| { | |
| "best_metric": 1.3997734785079956, | |
| "best_model_checkpoint": "alpaca_baichuan/checkpoint-4400", | |
| "epoch": 2.9992551518662585, | |
| "global_step": 4530, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.999939881018594e-05, | |
| "loss": 1.6257, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.999759526965809e-05, | |
| "loss": 1.6388, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.999458946515808e-05, | |
| "loss": 1.5034, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.999038154125061e-05, | |
| "loss": 1.5761, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.998497170031657e-05, | |
| "loss": 1.5066, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.997836020254328e-05, | |
| "loss": 1.5738, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9970547365911925e-05, | |
| "loss": 1.4921, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.996153356618233e-05, | |
| "loss": 1.4508, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.995131923687488e-05, | |
| "loss": 1.4714, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.9939904869249616e-05, | |
| "loss": 1.494, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.4796885251998901, | |
| "eval_runtime": 20.1174, | |
| "eval_samples_per_second": 24.307, | |
| "eval_steps_per_second": 6.114, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.992729101228267e-05, | |
| "loss": 1.4934, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.991347827263982e-05, | |
| "loss": 1.4789, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.9898467314647356e-05, | |
| "loss": 1.4511, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.9882258860260065e-05, | |
| "loss": 1.4876, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.9864853689026556e-05, | |
| "loss": 1.5124, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.984625263805178e-05, | |
| "loss": 1.4772, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.982645660195671e-05, | |
| "loss": 1.436, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.9805466532835376e-05, | |
| "loss": 1.4377, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.978328344020904e-05, | |
| "loss": 1.438, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.975990839097764e-05, | |
| "loss": 1.4448, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.45673668384552, | |
| "eval_runtime": 20.2667, | |
| "eval_samples_per_second": 24.128, | |
| "eval_steps_per_second": 6.069, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.973534250936851e-05, | |
| "loss": 1.452, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.970958697688226e-05, | |
| "loss": 1.4813, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.9682643032235996e-05, | |
| "loss": 1.41, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.965451197130373e-05, | |
| "loss": 1.428, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.9625195147054034e-05, | |
| "loss": 1.463, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.9594693969485006e-05, | |
| "loss": 1.4821, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.956300990555643e-05, | |
| "loss": 1.4855, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.9530144479119215e-05, | |
| "loss": 1.4322, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.9496099270842145e-05, | |
| "loss": 1.4397, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.9460875918135804e-05, | |
| "loss": 1.4107, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.4451508522033691, | |
| "eval_runtime": 19.869, | |
| "eval_samples_per_second": 24.611, | |
| "eval_steps_per_second": 6.191, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.942447611507386e-05, | |
| "loss": 1.4722, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.938690161231159e-05, | |
| "loss": 1.423, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.934815421700165e-05, | |
| "loss": 1.4288, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.9308235792707194e-05, | |
| "loss": 1.4294, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.9267148259312224e-05, | |
| "loss": 1.4233, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.9224893592929275e-05, | |
| "loss": 1.4553, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.9181473825804346e-05, | |
| "loss": 1.4206, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.913689104621917e-05, | |
| "loss": 1.442, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.909114739839079e-05, | |
| "loss": 1.4668, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.9044245082368415e-05, | |
| "loss": 1.4439, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.4394803047180176, | |
| "eval_runtime": 19.9302, | |
| "eval_samples_per_second": 24.536, | |
| "eval_steps_per_second": 6.172, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.8996186353927606e-05, | |
| "loss": 1.4224, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.894697352446182e-05, | |
| "loss": 1.4084, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.889660896087119e-05, | |
| "loss": 1.4398, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.884509508544874e-05, | |
| "loss": 1.4268, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.879243437576383e-05, | |
| "loss": 1.4522, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.8738629364543045e-05, | |
| "loss": 1.4222, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.8683682639548365e-05, | |
| "loss": 1.4956, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.862759684345269e-05, | |
| "loss": 1.4538, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.857037467371278e-05, | |
| "loss": 1.3748, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.8512018882439475e-05, | |
| "loss": 1.4127, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.435186505317688, | |
| "eval_runtime": 19.8689, | |
| "eval_samples_per_second": 24.611, | |
| "eval_steps_per_second": 6.191, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.8452532276265364e-05, | |
| "loss": 1.3795, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.8391917716209765e-05, | |
| "loss": 1.4414, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.833017811754119e-05, | |
| "loss": 1.4242, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.8267316449637054e-05, | |
| "loss": 1.4196, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.820333573584091e-05, | |
| "loss": 1.389, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.813823905331704e-05, | |
| "loss": 1.4597, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.8072029532902426e-05, | |
| "loss": 1.4275, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.800471035895624e-05, | |
| "loss": 1.4364, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.7936284769206584e-05, | |
| "loss": 1.4366, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.786675605459487e-05, | |
| "loss": 1.5086, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.4307918548583984, | |
| "eval_runtime": 20.0563, | |
| "eval_samples_per_second": 24.381, | |
| "eval_steps_per_second": 6.133, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.779612755911752e-05, | |
| "loss": 1.4309, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.772440267966508e-05, | |
| "loss": 1.4102, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.76515848658589e-05, | |
| "loss": 1.4035, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.7577677619885234e-05, | |
| "loss": 1.4478, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.7502684496326746e-05, | |
| "loss": 1.3999, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.7426609101991605e-05, | |
| "loss": 1.4042, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.734945509573997e-05, | |
| "loss": 1.4216, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.727122618830808e-05, | |
| "loss": 1.4786, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.719192614212969e-05, | |
| "loss": 1.4414, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.711155877115523e-05, | |
| "loss": 1.493, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.427127480506897, | |
| "eval_runtime": 20.5172, | |
| "eval_samples_per_second": 23.834, | |
| "eval_steps_per_second": 5.995, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.703012794066827e-05, | |
| "loss": 1.4078, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.694763756709967e-05, | |
| "loss": 1.4539, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.6864091617839235e-05, | |
| "loss": 1.4458, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.677949411104485e-05, | |
| "loss": 1.4001, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.669384911544927e-05, | |
| "loss": 1.433, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.660716075016442e-05, | |
| "loss": 1.4323, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.6519433184483245e-05, | |
| "loss": 1.4052, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.6430670637679295e-05, | |
| "loss": 1.4021, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.634087737880367e-05, | |
| "loss": 1.4049, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.625005772647979e-05, | |
| "loss": 1.3701, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.4250208139419556, | |
| "eval_runtime": 20.0939, | |
| "eval_samples_per_second": 24.336, | |
| "eval_steps_per_second": 6.121, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.615821604869564e-05, | |
| "loss": 1.4209, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.606535676259372e-05, | |
| "loss": 1.4373, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.597148433425857e-05, | |
| "loss": 1.4913, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.587660327850203e-05, | |
| "loss": 1.434, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.578071815864602e-05, | |
| "loss": 1.3932, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.5683833586303157e-05, | |
| "loss": 1.4232, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.5585954221154856e-05, | |
| "loss": 1.3651, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.548708477072733e-05, | |
| "loss": 1.4009, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.5387229990165073e-05, | |
| "loss": 1.428, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.528639468200226e-05, | |
| "loss": 1.413, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.4226006269454956, | |
| "eval_runtime": 20.161, | |
| "eval_samples_per_second": 24.255, | |
| "eval_steps_per_second": 6.101, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.51845836959317e-05, | |
| "loss": 1.4328, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.508180192857162e-05, | |
| "loss": 1.4262, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.497805432323015e-05, | |
| "loss": 1.3677, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.487334586966756e-05, | |
| "loss": 1.4546, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.476768160385632e-05, | |
| "loss": 1.4011, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.466106660773885e-05, | |
| "loss": 1.441, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.4553506008983126e-05, | |
| "loss": 1.3946, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.4445004980736064e-05, | |
| "loss": 1.4478, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 4.43355687413747e-05, | |
| "loss": 1.4093, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 4.4225202554255227e-05, | |
| "loss": 1.4285, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.4204448461532593, | |
| "eval_runtime": 19.9265, | |
| "eval_samples_per_second": 24.54, | |
| "eval_steps_per_second": 6.173, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 4.411391172745984e-05, | |
| "loss": 1.3971, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.4001701613541456e-05, | |
| "loss": 1.4024, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.388857760926629e-05, | |
| "loss": 1.3623, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.3774545155354254e-05, | |
| "loss": 1.3943, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.3659609736217344e-05, | |
| "loss": 1.4586, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.354377687969581e-05, | |
| "loss": 1.4178, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.342705215679232e-05, | |
| "loss": 1.4454, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.330944118140407e-05, | |
| "loss": 1.3769, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 4.3190949610052645e-05, | |
| "loss": 1.3912, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.3071583141612135e-05, | |
| "loss": 1.4116, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.4190473556518555, | |
| "eval_runtime": 19.9596, | |
| "eval_samples_per_second": 24.499, | |
| "eval_steps_per_second": 6.162, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.295134751703493e-05, | |
| "loss": 1.4019, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.283024851907565e-05, | |
| "loss": 1.378, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.2708291972013026e-05, | |
| "loss": 1.432, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.2585483741369755e-05, | |
| "loss": 1.4531, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.2461829733630435e-05, | |
| "loss": 1.4455, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.233733589595746e-05, | |
| "loss": 1.4081, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.2212008215905e-05, | |
| "loss": 1.4344, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.208585272113102e-05, | |
| "loss": 1.3935, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.195887547910741e-05, | |
| "loss": 1.4161, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.1831082596828106e-05, | |
| "loss": 1.4185, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.4168447256088257, | |
| "eval_runtime": 19.9431, | |
| "eval_samples_per_second": 24.52, | |
| "eval_steps_per_second": 6.168, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.1702480220515475e-05, | |
| "loss": 1.3714, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.157307453532457e-05, | |
| "loss": 1.4062, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 4.144287176504582e-05, | |
| "loss": 1.4007, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.131187817180554e-05, | |
| "loss": 1.4153, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.118010005576485e-05, | |
| "loss": 1.3619, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.104754375481664e-05, | |
| "loss": 1.507, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.0914215644280754e-05, | |
| "loss": 1.4487, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.0780122136597323e-05, | |
| "loss": 1.409, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.064526968101844e-05, | |
| "loss": 1.3994, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.050966476329793e-05, | |
| "loss": 1.4285, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 1.4150002002716064, | |
| "eval_runtime": 19.9449, | |
| "eval_samples_per_second": 24.518, | |
| "eval_steps_per_second": 6.167, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.037331390537939e-05, | |
| "loss": 1.4562, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.023622366508261e-05, | |
| "loss": 1.4202, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.0098400635788035e-05, | |
| "loss": 1.381, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.99598514461198e-05, | |
| "loss": 1.4656, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.9820582759626825e-05, | |
| "loss": 1.4094, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.968060127446236e-05, | |
| "loss": 1.4183, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.953991372306186e-05, | |
| "loss": 1.411, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.9398526871819154e-05, | |
| "loss": 1.418, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.925644752076101e-05, | |
| "loss": 1.4751, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.911368250322014e-05, | |
| "loss": 1.4246, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.4129770994186401, | |
| "eval_runtime": 19.9327, | |
| "eval_samples_per_second": 24.533, | |
| "eval_steps_per_second": 6.171, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.897023868550649e-05, | |
| "loss": 1.4102, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.882612296657701e-05, | |
| "loss": 1.3871, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.8681342277703906e-05, | |
| "loss": 1.4156, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.853590358214119e-05, | |
| "loss": 1.433, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.8389813874789856e-05, | |
| "loss": 1.4372, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.8243080181861435e-05, | |
| "loss": 1.3978, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.809570956054004e-05, | |
| "loss": 1.3964, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.794770909864298e-05, | |
| "loss": 1.4332, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.779908591427988e-05, | |
| "loss": 1.4044, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.764984715551032e-05, | |
| "loss": 1.4301, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.412743330001831, | |
| "eval_runtime": 19.9577, | |
| "eval_samples_per_second": 24.502, | |
| "eval_steps_per_second": 6.163, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 1.4721, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.734955165467563e-05, | |
| "loss": 1.3905, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.719850935537821e-05, | |
| "loss": 1.423, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.70468803665151e-05, | |
| "loss": 1.404, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.6894671980710574e-05, | |
| "loss": 1.4042, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.674189151845515e-05, | |
| "loss": 1.4158, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.6588546327753425e-05, | |
| "loss": 1.409, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.6434643783770736e-05, | |
| "loss": 1.3764, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.6280191288478436e-05, | |
| "loss": 1.4021, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.612519627029787e-05, | |
| "loss": 1.3973, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 1.411142349243164, | |
| "eval_runtime": 19.9375, | |
| "eval_samples_per_second": 24.527, | |
| "eval_steps_per_second": 6.169, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.596966618374313e-05, | |
| "loss": 1.3985, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.5813608509062526e-05, | |
| "loss": 1.3444, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.5657030751878814e-05, | |
| "loss": 1.4207, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.5499940442828206e-05, | |
| "loss": 1.4304, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.534234513719821e-05, | |
| "loss": 1.3924, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.51842524145642e-05, | |
| "loss": 1.3686, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.502566987842496e-05, | |
| "loss": 1.4248, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.4866605155836915e-05, | |
| "loss": 1.3906, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.470706589704734e-05, | |
| "loss": 1.444, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.4547059775126445e-05, | |
| "loss": 1.3589, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_loss": 1.4102592468261719, | |
| "eval_runtime": 19.9452, | |
| "eval_samples_per_second": 24.517, | |
| "eval_steps_per_second": 6.167, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.438659448559825e-05, | |
| "loss": 1.319, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.422567774607058e-05, | |
| "loss": 1.406, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.406431729586382e-05, | |
| "loss": 1.4114, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.390252089563867e-05, | |
| "loss": 1.3722, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.3740296327022984e-05, | |
| "loss": 1.3528, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.35776513922374e-05, | |
| "loss": 1.4274, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.341459391372016e-05, | |
| "loss": 1.4324, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.32511317337509e-05, | |
| "loss": 1.409, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.30872727140734e-05, | |
| "loss": 1.3464, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.292302473551757e-05, | |
| "loss": 1.4144, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 1.4091637134552002, | |
| "eval_runtime": 19.9455, | |
| "eval_samples_per_second": 24.517, | |
| "eval_steps_per_second": 6.167, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.2758395697620334e-05, | |
| "loss": 1.4139, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.259339351824575e-05, | |
| "loss": 1.4247, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.2428026133204184e-05, | |
| "loss": 1.4241, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.226230149587063e-05, | |
| "loss": 1.3941, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.20962275768022e-05, | |
| "loss": 1.4238, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.1929812363354766e-05, | |
| "loss": 1.382, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.1763063859298845e-05, | |
| "loss": 1.4124, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.159599008443459e-05, | |
| "loss": 1.3963, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.142859907420615e-05, | |
| "loss": 1.3542, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.126089887931515e-05, | |
| "loss": 1.3852, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 1.4086569547653198, | |
| "eval_runtime": 19.948, | |
| "eval_samples_per_second": 24.514, | |
| "eval_steps_per_second": 6.166, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.109289756533349e-05, | |
| "loss": 1.3972, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.092460321231547e-05, | |
| "loss": 1.3783, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.075602391440918e-05, | |
| "loss": 1.4122, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.058716777946713e-05, | |
| "loss": 1.4105, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.0418042928656414e-05, | |
| "loss": 1.4091, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.0248657496068027e-05, | |
| "loss": 1.4067, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.0079019628325706e-05, | |
| "loss": 1.4172, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.990913748419411e-05, | |
| "loss": 1.3803, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.97390192341864e-05, | |
| "loss": 1.4096, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.9568673060171326e-05, | |
| "loss": 1.3774, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 1.407130479812622, | |
| "eval_runtime": 19.928, | |
| "eval_samples_per_second": 24.538, | |
| "eval_steps_per_second": 6.172, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.9398107154979638e-05, | |
| "loss": 1.3729, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.922732972201014e-05, | |
| "loss": 1.3687, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.9056348974835067e-05, | |
| "loss": 1.3946, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.8885173136805127e-05, | |
| "loss": 1.3922, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.8713810440653926e-05, | |
| "loss": 1.3631, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.8542269128102063e-05, | |
| "loss": 1.4193, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.837055744946072e-05, | |
| "loss": 1.3776, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.819868366323488e-05, | |
| "loss": 1.4099, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.8026656035726095e-05, | |
| "loss": 1.41, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.7854482840634965e-05, | |
| "loss": 1.4604, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 1.406220555305481, | |
| "eval_runtime": 19.947, | |
| "eval_samples_per_second": 24.515, | |
| "eval_steps_per_second": 6.166, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.7682172358663173e-05, | |
| "loss": 1.4485, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.7509732877115257e-05, | |
| "loss": 1.4445, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.73371726895e-05, | |
| "loss": 1.3889, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.716450009513158e-05, | |
| "loss": 1.4167, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.6991723398730383e-05, | |
| "loss": 1.3388, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.68188509100236e-05, | |
| "loss": 1.4379, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.6645890943345585e-05, | |
| "loss": 1.4119, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.6472851817237948e-05, | |
| "loss": 1.3961, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.6299741854049508e-05, | |
| "loss": 1.3999, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.6126569379535985e-05, | |
| "loss": 1.3739, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 1.4052706956863403, | |
| "eval_runtime": 19.9293, | |
| "eval_samples_per_second": 24.537, | |
| "eval_steps_per_second": 6.172, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.5953342722459594e-05, | |
| "loss": 1.4256, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.5780070214188478e-05, | |
| "loss": 1.4615, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.5606760188296004e-05, | |
| "loss": 1.3877, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.5433420980159944e-05, | |
| "loss": 1.3752, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.526006092656161e-05, | |
| "loss": 1.4084, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.508668836528486e-05, | |
| "loss": 1.3921, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.491331163471514e-05, | |
| "loss": 1.4104, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.4739939073438397e-05, | |
| "loss": 1.4053, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.456657901984006e-05, | |
| "loss": 1.381, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.4393239811704e-05, | |
| "loss": 1.3752, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 1.4050989151000977, | |
| "eval_runtime": 19.9544, | |
| "eval_samples_per_second": 24.506, | |
| "eval_steps_per_second": 6.164, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.4219929785811518e-05, | |
| "loss": 1.4023, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.4046657277540412e-05, | |
| "loss": 1.3642, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.3873430620464024e-05, | |
| "loss": 1.3977, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.3700258145950495e-05, | |
| "loss": 1.3905, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.3527148182762054e-05, | |
| "loss": 1.4022, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.335410905665442e-05, | |
| "loss": 1.4162, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.3181149089976405e-05, | |
| "loss": 1.3877, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.3008276601269623e-05, | |
| "loss": 1.3704, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.283549990486842e-05, | |
| "loss": 1.3725, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.2662827310499995e-05, | |
| "loss": 1.4232, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 1.4044643640518188, | |
| "eval_runtime": 19.9565, | |
| "eval_samples_per_second": 24.503, | |
| "eval_steps_per_second": 6.163, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.249026712288474e-05, | |
| "loss": 1.3916, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.2317827641336833e-05, | |
| "loss": 1.384, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.2145517159365044e-05, | |
| "loss": 1.3969, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.197334396427391e-05, | |
| "loss": 1.3742, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.1801316336765126e-05, | |
| "loss": 1.3901, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.162944255053928e-05, | |
| "loss": 1.3853, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.145773087189794e-05, | |
| "loss": 1.3709, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.128618955934608e-05, | |
| "loss": 1.3758, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.1114826863194882e-05, | |
| "loss": 1.3561, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.0943651025164932e-05, | |
| "loss": 1.3774, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 1.4048223495483398, | |
| "eval_runtime": 19.9312, | |
| "eval_samples_per_second": 24.534, | |
| "eval_steps_per_second": 6.171, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.0772670277989864e-05, | |
| "loss": 1.3961, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.060189284502037e-05, | |
| "loss": 1.3794, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.0431326939828686e-05, | |
| "loss": 1.4147, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.0260980765813604e-05, | |
| "loss": 1.4336, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.0090862515805898e-05, | |
| "loss": 1.4228, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 1.99209803716743e-05, | |
| "loss": 1.4188, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 1.975134250393198e-05, | |
| "loss": 1.4492, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 1.9581957071343592e-05, | |
| "loss": 1.4492, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 1.9412832220532867e-05, | |
| "loss": 1.4261, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 1.9243976085590824e-05, | |
| "loss": 1.412, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 1.4038400650024414, | |
| "eval_runtime": 19.9456, | |
| "eval_samples_per_second": 24.517, | |
| "eval_steps_per_second": 6.167, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 1.9075396787684533e-05, | |
| "loss": 1.3858, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 1.8907102434666523e-05, | |
| "loss": 1.3648, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 1.8739101120684866e-05, | |
| "loss": 1.4267, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 1.8571400925793855e-05, | |
| "loss": 1.4115, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 1.840400991556541e-05, | |
| "loss": 1.3767, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 1.8236936140701165e-05, | |
| "loss": 1.3934, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 1.807018763664524e-05, | |
| "loss": 1.368, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 1.7903772423197806e-05, | |
| "loss": 1.3925, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.773769850412937e-05, | |
| "loss": 1.3786, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.7571973866795815e-05, | |
| "loss": 1.4204, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 1.4035720825195312, | |
| "eval_runtime": 19.9322, | |
| "eval_samples_per_second": 24.533, | |
| "eval_steps_per_second": 6.171, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.7406606481754258e-05, | |
| "loss": 1.3907, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.724160430237967e-05, | |
| "loss": 1.3598, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.7076975264482434e-05, | |
| "loss": 1.4157, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.6912727285926605e-05, | |
| "loss": 1.3922, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.6748868266249114e-05, | |
| "loss": 1.4413, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.658540608627985e-05, | |
| "loss": 1.4219, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.642234860776261e-05, | |
| "loss": 1.3447, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.6259703672977022e-05, | |
| "loss": 1.4383, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1.6097479104361326e-05, | |
| "loss": 1.3562, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 1.5935682704136183e-05, | |
| "loss": 1.3865, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 1.40265691280365, | |
| "eval_runtime": 19.9442, | |
| "eval_samples_per_second": 24.518, | |
| "eval_steps_per_second": 6.167, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.5774322253929425e-05, | |
| "loss": 1.3875, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.561340551440176e-05, | |
| "loss": 1.4282, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.5452940224873568e-05, | |
| "loss": 1.401, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.529293410295266e-05, | |
| "loss": 1.3645, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.5133394844163093e-05, | |
| "loss": 1.3877, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.4974330121575048e-05, | |
| "loss": 1.4026, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.4815747585435801e-05, | |
| "loss": 1.4235, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.4657654862801798e-05, | |
| "loss": 1.3623, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.4500059557171791e-05, | |
| "loss": 1.3823, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.4342969248121185e-05, | |
| "loss": 1.3717, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 1.4025269746780396, | |
| "eval_runtime": 19.9411, | |
| "eval_samples_per_second": 24.522, | |
| "eval_steps_per_second": 6.168, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.4186391490937481e-05, | |
| "loss": 1.434, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.403033381625688e-05, | |
| "loss": 1.3688, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.3874803729702141e-05, | |
| "loss": 1.3404, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.3719808711521573e-05, | |
| "loss": 1.3956, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.3565356216229268e-05, | |
| "loss": 1.366, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.341145367224657e-05, | |
| "loss": 1.4425, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.3258108481544849e-05, | |
| "loss": 1.3728, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.310532801928942e-05, | |
| "loss": 1.4581, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.2953119633484903e-05, | |
| "loss": 1.3678, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.2801490644621789e-05, | |
| "loss": 1.4091, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 1.4022454023361206, | |
| "eval_runtime": 19.9582, | |
| "eval_samples_per_second": 24.501, | |
| "eval_steps_per_second": 6.163, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.2650448345324384e-05, | |
| "loss": 1.3642, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 1.3949, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.235015284448969e-05, | |
| "loss": 1.3507, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.2200914085720119e-05, | |
| "loss": 1.3553, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.2052290901357025e-05, | |
| "loss": 1.4108, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.1904290439459973e-05, | |
| "loss": 1.3549, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 1.175691981813858e-05, | |
| "loss": 1.3371, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.1610186125210151e-05, | |
| "loss": 1.3775, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.1464096417858822e-05, | |
| "loss": 1.3884, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.1318657722296097e-05, | |
| "loss": 1.3516, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "eval_loss": 1.4020849466323853, | |
| "eval_runtime": 19.9491, | |
| "eval_samples_per_second": 24.512, | |
| "eval_steps_per_second": 6.166, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.1173877033422994e-05, | |
| "loss": 1.405, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.102976131449352e-05, | |
| "loss": 1.3909, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 1.0886317496779863e-05, | |
| "loss": 1.4057, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.0743552479238994e-05, | |
| "loss": 1.3807, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.0601473128180855e-05, | |
| "loss": 1.3804, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.0460086276938144e-05, | |
| "loss": 1.3368, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.0319398725537644e-05, | |
| "loss": 1.3465, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.0179417240373183e-05, | |
| "loss": 1.3716, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.0040148553880205e-05, | |
| "loss": 1.3833, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 9.90159936421197e-06, | |
| "loss": 1.3893, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 1.4016104936599731, | |
| "eval_runtime": 19.9587, | |
| "eval_samples_per_second": 24.501, | |
| "eval_steps_per_second": 6.163, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 9.763776334917399e-06, | |
| "loss": 1.4088, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 9.626686094620608e-06, | |
| "loss": 1.402, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 9.490335236702075e-06, | |
| "loss": 1.3151, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 9.354730318981562e-06, | |
| "loss": 1.4126, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 9.219877863402682e-06, | |
| "loss": 1.431, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 9.085784355719257e-06, | |
| "loss": 1.3843, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.95245624518336e-06, | |
| "loss": 1.3513, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 8.819899944235152e-06, | |
| "loss": 1.362, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.688121828194462e-06, | |
| "loss": 1.3979, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.55712823495419e-06, | |
| "loss": 1.3949, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 1.4013094902038574, | |
| "eval_runtime": 19.9488, | |
| "eval_samples_per_second": 24.513, | |
| "eval_steps_per_second": 6.166, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 8.426925464675433e-06, | |
| "loss": 1.3912, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.297519779484541e-06, | |
| "loss": 1.35, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 8.168917403171891e-06, | |
| "loss": 1.3528, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 8.041124520892598e-06, | |
| "loss": 1.3743, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.91414727886898e-06, | |
| "loss": 1.3708, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 7.787991784095e-06, | |
| "loss": 1.4525, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 7.662664104042538e-06, | |
| "loss": 1.3708, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.538170266369563e-06, | |
| "loss": 1.3871, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.414516258630244e-06, | |
| "loss": 1.3853, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 7.291708027986988e-06, | |
| "loss": 1.3861, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_loss": 1.4008599519729614, | |
| "eval_runtime": 19.9567, | |
| "eval_samples_per_second": 24.503, | |
| "eval_steps_per_second": 6.163, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.169751480924361e-06, | |
| "loss": 1.3738, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 7.048652482965079e-06, | |
| "loss": 1.3908, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 6.928416858387874e-06, | |
| "loss": 1.3652, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 6.809050389947363e-06, | |
| "loss": 1.3673, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 6.690558818595943e-06, | |
| "loss": 1.395, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 6.5729478432076775e-06, | |
| "loss": 1.3734, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 6.456223120304192e-06, | |
| "loss": 1.4366, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 6.340390263782655e-06, | |
| "loss": 1.4222, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 6.22545484464574e-06, | |
| "loss": 1.3545, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 6.111422390733715e-06, | |
| "loss": 1.3581, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 1.4005074501037598, | |
| "eval_runtime": 19.9485, | |
| "eval_samples_per_second": 24.513, | |
| "eval_steps_per_second": 6.166, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 5.998298386458545e-06, | |
| "loss": 1.4052, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 5.8860882725401665e-06, | |
| "loss": 1.3886, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 5.774797445744781e-06, | |
| "loss": 1.3818, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 5.664431258625305e-06, | |
| "loss": 1.3817, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 5.55499501926394e-06, | |
| "loss": 1.3617, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 5.446493991016879e-06, | |
| "loss": 1.3768, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 5.338933392261159e-06, | |
| "loss": 1.3755, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 5.23231839614369e-06, | |
| "loss": 1.3823, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 5.126654130332451e-06, | |
| "loss": 1.3883, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 5.02194567676986e-06, | |
| "loss": 1.3988, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_loss": 1.4005191326141357, | |
| "eval_runtime": 19.9633, | |
| "eval_samples_per_second": 24.495, | |
| "eval_steps_per_second": 6.161, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 4.918198071428382e-06, | |
| "loss": 1.3838, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.815416304068298e-06, | |
| "loss": 1.4422, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.713605317997741e-06, | |
| "loss": 1.3834, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 4.61277000983493e-06, | |
| "loss": 1.3743, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 4.51291522927268e-06, | |
| "loss": 1.451, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 4.414045778845144e-06, | |
| "loss": 1.3644, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 4.316166413696851e-06, | |
| "loss": 1.3944, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 4.219281841353981e-06, | |
| "loss": 1.3514, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 4.123396721497977e-06, | |
| "loss": 1.3389, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 4.028515665741439e-06, | |
| "loss": 1.3792, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_loss": 1.400659203529358, | |
| "eval_runtime": 19.9466, | |
| "eval_samples_per_second": 24.515, | |
| "eval_steps_per_second": 6.166, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 3.934643237406291e-06, | |
| "loss": 1.3686, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 3.8417839513043645e-06, | |
| "loss": 1.3424, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 3.7499422735202127e-06, | |
| "loss": 1.3684, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 3.6591226211963287e-06, | |
| "loss": 1.3868, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 3.5693293623207086e-06, | |
| "loss": 1.368, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 3.480566815516756e-06, | |
| "loss": 1.3027, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 3.3928392498355916e-06, | |
| "loss": 1.4223, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 3.3061508845507323e-06, | |
| "loss": 1.3674, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 3.22050588895515e-06, | |
| "loss": 1.3848, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 3.135908382160771e-06, | |
| "loss": 1.4191, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_loss": 1.4003913402557373, | |
| "eval_runtime": 19.9553, | |
| "eval_samples_per_second": 24.505, | |
| "eval_steps_per_second": 6.164, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 3.0523624329003324e-06, | |
| "loss": 1.3796, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 2.969872059331738e-06, | |
| "loss": 1.4101, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 2.8884412288447737e-06, | |
| "loss": 1.379, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 2.8080738578703054e-06, | |
| "loss": 1.3881, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 2.728773811691923e-06, | |
| "loss": 1.3464, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2.6505449042600244e-06, | |
| "loss": 1.367, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2.5733908980083988e-06, | |
| "loss": 1.3498, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 2.4973155036732534e-06, | |
| "loss": 1.3895, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 2.422322380114772e-06, | |
| "loss": 1.4072, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 2.348415134141102e-06, | |
| "loss": 1.347, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_loss": 1.400329351425171, | |
| "eval_runtime": 19.9385, | |
| "eval_samples_per_second": 24.525, | |
| "eval_steps_per_second": 6.169, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 2.2755973203349294e-06, | |
| "loss": 1.3605, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 2.2038724408824844e-06, | |
| "loss": 1.3105, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 2.133243945405128e-06, | |
| "loss": 1.3718, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 2.0637152307934228e-06, | |
| "loss": 1.3293, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 1.995289641043768e-06, | |
| "loss": 1.3677, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 1.927970467097573e-06, | |
| "loss": 1.409, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 1.8617609466829666e-06, | |
| "loss": 1.3973, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 1.7966642641590925e-06, | |
| "loss": 1.3991, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 1.732683550362954e-06, | |
| "loss": 1.3662, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 1.6698218824588164e-06, | |
| "loss": 1.3871, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_loss": 1.4001953601837158, | |
| "eval_runtime": 19.9558, | |
| "eval_samples_per_second": 24.504, | |
| "eval_steps_per_second": 6.164, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 1.6080822837902382e-06, | |
| "loss": 1.4072, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 1.5474677237346468e-06, | |
| "loss": 1.3841, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 1.4879811175605302e-06, | |
| "loss": 1.3729, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 1.4296253262872234e-06, | |
| "loss": 1.3648, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 1.3724031565473112e-06, | |
| "loss": 1.4043, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 1.316317360451641e-06, | |
| "loss": 1.4135, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 1.2613706354569571e-06, | |
| "loss": 1.399, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 1.2075656242361732e-06, | |
| "loss": 1.4024, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 1.1549049145512636e-06, | |
| "loss": 1.3668, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 1.1033910391288065e-06, | |
| "loss": 1.3692, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_loss": 1.399943232536316, | |
| "eval_runtime": 19.9364, | |
| "eval_samples_per_second": 24.528, | |
| "eval_steps_per_second": 6.17, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 1.0530264755381824e-06, | |
| "loss": 1.3908, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 1.0038136460723963e-06, | |
| "loss": 1.3999, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 9.557549176315934e-07, | |
| "loss": 1.4098, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 9.088526016092142e-07, | |
| "loss": 1.3973, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 8.631089537808307e-07, | |
| "loss": 1.3758, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 8.185261741956551e-07, | |
| "loss": 1.3197, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 7.751064070707248e-07, | |
| "loss": 1.3794, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 7.328517406877761e-07, | |
| "loss": 1.3764, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 6.917642072928137e-07, | |
| "loss": 1.4063, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 6.51845782998356e-07, | |
| "loss": 1.3959, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "eval_loss": 1.3998632431030273, | |
| "eval_runtime": 19.9527, | |
| "eval_samples_per_second": 24.508, | |
| "eval_steps_per_second": 6.165, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 6.130983876884155e-07, | |
| "loss": 1.3767, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 5.755238849261407e-07, | |
| "loss": 1.3619, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 5.391240818642007e-07, | |
| "loss": 1.3723, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 5.039007291578579e-07, | |
| "loss": 1.4262, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 4.698555208807853e-07, | |
| "loss": 1.3775, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 4.3699009444357344e-07, | |
| "loss": 1.4159, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 4.0530603051499584e-07, | |
| "loss": 1.4007, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.7480485294596747e-07, | |
| "loss": 1.3898, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 3.454880286962781e-07, | |
| "loss": 1.4173, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 3.1735696776400703e-07, | |
| "loss": 1.3539, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "eval_loss": 1.3998057842254639, | |
| "eval_runtime": 19.9318, | |
| "eval_samples_per_second": 24.534, | |
| "eval_steps_per_second": 6.171, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2.9041302311774433e-07, | |
| "loss": 1.3803, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.646574906314925e-07, | |
| "loss": 1.4141, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.4009160902235816e-07, | |
| "loss": 1.3444, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.1671655979096094e-07, | |
| "loss": 1.3669, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.9453346716462317e-07, | |
| "loss": 1.3776, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.73543398043291e-07, | |
| "loss": 1.4048, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.537473619482227e-07, | |
| "loss": 1.3623, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.351463109734441e-07, | |
| "loss": 1.3861, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.1774113973994083e-07, | |
| "loss": 1.3323, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.0153268535264827e-07, | |
| "loss": 1.3646, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_loss": 1.3997734785079956, | |
| "eval_runtime": 19.9549, | |
| "eval_samples_per_second": 24.505, | |
| "eval_steps_per_second": 6.164, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 8.652172736017816e-08, | |
| "loss": 1.3963, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 7.270898771733481e-08, | |
| "loss": 1.3812, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 6.00951307503872e-08, | |
| "loss": 1.375, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 4.868076312512515e-08, | |
| "loss": 1.4015, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 3.846643381766879e-08, | |
| "loss": 1.3795, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 2.94526340880813e-08, | |
| "loss": 1.4244, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 2.1639797456723952e-08, | |
| "loss": 1.3731, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.5028299683425562e-08, | |
| "loss": 1.4061, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 9.618458749391379e-09, | |
| "loss": 1.3842, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 5.41053484192644e-09, | |
| "loss": 1.3693, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_loss": 1.3998451232910156, | |
| "eval_runtime": 19.9451, | |
| "eval_samples_per_second": 24.517, | |
| "eval_steps_per_second": 6.167, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 2.4047303419094667e-09, | |
| "loss": 1.3439, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 6.011898140617645e-10, | |
| "loss": 1.3848, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.3852, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 4530, | |
| "total_flos": 1.828885230092206e+18, | |
| "train_loss": 1.4043121354732555, | |
| "train_runtime": 20600.2987, | |
| "train_samples_per_second": 7.038, | |
| "train_steps_per_second": 0.22 | |
| } | |
| ], | |
| "max_steps": 4530, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.828885230092206e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |