9.656565656565657e-06, | |
| "loss": 0.5937, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 9.616161616161616e-06, | |
| "loss": 0.4663, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 9.575757575757576e-06, | |
| "loss": 0.5177, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 9.535353535353537e-06, | |
| "loss": 0.3523, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "eval_accuracy": 0.64, | |
| "eval_loss": 0.9109216928482056, | |
| "eval_runtime": 5.0266, | |
| "eval_samples_per_second": 4.974, | |
| "eval_steps_per_second": 1.393, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 9.494949494949497e-06, | |
| "loss": 0.6953, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 9.454545454545456e-06, | |
| "loss": 0.4354, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 9.414141414141414e-06, | |
| "loss": 0.3926, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 9.373737373737375e-06, | |
| "loss": 0.4058, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 9.333333333333334e-06, | |
| "loss": 0.4581, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 0.4675277769565582, | |
| "eval_runtime": 5.0375, | |
| "eval_samples_per_second": 4.963, | |
| "eval_steps_per_second": 1.39, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9.292929292929294e-06, | |
| "loss": 0.597, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 9.252525252525253e-06, | |
| "loss": 0.4385, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 9.212121212121213e-06, | |
| "loss": 0.687, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 9.171717171717172e-06, | |
| "loss": 0.6669, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 9.131313131313132e-06, | |
| "loss": 0.5107, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 0.3648, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "eval_accuracy": 0.76, | |
| "eval_loss": 0.5780391693115234, | |
| "eval_runtime": 4.9069, | |
| "eval_samples_per_second": 5.095, | |
| "eval_steps_per_second": 1.427, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 9.050505050505052e-06, | |
| "loss": 0.2305, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 9.010101010101012e-06, | |
| "loss": 0.2993, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 8.969696969696971e-06, | |
| "loss": 0.4265, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 8.92929292929293e-06, | |
| "loss": 0.6946, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 8.888888888888888e-06, | |
| "loss": 0.4191, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 8.84848484848485e-06, | |
| "loss": 0.4622, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "eval_accuracy": 0.64, | |
| "eval_loss": 1.1120274066925049, | |
| "eval_runtime": 4.935, | |
| "eval_samples_per_second": 5.066, | |
| "eval_steps_per_second": 1.418, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 8.808080808080809e-06, | |
| "loss": 0.2502, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 8.767676767676768e-06, | |
| "loss": 0.2656, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 8.727272727272728e-06, | |
| "loss": 0.3627, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 8.686868686868687e-06, | |
| "loss": 0.4858, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 8.646464646464647e-06, | |
| "loss": 0.5836, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "eval_accuracy": 0.76, | |
| "eval_loss": 0.6369267106056213, | |
| "eval_runtime": 4.9248, | |
| "eval_samples_per_second": 5.076, | |
| "eval_steps_per_second": 1.421, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 8.606060606060606e-06, | |
| "loss": 0.3714, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 8.565656565656566e-06, | |
| "loss": 0.4537, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 8.525252525252527e-06, | |
| "loss": 0.1579, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 8.484848484848486e-06, | |
| "loss": 0.2635, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 8.444444444444446e-06, | |
| "loss": 0.7146, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 8.404040404040405e-06, | |
| "loss": 0.316, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "eval_accuracy": 0.64, | |
| "eval_loss": 0.8768600225448608, | |
| "eval_runtime": 4.9305, | |
| "eval_samples_per_second": 5.07, | |
| "eval_steps_per_second": 1.42, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 8.363636363636365e-06, | |
| "loss": 0.2406, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 8.323232323232324e-06, | |
| "loss": 0.0525, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 8.282828282828283e-06, | |
| "loss": 0.5016, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 8.242424242424243e-06, | |
| "loss": 0.4659, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 8.202020202020202e-06, | |
| "loss": 0.135, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "eval_accuracy": 0.72, | |
| "eval_loss": 0.6826868653297424, | |
| "eval_runtime": 4.9197, | |
| "eval_samples_per_second": 5.082, | |
| "eval_steps_per_second": 1.423, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 8.161616161616162e-06, | |
| "loss": 0.181, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 8.121212121212121e-06, | |
| "loss": 0.2238, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 8.08080808080808e-06, | |
| "loss": 0.2347, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 8.04040404040404e-06, | |
| "loss": 0.2645, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.487, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 7.95959595959596e-06, | |
| "loss": 0.0817, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "eval_accuracy": 0.64, | |
| "eval_loss": 0.9666504859924316, | |
| "eval_runtime": 5.0166, | |
| "eval_samples_per_second": 4.983, | |
| "eval_steps_per_second": 1.395, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 7.91919191919192e-06, | |
| "loss": 0.1581, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 7.87878787878788e-06, | |
| "loss": 0.1313, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 7.838383838383839e-06, | |
| "loss": 0.1097, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 7.797979797979799e-06, | |
| "loss": 0.108, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 7.757575757575758e-06, | |
| "loss": 0.0504, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 7.717171717171717e-06, | |
| "loss": 0.5254, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "eval_accuracy": 0.76, | |
| "eval_loss": 0.7441825866699219, | |
| "eval_runtime": 4.9503, | |
| "eval_samples_per_second": 5.05, | |
| "eval_steps_per_second": 1.414, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 7.676767676767677e-06, | |
| "loss": 0.1904, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 7.636363636363638e-06, | |
| "loss": 0.2687, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 7.595959595959597e-06, | |
| "loss": 0.2626, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 7.555555555555556e-06, | |
| "loss": 0.5363, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 7.515151515151516e-06, | |
| "loss": 0.2692, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "eval_accuracy": 0.84, | |
| "eval_loss": 0.5944011211395264, | |
| "eval_runtime": 4.7556, | |
| "eval_samples_per_second": 5.257, | |
| "eval_steps_per_second": 1.472, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 7.474747474747476e-06, | |
| "loss": 0.0987, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 7.434343434343435e-06, | |
| "loss": 0.0755, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 7.393939393939395e-06, | |
| "loss": 0.1298, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 7.353535353535353e-06, | |
| "loss": 0.6588, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 7.3131313131313146e-06, | |
| "loss": 0.0705, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 7.272727272727273e-06, | |
| "loss": 0.0177, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "eval_accuracy": 0.76, | |
| "eval_loss": 1.0163482427597046, | |
| "eval_runtime": 4.846, | |
| "eval_samples_per_second": 5.159, | |
| "eval_steps_per_second": 1.444, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 7.232323232323233e-06, | |
| "loss": 0.0157, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 7.191919191919192e-06, | |
| "loss": 0.1494, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 7.151515151515152e-06, | |
| "loss": 0.2343, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 7.111111111111112e-06, | |
| "loss": 0.0901, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 7.070707070707071e-06, | |
| "loss": 0.0386, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "eval_accuracy": 0.76, | |
| "eval_loss": 0.8789149522781372, | |
| "eval_runtime": 4.9461, | |
| "eval_samples_per_second": 5.055, | |
| "eval_steps_per_second": 1.415, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 7.030303030303031e-06, | |
| "loss": 0.0011, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 6.98989898989899e-06, | |
| "loss": 0.1129, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 6.9494949494949505e-06, | |
| "loss": 0.0008, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 6.90909090909091e-06, | |
| "loss": 0.0014, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 6.868686868686869e-06, | |
| "loss": 0.0303, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 6.828282828282828e-06, | |
| "loss": 0.2142, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "eval_accuracy": 0.68, | |
| "eval_loss": 1.0579525232315063, | |
| "eval_runtime": 4.9373, | |
| "eval_samples_per_second": 5.064, | |
| "eval_steps_per_second": 1.418, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 6.787878787878789e-06, | |
| "loss": 0.0012, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 6.747474747474749e-06, | |
| "loss": 0.005, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 6.707070707070707e-06, | |
| "loss": 0.0008, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.1648, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 6.626262626262627e-06, | |
| "loss": 0.0897, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 6.585858585858586e-06, | |
| "loss": 0.0653, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "eval_accuracy": 0.72, | |
| "eval_loss": 0.9189437627792358, | |
| "eval_runtime": 4.9929, | |
| "eval_samples_per_second": 5.007, | |
| "eval_steps_per_second": 1.402, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 6.545454545454546e-06, | |
| "loss": 0.0044, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 6.505050505050505e-06, | |
| "loss": 0.0012, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 6.464646464646466e-06, | |
| "loss": 0.006, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "learning_rate": 6.424242424242425e-06, | |
| "loss": 0.0005, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "learning_rate": 6.3838383838383845e-06, | |
| "loss": 0.0004, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 20.02, | |
| "eval_accuracy": 0.76, | |
| "eval_loss": 1.1912809610366821, | |
| "eval_runtime": 5.1317, | |
| "eval_samples_per_second": 4.872, | |
| "eval_steps_per_second": 1.364, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 6.343434343434344e-06, | |
| "loss": 0.0004, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 6.303030303030303e-06, | |
| "loss": 0.0024, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 6.262626262626264e-06, | |
| "loss": 0.0345, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "learning_rate": 6.222222222222223e-06, | |
| "loss": 0.0003, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 6.181818181818182e-06, | |
| "loss": 0.0003, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "learning_rate": 6.141414141414141e-06, | |
| "loss": 0.0006, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 21.02, | |
| "eval_accuracy": 0.72, | |
| "eval_loss": 1.1668070554733276, | |
| "eval_runtime": 5.1021, | |
| "eval_samples_per_second": 4.9, | |
| "eval_steps_per_second": 1.372, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 6.1010101010101015e-06, | |
| "loss": 0.0356, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 6.060606060606061e-06, | |
| "loss": 0.0005, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 6.0202020202020204e-06, | |
| "loss": 0.0013, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 5.97979797979798e-06, | |
| "loss": 0.1359, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "learning_rate": 5.93939393939394e-06, | |
| "loss": 0.0006, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "eval_accuracy": 0.76, | |
| "eval_loss": 1.2781660556793213, | |
| "eval_runtime": 5.0836, | |
| "eval_samples_per_second": 4.918, | |
| "eval_steps_per_second": 1.377, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 5.8989898989899e-06, | |
| "loss": 0.0003, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 5.858585858585859e-06, | |
| "loss": 0.0005, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 5.8181818181818185e-06, | |
| "loss": 0.0015, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "learning_rate": 5.777777777777778e-06, | |
| "loss": 0.0003, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "learning_rate": 5.737373737373738e-06, | |
| "loss": 0.0004, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "learning_rate": 5.696969696969698e-06, | |
| "loss": 0.0003, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 23.02, | |
| "eval_accuracy": 0.76, | |
| "eval_loss": 1.259096622467041, | |
| "eval_runtime": 5.0958, | |
| "eval_samples_per_second": 4.906, | |
| "eval_steps_per_second": 1.374, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 5.656565656565657e-06, | |
| "loss": 0.0002, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 5.616161616161616e-06, | |
| "loss": 0.0002, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 5.575757575757577e-06, | |
| "loss": 0.0002, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "learning_rate": 5.5353535353535355e-06, | |
| "loss": 0.0026, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "learning_rate": 5.494949494949495e-06, | |
| "loss": 0.1444, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "learning_rate": 5.4545454545454545e-06, | |
| "loss": 0.0004, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 24.02, | |
| "eval_accuracy": 0.72, | |
| "eval_loss": 1.5767698287963867, | |
| "eval_runtime": 5.2043, | |
| "eval_samples_per_second": 4.804, | |
| "eval_steps_per_second": 1.345, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 5.414141414141415e-06, | |
| "loss": 0.3487, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 5.373737373737374e-06, | |
| "loss": 0.0664, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 5.333333333333334e-06, | |
| "loss": 0.0134, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "learning_rate": 5.292929292929293e-06, | |
| "loss": 0.0905, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "learning_rate": 5.252525252525253e-06, | |
| "loss": 0.0431, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 25.02, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 1.1631672382354736, | |
| "eval_runtime": 5.2489, | |
| "eval_samples_per_second": 4.763, | |
| "eval_steps_per_second": 1.334, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 5.212121212121213e-06, | |
| "loss": 0.0004, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 5.171717171717172e-06, | |
| "loss": 0.0004, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 5.131313131313132e-06, | |
| "loss": 0.0002, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "learning_rate": 5.090909090909091e-06, | |
| "loss": 0.1211, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "learning_rate": 5.0505050505050515e-06, | |
| "loss": 0.0002, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "learning_rate": 5.010101010101011e-06, | |
| "loss": 0.008, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 26.02, | |
| "eval_accuracy": 0.76, | |
| "eval_loss": 1.4113043546676636, | |
| "eval_runtime": 5.0102, | |
| "eval_samples_per_second": 4.99, | |
| "eval_steps_per_second": 1.397, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 4.9696969696969696e-06, | |
| "loss": 0.0002, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 4.92929292929293e-06, | |
| "loss": 0.0003, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 4.888888888888889e-06, | |
| "loss": 0.0002, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "learning_rate": 4.848484848484849e-06, | |
| "loss": 0.0001, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "learning_rate": 4.808080808080808e-06, | |
| "loss": 0.0003, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 27.02, | |
| "eval_accuracy": 0.76, | |
| "eval_loss": 1.2238938808441162, | |
| "eval_runtime": 4.9902, | |
| "eval_samples_per_second": 5.01, | |
| "eval_steps_per_second": 1.403, | |
| "step": 1568 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 4.7676767676767685e-06, | |
| "loss": 0.0001, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 4.727272727272728e-06, | |
| "loss": 0.0001, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "learning_rate": 4.6868686868686874e-06, | |
| "loss": 0.0002, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "learning_rate": 4.646464646464647e-06, | |
| "loss": 0.0193, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "learning_rate": 4.606060606060606e-06, | |
| "loss": 0.0072, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "learning_rate": 4.565656565656566e-06, | |
| "loss": 0.003, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "eval_accuracy": 0.72, | |
| "eval_loss": 1.719529151916504, | |
| "eval_runtime": 5.0061, | |
| "eval_samples_per_second": 4.994, | |
| "eval_steps_per_second": 1.398, | |
| "step": 1624 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 4.525252525252526e-06, | |
| "loss": 0.0002, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 4.4848484848484855e-06, | |
| "loss": 0.0001, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 0.0862, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 4.4040404040404044e-06, | |
| "loss": 0.1493, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 4.363636363636364e-06, | |
| "loss": 0.2325, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 4.323232323232323e-06, | |
| "loss": 0.3129, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "eval_accuracy": 0.68, | |
| "eval_loss": 1.9160839319229126, | |
| "eval_runtime": 5.0112, | |
| "eval_samples_per_second": 4.989, | |
| "eval_steps_per_second": 1.397, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 4.282828282828283e-06, | |
| "loss": 0.1379, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 4.242424242424243e-06, | |
| "loss": 0.0002, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 4.2020202020202026e-06, | |
| "loss": 0.0002, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "learning_rate": 4.161616161616162e-06, | |
| "loss": 0.023, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "learning_rate": 4.1212121212121215e-06, | |
| "loss": 0.0001, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 30.02, | |
| "eval_accuracy": 0.76, | |
| "eval_loss": 1.4176759719848633, | |
| "eval_runtime": 5.0603, | |
| "eval_samples_per_second": 4.94, | |
| "eval_steps_per_second": 1.383, | |
| "step": 1736 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 4.080808080808081e-06, | |
| "loss": 0.0001, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 4.04040404040404e-06, | |
| "loss": 0.0001, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0002, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "learning_rate": 3.95959595959596e-06, | |
| "loss": 0.0818, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 31.02, | |
| "learning_rate": 3.9191919191919196e-06, | |
| "loss": 0.0002, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 31.02, | |
| "learning_rate": 3.878787878787879e-06, | |
| "loss": 0.0001, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 31.02, | |
| "eval_accuracy": 0.68, | |
| "eval_loss": 1.468752145767212, | |
| "eval_runtime": 5.0305, | |
| "eval_samples_per_second": 4.97, | |
| "eval_steps_per_second": 1.391, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 3.8383838383838385e-06, | |
| "loss": 0.0002, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 3.7979797979797984e-06, | |
| "loss": 0.0003, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 3.757575757575758e-06, | |
| "loss": 0.0004, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "learning_rate": 3.7171717171717177e-06, | |
| "loss": 0.0001, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 32.02, | |
| "learning_rate": 3.6767676767676767e-06, | |
| "loss": 0.0314, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 32.02, | |
| "eval_accuracy": 0.68, | |
| "eval_loss": 1.4025585651397705, | |
| "eval_runtime": 5.016, | |
| "eval_samples_per_second": 4.984, | |
| "eval_steps_per_second": 1.396, | |
| "step": 1848 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 3.6363636363636366e-06, | |
| "loss": 0.0591, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 3.595959595959596e-06, | |
| "loss": 0.0852, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "learning_rate": 3.555555555555556e-06, | |
| "loss": 0.0007, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "learning_rate": 3.5151515151515154e-06, | |
| "loss": 0.0001, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "learning_rate": 3.4747474747474752e-06, | |
| "loss": 0.0012, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "learning_rate": 3.4343434343434347e-06, | |
| "loss": 0.0001, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 33.02, | |
| "eval_accuracy": 0.72, | |
| "eval_loss": 1.584563136100769, | |
| "eval_runtime": 5.0691, | |
| "eval_samples_per_second": 4.932, | |
| "eval_steps_per_second": 1.381, | |
| "step": 1904 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 3.3939393939393946e-06, | |
| "loss": 0.0001, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 3.3535353535353536e-06, | |
| "loss": 0.0001, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 3.3131313131313135e-06, | |
| "loss": 0.0001, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 3.272727272727273e-06, | |
| "loss": 0.0002, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 34.02, | |
| "learning_rate": 3.232323232323233e-06, | |
| "loss": 0.0024, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 34.02, | |
| "learning_rate": 3.1919191919191923e-06, | |
| "loss": 0.0001, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 34.02, | |
| "eval_accuracy": 0.64, | |
| "eval_loss": 1.4020888805389404, | |
| "eval_runtime": 5.0416, | |
| "eval_samples_per_second": 4.959, | |
| "eval_steps_per_second": 1.388, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 3.1515151515151517e-06, | |
| "loss": 0.0132, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 3.1111111111111116e-06, | |
| "loss": 0.0001, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 3.0707070707070706e-06, | |
| "loss": 0.0001, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "learning_rate": 3.0303030303030305e-06, | |
| "loss": 0.0002, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 35.02, | |
| "learning_rate": 2.98989898989899e-06, | |
| "loss": 0.0002, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 35.02, | |
| "eval_accuracy": 0.72, | |
| "eval_loss": 1.5993890762329102, | |
| "eval_runtime": 5.078, | |
| "eval_samples_per_second": 4.923, | |
| "eval_steps_per_second": 1.379, | |
| "step": 2016 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 2.94949494949495e-06, | |
| "loss": 0.0003, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 2.9090909090909093e-06, | |
| "loss": 0.0001, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 2.868686868686869e-06, | |
| "loss": 0.0001, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "learning_rate": 2.8282828282828286e-06, | |
| "loss": 0.0001, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 36.02, | |
| "learning_rate": 2.7878787878787885e-06, | |
| "loss": 0.0001, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 36.02, | |
| "learning_rate": 2.7474747474747475e-06, | |
| "loss": 0.0001, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 36.02, | |
| "eval_accuracy": 0.72, | |
| "eval_loss": 1.4026561975479126, | |
| "eval_runtime": 4.9911, | |
| "eval_samples_per_second": 5.009, | |
| "eval_steps_per_second": 1.402, | |
| "step": 2072 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "learning_rate": 2.7070707070707074e-06, | |
| "loss": 0.0004, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 0.0036, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 2.6262626262626267e-06, | |
| "loss": 0.0001, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "learning_rate": 2.585858585858586e-06, | |
| "loss": 0.0001, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "learning_rate": 2.5454545454545456e-06, | |
| "loss": 0.0002, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 37.02, | |
| "eval_accuracy": 0.76, | |
| "eval_loss": 1.360788106918335, | |
| "eval_runtime": 4.9882, | |
| "eval_samples_per_second": 5.012, | |
| "eval_steps_per_second": 1.403, | |
| "step": 2128 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 2.5050505050505055e-06, | |
| "loss": 0.0007, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 2.464646464646465e-06, | |
| "loss": 0.0001, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 2.4242424242424244e-06, | |
| "loss": 0.0002, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "learning_rate": 2.3838383838383843e-06, | |
| "loss": 0.0001, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "learning_rate": 2.3434343434343437e-06, | |
| "loss": 0.0001, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "learning_rate": 2.303030303030303e-06, | |
| "loss": 0.0001, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 1.356919288635254, | |
| "eval_runtime": 4.9514, | |
| "eval_samples_per_second": 5.049, | |
| "eval_steps_per_second": 1.414, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "learning_rate": 2.262626262626263e-06, | |
| "loss": 0.0007, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 2.222222222222222e-06, | |
| "loss": 0.0001, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 2.181818181818182e-06, | |
| "loss": 0.002, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 2.1414141414141414e-06, | |
| "loss": 0.0001, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "learning_rate": 2.1010101010101013e-06, | |
| "loss": 0.0001, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "learning_rate": 2.0606060606060607e-06, | |
| "loss": 0.0001, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 1.4026089906692505, | |
| "eval_runtime": 4.9521, | |
| "eval_samples_per_second": 5.048, | |
| "eval_steps_per_second": 1.414, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 2.02020202020202e-06, | |
| "loss": 0.0001, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "learning_rate": 1.97979797979798e-06, | |
| "loss": 0.0001, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "learning_rate": 1.9393939393939395e-06, | |
| "loss": 0.0001, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "learning_rate": 1.8989898989898992e-06, | |
| "loss": 0.0002, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 40.02, | |
| "learning_rate": 1.8585858585858588e-06, | |
| "loss": 0.0001, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 40.02, | |
| "eval_accuracy": 0.72, | |
| "eval_loss": 1.4563390016555786, | |
| "eval_runtime": 4.9991, | |
| "eval_samples_per_second": 5.001, | |
| "eval_steps_per_second": 1.4, | |
| "step": 2296 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "learning_rate": 1.8181818181818183e-06, | |
| "loss": 0.0001, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 1.777777777777778e-06, | |
| "loss": 0.0001, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 1.7373737373737376e-06, | |
| "loss": 0.0001, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "learning_rate": 1.6969696969696973e-06, | |
| "loss": 0.0019, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 41.02, | |
| "learning_rate": 1.6565656565656567e-06, | |
| "loss": 0.0001, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 41.02, | |
| "learning_rate": 1.6161616161616164e-06, | |
| "loss": 0.0028, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 41.02, | |
| "eval_accuracy": 0.76, | |
| "eval_loss": 1.3389179706573486, | |
| "eval_runtime": 5.702, | |
| "eval_samples_per_second": 4.384, | |
| "eval_steps_per_second": 1.228, | |
| "step": 2352 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 1.5757575757575759e-06, | |
| "loss": 0.0001, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 1.5353535353535353e-06, | |
| "loss": 0.0001, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 1.494949494949495e-06, | |
| "loss": 0.0001, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "learning_rate": 1.4545454545454546e-06, | |
| "loss": 0.0001, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 42.02, | |
| "learning_rate": 1.4141414141414143e-06, | |
| "loss": 0.0001, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 42.02, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 1.3354742527008057, | |
| "eval_runtime": 5.6534, | |
| "eval_samples_per_second": 4.422, | |
| "eval_steps_per_second": 1.238, | |
| "step": 2408 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 1.3737373737373738e-06, | |
| "loss": 0.0001, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 1.3333333333333334e-06, | |
| "loss": 0.0001, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 1.292929292929293e-06, | |
| "loss": 0.0001, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "learning_rate": 1.2525252525252527e-06, | |
| "loss": 0.0001, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "learning_rate": 1.2121212121212122e-06, | |
| "loss": 0.0001, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "learning_rate": 1.1717171717171719e-06, | |
| "loss": 0.0001, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 43.02, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 1.3445130586624146, | |
| "eval_runtime": 5.7756, | |
| "eval_samples_per_second": 4.329, | |
| "eval_steps_per_second": 1.212, | |
| "step": 2464 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 1.1313131313131315e-06, | |
| "loss": 0.0001, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 1.090909090909091e-06, | |
| "loss": 0.0001, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 1.0505050505050506e-06, | |
| "loss": 0.0001, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "learning_rate": 1.01010101010101e-06, | |
| "loss": 0.0001, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 44.02, | |
| "learning_rate": 9.696969696969698e-07, | |
| "loss": 0.0001, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 44.02, | |
| "learning_rate": 9.292929292929294e-07, | |
| "loss": 0.0001, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 44.02, | |
| "eval_accuracy": 0.8, | |
| "eval_loss": 1.352601170539856, | |
| "eval_runtime": 5.381, | |
| "eval_samples_per_second": 4.646, | |
| "eval_steps_per_second": 1.301, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 8.88888888888889e-07, | |
| "loss": 0.0001, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "learning_rate": 8.484848484848486e-07, | |
| "loss": 0.0001, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "learning_rate": 8.080808080808082e-07, | |
| "loss": 0.0001, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "learning_rate": 7.676767676767677e-07, | |
| "loss": 0.0001, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 45.02, | |
| "learning_rate": 7.272727272727273e-07, | |
| "loss": 0.0001, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 45.02, | |
| "eval_accuracy": 0.72, | |
| "eval_loss": 1.3842326402664185, | |
| "eval_runtime": 5.5724, | |
| "eval_samples_per_second": 4.486, | |
| "eval_steps_per_second": 1.256, | |
| "step": 2576 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 6.868686868686869e-07, | |
| "loss": 0.0001, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 6.464646464646465e-07, | |
| "loss": 0.0001, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 6.060606060606061e-07, | |
| "loss": 0.0001, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "learning_rate": 5.656565656565658e-07, | |
| "loss": 0.0001, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 46.02, | |
| "learning_rate": 5.252525252525253e-07, | |
| "loss": 0.0001, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 46.02, | |
| "learning_rate": 4.848484848484849e-07, | |
| "loss": 0.0001, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 46.02, | |
| "eval_accuracy": 0.72, | |
| "eval_loss": 1.3894717693328857, | |
| "eval_runtime": 5.0324, | |
| "eval_samples_per_second": 4.968, | |
| "eval_steps_per_second": 1.391, | |
| "step": 2632 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "learning_rate": 4.444444444444445e-07, | |
| "loss": 0.0001, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 4.040404040404041e-07, | |
| "loss": 0.0001, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 3.6363636363636366e-07, | |
| "loss": 0.0004, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "learning_rate": 3.2323232323232327e-07, | |
| "loss": 0.0001, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "learning_rate": 2.828282828282829e-07, | |
| "loss": 0.0025, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 47.02, | |
| "eval_accuracy": 0.76, | |
| "eval_loss": 1.482791543006897, | |
| "eval_runtime": 4.9577, | |
| "eval_samples_per_second": 5.043, | |
| "eval_steps_per_second": 1.412, | |
| "step": 2688 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 2.4242424242424244e-07, | |
| "loss": 0.0001, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 2.0202020202020205e-07, | |
| "loss": 0.0001, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "learning_rate": 1.6161616161616163e-07, | |
| "loss": 0.0002, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "learning_rate": 1.2121212121212122e-07, | |
| "loss": 0.0001, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "learning_rate": 8.080808080808082e-08, | |
| "loss": 0.0001, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "learning_rate": 4.040404040404041e-08, | |
| "loss": 0.0001, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "eval_accuracy": 0.76, | |
| "eval_loss": 1.4091929197311401, | |
| "eval_runtime": 4.9307, | |
| "eval_samples_per_second": 5.07, | |
| "eval_steps_per_second": 1.42, | |
| "step": 2744 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.2131, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.76, | |
| "eval_loss": 1.4071288108825684, | |
| "eval_runtime": 5.1054, | |
| "eval_samples_per_second": 4.897, | |
| "eval_steps_per_second": 1.371, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "step": 2750, | |
| "total_flos": 4.808612917881491e+19, | |
| "train_loss": 0.16666692824898796, | |
| "train_runtime": 5075.4297, | |
| "train_samples_per_second": 2.167, | |
| "train_steps_per_second": 0.542 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 1.2706124782562256, | |
| "eval_runtime": 6.9128, | |
| "eval_samples_per_second": 4.34, | |
| "eval_steps_per_second": 1.157, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.7333333333333333, | |
| "eval_loss": 1.2706125974655151, | |
| "eval_runtime": 6.4418, | |
| "eval_samples_per_second": 4.657, | |
| "eval_steps_per_second": 1.242, | |
| "step": 2750 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2750, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 4.808612917881491e+19, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |