|
{ |
|
"best_metric": 1.0115959644317627, |
|
"best_model_checkpoint": "checkpoints/instrucode/text_models/llama-2-13b/checkpoint-6200", |
|
"epoch": 1.9838412926965843, |
|
"eval_steps": 200, |
|
"global_step": 6200, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 1e-05, |
|
"loss": 1.8592, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 2e-05, |
|
"loss": 1.7835, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 3e-05, |
|
"loss": 1.7661, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4e-05, |
|
"loss": 1.5736, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 5e-05, |
|
"loss": 1.3416, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 6e-05, |
|
"loss": 1.1455, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 7e-05, |
|
"loss": 1.0841, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 7.900000000000001e-05, |
|
"loss": 1.0352, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 8.900000000000001e-05, |
|
"loss": 1.0574, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 9.900000000000001e-05, |
|
"loss": 1.0802, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 9.994202898550726e-05, |
|
"loss": 1.027, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 9.987761674718196e-05, |
|
"loss": 1.0086, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 9.981320450885668e-05, |
|
"loss": 1.0188, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 9.974879227053141e-05, |
|
"loss": 1.0513, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 9.968438003220612e-05, |
|
"loss": 1.074, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 9.962640901771337e-05, |
|
"loss": 1.0432, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 9.956199677938809e-05, |
|
"loss": 1.0586, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 9.949758454106281e-05, |
|
"loss": 1.0195, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 9.943961352657005e-05, |
|
"loss": 1.1137, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 9.937520128824477e-05, |
|
"loss": 1.012, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"eval_loss": 1.050466537475586, |
|
"eval_runtime": 186.7925, |
|
"eval_samples_per_second": 10.707, |
|
"eval_steps_per_second": 1.338, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 9.931078904991949e-05, |
|
"loss": 1.0544, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 9.924637681159421e-05, |
|
"loss": 1.0796, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 9.918196457326893e-05, |
|
"loss": 1.0681, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 9.911755233494364e-05, |
|
"loss": 1.066, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 9.905314009661836e-05, |
|
"loss": 1.0483, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 9.898872785829308e-05, |
|
"loss": 1.0917, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 9.89243156199678e-05, |
|
"loss": 1.0391, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 9.885990338164252e-05, |
|
"loss": 1.023, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 9.879549114331724e-05, |
|
"loss": 1.072, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 9.873107890499196e-05, |
|
"loss": 1.038, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 9.866666666666668e-05, |
|
"loss": 1.0242, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 9.86022544283414e-05, |
|
"loss": 1.0045, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 9.85378421900161e-05, |
|
"loss": 1.0362, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 9.847342995169082e-05, |
|
"loss": 1.0272, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 9.840901771336555e-05, |
|
"loss": 0.9938, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 9.834460547504027e-05, |
|
"loss": 1.0338, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 9.828019323671497e-05, |
|
"loss": 1.0146, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 9.821578099838969e-05, |
|
"loss": 1.0324, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 9.815136876006442e-05, |
|
"loss": 1.0159, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 9.808695652173914e-05, |
|
"loss": 1.0283, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"eval_loss": 1.041812777519226, |
|
"eval_runtime": 187.3424, |
|
"eval_samples_per_second": 10.676, |
|
"eval_steps_per_second": 1.334, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 9.802254428341385e-05, |
|
"loss": 1.0189, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 9.795813204508857e-05, |
|
"loss": 1.0623, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 9.789371980676329e-05, |
|
"loss": 1.0266, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 9.7829307568438e-05, |
|
"loss": 1.0436, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 9.776489533011272e-05, |
|
"loss": 1.0393, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 9.770048309178744e-05, |
|
"loss": 1.0452, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 9.763607085346216e-05, |
|
"loss": 1.06, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 9.757165861513688e-05, |
|
"loss": 1.0115, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 9.75072463768116e-05, |
|
"loss": 1.0523, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 9.744283413848632e-05, |
|
"loss": 1.028, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 9.737842190016104e-05, |
|
"loss": 1.0984, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 9.731400966183575e-05, |
|
"loss": 1.0312, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 9.724959742351047e-05, |
|
"loss": 1.0687, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 9.718518518518519e-05, |
|
"loss": 1.0485, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 9.712077294685991e-05, |
|
"loss": 1.0423, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 9.705636070853462e-05, |
|
"loss": 1.0005, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 9.699194847020935e-05, |
|
"loss": 1.0217, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 9.692753623188407e-05, |
|
"loss": 1.0233, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 9.686312399355879e-05, |
|
"loss": 1.0381, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 9.679871175523349e-05, |
|
"loss": 1.0045, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"eval_loss": 1.0341911315917969, |
|
"eval_runtime": 190.2864, |
|
"eval_samples_per_second": 10.51, |
|
"eval_steps_per_second": 1.314, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 9.673429951690822e-05, |
|
"loss": 1.0345, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 9.666988727858294e-05, |
|
"loss": 1.0507, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 9.660547504025766e-05, |
|
"loss": 1.0261, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 9.654106280193237e-05, |
|
"loss": 1.0063, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 9.647665056360708e-05, |
|
"loss": 1.011, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 9.641223832528182e-05, |
|
"loss": 0.9829, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 9.634782608695652e-05, |
|
"loss": 1.0007, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 9.628341384863124e-05, |
|
"loss": 1.0159, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 9.621900161030596e-05, |
|
"loss": 1.0307, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 9.615458937198069e-05, |
|
"loss": 0.9949, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 9.60901771336554e-05, |
|
"loss": 1.0362, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 9.602576489533011e-05, |
|
"loss": 1.0397, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 9.596135265700483e-05, |
|
"loss": 1.0709, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 9.589694041867955e-05, |
|
"loss": 1.0271, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 9.583252818035427e-05, |
|
"loss": 1.0336, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 9.576811594202899e-05, |
|
"loss": 0.9954, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 9.570370370370371e-05, |
|
"loss": 0.9927, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 9.563929146537843e-05, |
|
"loss": 1.0313, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 9.557487922705315e-05, |
|
"loss": 1.0671, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 9.551046698872786e-05, |
|
"loss": 1.0038, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"eval_loss": 1.0327339172363281, |
|
"eval_runtime": 187.9065, |
|
"eval_samples_per_second": 10.644, |
|
"eval_steps_per_second": 1.33, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 9.544605475040258e-05, |
|
"loss": 1.0013, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 9.53816425120773e-05, |
|
"loss": 0.9574, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 9.531723027375202e-05, |
|
"loss": 1.0208, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 9.525281803542674e-05, |
|
"loss": 1.0067, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 9.518840579710146e-05, |
|
"loss": 1.0408, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 9.512399355877616e-05, |
|
"loss": 1.0299, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 9.505958132045088e-05, |
|
"loss": 1.0195, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 9.499516908212561e-05, |
|
"loss": 1.0095, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 9.493075684380033e-05, |
|
"loss": 1.0174, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 9.486634460547504e-05, |
|
"loss": 1.0238, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 9.480193236714976e-05, |
|
"loss": 1.0506, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 9.473752012882449e-05, |
|
"loss": 1.0308, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 9.467310789049921e-05, |
|
"loss": 1.018, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 9.460869565217391e-05, |
|
"loss": 1.058, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 9.454428341384863e-05, |
|
"loss": 1.0226, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 9.447987117552335e-05, |
|
"loss": 1.0569, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 9.441545893719808e-05, |
|
"loss": 0.988, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 9.435104669887279e-05, |
|
"loss": 1.0036, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 9.42866344605475e-05, |
|
"loss": 1.012, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 9.422222222222223e-05, |
|
"loss": 0.9998, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"eval_loss": 1.0286028385162354, |
|
"eval_runtime": 186.8358, |
|
"eval_samples_per_second": 10.705, |
|
"eval_steps_per_second": 1.338, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 9.415780998389694e-05, |
|
"loss": 1.0794, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 9.409339774557166e-05, |
|
"loss": 1.0211, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 9.402898550724638e-05, |
|
"loss": 1.039, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 9.39645732689211e-05, |
|
"loss": 1.0337, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 9.390016103059582e-05, |
|
"loss": 1.0546, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 9.383574879227054e-05, |
|
"loss": 1.0126, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 9.377133655394526e-05, |
|
"loss": 1.01, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 9.370692431561997e-05, |
|
"loss": 1.005, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 9.364251207729468e-05, |
|
"loss": 1.0742, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 9.357809983896941e-05, |
|
"loss": 1.0131, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 9.351368760064413e-05, |
|
"loss": 1.0148, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 9.344927536231885e-05, |
|
"loss": 1.0298, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 9.338486312399355e-05, |
|
"loss": 1.0235, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 9.332045088566829e-05, |
|
"loss": 1.0461, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 9.3256038647343e-05, |
|
"loss": 1.0328, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 9.319162640901772e-05, |
|
"loss": 1.0336, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 9.312721417069243e-05, |
|
"loss": 1.0651, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 9.306280193236715e-05, |
|
"loss": 0.9966, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 9.299838969404188e-05, |
|
"loss": 1.0428, |
|
"step": 1190 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 9.293397745571659e-05, |
|
"loss": 1.0506, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"eval_loss": 1.0272533893585205, |
|
"eval_runtime": 193.4811, |
|
"eval_samples_per_second": 10.337, |
|
"eval_steps_per_second": 1.292, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 9.28695652173913e-05, |
|
"loss": 1.0431, |
|
"step": 1210 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 9.280515297906602e-05, |
|
"loss": 0.9844, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 9.274074074074076e-05, |
|
"loss": 1.0488, |
|
"step": 1230 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 9.267632850241546e-05, |
|
"loss": 0.9965, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 9.261191626409018e-05, |
|
"loss": 1.0397, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 9.25475040257649e-05, |
|
"loss": 1.0347, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 9.248309178743962e-05, |
|
"loss": 0.9955, |
|
"step": 1270 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 9.241867954911434e-05, |
|
"loss": 0.9883, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 9.235426731078905e-05, |
|
"loss": 0.9947, |
|
"step": 1290 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 9.228985507246377e-05, |
|
"loss": 1.0275, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 9.222544283413849e-05, |
|
"loss": 0.9823, |
|
"step": 1310 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 9.216103059581321e-05, |
|
"loss": 1.0227, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 9.209661835748793e-05, |
|
"loss": 1.0172, |
|
"step": 1330 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 9.203220611916265e-05, |
|
"loss": 0.9689, |
|
"step": 1340 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 9.196779388083737e-05, |
|
"loss": 1.0471, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 9.190338164251207e-05, |
|
"loss": 1.0608, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 9.18389694041868e-05, |
|
"loss": 1.0556, |
|
"step": 1370 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 9.177455716586152e-05, |
|
"loss": 0.9823, |
|
"step": 1380 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 9.171014492753624e-05, |
|
"loss": 1.0325, |
|
"step": 1390 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 9.164573268921095e-05, |
|
"loss": 1.0067, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"eval_loss": 1.0259579420089722, |
|
"eval_runtime": 187.0176, |
|
"eval_samples_per_second": 10.694, |
|
"eval_steps_per_second": 1.337, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 9.158132045088568e-05, |
|
"loss": 1.0186, |
|
"step": 1410 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 9.15169082125604e-05, |
|
"loss": 1.0293, |
|
"step": 1420 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 9.14524959742351e-05, |
|
"loss": 1.0173, |
|
"step": 1430 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 9.138808373590982e-05, |
|
"loss": 1.064, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 9.132367149758455e-05, |
|
"loss": 1.0415, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 9.125925925925927e-05, |
|
"loss": 1.0465, |
|
"step": 1460 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 9.119484702093398e-05, |
|
"loss": 1.0284, |
|
"step": 1470 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 9.11304347826087e-05, |
|
"loss": 1.036, |
|
"step": 1480 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 9.106602254428341e-05, |
|
"loss": 1.0351, |
|
"step": 1490 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 9.100161030595815e-05, |
|
"loss": 1.0446, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 9.093719806763285e-05, |
|
"loss": 1.0019, |
|
"step": 1510 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 9.087278582930757e-05, |
|
"loss": 1.018, |
|
"step": 1520 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 9.080837359098229e-05, |
|
"loss": 1.0221, |
|
"step": 1530 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 9.074396135265701e-05, |
|
"loss": 1.047, |
|
"step": 1540 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 9.067954911433173e-05, |
|
"loss": 1.0105, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 9.061513687600645e-05, |
|
"loss": 1.0245, |
|
"step": 1560 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 9.055072463768116e-05, |
|
"loss": 1.0513, |
|
"step": 1570 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 9.048631239935588e-05, |
|
"loss": 1.0033, |
|
"step": 1580 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 9.04219001610306e-05, |
|
"loss": 0.9867, |
|
"step": 1590 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 9.035748792270532e-05, |
|
"loss": 1.0351, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"eval_loss": 1.0244308710098267, |
|
"eval_runtime": 186.9957, |
|
"eval_samples_per_second": 10.695, |
|
"eval_steps_per_second": 1.337, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 9.029307568438004e-05, |
|
"loss": 1.0109, |
|
"step": 1610 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 9.022866344605474e-05, |
|
"loss": 1.0464, |
|
"step": 1620 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 9.016425120772948e-05, |
|
"loss": 1.0204, |
|
"step": 1630 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 9.00998389694042e-05, |
|
"loss": 1.0605, |
|
"step": 1640 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 9.003542673107891e-05, |
|
"loss": 1.0209, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 8.997101449275362e-05, |
|
"loss": 1.0588, |
|
"step": 1660 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 8.990660225442834e-05, |
|
"loss": 1.0094, |
|
"step": 1670 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 8.984219001610307e-05, |
|
"loss": 1.1152, |
|
"step": 1680 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 8.977777777777779e-05, |
|
"loss": 1.0059, |
|
"step": 1690 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 8.97133655394525e-05, |
|
"loss": 1.042, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 8.964895330112721e-05, |
|
"loss": 0.9825, |
|
"step": 1710 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 8.958454106280194e-05, |
|
"loss": 1.0188, |
|
"step": 1720 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 8.952012882447666e-05, |
|
"loss": 1.0384, |
|
"step": 1730 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 8.945571658615137e-05, |
|
"loss": 1.0454, |
|
"step": 1740 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 8.939130434782609e-05, |
|
"loss": 1.0252, |
|
"step": 1750 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 8.932689210950082e-05, |
|
"loss": 1.0093, |
|
"step": 1760 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 8.926247987117552e-05, |
|
"loss": 1.0079, |
|
"step": 1770 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 8.919806763285024e-05, |
|
"loss": 1.0162, |
|
"step": 1780 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 8.913365539452496e-05, |
|
"loss": 1.0445, |
|
"step": 1790 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 8.906924315619968e-05, |
|
"loss": 1.0151, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"eval_loss": 1.022465467453003, |
|
"eval_runtime": 187.4046, |
|
"eval_samples_per_second": 10.672, |
|
"eval_steps_per_second": 1.334, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 8.90048309178744e-05, |
|
"loss": 1.0026, |
|
"step": 1810 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 8.894041867954912e-05, |
|
"loss": 1.0338, |
|
"step": 1820 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 8.887600644122384e-05, |
|
"loss": 1.0004, |
|
"step": 1830 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 8.881159420289856e-05, |
|
"loss": 1.0013, |
|
"step": 1840 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 8.874718196457327e-05, |
|
"loss": 0.9698, |
|
"step": 1850 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 8.868276972624799e-05, |
|
"loss": 1.0308, |
|
"step": 1860 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 8.861835748792271e-05, |
|
"loss": 0.9898, |
|
"step": 1870 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 8.855394524959743e-05, |
|
"loss": 1.0491, |
|
"step": 1880 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 8.848953301127214e-05, |
|
"loss": 1.0242, |
|
"step": 1890 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 8.842512077294687e-05, |
|
"loss": 1.0419, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 8.836070853462159e-05, |
|
"loss": 1.0346, |
|
"step": 1910 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 8.82962962962963e-05, |
|
"loss": 0.9888, |
|
"step": 1920 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 8.823188405797101e-05, |
|
"loss": 1.0115, |
|
"step": 1930 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 8.816747181964574e-05, |
|
"loss": 1.0193, |
|
"step": 1940 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 8.810305958132046e-05, |
|
"loss": 1.0633, |
|
"step": 1950 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 8.803864734299517e-05, |
|
"loss": 1.048, |
|
"step": 1960 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 8.797423510466989e-05, |
|
"loss": 1.0345, |
|
"step": 1970 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 8.79098228663446e-05, |
|
"loss": 1.0477, |
|
"step": 1980 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 8.784541062801934e-05, |
|
"loss": 1.0232, |
|
"step": 1990 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 8.778099838969404e-05, |
|
"loss": 1.0614, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"eval_loss": 1.0219651460647583, |
|
"eval_runtime": 187.5045, |
|
"eval_samples_per_second": 10.666, |
|
"eval_steps_per_second": 1.333, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 8.771658615136876e-05, |
|
"loss": 1.0489, |
|
"step": 2010 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 8.765217391304348e-05, |
|
"loss": 0.9984, |
|
"step": 2020 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 8.758776167471821e-05, |
|
"loss": 1.0021, |
|
"step": 2030 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 8.752334943639292e-05, |
|
"loss": 1.0382, |
|
"step": 2040 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 8.745893719806763e-05, |
|
"loss": 1.0086, |
|
"step": 2050 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 8.739452495974235e-05, |
|
"loss": 1.0211, |
|
"step": 2060 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 8.733011272141707e-05, |
|
"loss": 0.9975, |
|
"step": 2070 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 8.726570048309179e-05, |
|
"loss": 1.0468, |
|
"step": 2080 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 8.720128824476651e-05, |
|
"loss": 1.0646, |
|
"step": 2090 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 8.713687600644123e-05, |
|
"loss": 1.0311, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 8.707246376811595e-05, |
|
"loss": 1.0253, |
|
"step": 2110 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 8.700805152979067e-05, |
|
"loss": 1.0511, |
|
"step": 2120 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 8.694363929146538e-05, |
|
"loss": 1.0652, |
|
"step": 2130 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 8.68792270531401e-05, |
|
"loss": 1.0397, |
|
"step": 2140 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 8.681481481481482e-05, |
|
"loss": 1.0262, |
|
"step": 2150 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 8.675040257648954e-05, |
|
"loss": 1.0374, |
|
"step": 2160 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 8.668599033816426e-05, |
|
"loss": 1.0446, |
|
"step": 2170 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 8.662157809983898e-05, |
|
"loss": 1.0278, |
|
"step": 2180 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 8.655716586151368e-05, |
|
"loss": 0.9984, |
|
"step": 2190 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 8.64927536231884e-05, |
|
"loss": 1.0373, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"eval_loss": 1.020651936531067, |
|
"eval_runtime": 187.3402, |
|
"eval_samples_per_second": 10.676, |
|
"eval_steps_per_second": 1.334, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 8.642834138486313e-05, |
|
"loss": 1.0451, |
|
"step": 2210 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 8.636392914653785e-05, |
|
"loss": 1.0249, |
|
"step": 2220 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 8.629951690821256e-05, |
|
"loss": 0.9943, |
|
"step": 2230 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 8.623510466988728e-05, |
|
"loss": 1.0084, |
|
"step": 2240 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 8.617069243156201e-05, |
|
"loss": 1.0046, |
|
"step": 2250 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 8.610628019323673e-05, |
|
"loss": 0.982, |
|
"step": 2260 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 8.604186795491143e-05, |
|
"loss": 1.0438, |
|
"step": 2270 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 8.597745571658615e-05, |
|
"loss": 1.032, |
|
"step": 2280 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 8.591304347826087e-05, |
|
"loss": 1.0066, |
|
"step": 2290 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 8.584863123993559e-05, |
|
"loss": 1.0412, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 8.578421900161031e-05, |
|
"loss": 0.9981, |
|
"step": 2310 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 8.571980676328503e-05, |
|
"loss": 1.0111, |
|
"step": 2320 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 8.565539452495974e-05, |
|
"loss": 1.0057, |
|
"step": 2330 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 8.559098228663446e-05, |
|
"loss": 1.022, |
|
"step": 2340 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 8.552657004830918e-05, |
|
"loss": 0.9963, |
|
"step": 2350 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 8.54621578099839e-05, |
|
"loss": 1.0382, |
|
"step": 2360 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 8.539774557165862e-05, |
|
"loss": 1.0083, |
|
"step": 2370 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 8.533333333333334e-05, |
|
"loss": 1.0126, |
|
"step": 2380 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 8.526892109500806e-05, |
|
"loss": 0.9937, |
|
"step": 2390 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 8.520450885668278e-05, |
|
"loss": 1.0266, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"eval_loss": 1.0203664302825928, |
|
"eval_runtime": 188.9153, |
|
"eval_samples_per_second": 10.587, |
|
"eval_steps_per_second": 1.323, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 8.51400966183575e-05, |
|
"loss": 1.0608, |
|
"step": 2410 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 8.50756843800322e-05, |
|
"loss": 1.0238, |
|
"step": 2420 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 8.501127214170693e-05, |
|
"loss": 1.0271, |
|
"step": 2430 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 8.494685990338165e-05, |
|
"loss": 1.0275, |
|
"step": 2440 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 8.488244766505637e-05, |
|
"loss": 1.0453, |
|
"step": 2450 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 8.481803542673107e-05, |
|
"loss": 1.045, |
|
"step": 2460 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 8.475362318840581e-05, |
|
"loss": 1.0463, |
|
"step": 2470 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 8.468921095008053e-05, |
|
"loss": 1.0199, |
|
"step": 2480 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 8.462479871175524e-05, |
|
"loss": 0.9889, |
|
"step": 2490 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 8.456038647342995e-05, |
|
"loss": 0.9973, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 8.449597423510467e-05, |
|
"loss": 1.041, |
|
"step": 2510 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 8.44315619967794e-05, |
|
"loss": 1.0169, |
|
"step": 2520 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 8.43671497584541e-05, |
|
"loss": 1.0221, |
|
"step": 2530 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 8.430273752012882e-05, |
|
"loss": 1.0357, |
|
"step": 2540 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 8.423832528180354e-05, |
|
"loss": 0.9808, |
|
"step": 2550 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 8.417391304347828e-05, |
|
"loss": 1.0055, |
|
"step": 2560 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 8.410950080515298e-05, |
|
"loss": 1.0113, |
|
"step": 2570 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 8.40450885668277e-05, |
|
"loss": 1.0418, |
|
"step": 2580 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 8.398067632850242e-05, |
|
"loss": 1.0252, |
|
"step": 2590 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 8.391626409017714e-05, |
|
"loss": 1.0141, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"eval_loss": 1.0183026790618896, |
|
"eval_runtime": 188.3677, |
|
"eval_samples_per_second": 10.618, |
|
"eval_steps_per_second": 1.327, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 8.385185185185186e-05, |
|
"loss": 0.9696, |
|
"step": 2610 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 8.378743961352657e-05, |
|
"loss": 1.0527, |
|
"step": 2620 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 8.372302737520129e-05, |
|
"loss": 1.0197, |
|
"step": 2630 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 8.365861513687601e-05, |
|
"loss": 1.0035, |
|
"step": 2640 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 8.359420289855073e-05, |
|
"loss": 1.0426, |
|
"step": 2650 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 8.352979066022545e-05, |
|
"loss": 1.0199, |
|
"step": 2660 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 8.346537842190017e-05, |
|
"loss": 1.0231, |
|
"step": 2670 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 8.340096618357489e-05, |
|
"loss": 1.0153, |
|
"step": 2680 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 8.33365539452496e-05, |
|
"loss": 0.9991, |
|
"step": 2690 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 8.327214170692432e-05, |
|
"loss": 1.0103, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 8.320772946859904e-05, |
|
"loss": 0.9782, |
|
"step": 2710 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 8.314331723027375e-05, |
|
"loss": 1.0254, |
|
"step": 2720 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 8.307890499194847e-05, |
|
"loss": 1.0162, |
|
"step": 2730 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 8.30144927536232e-05, |
|
"loss": 0.9674, |
|
"step": 2740 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 8.295008051529792e-05, |
|
"loss": 1.0262, |
|
"step": 2750 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 8.288566827697262e-05, |
|
"loss": 1.0294, |
|
"step": 2760 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 8.282125603864734e-05, |
|
"loss": 1.0064, |
|
"step": 2770 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 8.275684380032207e-05, |
|
"loss": 0.9869, |
|
"step": 2780 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 8.269243156199679e-05, |
|
"loss": 1.0191, |
|
"step": 2790 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 8.26280193236715e-05, |
|
"loss": 1.0347, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"eval_loss": 1.0175596475601196, |
|
"eval_runtime": 187.2212, |
|
"eval_samples_per_second": 10.683, |
|
"eval_steps_per_second": 1.335, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 8.256360708534622e-05, |
|
"loss": 1.0247, |
|
"step": 2810 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 8.249919484702093e-05, |
|
"loss": 1.016, |
|
"step": 2820 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 8.243478260869565e-05, |
|
"loss": 1.0039, |
|
"step": 2830 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 8.237037037037037e-05, |
|
"loss": 1.0306, |
|
"step": 2840 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 8.230595813204509e-05, |
|
"loss": 1.0314, |
|
"step": 2850 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 8.224154589371981e-05, |
|
"loss": 0.9795, |
|
"step": 2860 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 8.217713365539453e-05, |
|
"loss": 1.0489, |
|
"step": 2870 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 8.211272141706925e-05, |
|
"loss": 1.0023, |
|
"step": 2880 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 8.204830917874397e-05, |
|
"loss": 0.9973, |
|
"step": 2890 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 8.198389694041868e-05, |
|
"loss": 1.0281, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 8.19194847020934e-05, |
|
"loss": 1.0256, |
|
"step": 2910 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 8.185507246376812e-05, |
|
"loss": 1.015, |
|
"step": 2920 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 8.179066022544284e-05, |
|
"loss": 0.981, |
|
"step": 2930 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 8.172624798711756e-05, |
|
"loss": 1.0001, |
|
"step": 2940 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 8.166183574879226e-05, |
|
"loss": 1.0324, |
|
"step": 2950 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 8.1597423510467e-05, |
|
"loss": 0.9589, |
|
"step": 2960 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 8.153301127214171e-05, |
|
"loss": 0.994, |
|
"step": 2970 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 8.146859903381643e-05, |
|
"loss": 1.0238, |
|
"step": 2980 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 8.140418679549114e-05, |
|
"loss": 1.0347, |
|
"step": 2990 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 8.133977455716587e-05, |
|
"loss": 1.0248, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"eval_loss": 1.0177215337753296, |
|
"eval_runtime": 187.3372, |
|
"eval_samples_per_second": 10.676, |
|
"eval_steps_per_second": 1.334, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 8.127536231884059e-05, |
|
"loss": 1.0349, |
|
"step": 3010 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 8.121095008051531e-05, |
|
"loss": 1.0264, |
|
"step": 3020 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 8.114653784219001e-05, |
|
"loss": 0.9841, |
|
"step": 3030 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 8.108212560386473e-05, |
|
"loss": 1.0262, |
|
"step": 3040 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 8.101771336553946e-05, |
|
"loss": 1.0255, |
|
"step": 3050 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 8.095330112721417e-05, |
|
"loss": 0.9856, |
|
"step": 3060 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 8.088888888888889e-05, |
|
"loss": 1.0685, |
|
"step": 3070 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 8.082447665056361e-05, |
|
"loss": 1.0094, |
|
"step": 3080 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 8.076006441223834e-05, |
|
"loss": 1.022, |
|
"step": 3090 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 8.069565217391304e-05, |
|
"loss": 0.9743, |
|
"step": 3100 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 8.063123993558776e-05, |
|
"loss": 1.0228, |
|
"step": 3110 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 8.056682769726248e-05, |
|
"loss": 1.0398, |
|
"step": 3120 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 8.05024154589372e-05, |
|
"loss": 1.0022, |
|
"step": 3130 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 8.043800322061192e-05, |
|
"loss": 1.0136, |
|
"step": 3140 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 8.038003220611917e-05, |
|
"loss": 0.9806, |
|
"step": 3150 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 8.031561996779389e-05, |
|
"loss": 1.0222, |
|
"step": 3160 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 8.02512077294686e-05, |
|
"loss": 0.9584, |
|
"step": 3170 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 8.018679549114332e-05, |
|
"loss": 0.9746, |
|
"step": 3180 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 8.012238325281803e-05, |
|
"loss": 1.0131, |
|
"step": 3190 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 8.005797101449277e-05, |
|
"loss": 0.977, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"eval_loss": 1.0170557498931885, |
|
"eval_runtime": 187.1066, |
|
"eval_samples_per_second": 10.689, |
|
"eval_steps_per_second": 1.336, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 7.999355877616747e-05, |
|
"loss": 1.0382, |
|
"step": 3210 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 7.992914653784219e-05, |
|
"loss": 0.958, |
|
"step": 3220 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 7.986473429951691e-05, |
|
"loss": 1.0106, |
|
"step": 3230 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 7.980032206119164e-05, |
|
"loss": 1.0137, |
|
"step": 3240 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 7.973590982286635e-05, |
|
"loss": 0.9941, |
|
"step": 3250 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 7.967149758454107e-05, |
|
"loss": 1.0061, |
|
"step": 3260 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 7.960708534621578e-05, |
|
"loss": 1.0035, |
|
"step": 3270 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 7.95426731078905e-05, |
|
"loss": 1.0023, |
|
"step": 3280 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 7.947826086956522e-05, |
|
"loss": 0.9759, |
|
"step": 3290 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 7.941384863123994e-05, |
|
"loss": 0.9744, |
|
"step": 3300 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 7.934943639291466e-05, |
|
"loss": 1.0105, |
|
"step": 3310 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 7.928502415458938e-05, |
|
"loss": 0.9845, |
|
"step": 3320 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 7.92206119162641e-05, |
|
"loss": 1.0166, |
|
"step": 3330 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 7.915619967793881e-05, |
|
"loss": 0.9917, |
|
"step": 3340 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 7.909178743961353e-05, |
|
"loss": 0.994, |
|
"step": 3350 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 7.902737520128824e-05, |
|
"loss": 1.0173, |
|
"step": 3360 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 7.896296296296297e-05, |
|
"loss": 1.0043, |
|
"step": 3370 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 7.889855072463769e-05, |
|
"loss": 1.0058, |
|
"step": 3380 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 7.883413848631241e-05, |
|
"loss": 1.0035, |
|
"step": 3390 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 7.876972624798711e-05, |
|
"loss": 0.9418, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"eval_loss": 1.017248511314392, |
|
"eval_runtime": 187.1833, |
|
"eval_samples_per_second": 10.685, |
|
"eval_steps_per_second": 1.336, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 7.870531400966183e-05, |
|
"loss": 1.0129, |
|
"step": 3410 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 7.864090177133656e-05, |
|
"loss": 0.9637, |
|
"step": 3420 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 7.857648953301128e-05, |
|
"loss": 0.9824, |
|
"step": 3430 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 7.851207729468599e-05, |
|
"loss": 0.9758, |
|
"step": 3440 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 7.844766505636071e-05, |
|
"loss": 0.9935, |
|
"step": 3450 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 7.838325281803544e-05, |
|
"loss": 1.0135, |
|
"step": 3460 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 7.831884057971014e-05, |
|
"loss": 1.0353, |
|
"step": 3470 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 7.825442834138486e-05, |
|
"loss": 0.9855, |
|
"step": 3480 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 7.819001610305958e-05, |
|
"loss": 0.9416, |
|
"step": 3490 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 7.81256038647343e-05, |
|
"loss": 0.9333, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 7.806119162640902e-05, |
|
"loss": 0.9864, |
|
"step": 3510 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 7.799677938808374e-05, |
|
"loss": 1.0263, |
|
"step": 3520 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 7.793236714975846e-05, |
|
"loss": 0.9814, |
|
"step": 3530 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 7.786795491143318e-05, |
|
"loss": 1.011, |
|
"step": 3540 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 7.78035426731079e-05, |
|
"loss": 1.0106, |
|
"step": 3550 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 7.773913043478261e-05, |
|
"loss": 0.9994, |
|
"step": 3560 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 7.767471819645733e-05, |
|
"loss": 0.993, |
|
"step": 3570 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 7.761030595813205e-05, |
|
"loss": 0.9515, |
|
"step": 3580 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 7.754589371980677e-05, |
|
"loss": 1.0204, |
|
"step": 3590 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 7.748148148148149e-05, |
|
"loss": 1.0048, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"eval_loss": 1.016575574874878, |
|
"eval_runtime": 187.3536, |
|
"eval_samples_per_second": 10.675, |
|
"eval_steps_per_second": 1.334, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 7.74170692431562e-05, |
|
"loss": 0.9734, |
|
"step": 3610 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 7.735265700483092e-05, |
|
"loss": 0.9742, |
|
"step": 3620 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 7.728824476650563e-05, |
|
"loss": 1.0187, |
|
"step": 3630 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 7.722383252818036e-05, |
|
"loss": 1.0016, |
|
"step": 3640 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 7.715942028985508e-05, |
|
"loss": 0.9926, |
|
"step": 3650 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 7.70950080515298e-05, |
|
"loss": 0.9847, |
|
"step": 3660 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 7.70305958132045e-05, |
|
"loss": 1.0032, |
|
"step": 3670 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 7.696618357487924e-05, |
|
"loss": 1.0086, |
|
"step": 3680 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 7.690177133655396e-05, |
|
"loss": 0.9906, |
|
"step": 3690 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 7.683735909822866e-05, |
|
"loss": 0.9989, |
|
"step": 3700 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 7.677294685990338e-05, |
|
"loss": 0.9741, |
|
"step": 3710 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 7.67085346215781e-05, |
|
"loss": 1.0101, |
|
"step": 3720 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 7.664412238325283e-05, |
|
"loss": 1.012, |
|
"step": 3730 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 7.657971014492754e-05, |
|
"loss": 0.9715, |
|
"step": 3740 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 7.651529790660225e-05, |
|
"loss": 1.028, |
|
"step": 3750 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 7.645088566827697e-05, |
|
"loss": 0.9875, |
|
"step": 3760 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 7.63864734299517e-05, |
|
"loss": 0.9787, |
|
"step": 3770 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 7.632206119162641e-05, |
|
"loss": 0.9776, |
|
"step": 3780 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 7.625764895330113e-05, |
|
"loss": 1.0093, |
|
"step": 3790 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 7.619323671497585e-05, |
|
"loss": 0.9882, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"eval_loss": 1.0168739557266235, |
|
"eval_runtime": 187.0506, |
|
"eval_samples_per_second": 10.692, |
|
"eval_steps_per_second": 1.337, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 7.612882447665057e-05, |
|
"loss": 1.0298, |
|
"step": 3810 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 7.606441223832529e-05, |
|
"loss": 1.0028, |
|
"step": 3820 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 7.6e-05, |
|
"loss": 1.0006, |
|
"step": 3830 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 7.593558776167472e-05, |
|
"loss": 1.037, |
|
"step": 3840 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 7.587117552334944e-05, |
|
"loss": 1.0014, |
|
"step": 3850 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 7.580676328502416e-05, |
|
"loss": 0.9677, |
|
"step": 3860 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 7.574235104669888e-05, |
|
"loss": 1.0172, |
|
"step": 3870 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 7.56779388083736e-05, |
|
"loss": 1.0142, |
|
"step": 3880 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 7.561352657004832e-05, |
|
"loss": 1.0057, |
|
"step": 3890 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 7.554911433172304e-05, |
|
"loss": 0.9965, |
|
"step": 3900 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 7.548470209339775e-05, |
|
"loss": 1.003, |
|
"step": 3910 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 7.542028985507247e-05, |
|
"loss": 0.9872, |
|
"step": 3920 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 7.535587761674718e-05, |
|
"loss": 0.9755, |
|
"step": 3930 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 7.52914653784219e-05, |
|
"loss": 0.9956, |
|
"step": 3940 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 7.522705314009663e-05, |
|
"loss": 0.9961, |
|
"step": 3950 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 7.516264090177135e-05, |
|
"loss": 0.9804, |
|
"step": 3960 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 7.509822866344605e-05, |
|
"loss": 0.983, |
|
"step": 3970 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 7.503381642512077e-05, |
|
"loss": 1.0013, |
|
"step": 3980 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 7.49694041867955e-05, |
|
"loss": 0.9991, |
|
"step": 3990 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 7.490499194847022e-05, |
|
"loss": 1.0178, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"eval_loss": 1.0156399011611938, |
|
"eval_runtime": 187.0787, |
|
"eval_samples_per_second": 10.691, |
|
"eval_steps_per_second": 1.336, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 7.484057971014493e-05, |
|
"loss": 1.0248, |
|
"step": 4010 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 7.477616747181965e-05, |
|
"loss": 0.9947, |
|
"step": 4020 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 7.471175523349436e-05, |
|
"loss": 0.9559, |
|
"step": 4030 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 7.464734299516908e-05, |
|
"loss": 1.0175, |
|
"step": 4040 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 7.45829307568438e-05, |
|
"loss": 0.9885, |
|
"step": 4050 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 7.451851851851852e-05, |
|
"loss": 0.9748, |
|
"step": 4060 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 7.445410628019324e-05, |
|
"loss": 0.9759, |
|
"step": 4070 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 7.438969404186796e-05, |
|
"loss": 1.0137, |
|
"step": 4080 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 7.432528180354268e-05, |
|
"loss": 0.9924, |
|
"step": 4090 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 7.42608695652174e-05, |
|
"loss": 0.9475, |
|
"step": 4100 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 7.419645732689211e-05, |
|
"loss": 0.9703, |
|
"step": 4110 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 7.413204508856682e-05, |
|
"loss": 0.9994, |
|
"step": 4120 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 7.406763285024155e-05, |
|
"loss": 0.9504, |
|
"step": 4130 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 7.400322061191627e-05, |
|
"loss": 1.0119, |
|
"step": 4140 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 7.393880837359099e-05, |
|
"loss": 0.9706, |
|
"step": 4150 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 7.38743961352657e-05, |
|
"loss": 1.0015, |
|
"step": 4160 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 7.380998389694043e-05, |
|
"loss": 0.9691, |
|
"step": 4170 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 7.374557165861515e-05, |
|
"loss": 0.952, |
|
"step": 4180 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 7.368115942028986e-05, |
|
"loss": 1.0084, |
|
"step": 4190 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 7.361674718196457e-05, |
|
"loss": 1.0056, |
|
"step": 4200 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"eval_loss": 1.0150794982910156, |
|
"eval_runtime": 187.7211, |
|
"eval_samples_per_second": 10.654, |
|
"eval_steps_per_second": 1.332, |
|
"step": 4200 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 7.355233494363929e-05, |
|
"loss": 0.996, |
|
"step": 4210 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 7.348792270531402e-05, |
|
"loss": 1.0038, |
|
"step": 4220 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 7.342351046698873e-05, |
|
"loss": 0.9989, |
|
"step": 4230 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 7.335909822866344e-05, |
|
"loss": 1.0098, |
|
"step": 4240 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 7.329468599033816e-05, |
|
"loss": 0.975, |
|
"step": 4250 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 7.32302737520129e-05, |
|
"loss": 0.9879, |
|
"step": 4260 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 7.31658615136876e-05, |
|
"loss": 1.0246, |
|
"step": 4270 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 7.310144927536232e-05, |
|
"loss": 0.9887, |
|
"step": 4280 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 7.303703703703704e-05, |
|
"loss": 0.9639, |
|
"step": 4290 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 7.297262479871177e-05, |
|
"loss": 0.9882, |
|
"step": 4300 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 7.290821256038647e-05, |
|
"loss": 1.003, |
|
"step": 4310 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 7.28438003220612e-05, |
|
"loss": 0.9804, |
|
"step": 4320 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 7.277938808373591e-05, |
|
"loss": 0.999, |
|
"step": 4330 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 7.271497584541063e-05, |
|
"loss": 0.9829, |
|
"step": 4340 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 7.265056360708535e-05, |
|
"loss": 1.0062, |
|
"step": 4350 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 7.258615136876007e-05, |
|
"loss": 1.0131, |
|
"step": 4360 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 7.252173913043479e-05, |
|
"loss": 0.9988, |
|
"step": 4370 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 7.24573268921095e-05, |
|
"loss": 1.018, |
|
"step": 4380 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 7.239291465378422e-05, |
|
"loss": 1.0007, |
|
"step": 4390 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 7.232850241545894e-05, |
|
"loss": 1.0071, |
|
"step": 4400 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"eval_loss": 1.0151050090789795, |
|
"eval_runtime": 187.3911, |
|
"eval_samples_per_second": 10.673, |
|
"eval_steps_per_second": 1.334, |
|
"step": 4400 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 7.226409017713366e-05, |
|
"loss": 1.0332, |
|
"step": 4410 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 7.219967793880838e-05, |
|
"loss": 0.9705, |
|
"step": 4420 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 7.213526570048309e-05, |
|
"loss": 1.0056, |
|
"step": 4430 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 7.207085346215782e-05, |
|
"loss": 0.9856, |
|
"step": 4440 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 7.200644122383254e-05, |
|
"loss": 0.9867, |
|
"step": 4450 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 7.194202898550724e-05, |
|
"loss": 1.0127, |
|
"step": 4460 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 7.187761674718196e-05, |
|
"loss": 0.9923, |
|
"step": 4470 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 7.181320450885669e-05, |
|
"loss": 0.9255, |
|
"step": 4480 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 7.174879227053141e-05, |
|
"loss": 1.0205, |
|
"step": 4490 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 7.168438003220612e-05, |
|
"loss": 0.9925, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 7.161996779388084e-05, |
|
"loss": 0.9856, |
|
"step": 4510 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 7.155555555555555e-05, |
|
"loss": 1.0136, |
|
"step": 4520 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 7.149114331723029e-05, |
|
"loss": 1.0018, |
|
"step": 4530 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 7.142673107890499e-05, |
|
"loss": 0.9814, |
|
"step": 4540 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 7.136231884057971e-05, |
|
"loss": 0.9785, |
|
"step": 4550 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 7.129790660225443e-05, |
|
"loss": 1.0153, |
|
"step": 4560 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 7.123349436392915e-05, |
|
"loss": 1.0266, |
|
"step": 4570 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 7.116908212560387e-05, |
|
"loss": 1.0527, |
|
"step": 4580 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 7.110466988727859e-05, |
|
"loss": 0.9867, |
|
"step": 4590 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 7.10402576489533e-05, |
|
"loss": 1.0175, |
|
"step": 4600 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"eval_loss": 1.0150611400604248, |
|
"eval_runtime": 187.508, |
|
"eval_samples_per_second": 10.666, |
|
"eval_steps_per_second": 1.333, |
|
"step": 4600 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 7.097584541062802e-05, |
|
"loss": 1.0153, |
|
"step": 4610 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 7.091143317230274e-05, |
|
"loss": 0.9565, |
|
"step": 4620 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 7.084702093397746e-05, |
|
"loss": 0.9942, |
|
"step": 4630 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 7.078260869565218e-05, |
|
"loss": 1.0096, |
|
"step": 4640 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 7.07181964573269e-05, |
|
"loss": 0.9973, |
|
"step": 4650 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 7.065378421900162e-05, |
|
"loss": 0.9457, |
|
"step": 4660 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 7.058937198067633e-05, |
|
"loss": 0.9938, |
|
"step": 4670 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 7.052495974235105e-05, |
|
"loss": 0.9798, |
|
"step": 4680 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 7.046054750402576e-05, |
|
"loss": 0.9603, |
|
"step": 4690 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 7.039613526570049e-05, |
|
"loss": 0.975, |
|
"step": 4700 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 7.033172302737521e-05, |
|
"loss": 0.998, |
|
"step": 4710 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 7.026731078904993e-05, |
|
"loss": 1.0167, |
|
"step": 4720 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 7.020289855072463e-05, |
|
"loss": 0.9682, |
|
"step": 4730 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 7.013848631239935e-05, |
|
"loss": 0.9827, |
|
"step": 4740 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 7.007407407407408e-05, |
|
"loss": 0.9866, |
|
"step": 4750 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 7.00096618357488e-05, |
|
"loss": 1.0018, |
|
"step": 4760 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 6.994524959742351e-05, |
|
"loss": 1.0173, |
|
"step": 4770 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 6.988083735909823e-05, |
|
"loss": 1.0103, |
|
"step": 4780 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 6.981642512077296e-05, |
|
"loss": 0.9881, |
|
"step": 4790 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 6.975201288244766e-05, |
|
"loss": 1.0108, |
|
"step": 4800 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"eval_loss": 1.014174461364746, |
|
"eval_runtime": 187.5385, |
|
"eval_samples_per_second": 10.664, |
|
"eval_steps_per_second": 1.333, |
|
"step": 4800 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 6.968760064412238e-05, |
|
"loss": 0.9903, |
|
"step": 4810 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 6.96231884057971e-05, |
|
"loss": 1.0169, |
|
"step": 4820 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"learning_rate": 6.955877616747182e-05, |
|
"loss": 0.9837, |
|
"step": 4830 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"learning_rate": 6.949436392914654e-05, |
|
"loss": 0.9573, |
|
"step": 4840 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"learning_rate": 6.942995169082126e-05, |
|
"loss": 0.9814, |
|
"step": 4850 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 6.936553945249598e-05, |
|
"loss": 0.9829, |
|
"step": 4860 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 6.93011272141707e-05, |
|
"loss": 0.9956, |
|
"step": 4870 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 6.923671497584541e-05, |
|
"loss": 1.0234, |
|
"step": 4880 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 6.917230273752013e-05, |
|
"loss": 0.986, |
|
"step": 4890 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 6.910789049919485e-05, |
|
"loss": 0.9829, |
|
"step": 4900 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 6.904347826086957e-05, |
|
"loss": 1.0251, |
|
"step": 4910 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 6.897906602254429e-05, |
|
"loss": 0.9879, |
|
"step": 4920 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 6.891465378421901e-05, |
|
"loss": 1.039, |
|
"step": 4930 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 6.885024154589373e-05, |
|
"loss": 0.9752, |
|
"step": 4940 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 6.878582930756844e-05, |
|
"loss": 1.0013, |
|
"step": 4950 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 6.872141706924315e-05, |
|
"loss": 0.9558, |
|
"step": 4960 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 6.865700483091788e-05, |
|
"loss": 1.0102, |
|
"step": 4970 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 6.85925925925926e-05, |
|
"loss": 0.9936, |
|
"step": 4980 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 6.85281803542673e-05, |
|
"loss": 0.9864, |
|
"step": 4990 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 6.846376811594202e-05, |
|
"loss": 1.0204, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"eval_loss": 1.013562798500061, |
|
"eval_runtime": 187.3848, |
|
"eval_samples_per_second": 10.673, |
|
"eval_steps_per_second": 1.334, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 6.839935587761676e-05, |
|
"loss": 0.9885, |
|
"step": 5010 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"learning_rate": 6.833494363929148e-05, |
|
"loss": 0.9857, |
|
"step": 5020 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"learning_rate": 6.827053140096618e-05, |
|
"loss": 0.9764, |
|
"step": 5030 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"learning_rate": 6.82061191626409e-05, |
|
"loss": 0.9809, |
|
"step": 5040 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 6.814170692431562e-05, |
|
"loss": 0.9855, |
|
"step": 5050 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 6.807729468599035e-05, |
|
"loss": 1.0134, |
|
"step": 5060 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 6.801288244766506e-05, |
|
"loss": 0.9927, |
|
"step": 5070 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 6.794847020933977e-05, |
|
"loss": 1.0337, |
|
"step": 5080 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 6.788405797101449e-05, |
|
"loss": 0.9835, |
|
"step": 5090 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 6.781964573268923e-05, |
|
"loss": 1.0772, |
|
"step": 5100 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 6.775523349436393e-05, |
|
"loss": 0.9874, |
|
"step": 5110 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 6.769082125603865e-05, |
|
"loss": 0.9956, |
|
"step": 5120 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 6.762640901771337e-05, |
|
"loss": 1.014, |
|
"step": 5130 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 6.756199677938809e-05, |
|
"loss": 0.9957, |
|
"step": 5140 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 6.74975845410628e-05, |
|
"loss": 0.9861, |
|
"step": 5150 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 6.743317230273752e-05, |
|
"loss": 0.9824, |
|
"step": 5160 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 6.736876006441224e-05, |
|
"loss": 1.0184, |
|
"step": 5170 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 6.730434782608696e-05, |
|
"loss": 1.0121, |
|
"step": 5180 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 6.723993558776168e-05, |
|
"loss": 0.9957, |
|
"step": 5190 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 6.71755233494364e-05, |
|
"loss": 1.0209, |
|
"step": 5200 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"eval_loss": 1.0133100748062134, |
|
"eval_runtime": 187.3315, |
|
"eval_samples_per_second": 10.676, |
|
"eval_steps_per_second": 1.335, |
|
"step": 5200 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 6.711111111111112e-05, |
|
"loss": 0.9808, |
|
"step": 5210 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 6.704669887278582e-05, |
|
"loss": 1.0036, |
|
"step": 5220 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 6.698228663446055e-05, |
|
"loss": 0.9727, |
|
"step": 5230 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 6.691787439613527e-05, |
|
"loss": 1.0178, |
|
"step": 5240 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 6.685346215780999e-05, |
|
"loss": 0.976, |
|
"step": 5250 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 6.67890499194847e-05, |
|
"loss": 0.9991, |
|
"step": 5260 |
|
}, |
|
{ |
|
"epoch": 1.69, |
|
"learning_rate": 6.672463768115942e-05, |
|
"loss": 0.9956, |
|
"step": 5270 |
|
}, |
|
{ |
|
"epoch": 1.69, |
|
"learning_rate": 6.666022544283415e-05, |
|
"loss": 0.9791, |
|
"step": 5280 |
|
}, |
|
{ |
|
"epoch": 1.69, |
|
"learning_rate": 6.659581320450887e-05, |
|
"loss": 1.0081, |
|
"step": 5290 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 6.653140096618357e-05, |
|
"loss": 1.0244, |
|
"step": 5300 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 6.646698872785829e-05, |
|
"loss": 1.0103, |
|
"step": 5310 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 6.640257648953302e-05, |
|
"loss": 1.0579, |
|
"step": 5320 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 6.633816425120773e-05, |
|
"loss": 0.9774, |
|
"step": 5330 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 6.627375201288245e-05, |
|
"loss": 0.9376, |
|
"step": 5340 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 6.620933977455717e-05, |
|
"loss": 1.006, |
|
"step": 5350 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 6.614492753623188e-05, |
|
"loss": 0.9889, |
|
"step": 5360 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 6.60805152979066e-05, |
|
"loss": 1.0201, |
|
"step": 5370 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 6.601610305958132e-05, |
|
"loss": 1.0034, |
|
"step": 5380 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 6.595169082125604e-05, |
|
"loss": 1.0556, |
|
"step": 5390 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 6.588727858293076e-05, |
|
"loss": 1.0124, |
|
"step": 5400 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"eval_loss": 1.012602686882019, |
|
"eval_runtime": 187.4458, |
|
"eval_samples_per_second": 10.67, |
|
"eval_steps_per_second": 1.334, |
|
"step": 5400 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 6.582286634460548e-05, |
|
"loss": 0.9938, |
|
"step": 5410 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 6.57584541062802e-05, |
|
"loss": 0.9905, |
|
"step": 5420 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 6.569404186795492e-05, |
|
"loss": 0.9896, |
|
"step": 5430 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 6.562962962962963e-05, |
|
"loss": 1.0039, |
|
"step": 5440 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 6.556521739130434e-05, |
|
"loss": 1.0021, |
|
"step": 5450 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"learning_rate": 6.550080515297907e-05, |
|
"loss": 0.99, |
|
"step": 5460 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"learning_rate": 6.543639291465379e-05, |
|
"loss": 0.9826, |
|
"step": 5470 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"learning_rate": 6.537198067632851e-05, |
|
"loss": 0.9841, |
|
"step": 5480 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 6.530756843800321e-05, |
|
"loss": 0.9749, |
|
"step": 5490 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 6.524315619967795e-05, |
|
"loss": 0.9905, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 6.517874396135267e-05, |
|
"loss": 1.0376, |
|
"step": 5510 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 6.511433172302738e-05, |
|
"loss": 1.0513, |
|
"step": 5520 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 6.504991948470209e-05, |
|
"loss": 1.0093, |
|
"step": 5530 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 6.498550724637682e-05, |
|
"loss": 1.0263, |
|
"step": 5540 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 6.492109500805154e-05, |
|
"loss": 0.9843, |
|
"step": 5550 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 6.485668276972625e-05, |
|
"loss": 1.0204, |
|
"step": 5560 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 6.479227053140096e-05, |
|
"loss": 0.9995, |
|
"step": 5570 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 6.472785829307568e-05, |
|
"loss": 1.0205, |
|
"step": 5580 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 6.466344605475041e-05, |
|
"loss": 0.9466, |
|
"step": 5590 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 6.459903381642512e-05, |
|
"loss": 1.0259, |
|
"step": 5600 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"eval_loss": 1.0134350061416626, |
|
"eval_runtime": 187.4026, |
|
"eval_samples_per_second": 10.672, |
|
"eval_steps_per_second": 1.334, |
|
"step": 5600 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 6.453462157809984e-05, |
|
"loss": 0.9799, |
|
"step": 5610 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 6.447020933977456e-05, |
|
"loss": 1.014, |
|
"step": 5620 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 6.440579710144929e-05, |
|
"loss": 1.0418, |
|
"step": 5630 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 6.4341384863124e-05, |
|
"loss": 1.0168, |
|
"step": 5640 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 6.427697262479871e-05, |
|
"loss": 0.948, |
|
"step": 5650 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 6.421256038647343e-05, |
|
"loss": 1.0076, |
|
"step": 5660 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 6.414814814814815e-05, |
|
"loss": 1.0181, |
|
"step": 5670 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 6.408373590982287e-05, |
|
"loss": 1.0225, |
|
"step": 5680 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 6.401932367149759e-05, |
|
"loss": 1.0063, |
|
"step": 5690 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 6.395491143317231e-05, |
|
"loss": 1.0238, |
|
"step": 5700 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"learning_rate": 6.389049919484703e-05, |
|
"loss": 0.9782, |
|
"step": 5710 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"learning_rate": 6.382608695652174e-05, |
|
"loss": 1.0378, |
|
"step": 5720 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"learning_rate": 6.376167471819646e-05, |
|
"loss": 0.954, |
|
"step": 5730 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 6.369726247987118e-05, |
|
"loss": 1.004, |
|
"step": 5740 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 6.36328502415459e-05, |
|
"loss": 0.9934, |
|
"step": 5750 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 6.35684380032206e-05, |
|
"loss": 0.9874, |
|
"step": 5760 |
|
}, |
|
{ |
|
"epoch": 1.85, |
|
"learning_rate": 6.350402576489534e-05, |
|
"loss": 0.9677, |
|
"step": 5770 |
|
}, |
|
{ |
|
"epoch": 1.85, |
|
"learning_rate": 6.343961352657006e-05, |
|
"loss": 0.9833, |
|
"step": 5780 |
|
}, |
|
{ |
|
"epoch": 1.85, |
|
"learning_rate": 6.337520128824476e-05, |
|
"loss": 0.9972, |
|
"step": 5790 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 6.331078904991948e-05, |
|
"loss": 1.0289, |
|
"step": 5800 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"eval_loss": 1.0126157999038696, |
|
"eval_runtime": 187.3366, |
|
"eval_samples_per_second": 10.676, |
|
"eval_steps_per_second": 1.334, |
|
"step": 5800 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 6.324637681159421e-05, |
|
"loss": 0.9907, |
|
"step": 5810 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 6.318196457326893e-05, |
|
"loss": 0.9942, |
|
"step": 5820 |
|
}, |
|
{ |
|
"epoch": 1.87, |
|
"learning_rate": 6.311755233494364e-05, |
|
"loss": 0.9764, |
|
"step": 5830 |
|
}, |
|
{ |
|
"epoch": 1.87, |
|
"learning_rate": 6.305314009661836e-05, |
|
"loss": 0.9942, |
|
"step": 5840 |
|
}, |
|
{ |
|
"epoch": 1.87, |
|
"learning_rate": 6.298872785829309e-05, |
|
"loss": 1.0397, |
|
"step": 5850 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 6.29243156199678e-05, |
|
"loss": 1.0182, |
|
"step": 5860 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 6.285990338164251e-05, |
|
"loss": 0.9443, |
|
"step": 5870 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 6.279549114331723e-05, |
|
"loss": 0.973, |
|
"step": 5880 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 6.273107890499195e-05, |
|
"loss": 0.951, |
|
"step": 5890 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"learning_rate": 6.266666666666667e-05, |
|
"loss": 0.9824, |
|
"step": 5900 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"learning_rate": 6.260225442834139e-05, |
|
"loss": 1.0014, |
|
"step": 5910 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"learning_rate": 6.25378421900161e-05, |
|
"loss": 1.0029, |
|
"step": 5920 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 6.247342995169082e-05, |
|
"loss": 1.0166, |
|
"step": 5930 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 6.240901771336554e-05, |
|
"loss": 1.0011, |
|
"step": 5940 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 6.234460547504026e-05, |
|
"loss": 1.0156, |
|
"step": 5950 |
|
}, |
|
{ |
|
"epoch": 1.91, |
|
"learning_rate": 6.228019323671498e-05, |
|
"loss": 1.0166, |
|
"step": 5960 |
|
}, |
|
{ |
|
"epoch": 1.91, |
|
"learning_rate": 6.22157809983897e-05, |
|
"loss": 0.9613, |
|
"step": 5970 |
|
}, |
|
{ |
|
"epoch": 1.91, |
|
"learning_rate": 6.21513687600644e-05, |
|
"loss": 0.9551, |
|
"step": 5980 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 6.208695652173914e-05, |
|
"loss": 0.9628, |
|
"step": 5990 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 6.202254428341385e-05, |
|
"loss": 0.9675, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"eval_loss": 1.012001633644104, |
|
"eval_runtime": 187.1833, |
|
"eval_samples_per_second": 10.685, |
|
"eval_steps_per_second": 1.336, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 6.195813204508857e-05, |
|
"loss": 0.9864, |
|
"step": 6010 |
|
}, |
|
{ |
|
"epoch": 1.93, |
|
"learning_rate": 6.189371980676328e-05, |
|
"loss": 0.9786, |
|
"step": 6020 |
|
}, |
|
{ |
|
"epoch": 1.93, |
|
"learning_rate": 6.182930756843801e-05, |
|
"loss": 0.9732, |
|
"step": 6030 |
|
}, |
|
{ |
|
"epoch": 1.93, |
|
"learning_rate": 6.176489533011273e-05, |
|
"loss": 0.9915, |
|
"step": 6040 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 6.170048309178745e-05, |
|
"loss": 0.967, |
|
"step": 6050 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 6.163607085346215e-05, |
|
"loss": 1.0035, |
|
"step": 6060 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 6.157165861513687e-05, |
|
"loss": 1.0008, |
|
"step": 6070 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 6.15072463768116e-05, |
|
"loss": 0.9626, |
|
"step": 6080 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 6.144283413848631e-05, |
|
"loss": 1.0128, |
|
"step": 6090 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 6.137842190016103e-05, |
|
"loss": 0.9504, |
|
"step": 6100 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 6.131400966183575e-05, |
|
"loss": 1.004, |
|
"step": 6110 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 6.124959742351048e-05, |
|
"loss": 1.0037, |
|
"step": 6120 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 6.118518518518518e-05, |
|
"loss": 1.0124, |
|
"step": 6130 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 6.11207729468599e-05, |
|
"loss": 1.0248, |
|
"step": 6140 |
|
}, |
|
{ |
|
"epoch": 1.97, |
|
"learning_rate": 6.105636070853462e-05, |
|
"loss": 0.9643, |
|
"step": 6150 |
|
}, |
|
{ |
|
"epoch": 1.97, |
|
"learning_rate": 6.099194847020935e-05, |
|
"loss": 0.9443, |
|
"step": 6160 |
|
}, |
|
{ |
|
"epoch": 1.97, |
|
"learning_rate": 6.0927536231884066e-05, |
|
"loss": 1.0231, |
|
"step": 6170 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 6.086312399355878e-05, |
|
"loss": 1.0228, |
|
"step": 6180 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 6.0798711755233496e-05, |
|
"loss": 1.0145, |
|
"step": 6190 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 6.073429951690821e-05, |
|
"loss": 1.0081, |
|
"step": 6200 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"eval_loss": 1.0115959644317627, |
|
"eval_runtime": 187.1705, |
|
"eval_samples_per_second": 10.685, |
|
"eval_steps_per_second": 1.336, |
|
"step": 6200 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 15625, |
|
"num_train_epochs": 5, |
|
"save_steps": 200, |
|
"total_flos": 1.3300381203687014e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|