{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.125, "eval_steps": 5000, "global_step": 5000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "grad_norm": 90.0, "learning_rate": 2e-08, "loss": 6.8274, "step": 10 }, { "epoch": 0.0, "grad_norm": 89.5, "learning_rate": 4e-08, "loss": 6.8083, "step": 20 }, { "epoch": 0.0, "grad_norm": 89.5, "learning_rate": 6e-08, "loss": 6.8347, "step": 30 }, { "epoch": 0.0, "grad_norm": 92.0, "learning_rate": 8e-08, "loss": 6.8096, "step": 40 }, { "epoch": 0.0, "grad_norm": 93.0, "learning_rate": 1e-07, "loss": 6.797, "step": 50 }, { "epoch": 0.0, "grad_norm": 91.5, "learning_rate": 1.2e-07, "loss": 6.8509, "step": 60 }, { "epoch": 0.0, "grad_norm": 93.0, "learning_rate": 1.4e-07, "loss": 6.8584, "step": 70 }, { "epoch": 0.0, "grad_norm": 89.0, "learning_rate": 1.6e-07, "loss": 6.8086, "step": 80 }, { "epoch": 0.0, "grad_norm": 95.0, "learning_rate": 1.8e-07, "loss": 6.8356, "step": 90 }, { "epoch": 0.0, "grad_norm": 87.5, "learning_rate": 2e-07, "loss": 6.8266, "step": 100 }, { "epoch": 0.0, "grad_norm": 89.0, "learning_rate": 2.1999999999999998e-07, "loss": 6.8343, "step": 110 }, { "epoch": 0.0, "grad_norm": 88.0, "learning_rate": 2.4e-07, "loss": 6.8105, "step": 120 }, { "epoch": 0.0, "grad_norm": 87.5, "learning_rate": 2.6e-07, "loss": 6.8398, "step": 130 }, { "epoch": 0.0, "grad_norm": 87.0, "learning_rate": 2.8e-07, "loss": 6.8298, "step": 140 }, { "epoch": 0.0, "grad_norm": 93.0, "learning_rate": 3e-07, "loss": 6.7857, "step": 150 }, { "epoch": 0.0, "grad_norm": 90.0, "learning_rate": 3.2e-07, "loss": 6.7761, "step": 160 }, { "epoch": 0.0, "grad_norm": 87.5, "learning_rate": 3.4000000000000003e-07, "loss": 6.7807, "step": 170 }, { "epoch": 0.0, "grad_norm": 90.5, "learning_rate": 3.6e-07, "loss": 6.7772, "step": 180 }, { "epoch": 0.0, "grad_norm": 88.5, "learning_rate": 3.7999999999999996e-07, "loss": 6.7754, "step": 190 }, { "epoch": 0.01, "grad_norm": 95.5, "learning_rate": 4e-07, "loss": 6.7319, "step": 200 }, { "epoch": 0.01, "grad_norm": 96.0, "learning_rate": 4.1999999999999995e-07, "loss": 6.6868, "step": 210 }, { "epoch": 0.01, "grad_norm": 93.0, "learning_rate": 4.3999999999999997e-07, "loss": 6.6913, "step": 220 }, { "epoch": 0.01, "grad_norm": 89.5, "learning_rate": 4.6e-07, "loss": 6.6759, "step": 230 }, { "epoch": 0.01, "grad_norm": 89.0, "learning_rate": 4.8e-07, "loss": 6.6891, "step": 240 }, { "epoch": 0.01, "grad_norm": 87.0, "learning_rate": 5e-07, "loss": 6.6378, "step": 250 }, { "epoch": 0.01, "grad_norm": 103.5, "learning_rate": 5.2e-07, "loss": 6.6767, "step": 260 }, { "epoch": 0.01, "grad_norm": 92.5, "learning_rate": 5.4e-07, "loss": 6.5617, "step": 270 }, { "epoch": 0.01, "grad_norm": 88.5, "learning_rate": 5.6e-07, "loss": 6.5812, "step": 280 }, { "epoch": 0.01, "grad_norm": 80.5, "learning_rate": 5.8e-07, "loss": 6.5442, "step": 290 }, { "epoch": 0.01, "grad_norm": 82.0, "learning_rate": 6e-07, "loss": 6.4611, "step": 300 }, { "epoch": 0.01, "grad_norm": 85.0, "learning_rate": 6.2e-07, "loss": 6.4348, "step": 310 }, { "epoch": 0.01, "grad_norm": 91.0, "learning_rate": 6.4e-07, "loss": 6.4133, "step": 320 }, { "epoch": 0.01, "grad_norm": 91.0, "learning_rate": 6.6e-07, "loss": 6.3978, "step": 330 }, { "epoch": 0.01, "grad_norm": 87.0, "learning_rate": 6.800000000000001e-07, "loss": 6.324, "step": 340 }, { "epoch": 0.01, "grad_norm": 86.5, "learning_rate": 7e-07, "loss": 6.2901, "step": 350 }, { "epoch": 0.01, "grad_norm": 83.0, "learning_rate": 7.2e-07, "loss": 6.243, "step": 360 }, { "epoch": 0.01, "grad_norm": 80.0, "learning_rate": 7.4e-07, "loss": 6.1756, "step": 370 }, { "epoch": 0.01, "grad_norm": 84.5, "learning_rate": 7.599999999999999e-07, "loss": 6.1589, "step": 380 }, { "epoch": 0.01, "grad_norm": 78.5, "learning_rate": 7.799999999999999e-07, "loss": 6.1148, "step": 390 }, { "epoch": 0.01, "grad_norm": 81.5, "learning_rate": 8e-07, "loss": 6.06, "step": 400 }, { "epoch": 0.01, "grad_norm": 87.0, "learning_rate": 8.199999999999999e-07, "loss": 6.0328, "step": 410 }, { "epoch": 0.01, "grad_norm": 84.0, "learning_rate": 8.399999999999999e-07, "loss": 5.9817, "step": 420 }, { "epoch": 0.01, "grad_norm": 85.0, "learning_rate": 8.599999999999999e-07, "loss": 5.9352, "step": 430 }, { "epoch": 0.01, "grad_norm": 87.0, "learning_rate": 8.799999999999999e-07, "loss": 5.8731, "step": 440 }, { "epoch": 0.01, "grad_norm": 82.0, "learning_rate": 9e-07, "loss": 5.8381, "step": 450 }, { "epoch": 0.01, "grad_norm": 85.5, "learning_rate": 9.2e-07, "loss": 5.7847, "step": 460 }, { "epoch": 0.01, "grad_norm": 79.5, "learning_rate": 9.399999999999999e-07, "loss": 5.7146, "step": 470 }, { "epoch": 0.01, "grad_norm": 83.0, "learning_rate": 9.6e-07, "loss": 5.6431, "step": 480 }, { "epoch": 0.01, "grad_norm": 83.0, "learning_rate": 9.8e-07, "loss": 5.5353, "step": 490 }, { "epoch": 0.01, "grad_norm": 78.5, "learning_rate": 1e-06, "loss": 5.4188, "step": 500 }, { "epoch": 0.01, "grad_norm": 80.0, "learning_rate": 9.996610169491525e-07, "loss": 5.3305, "step": 510 }, { "epoch": 0.01, "grad_norm": 77.5, "learning_rate": 9.99322033898305e-07, "loss": 5.1901, "step": 520 }, { "epoch": 0.01, "grad_norm": 79.0, "learning_rate": 9.989830508474575e-07, "loss": 5.1047, "step": 530 }, { "epoch": 0.01, "grad_norm": 78.0, "learning_rate": 9.9864406779661e-07, "loss": 4.9914, "step": 540 }, { "epoch": 0.01, "grad_norm": 79.0, "learning_rate": 9.983050847457626e-07, "loss": 4.9194, "step": 550 }, { "epoch": 0.01, "grad_norm": 81.5, "learning_rate": 9.979661016949153e-07, "loss": 4.799, "step": 560 }, { "epoch": 0.01, "grad_norm": 79.5, "learning_rate": 9.976271186440679e-07, "loss": 4.7051, "step": 570 }, { "epoch": 0.01, "grad_norm": 79.0, "learning_rate": 9.972881355932204e-07, "loss": 4.6324, "step": 580 }, { "epoch": 0.01, "grad_norm": 77.5, "learning_rate": 9.96949152542373e-07, "loss": 4.5426, "step": 590 }, { "epoch": 0.01, "grad_norm": 80.0, "learning_rate": 9.966101694915254e-07, "loss": 4.4262, "step": 600 }, { "epoch": 0.02, "grad_norm": 77.0, "learning_rate": 9.96271186440678e-07, "loss": 4.3657, "step": 610 }, { "epoch": 0.02, "grad_norm": 81.5, "learning_rate": 9.959322033898305e-07, "loss": 4.3496, "step": 620 }, { "epoch": 0.02, "grad_norm": 79.0, "learning_rate": 9.95593220338983e-07, "loss": 4.2415, "step": 630 }, { "epoch": 0.02, "grad_norm": 77.5, "learning_rate": 9.952542372881356e-07, "loss": 4.1497, "step": 640 }, { "epoch": 0.02, "grad_norm": 76.5, "learning_rate": 9.94915254237288e-07, "loss": 4.1079, "step": 650 }, { "epoch": 0.02, "grad_norm": 77.5, "learning_rate": 9.945762711864406e-07, "loss": 4.0541, "step": 660 }, { "epoch": 0.02, "grad_norm": 77.5, "learning_rate": 9.942372881355931e-07, "loss": 3.9799, "step": 670 }, { "epoch": 0.02, "grad_norm": 77.0, "learning_rate": 9.938983050847457e-07, "loss": 3.9074, "step": 680 }, { "epoch": 0.02, "grad_norm": 78.0, "learning_rate": 9.935593220338982e-07, "loss": 3.8532, "step": 690 }, { "epoch": 0.02, "grad_norm": 80.0, "learning_rate": 9.932203389830507e-07, "loss": 3.781, "step": 700 }, { "epoch": 0.02, "grad_norm": 76.5, "learning_rate": 9.928813559322032e-07, "loss": 3.7504, "step": 710 }, { "epoch": 0.02, "grad_norm": 77.5, "learning_rate": 9.92542372881356e-07, "loss": 3.7237, "step": 720 }, { "epoch": 0.02, "grad_norm": 76.0, "learning_rate": 9.922033898305085e-07, "loss": 3.6538, "step": 730 }, { "epoch": 0.02, "grad_norm": 79.0, "learning_rate": 9.91864406779661e-07, "loss": 3.5991, "step": 740 }, { "epoch": 0.02, "grad_norm": 76.0, "learning_rate": 9.915254237288136e-07, "loss": 3.5435, "step": 750 }, { "epoch": 0.02, "grad_norm": 76.5, "learning_rate": 9.91186440677966e-07, "loss": 3.4975, "step": 760 }, { "epoch": 0.02, "grad_norm": 76.5, "learning_rate": 9.908474576271186e-07, "loss": 3.4701, "step": 770 }, { "epoch": 0.02, "grad_norm": 79.0, "learning_rate": 9.905084745762712e-07, "loss": 3.3482, "step": 780 }, { "epoch": 0.02, "grad_norm": 75.0, "learning_rate": 9.901694915254237e-07, "loss": 3.3289, "step": 790 }, { "epoch": 0.02, "grad_norm": 75.0, "learning_rate": 9.898305084745762e-07, "loss": 3.2755, "step": 800 }, { "epoch": 0.02, "grad_norm": 77.5, "learning_rate": 9.894915254237287e-07, "loss": 3.2532, "step": 810 }, { "epoch": 0.02, "grad_norm": 74.5, "learning_rate": 9.891525423728813e-07, "loss": 3.2162, "step": 820 }, { "epoch": 0.02, "grad_norm": 75.0, "learning_rate": 9.888135593220338e-07, "loss": 3.1885, "step": 830 }, { "epoch": 0.02, "grad_norm": 75.0, "learning_rate": 9.884745762711863e-07, "loss": 3.1086, "step": 840 }, { "epoch": 0.02, "grad_norm": 76.0, "learning_rate": 9.881355932203388e-07, "loss": 3.0738, "step": 850 }, { "epoch": 0.02, "grad_norm": 74.5, "learning_rate": 9.877966101694914e-07, "loss": 3.0059, "step": 860 }, { "epoch": 0.02, "grad_norm": 73.5, "learning_rate": 9.87457627118644e-07, "loss": 2.9603, "step": 870 }, { "epoch": 0.02, "grad_norm": 75.0, "learning_rate": 9.871186440677966e-07, "loss": 2.9388, "step": 880 }, { "epoch": 0.02, "grad_norm": 74.5, "learning_rate": 9.867796610169492e-07, "loss": 2.9279, "step": 890 }, { "epoch": 0.02, "grad_norm": 75.5, "learning_rate": 9.864406779661017e-07, "loss": 2.8923, "step": 900 }, { "epoch": 0.02, "grad_norm": 74.5, "learning_rate": 9.861016949152542e-07, "loss": 2.8519, "step": 910 }, { "epoch": 0.02, "grad_norm": 74.5, "learning_rate": 9.857627118644068e-07, "loss": 2.8075, "step": 920 }, { "epoch": 0.02, "grad_norm": 75.5, "learning_rate": 9.854237288135593e-07, "loss": 2.783, "step": 930 }, { "epoch": 0.02, "grad_norm": 74.5, "learning_rate": 9.850847457627118e-07, "loss": 2.7459, "step": 940 }, { "epoch": 0.02, "grad_norm": 74.5, "learning_rate": 9.847457627118643e-07, "loss": 2.7201, "step": 950 }, { "epoch": 0.02, "grad_norm": 74.0, "learning_rate": 9.844067796610169e-07, "loss": 2.6724, "step": 960 }, { "epoch": 0.02, "grad_norm": 75.0, "learning_rate": 9.840677966101694e-07, "loss": 2.6573, "step": 970 }, { "epoch": 0.02, "grad_norm": 74.5, "learning_rate": 9.83728813559322e-07, "loss": 2.6356, "step": 980 }, { "epoch": 0.02, "grad_norm": 76.5, "learning_rate": 9.833898305084747e-07, "loss": 2.5692, "step": 990 }, { "epoch": 0.03, "grad_norm": 72.5, "learning_rate": 9.830508474576272e-07, "loss": 2.5829, "step": 1000 }, { "epoch": 0.03, "grad_norm": 73.5, "learning_rate": 9.827118644067797e-07, "loss": 2.5146, "step": 1010 }, { "epoch": 0.03, "grad_norm": 74.0, "learning_rate": 9.82372881355932e-07, "loss": 2.5395, "step": 1020 }, { "epoch": 0.03, "grad_norm": 74.0, "learning_rate": 9.820338983050846e-07, "loss": 2.4929, "step": 1030 }, { "epoch": 0.03, "grad_norm": 72.5, "learning_rate": 9.816949152542373e-07, "loss": 2.4339, "step": 1040 }, { "epoch": 0.03, "grad_norm": 73.0, "learning_rate": 9.813559322033898e-07, "loss": 2.404, "step": 1050 }, { "epoch": 0.03, "grad_norm": 74.5, "learning_rate": 9.810169491525424e-07, "loss": 2.397, "step": 1060 }, { "epoch": 0.03, "grad_norm": 71.5, "learning_rate": 9.806779661016949e-07, "loss": 2.3533, "step": 1070 }, { "epoch": 0.03, "grad_norm": 72.0, "learning_rate": 9.803389830508474e-07, "loss": 2.2966, "step": 1080 }, { "epoch": 0.03, "grad_norm": 71.5, "learning_rate": 9.8e-07, "loss": 2.2989, "step": 1090 }, { "epoch": 0.03, "grad_norm": 74.5, "learning_rate": 9.796610169491525e-07, "loss": 2.2941, "step": 1100 }, { "epoch": 0.03, "grad_norm": 75.0, "learning_rate": 9.79322033898305e-07, "loss": 2.2903, "step": 1110 }, { "epoch": 0.03, "grad_norm": 71.0, "learning_rate": 9.789830508474575e-07, "loss": 2.1909, "step": 1120 }, { "epoch": 0.03, "grad_norm": 72.5, "learning_rate": 9.7864406779661e-07, "loss": 2.2198, "step": 1130 }, { "epoch": 0.03, "grad_norm": 71.0, "learning_rate": 9.783050847457626e-07, "loss": 2.1776, "step": 1140 }, { "epoch": 0.03, "grad_norm": 72.0, "learning_rate": 9.779661016949153e-07, "loss": 2.196, "step": 1150 }, { "epoch": 0.03, "grad_norm": 73.5, "learning_rate": 9.776271186440678e-07, "loss": 2.1479, "step": 1160 }, { "epoch": 0.03, "grad_norm": 71.0, "learning_rate": 9.772881355932204e-07, "loss": 2.0738, "step": 1170 }, { "epoch": 0.03, "grad_norm": 70.0, "learning_rate": 9.76949152542373e-07, "loss": 2.1353, "step": 1180 }, { "epoch": 0.03, "grad_norm": 73.0, "learning_rate": 9.766101694915254e-07, "loss": 2.0684, "step": 1190 }, { "epoch": 0.03, "grad_norm": 72.5, "learning_rate": 9.76271186440678e-07, "loss": 2.0626, "step": 1200 }, { "epoch": 0.03, "grad_norm": 72.5, "learning_rate": 9.759322033898305e-07, "loss": 2.0793, "step": 1210 }, { "epoch": 0.03, "grad_norm": 68.5, "learning_rate": 9.75593220338983e-07, "loss": 2.0539, "step": 1220 }, { "epoch": 0.03, "grad_norm": 70.0, "learning_rate": 9.752542372881355e-07, "loss": 2.0261, "step": 1230 }, { "epoch": 0.03, "grad_norm": 69.5, "learning_rate": 9.74915254237288e-07, "loss": 2.0405, "step": 1240 }, { "epoch": 0.03, "grad_norm": 69.0, "learning_rate": 9.745762711864406e-07, "loss": 2.0291, "step": 1250 }, { "epoch": 0.03, "grad_norm": 69.5, "learning_rate": 9.742372881355931e-07, "loss": 1.9667, "step": 1260 }, { "epoch": 0.03, "grad_norm": 77.0, "learning_rate": 9.738983050847456e-07, "loss": 1.9781, "step": 1270 }, { "epoch": 0.03, "grad_norm": 72.0, "learning_rate": 9.735593220338982e-07, "loss": 2.0106, "step": 1280 }, { "epoch": 0.03, "grad_norm": 71.5, "learning_rate": 9.732203389830507e-07, "loss": 1.9822, "step": 1290 }, { "epoch": 0.03, "grad_norm": 69.0, "learning_rate": 9.728813559322032e-07, "loss": 1.9494, "step": 1300 }, { "epoch": 0.03, "grad_norm": 68.0, "learning_rate": 9.72542372881356e-07, "loss": 1.9647, "step": 1310 }, { "epoch": 0.03, "grad_norm": 70.5, "learning_rate": 9.722033898305085e-07, "loss": 1.9182, "step": 1320 }, { "epoch": 0.03, "grad_norm": 70.0, "learning_rate": 9.71864406779661e-07, "loss": 1.9238, "step": 1330 }, { "epoch": 0.03, "grad_norm": 72.0, "learning_rate": 9.715254237288135e-07, "loss": 1.9369, "step": 1340 }, { "epoch": 0.03, "grad_norm": 69.5, "learning_rate": 9.71186440677966e-07, "loss": 1.9225, "step": 1350 }, { "epoch": 0.03, "grad_norm": 67.5, "learning_rate": 9.708474576271186e-07, "loss": 1.9043, "step": 1360 }, { "epoch": 0.03, "grad_norm": 74.5, "learning_rate": 9.705084745762711e-07, "loss": 1.924, "step": 1370 }, { "epoch": 0.03, "grad_norm": 70.0, "learning_rate": 9.701694915254237e-07, "loss": 1.8824, "step": 1380 }, { "epoch": 0.03, "grad_norm": 68.0, "learning_rate": 9.698305084745762e-07, "loss": 1.8886, "step": 1390 }, { "epoch": 0.04, "grad_norm": 69.5, "learning_rate": 9.694915254237287e-07, "loss": 1.8851, "step": 1400 }, { "epoch": 0.04, "grad_norm": 68.0, "learning_rate": 9.691525423728815e-07, "loss": 1.9012, "step": 1410 }, { "epoch": 0.04, "grad_norm": 70.0, "learning_rate": 9.68813559322034e-07, "loss": 1.8949, "step": 1420 }, { "epoch": 0.04, "grad_norm": 71.5, "learning_rate": 9.684745762711865e-07, "loss": 1.8203, "step": 1430 }, { "epoch": 0.04, "grad_norm": 69.5, "learning_rate": 9.681355932203388e-07, "loss": 1.8582, "step": 1440 }, { "epoch": 0.04, "grad_norm": 68.5, "learning_rate": 9.677966101694914e-07, "loss": 1.8363, "step": 1450 }, { "epoch": 0.04, "grad_norm": 71.0, "learning_rate": 9.674576271186439e-07, "loss": 1.8069, "step": 1460 }, { "epoch": 0.04, "grad_norm": 68.5, "learning_rate": 9.671186440677966e-07, "loss": 1.8681, "step": 1470 }, { "epoch": 0.04, "grad_norm": 70.0, "learning_rate": 9.667796610169491e-07, "loss": 1.8022, "step": 1480 }, { "epoch": 0.04, "grad_norm": 73.5, "learning_rate": 9.664406779661017e-07, "loss": 1.8337, "step": 1490 }, { "epoch": 0.04, "grad_norm": 67.5, "learning_rate": 9.661016949152542e-07, "loss": 1.7858, "step": 1500 }, { "epoch": 0.04, "grad_norm": 75.5, "learning_rate": 9.657627118644067e-07, "loss": 1.8289, "step": 1510 }, { "epoch": 0.04, "grad_norm": 70.0, "learning_rate": 9.654237288135593e-07, "loss": 1.7982, "step": 1520 }, { "epoch": 0.04, "grad_norm": 70.0, "learning_rate": 9.650847457627118e-07, "loss": 1.8271, "step": 1530 }, { "epoch": 0.04, "grad_norm": 67.0, "learning_rate": 9.647457627118643e-07, "loss": 1.7395, "step": 1540 }, { "epoch": 0.04, "grad_norm": 67.0, "learning_rate": 9.644067796610168e-07, "loss": 1.82, "step": 1550 }, { "epoch": 0.04, "grad_norm": 67.5, "learning_rate": 9.640677966101694e-07, "loss": 1.8157, "step": 1560 }, { "epoch": 0.04, "grad_norm": 67.0, "learning_rate": 9.637288135593221e-07, "loss": 1.8164, "step": 1570 }, { "epoch": 0.04, "grad_norm": 72.0, "learning_rate": 9.633898305084746e-07, "loss": 1.7715, "step": 1580 }, { "epoch": 0.04, "grad_norm": 71.0, "learning_rate": 9.630508474576272e-07, "loss": 1.7947, "step": 1590 }, { "epoch": 0.04, "grad_norm": 69.5, "learning_rate": 9.627118644067797e-07, "loss": 1.8159, "step": 1600 }, { "epoch": 0.04, "grad_norm": 69.0, "learning_rate": 9.623728813559322e-07, "loss": 1.7614, "step": 1610 }, { "epoch": 0.04, "grad_norm": 71.5, "learning_rate": 9.620338983050847e-07, "loss": 1.7962, "step": 1620 }, { "epoch": 0.04, "grad_norm": 73.5, "learning_rate": 9.616949152542373e-07, "loss": 1.7961, "step": 1630 }, { "epoch": 0.04, "grad_norm": 74.0, "learning_rate": 9.613559322033898e-07, "loss": 1.7997, "step": 1640 }, { "epoch": 0.04, "grad_norm": 71.0, "learning_rate": 9.610169491525423e-07, "loss": 1.7955, "step": 1650 }, { "epoch": 0.04, "grad_norm": 69.0, "learning_rate": 9.606779661016949e-07, "loss": 1.7388, "step": 1660 }, { "epoch": 0.04, "grad_norm": 66.5, "learning_rate": 9.603389830508474e-07, "loss": 1.7265, "step": 1670 }, { "epoch": 0.04, "grad_norm": 69.5, "learning_rate": 9.6e-07, "loss": 1.8179, "step": 1680 }, { "epoch": 0.04, "grad_norm": 72.0, "learning_rate": 9.596610169491524e-07, "loss": 1.7152, "step": 1690 }, { "epoch": 0.04, "grad_norm": 69.5, "learning_rate": 9.59322033898305e-07, "loss": 1.7607, "step": 1700 }, { "epoch": 0.04, "grad_norm": 66.5, "learning_rate": 9.589830508474575e-07, "loss": 1.7638, "step": 1710 }, { "epoch": 0.04, "grad_norm": 69.5, "learning_rate": 9.5864406779661e-07, "loss": 1.726, "step": 1720 }, { "epoch": 0.04, "grad_norm": 67.5, "learning_rate": 9.583050847457628e-07, "loss": 1.7371, "step": 1730 }, { "epoch": 0.04, "grad_norm": 69.5, "learning_rate": 9.579661016949153e-07, "loss": 1.6961, "step": 1740 }, { "epoch": 0.04, "grad_norm": 71.5, "learning_rate": 9.576271186440678e-07, "loss": 1.7849, "step": 1750 }, { "epoch": 0.04, "grad_norm": 70.0, "learning_rate": 9.572881355932203e-07, "loss": 1.7208, "step": 1760 }, { "epoch": 0.04, "grad_norm": 71.0, "learning_rate": 9.569491525423729e-07, "loss": 1.7974, "step": 1770 }, { "epoch": 0.04, "grad_norm": 70.5, "learning_rate": 9.566101694915254e-07, "loss": 1.7476, "step": 1780 }, { "epoch": 0.04, "grad_norm": 69.0, "learning_rate": 9.56271186440678e-07, "loss": 1.752, "step": 1790 }, { "epoch": 0.04, "grad_norm": 69.0, "learning_rate": 9.559322033898305e-07, "loss": 1.7256, "step": 1800 }, { "epoch": 0.05, "grad_norm": 72.0, "learning_rate": 9.55593220338983e-07, "loss": 1.7196, "step": 1810 }, { "epoch": 0.05, "grad_norm": 67.5, "learning_rate": 9.552542372881355e-07, "loss": 1.6905, "step": 1820 }, { "epoch": 0.05, "grad_norm": 67.5, "learning_rate": 9.54915254237288e-07, "loss": 1.6826, "step": 1830 }, { "epoch": 0.05, "grad_norm": 69.0, "learning_rate": 9.545762711864408e-07, "loss": 1.7369, "step": 1840 }, { "epoch": 0.05, "grad_norm": 73.0, "learning_rate": 9.542372881355933e-07, "loss": 1.6937, "step": 1850 }, { "epoch": 0.05, "grad_norm": 68.5, "learning_rate": 9.538983050847456e-07, "loss": 1.6722, "step": 1860 }, { "epoch": 0.05, "grad_norm": 68.5, "learning_rate": 9.535593220338983e-07, "loss": 1.688, "step": 1870 }, { "epoch": 0.05, "grad_norm": 70.0, "learning_rate": 9.532203389830508e-07, "loss": 1.692, "step": 1880 }, { "epoch": 0.05, "grad_norm": 71.5, "learning_rate": 9.528813559322033e-07, "loss": 1.6849, "step": 1890 }, { "epoch": 0.05, "grad_norm": 70.0, "learning_rate": 9.525423728813558e-07, "loss": 1.6826, "step": 1900 }, { "epoch": 0.05, "grad_norm": 66.5, "learning_rate": 9.522033898305084e-07, "loss": 1.7051, "step": 1910 }, { "epoch": 0.05, "grad_norm": 66.0, "learning_rate": 9.51864406779661e-07, "loss": 1.6736, "step": 1920 }, { "epoch": 0.05, "grad_norm": 68.0, "learning_rate": 9.515254237288135e-07, "loss": 1.6739, "step": 1930 }, { "epoch": 0.05, "grad_norm": 69.0, "learning_rate": 9.511864406779661e-07, "loss": 1.6862, "step": 1940 }, { "epoch": 0.05, "grad_norm": 75.0, "learning_rate": 9.508474576271186e-07, "loss": 1.647, "step": 1950 }, { "epoch": 0.05, "grad_norm": 67.0, "learning_rate": 9.505084745762711e-07, "loss": 1.6635, "step": 1960 }, { "epoch": 0.05, "grad_norm": 66.5, "learning_rate": 9.501694915254237e-07, "loss": 1.6047, "step": 1970 }, { "epoch": 0.05, "grad_norm": 63.25, "learning_rate": 9.498305084745763e-07, "loss": 1.6744, "step": 1980 }, { "epoch": 0.05, "grad_norm": 67.0, "learning_rate": 9.494915254237288e-07, "loss": 1.7308, "step": 1990 }, { "epoch": 0.05, "grad_norm": 68.0, "learning_rate": 9.491525423728813e-07, "loss": 1.6831, "step": 2000 }, { "epoch": 0.05, "grad_norm": 69.0, "learning_rate": 9.488135593220339e-07, "loss": 1.6635, "step": 2010 }, { "epoch": 0.05, "grad_norm": 67.0, "learning_rate": 9.484745762711864e-07, "loss": 1.6199, "step": 2020 }, { "epoch": 0.05, "grad_norm": 67.0, "learning_rate": 9.48135593220339e-07, "loss": 1.673, "step": 2030 }, { "epoch": 0.05, "grad_norm": 70.5, "learning_rate": 9.477966101694915e-07, "loss": 1.6659, "step": 2040 }, { "epoch": 0.05, "grad_norm": 69.5, "learning_rate": 9.474576271186441e-07, "loss": 1.6399, "step": 2050 }, { "epoch": 0.05, "grad_norm": 68.5, "learning_rate": 9.471186440677965e-07, "loss": 1.6694, "step": 2060 }, { "epoch": 0.05, "grad_norm": 70.5, "learning_rate": 9.46779661016949e-07, "loss": 1.65, "step": 2070 }, { "epoch": 0.05, "grad_norm": 69.0, "learning_rate": 9.464406779661017e-07, "loss": 1.6637, "step": 2080 }, { "epoch": 0.05, "grad_norm": 67.0, "learning_rate": 9.461016949152542e-07, "loss": 1.6598, "step": 2090 }, { "epoch": 0.05, "grad_norm": 70.0, "learning_rate": 9.457627118644067e-07, "loss": 1.6303, "step": 2100 }, { "epoch": 0.05, "grad_norm": 66.0, "learning_rate": 9.454237288135592e-07, "loss": 1.6766, "step": 2110 }, { "epoch": 0.05, "grad_norm": 67.0, "learning_rate": 9.450847457627118e-07, "loss": 1.6083, "step": 2120 }, { "epoch": 0.05, "grad_norm": 67.5, "learning_rate": 9.447457627118643e-07, "loss": 1.665, "step": 2130 }, { "epoch": 0.05, "grad_norm": 68.0, "learning_rate": 9.444067796610169e-07, "loss": 1.644, "step": 2140 }, { "epoch": 0.05, "grad_norm": 70.0, "learning_rate": 9.440677966101695e-07, "loss": 1.6322, "step": 2150 }, { "epoch": 0.05, "grad_norm": 66.5, "learning_rate": 9.43728813559322e-07, "loss": 1.6223, "step": 2160 }, { "epoch": 0.05, "grad_norm": 66.5, "learning_rate": 9.433898305084745e-07, "loss": 1.6727, "step": 2170 }, { "epoch": 0.05, "grad_norm": 69.0, "learning_rate": 9.43050847457627e-07, "loss": 1.6328, "step": 2180 }, { "epoch": 0.05, "grad_norm": 68.5, "learning_rate": 9.427118644067797e-07, "loss": 1.6439, "step": 2190 }, { "epoch": 0.06, "grad_norm": 67.5, "learning_rate": 9.423728813559322e-07, "loss": 1.6537, "step": 2200 }, { "epoch": 0.06, "grad_norm": 64.5, "learning_rate": 9.420338983050847e-07, "loss": 1.6508, "step": 2210 }, { "epoch": 0.06, "grad_norm": 66.5, "learning_rate": 9.416949152542373e-07, "loss": 1.5704, "step": 2220 }, { "epoch": 0.06, "grad_norm": 66.5, "learning_rate": 9.413559322033898e-07, "loss": 1.5994, "step": 2230 }, { "epoch": 0.06, "grad_norm": 69.0, "learning_rate": 9.410169491525424e-07, "loss": 1.6123, "step": 2240 }, { "epoch": 0.06, "grad_norm": 71.5, "learning_rate": 9.406779661016949e-07, "loss": 1.6146, "step": 2250 }, { "epoch": 0.06, "grad_norm": 68.5, "learning_rate": 9.403389830508475e-07, "loss": 1.6318, "step": 2260 }, { "epoch": 0.06, "grad_norm": 66.0, "learning_rate": 9.399999999999999e-07, "loss": 1.584, "step": 2270 }, { "epoch": 0.06, "grad_norm": 66.5, "learning_rate": 9.396610169491524e-07, "loss": 1.6058, "step": 2280 }, { "epoch": 0.06, "grad_norm": 67.0, "learning_rate": 9.39322033898305e-07, "loss": 1.6386, "step": 2290 }, { "epoch": 0.06, "grad_norm": 67.5, "learning_rate": 9.389830508474576e-07, "loss": 1.6293, "step": 2300 }, { "epoch": 0.06, "grad_norm": 67.5, "learning_rate": 9.386440677966101e-07, "loss": 1.596, "step": 2310 }, { "epoch": 0.06, "grad_norm": 67.5, "learning_rate": 9.383050847457626e-07, "loss": 1.6159, "step": 2320 }, { "epoch": 0.06, "grad_norm": 66.5, "learning_rate": 9.379661016949152e-07, "loss": 1.5201, "step": 2330 }, { "epoch": 0.06, "grad_norm": 71.0, "learning_rate": 9.376271186440677e-07, "loss": 1.6464, "step": 2340 }, { "epoch": 0.06, "grad_norm": 66.0, "learning_rate": 9.372881355932203e-07, "loss": 1.6035, "step": 2350 }, { "epoch": 0.06, "grad_norm": 69.0, "learning_rate": 9.369491525423729e-07, "loss": 1.6379, "step": 2360 }, { "epoch": 0.06, "grad_norm": 68.0, "learning_rate": 9.366101694915254e-07, "loss": 1.6182, "step": 2370 }, { "epoch": 0.06, "grad_norm": 67.0, "learning_rate": 9.362711864406779e-07, "loss": 1.6201, "step": 2380 }, { "epoch": 0.06, "grad_norm": 71.0, "learning_rate": 9.359322033898304e-07, "loss": 1.569, "step": 2390 }, { "epoch": 0.06, "grad_norm": 67.5, "learning_rate": 9.355932203389831e-07, "loss": 1.5749, "step": 2400 }, { "epoch": 0.06, "grad_norm": 67.0, "learning_rate": 9.352542372881356e-07, "loss": 1.6154, "step": 2410 }, { "epoch": 0.06, "grad_norm": 67.0, "learning_rate": 9.349152542372881e-07, "loss": 1.5639, "step": 2420 }, { "epoch": 0.06, "grad_norm": 65.5, "learning_rate": 9.345762711864407e-07, "loss": 1.5745, "step": 2430 }, { "epoch": 0.06, "grad_norm": 71.5, "learning_rate": 9.342372881355932e-07, "loss": 1.5988, "step": 2440 }, { "epoch": 0.06, "grad_norm": 72.0, "learning_rate": 9.338983050847458e-07, "loss": 1.6111, "step": 2450 }, { "epoch": 0.06, "grad_norm": 68.5, "learning_rate": 9.335593220338983e-07, "loss": 1.6351, "step": 2460 }, { "epoch": 0.06, "grad_norm": 68.5, "learning_rate": 9.332203389830509e-07, "loss": 1.5946, "step": 2470 }, { "epoch": 0.06, "grad_norm": 69.5, "learning_rate": 9.328813559322033e-07, "loss": 1.5306, "step": 2480 }, { "epoch": 0.06, "grad_norm": 65.5, "learning_rate": 9.325423728813558e-07, "loss": 1.5605, "step": 2490 }, { "epoch": 0.06, "grad_norm": 68.5, "learning_rate": 9.322033898305083e-07, "loss": 1.5907, "step": 2500 }, { "epoch": 0.06, "grad_norm": 66.0, "learning_rate": 9.31864406779661e-07, "loss": 1.5823, "step": 2510 }, { "epoch": 0.06, "grad_norm": 65.5, "learning_rate": 9.315254237288135e-07, "loss": 1.565, "step": 2520 }, { "epoch": 0.06, "grad_norm": 69.0, "learning_rate": 9.31186440677966e-07, "loss": 1.5669, "step": 2530 }, { "epoch": 0.06, "grad_norm": 67.5, "learning_rate": 9.308474576271186e-07, "loss": 1.5595, "step": 2540 }, { "epoch": 0.06, "grad_norm": 65.5, "learning_rate": 9.305084745762711e-07, "loss": 1.5367, "step": 2550 }, { "epoch": 0.06, "grad_norm": 67.5, "learning_rate": 9.301694915254237e-07, "loss": 1.6048, "step": 2560 }, { "epoch": 0.06, "grad_norm": 66.5, "learning_rate": 9.298305084745763e-07, "loss": 1.6001, "step": 2570 }, { "epoch": 0.06, "grad_norm": 71.0, "learning_rate": 9.294915254237288e-07, "loss": 1.6077, "step": 2580 }, { "epoch": 0.06, "grad_norm": 66.5, "learning_rate": 9.291525423728813e-07, "loss": 1.5488, "step": 2590 }, { "epoch": 0.07, "grad_norm": 67.0, "learning_rate": 9.288135593220338e-07, "loss": 1.5676, "step": 2600 }, { "epoch": 0.07, "grad_norm": 67.5, "learning_rate": 9.284745762711864e-07, "loss": 1.5455, "step": 2610 }, { "epoch": 0.07, "grad_norm": 65.0, "learning_rate": 9.28135593220339e-07, "loss": 1.5867, "step": 2620 }, { "epoch": 0.07, "grad_norm": 67.0, "learning_rate": 9.277966101694915e-07, "loss": 1.5505, "step": 2630 }, { "epoch": 0.07, "grad_norm": 68.0, "learning_rate": 9.274576271186441e-07, "loss": 1.5646, "step": 2640 }, { "epoch": 0.07, "grad_norm": 65.0, "learning_rate": 9.271186440677966e-07, "loss": 1.5345, "step": 2650 }, { "epoch": 0.07, "grad_norm": 69.5, "learning_rate": 9.267796610169491e-07, "loss": 1.6042, "step": 2660 }, { "epoch": 0.07, "grad_norm": 66.0, "learning_rate": 9.264406779661017e-07, "loss": 1.5496, "step": 2670 }, { "epoch": 0.07, "grad_norm": 67.0, "learning_rate": 9.261016949152543e-07, "loss": 1.565, "step": 2680 }, { "epoch": 0.07, "grad_norm": 67.0, "learning_rate": 9.257627118644067e-07, "loss": 1.5168, "step": 2690 }, { "epoch": 0.07, "grad_norm": 68.0, "learning_rate": 9.254237288135592e-07, "loss": 1.5704, "step": 2700 }, { "epoch": 0.07, "grad_norm": 68.5, "learning_rate": 9.250847457627117e-07, "loss": 1.5708, "step": 2710 }, { "epoch": 0.07, "grad_norm": 71.0, "learning_rate": 9.247457627118644e-07, "loss": 1.5891, "step": 2720 }, { "epoch": 0.07, "grad_norm": 66.0, "learning_rate": 9.244067796610169e-07, "loss": 1.5333, "step": 2730 }, { "epoch": 0.07, "grad_norm": 69.0, "learning_rate": 9.240677966101694e-07, "loss": 1.5307, "step": 2740 }, { "epoch": 0.07, "grad_norm": 66.0, "learning_rate": 9.23728813559322e-07, "loss": 1.5467, "step": 2750 }, { "epoch": 0.07, "grad_norm": 66.0, "learning_rate": 9.233898305084745e-07, "loss": 1.5557, "step": 2760 }, { "epoch": 0.07, "grad_norm": 69.5, "learning_rate": 9.23050847457627e-07, "loss": 1.54, "step": 2770 }, { "epoch": 0.07, "grad_norm": 69.5, "learning_rate": 9.227118644067797e-07, "loss": 1.5305, "step": 2780 }, { "epoch": 0.07, "grad_norm": 68.0, "learning_rate": 9.223728813559322e-07, "loss": 1.4947, "step": 2790 }, { "epoch": 0.07, "grad_norm": 70.5, "learning_rate": 9.220338983050847e-07, "loss": 1.5353, "step": 2800 }, { "epoch": 0.07, "grad_norm": 66.5, "learning_rate": 9.216949152542372e-07, "loss": 1.578, "step": 2810 }, { "epoch": 0.07, "grad_norm": 70.5, "learning_rate": 9.213559322033898e-07, "loss": 1.5556, "step": 2820 }, { "epoch": 0.07, "grad_norm": 66.5, "learning_rate": 9.210169491525424e-07, "loss": 1.4998, "step": 2830 }, { "epoch": 0.07, "grad_norm": 66.5, "learning_rate": 9.206779661016949e-07, "loss": 1.5517, "step": 2840 }, { "epoch": 0.07, "grad_norm": 67.5, "learning_rate": 9.203389830508475e-07, "loss": 1.5942, "step": 2850 }, { "epoch": 0.07, "grad_norm": 67.5, "learning_rate": 9.2e-07, "loss": 1.5581, "step": 2860 }, { "epoch": 0.07, "grad_norm": 66.0, "learning_rate": 9.196610169491525e-07, "loss": 1.5578, "step": 2870 }, { "epoch": 0.07, "grad_norm": 69.5, "learning_rate": 9.193220338983051e-07, "loss": 1.5153, "step": 2880 }, { "epoch": 0.07, "grad_norm": 66.5, "learning_rate": 9.189830508474576e-07, "loss": 1.5391, "step": 2890 }, { "epoch": 0.07, "grad_norm": 69.0, "learning_rate": 9.186440677966101e-07, "loss": 1.5475, "step": 2900 }, { "epoch": 0.07, "grad_norm": 68.5, "learning_rate": 9.183050847457626e-07, "loss": 1.5681, "step": 2910 }, { "epoch": 0.07, "grad_norm": 67.0, "learning_rate": 9.179661016949151e-07, "loss": 1.5216, "step": 2920 }, { "epoch": 0.07, "grad_norm": 67.0, "learning_rate": 9.176271186440677e-07, "loss": 1.5378, "step": 2930 }, { "epoch": 0.07, "grad_norm": 67.5, "learning_rate": 9.172881355932203e-07, "loss": 1.5092, "step": 2940 }, { "epoch": 0.07, "grad_norm": 68.0, "learning_rate": 9.169491525423728e-07, "loss": 1.5565, "step": 2950 }, { "epoch": 0.07, "grad_norm": 68.5, "learning_rate": 9.166101694915254e-07, "loss": 1.5672, "step": 2960 }, { "epoch": 0.07, "grad_norm": 66.0, "learning_rate": 9.162711864406779e-07, "loss": 1.5431, "step": 2970 }, { "epoch": 0.07, "grad_norm": 68.0, "learning_rate": 9.159322033898304e-07, "loss": 1.5306, "step": 2980 }, { "epoch": 0.07, "grad_norm": 69.0, "learning_rate": 9.15593220338983e-07, "loss": 1.5469, "step": 2990 }, { "epoch": 0.07, "grad_norm": 66.5, "learning_rate": 9.152542372881356e-07, "loss": 1.4952, "step": 3000 }, { "epoch": 0.08, "grad_norm": 66.5, "learning_rate": 9.149152542372881e-07, "loss": 1.5161, "step": 3010 }, { "epoch": 0.08, "grad_norm": 65.5, "learning_rate": 9.145762711864406e-07, "loss": 1.5524, "step": 3020 }, { "epoch": 0.08, "grad_norm": 69.0, "learning_rate": 9.142372881355932e-07, "loss": 1.5231, "step": 3030 }, { "epoch": 0.08, "grad_norm": 70.5, "learning_rate": 9.138983050847458e-07, "loss": 1.5075, "step": 3040 }, { "epoch": 0.08, "grad_norm": 66.5, "learning_rate": 9.135593220338983e-07, "loss": 1.5372, "step": 3050 }, { "epoch": 0.08, "grad_norm": 70.5, "learning_rate": 9.132203389830509e-07, "loss": 1.4916, "step": 3060 }, { "epoch": 0.08, "grad_norm": 64.5, "learning_rate": 9.128813559322034e-07, "loss": 1.4986, "step": 3070 }, { "epoch": 0.08, "grad_norm": 71.0, "learning_rate": 9.125423728813559e-07, "loss": 1.5884, "step": 3080 }, { "epoch": 0.08, "grad_norm": 69.5, "learning_rate": 9.122033898305084e-07, "loss": 1.5365, "step": 3090 }, { "epoch": 0.08, "grad_norm": 68.0, "learning_rate": 9.11864406779661e-07, "loss": 1.5629, "step": 3100 }, { "epoch": 0.08, "grad_norm": 69.0, "learning_rate": 9.115254237288135e-07, "loss": 1.5343, "step": 3110 }, { "epoch": 0.08, "grad_norm": 70.0, "learning_rate": 9.11186440677966e-07, "loss": 1.558, "step": 3120 }, { "epoch": 0.08, "grad_norm": 70.0, "learning_rate": 9.108474576271185e-07, "loss": 1.4962, "step": 3130 }, { "epoch": 0.08, "grad_norm": 67.0, "learning_rate": 9.105084745762711e-07, "loss": 1.4927, "step": 3140 }, { "epoch": 0.08, "grad_norm": 70.0, "learning_rate": 9.101694915254237e-07, "loss": 1.4935, "step": 3150 }, { "epoch": 0.08, "grad_norm": 65.5, "learning_rate": 9.098305084745762e-07, "loss": 1.493, "step": 3160 }, { "epoch": 0.08, "grad_norm": 65.0, "learning_rate": 9.094915254237288e-07, "loss": 1.5289, "step": 3170 }, { "epoch": 0.08, "grad_norm": 69.5, "learning_rate": 9.091525423728813e-07, "loss": 1.4893, "step": 3180 }, { "epoch": 0.08, "grad_norm": 69.0, "learning_rate": 9.088135593220338e-07, "loss": 1.4864, "step": 3190 }, { "epoch": 0.08, "grad_norm": 67.5, "learning_rate": 9.084745762711864e-07, "loss": 1.4915, "step": 3200 }, { "epoch": 0.08, "grad_norm": 65.5, "learning_rate": 9.08135593220339e-07, "loss": 1.4848, "step": 3210 }, { "epoch": 0.08, "grad_norm": 69.5, "learning_rate": 9.077966101694915e-07, "loss": 1.5586, "step": 3220 }, { "epoch": 0.08, "grad_norm": 72.0, "learning_rate": 9.07457627118644e-07, "loss": 1.5623, "step": 3230 }, { "epoch": 0.08, "grad_norm": 71.0, "learning_rate": 9.071186440677966e-07, "loss": 1.529, "step": 3240 }, { "epoch": 0.08, "grad_norm": 67.5, "learning_rate": 9.067796610169491e-07, "loss": 1.5422, "step": 3250 }, { "epoch": 0.08, "grad_norm": 71.5, "learning_rate": 9.064406779661017e-07, "loss": 1.5146, "step": 3260 }, { "epoch": 0.08, "grad_norm": 66.0, "learning_rate": 9.061016949152542e-07, "loss": 1.5405, "step": 3270 }, { "epoch": 0.08, "grad_norm": 69.0, "learning_rate": 9.057627118644068e-07, "loss": 1.5228, "step": 3280 }, { "epoch": 0.08, "grad_norm": 63.0, "learning_rate": 9.054237288135593e-07, "loss": 1.4958, "step": 3290 }, { "epoch": 0.08, "grad_norm": 65.5, "learning_rate": 9.050847457627118e-07, "loss": 1.4941, "step": 3300 }, { "epoch": 0.08, "grad_norm": 67.0, "learning_rate": 9.047457627118644e-07, "loss": 1.4789, "step": 3310 }, { "epoch": 0.08, "grad_norm": 70.5, "learning_rate": 9.044067796610169e-07, "loss": 1.5649, "step": 3320 }, { "epoch": 0.08, "grad_norm": 62.5, "learning_rate": 9.040677966101694e-07, "loss": 1.5423, "step": 3330 }, { "epoch": 0.08, "grad_norm": 66.5, "learning_rate": 9.037288135593219e-07, "loss": 1.5643, "step": 3340 }, { "epoch": 0.08, "grad_norm": 67.5, "learning_rate": 9.033898305084745e-07, "loss": 1.5374, "step": 3350 }, { "epoch": 0.08, "grad_norm": 67.0, "learning_rate": 9.030508474576271e-07, "loss": 1.513, "step": 3360 }, { "epoch": 0.08, "grad_norm": 66.5, "learning_rate": 9.027118644067796e-07, "loss": 1.4677, "step": 3370 }, { "epoch": 0.08, "grad_norm": 66.5, "learning_rate": 9.023728813559322e-07, "loss": 1.5205, "step": 3380 }, { "epoch": 0.08, "grad_norm": 65.5, "learning_rate": 9.020338983050847e-07, "loss": 1.4427, "step": 3390 }, { "epoch": 0.09, "grad_norm": 67.5, "learning_rate": 9.016949152542372e-07, "loss": 1.4932, "step": 3400 }, { "epoch": 0.09, "grad_norm": 65.0, "learning_rate": 9.013559322033897e-07, "loss": 1.4896, "step": 3410 }, { "epoch": 0.09, "grad_norm": 69.5, "learning_rate": 9.010169491525424e-07, "loss": 1.4794, "step": 3420 }, { "epoch": 0.09, "grad_norm": 69.5, "learning_rate": 9.006779661016949e-07, "loss": 1.4937, "step": 3430 }, { "epoch": 0.09, "grad_norm": 63.5, "learning_rate": 9.003389830508474e-07, "loss": 1.505, "step": 3440 }, { "epoch": 0.09, "grad_norm": 68.0, "learning_rate": 9e-07, "loss": 1.5064, "step": 3450 }, { "epoch": 0.09, "grad_norm": 66.0, "learning_rate": 8.996610169491525e-07, "loss": 1.5155, "step": 3460 }, { "epoch": 0.09, "grad_norm": 67.0, "learning_rate": 8.993220338983051e-07, "loss": 1.4963, "step": 3470 }, { "epoch": 0.09, "grad_norm": 69.0, "learning_rate": 8.989830508474576e-07, "loss": 1.5501, "step": 3480 }, { "epoch": 0.09, "grad_norm": 68.0, "learning_rate": 8.986440677966102e-07, "loss": 1.4952, "step": 3490 }, { "epoch": 0.09, "grad_norm": 67.5, "learning_rate": 8.983050847457627e-07, "loss": 1.5111, "step": 3500 }, { "epoch": 0.09, "grad_norm": 72.5, "learning_rate": 8.979661016949152e-07, "loss": 1.458, "step": 3510 }, { "epoch": 0.09, "grad_norm": 65.0, "learning_rate": 8.976271186440677e-07, "loss": 1.4459, "step": 3520 }, { "epoch": 0.09, "grad_norm": 66.0, "learning_rate": 8.972881355932203e-07, "loss": 1.4634, "step": 3530 }, { "epoch": 0.09, "grad_norm": 65.0, "learning_rate": 8.969491525423728e-07, "loss": 1.5086, "step": 3540 }, { "epoch": 0.09, "grad_norm": 69.0, "learning_rate": 8.966101694915253e-07, "loss": 1.5226, "step": 3550 }, { "epoch": 0.09, "grad_norm": 69.0, "learning_rate": 8.962711864406779e-07, "loss": 1.5094, "step": 3560 }, { "epoch": 0.09, "grad_norm": 75.5, "learning_rate": 8.959322033898304e-07, "loss": 1.4869, "step": 3570 }, { "epoch": 0.09, "grad_norm": 65.0, "learning_rate": 8.95593220338983e-07, "loss": 1.4863, "step": 3580 }, { "epoch": 0.09, "grad_norm": 66.0, "learning_rate": 8.952542372881356e-07, "loss": 1.4733, "step": 3590 }, { "epoch": 0.09, "grad_norm": 76.5, "learning_rate": 8.949152542372881e-07, "loss": 1.4918, "step": 3600 }, { "epoch": 0.09, "grad_norm": 69.0, "learning_rate": 8.945762711864406e-07, "loss": 1.5012, "step": 3610 }, { "epoch": 0.09, "grad_norm": 68.5, "learning_rate": 8.942372881355931e-07, "loss": 1.4974, "step": 3620 }, { "epoch": 0.09, "grad_norm": 64.0, "learning_rate": 8.938983050847458e-07, "loss": 1.441, "step": 3630 }, { "epoch": 0.09, "grad_norm": 65.5, "learning_rate": 8.935593220338983e-07, "loss": 1.4837, "step": 3640 }, { "epoch": 0.09, "grad_norm": 67.5, "learning_rate": 8.932203389830508e-07, "loss": 1.4722, "step": 3650 }, { "epoch": 0.09, "grad_norm": 69.5, "learning_rate": 8.928813559322034e-07, "loss": 1.4821, "step": 3660 }, { "epoch": 0.09, "grad_norm": 68.0, "learning_rate": 8.925423728813559e-07, "loss": 1.5346, "step": 3670 }, { "epoch": 0.09, "grad_norm": 65.0, "learning_rate": 8.922033898305085e-07, "loss": 1.5196, "step": 3680 }, { "epoch": 0.09, "grad_norm": 66.0, "learning_rate": 8.91864406779661e-07, "loss": 1.4761, "step": 3690 }, { "epoch": 0.09, "grad_norm": 65.5, "learning_rate": 8.915254237288136e-07, "loss": 1.4885, "step": 3700 }, { "epoch": 0.09, "grad_norm": 66.0, "learning_rate": 8.911864406779661e-07, "loss": 1.5114, "step": 3710 }, { "epoch": 0.09, "grad_norm": 68.0, "learning_rate": 8.908474576271186e-07, "loss": 1.4701, "step": 3720 }, { "epoch": 0.09, "grad_norm": 64.5, "learning_rate": 8.90508474576271e-07, "loss": 1.501, "step": 3730 }, { "epoch": 0.09, "grad_norm": 68.0, "learning_rate": 8.901694915254237e-07, "loss": 1.4863, "step": 3740 }, { "epoch": 0.09, "grad_norm": 66.5, "learning_rate": 8.898305084745762e-07, "loss": 1.4616, "step": 3750 }, { "epoch": 0.09, "grad_norm": 67.5, "learning_rate": 8.894915254237287e-07, "loss": 1.4995, "step": 3760 }, { "epoch": 0.09, "grad_norm": 66.0, "learning_rate": 8.891525423728813e-07, "loss": 1.4846, "step": 3770 }, { "epoch": 0.09, "grad_norm": 67.0, "learning_rate": 8.888135593220338e-07, "loss": 1.4895, "step": 3780 }, { "epoch": 0.09, "grad_norm": 67.5, "learning_rate": 8.884745762711864e-07, "loss": 1.5152, "step": 3790 }, { "epoch": 0.1, "grad_norm": 70.0, "learning_rate": 8.88135593220339e-07, "loss": 1.4775, "step": 3800 }, { "epoch": 0.1, "grad_norm": 62.5, "learning_rate": 8.877966101694915e-07, "loss": 1.454, "step": 3810 }, { "epoch": 0.1, "grad_norm": 65.0, "learning_rate": 8.87457627118644e-07, "loss": 1.5004, "step": 3820 }, { "epoch": 0.1, "grad_norm": 66.0, "learning_rate": 8.871186440677965e-07, "loss": 1.4825, "step": 3830 }, { "epoch": 0.1, "grad_norm": 68.0, "learning_rate": 8.867796610169492e-07, "loss": 1.5067, "step": 3840 }, { "epoch": 0.1, "grad_norm": 67.5, "learning_rate": 8.864406779661017e-07, "loss": 1.5393, "step": 3850 }, { "epoch": 0.1, "grad_norm": 68.5, "learning_rate": 8.861016949152542e-07, "loss": 1.467, "step": 3860 }, { "epoch": 0.1, "grad_norm": 68.0, "learning_rate": 8.857627118644068e-07, "loss": 1.477, "step": 3870 }, { "epoch": 0.1, "grad_norm": 67.5, "learning_rate": 8.854237288135593e-07, "loss": 1.4855, "step": 3880 }, { "epoch": 0.1, "grad_norm": 67.0, "learning_rate": 8.850847457627118e-07, "loss": 1.4544, "step": 3890 }, { "epoch": 0.1, "grad_norm": 66.5, "learning_rate": 8.847457627118644e-07, "loss": 1.4787, "step": 3900 }, { "epoch": 0.1, "grad_norm": 73.0, "learning_rate": 8.84406779661017e-07, "loss": 1.4947, "step": 3910 }, { "epoch": 0.1, "grad_norm": 65.5, "learning_rate": 8.840677966101695e-07, "loss": 1.4749, "step": 3920 }, { "epoch": 0.1, "grad_norm": 66.0, "learning_rate": 8.837288135593219e-07, "loss": 1.5096, "step": 3930 }, { "epoch": 0.1, "grad_norm": 68.5, "learning_rate": 8.833898305084745e-07, "loss": 1.5044, "step": 3940 }, { "epoch": 0.1, "grad_norm": 77.0, "learning_rate": 8.830508474576271e-07, "loss": 1.4945, "step": 3950 }, { "epoch": 0.1, "grad_norm": 67.5, "learning_rate": 8.827118644067796e-07, "loss": 1.4693, "step": 3960 }, { "epoch": 0.1, "grad_norm": 68.5, "learning_rate": 8.823728813559321e-07, "loss": 1.4914, "step": 3970 }, { "epoch": 0.1, "grad_norm": 71.0, "learning_rate": 8.820338983050847e-07, "loss": 1.4551, "step": 3980 }, { "epoch": 0.1, "grad_norm": 65.5, "learning_rate": 8.816949152542372e-07, "loss": 1.5076, "step": 3990 }, { "epoch": 0.1, "grad_norm": 66.0, "learning_rate": 8.813559322033897e-07, "loss": 1.48, "step": 4000 }, { "epoch": 0.1, "grad_norm": 65.5, "learning_rate": 8.810169491525424e-07, "loss": 1.4452, "step": 4010 }, { "epoch": 0.1, "grad_norm": 64.5, "learning_rate": 8.806779661016949e-07, "loss": 1.4619, "step": 4020 }, { "epoch": 0.1, "grad_norm": 65.0, "learning_rate": 8.803389830508474e-07, "loss": 1.454, "step": 4030 }, { "epoch": 0.1, "grad_norm": 67.0, "learning_rate": 8.799999999999999e-07, "loss": 1.4648, "step": 4040 }, { "epoch": 0.1, "grad_norm": 64.5, "learning_rate": 8.796610169491525e-07, "loss": 1.5015, "step": 4050 }, { "epoch": 0.1, "grad_norm": 66.5, "learning_rate": 8.793220338983051e-07, "loss": 1.4932, "step": 4060 }, { "epoch": 0.1, "grad_norm": 66.0, "learning_rate": 8.789830508474576e-07, "loss": 1.4945, "step": 4070 }, { "epoch": 0.1, "grad_norm": 67.5, "learning_rate": 8.786440677966102e-07, "loss": 1.5184, "step": 4080 }, { "epoch": 0.1, "grad_norm": 65.0, "learning_rate": 8.783050847457627e-07, "loss": 1.4599, "step": 4090 }, { "epoch": 0.1, "grad_norm": 65.5, "learning_rate": 8.779661016949152e-07, "loss": 1.5357, "step": 4100 }, { "epoch": 0.1, "grad_norm": 69.0, "learning_rate": 8.776271186440678e-07, "loss": 1.4867, "step": 4110 }, { "epoch": 0.1, "grad_norm": 67.5, "learning_rate": 8.772881355932204e-07, "loss": 1.4618, "step": 4120 }, { "epoch": 0.1, "grad_norm": 66.5, "learning_rate": 8.769491525423729e-07, "loss": 1.4736, "step": 4130 }, { "epoch": 0.1, "grad_norm": 66.0, "learning_rate": 8.766101694915253e-07, "loss": 1.4781, "step": 4140 }, { "epoch": 0.1, "grad_norm": 66.0, "learning_rate": 8.762711864406778e-07, "loss": 1.4892, "step": 4150 }, { "epoch": 0.1, "grad_norm": 68.5, "learning_rate": 8.759322033898304e-07, "loss": 1.4566, "step": 4160 }, { "epoch": 0.1, "grad_norm": 66.0, "learning_rate": 8.75593220338983e-07, "loss": 1.4814, "step": 4170 }, { "epoch": 0.1, "grad_norm": 71.0, "learning_rate": 8.752542372881355e-07, "loss": 1.4921, "step": 4180 }, { "epoch": 0.1, "grad_norm": 70.5, "learning_rate": 8.749152542372881e-07, "loss": 1.5361, "step": 4190 }, { "epoch": 0.1, "grad_norm": 65.0, "learning_rate": 8.745762711864406e-07, "loss": 1.4342, "step": 4200 }, { "epoch": 0.11, "grad_norm": 66.0, "learning_rate": 8.742372881355931e-07, "loss": 1.5141, "step": 4210 }, { "epoch": 0.11, "grad_norm": 67.5, "learning_rate": 8.738983050847458e-07, "loss": 1.5203, "step": 4220 }, { "epoch": 0.11, "grad_norm": 69.5, "learning_rate": 8.735593220338983e-07, "loss": 1.4885, "step": 4230 }, { "epoch": 0.11, "grad_norm": 65.5, "learning_rate": 8.732203389830508e-07, "loss": 1.5292, "step": 4240 }, { "epoch": 0.11, "grad_norm": 65.0, "learning_rate": 8.728813559322033e-07, "loss": 1.5156, "step": 4250 }, { "epoch": 0.11, "grad_norm": 64.0, "learning_rate": 8.725423728813559e-07, "loss": 1.4583, "step": 4260 }, { "epoch": 0.11, "grad_norm": 64.0, "learning_rate": 8.722033898305085e-07, "loss": 1.5098, "step": 4270 }, { "epoch": 0.11, "grad_norm": 67.0, "learning_rate": 8.71864406779661e-07, "loss": 1.4739, "step": 4280 }, { "epoch": 0.11, "grad_norm": 68.0, "learning_rate": 8.715254237288136e-07, "loss": 1.484, "step": 4290 }, { "epoch": 0.11, "grad_norm": 67.5, "learning_rate": 8.711864406779661e-07, "loss": 1.5197, "step": 4300 }, { "epoch": 0.11, "grad_norm": 66.5, "learning_rate": 8.708474576271186e-07, "loss": 1.5088, "step": 4310 }, { "epoch": 0.11, "grad_norm": 68.0, "learning_rate": 8.705084745762711e-07, "loss": 1.4749, "step": 4320 }, { "epoch": 0.11, "grad_norm": 67.0, "learning_rate": 8.701694915254238e-07, "loss": 1.4429, "step": 4330 }, { "epoch": 0.11, "grad_norm": 67.0, "learning_rate": 8.698305084745763e-07, "loss": 1.4921, "step": 4340 }, { "epoch": 0.11, "grad_norm": 65.5, "learning_rate": 8.694915254237287e-07, "loss": 1.4362, "step": 4350 }, { "epoch": 0.11, "grad_norm": 69.0, "learning_rate": 8.691525423728812e-07, "loss": 1.4985, "step": 4360 }, { "epoch": 0.11, "grad_norm": 62.75, "learning_rate": 8.688135593220338e-07, "loss": 1.4431, "step": 4370 }, { "epoch": 0.11, "grad_norm": 67.0, "learning_rate": 8.684745762711864e-07, "loss": 1.4694, "step": 4380 }, { "epoch": 0.11, "grad_norm": 67.0, "learning_rate": 8.681355932203389e-07, "loss": 1.5127, "step": 4390 }, { "epoch": 0.11, "grad_norm": 70.0, "learning_rate": 8.677966101694915e-07, "loss": 1.5039, "step": 4400 }, { "epoch": 0.11, "grad_norm": 66.5, "learning_rate": 8.67457627118644e-07, "loss": 1.4797, "step": 4410 }, { "epoch": 0.11, "grad_norm": 70.0, "learning_rate": 8.671186440677965e-07, "loss": 1.4775, "step": 4420 }, { "epoch": 0.11, "grad_norm": 67.0, "learning_rate": 8.667796610169492e-07, "loss": 1.4614, "step": 4430 }, { "epoch": 0.11, "grad_norm": 66.5, "learning_rate": 8.664406779661017e-07, "loss": 1.4886, "step": 4440 }, { "epoch": 0.11, "grad_norm": 65.5, "learning_rate": 8.661016949152542e-07, "loss": 1.4871, "step": 4450 }, { "epoch": 0.11, "grad_norm": 66.5, "learning_rate": 8.657627118644067e-07, "loss": 1.4607, "step": 4460 }, { "epoch": 0.11, "grad_norm": 68.5, "learning_rate": 8.654237288135593e-07, "loss": 1.4581, "step": 4470 }, { "epoch": 0.11, "grad_norm": 64.0, "learning_rate": 8.650847457627118e-07, "loss": 1.4685, "step": 4480 }, { "epoch": 0.11, "grad_norm": 69.0, "learning_rate": 8.647457627118644e-07, "loss": 1.4421, "step": 4490 }, { "epoch": 0.11, "grad_norm": 64.5, "learning_rate": 8.64406779661017e-07, "loss": 1.4878, "step": 4500 }, { "epoch": 0.11, "grad_norm": 65.0, "learning_rate": 8.640677966101695e-07, "loss": 1.4713, "step": 4510 }, { "epoch": 0.11, "grad_norm": 66.0, "learning_rate": 8.63728813559322e-07, "loss": 1.5214, "step": 4520 }, { "epoch": 0.11, "grad_norm": 63.75, "learning_rate": 8.633898305084745e-07, "loss": 1.4646, "step": 4530 }, { "epoch": 0.11, "grad_norm": 67.0, "learning_rate": 8.630508474576272e-07, "loss": 1.4881, "step": 4540 }, { "epoch": 0.11, "grad_norm": 66.0, "learning_rate": 8.627118644067797e-07, "loss": 1.4766, "step": 4550 }, { "epoch": 0.11, "grad_norm": 70.5, "learning_rate": 8.623728813559321e-07, "loss": 1.4862, "step": 4560 }, { "epoch": 0.11, "grad_norm": 68.5, "learning_rate": 8.620338983050846e-07, "loss": 1.3567, "step": 4570 }, { "epoch": 0.11, "grad_norm": 65.0, "learning_rate": 8.616949152542372e-07, "loss": 1.4422, "step": 4580 }, { "epoch": 0.11, "grad_norm": 67.0, "learning_rate": 8.613559322033898e-07, "loss": 1.4581, "step": 4590 }, { "epoch": 0.12, "grad_norm": 65.0, "learning_rate": 8.610169491525423e-07, "loss": 1.4973, "step": 4600 }, { "epoch": 0.12, "grad_norm": 66.0, "learning_rate": 8.606779661016949e-07, "loss": 1.4999, "step": 4610 }, { "epoch": 0.12, "grad_norm": 68.0, "learning_rate": 8.603389830508474e-07, "loss": 1.4901, "step": 4620 }, { "epoch": 0.12, "grad_norm": 66.0, "learning_rate": 8.599999999999999e-07, "loss": 1.4738, "step": 4630 }, { "epoch": 0.12, "grad_norm": 71.0, "learning_rate": 8.596610169491524e-07, "loss": 1.4951, "step": 4640 }, { "epoch": 0.12, "grad_norm": 65.0, "learning_rate": 8.593220338983051e-07, "loss": 1.4923, "step": 4650 }, { "epoch": 0.12, "grad_norm": 67.5, "learning_rate": 8.589830508474576e-07, "loss": 1.4571, "step": 4660 }, { "epoch": 0.12, "grad_norm": 67.0, "learning_rate": 8.586440677966101e-07, "loss": 1.4913, "step": 4670 }, { "epoch": 0.12, "grad_norm": 65.5, "learning_rate": 8.583050847457627e-07, "loss": 1.4655, "step": 4680 }, { "epoch": 0.12, "grad_norm": 68.5, "learning_rate": 8.579661016949152e-07, "loss": 1.485, "step": 4690 }, { "epoch": 0.12, "grad_norm": 65.5, "learning_rate": 8.576271186440678e-07, "loss": 1.4815, "step": 4700 }, { "epoch": 0.12, "grad_norm": 70.0, "learning_rate": 8.572881355932204e-07, "loss": 1.5056, "step": 4710 }, { "epoch": 0.12, "grad_norm": 68.0, "learning_rate": 8.569491525423729e-07, "loss": 1.4773, "step": 4720 }, { "epoch": 0.12, "grad_norm": 69.5, "learning_rate": 8.566101694915254e-07, "loss": 1.5163, "step": 4730 }, { "epoch": 0.12, "grad_norm": 69.0, "learning_rate": 8.562711864406779e-07, "loss": 1.4273, "step": 4740 }, { "epoch": 0.12, "grad_norm": 67.0, "learning_rate": 8.559322033898306e-07, "loss": 1.4475, "step": 4750 }, { "epoch": 0.12, "grad_norm": 71.5, "learning_rate": 8.55593220338983e-07, "loss": 1.4884, "step": 4760 }, { "epoch": 0.12, "grad_norm": 71.5, "learning_rate": 8.552542372881355e-07, "loss": 1.5041, "step": 4770 }, { "epoch": 0.12, "grad_norm": 66.0, "learning_rate": 8.54915254237288e-07, "loss": 1.4597, "step": 4780 }, { "epoch": 0.12, "grad_norm": 68.0, "learning_rate": 8.545762711864406e-07, "loss": 1.4828, "step": 4790 }, { "epoch": 0.12, "grad_norm": 65.5, "learning_rate": 8.542372881355931e-07, "loss": 1.4992, "step": 4800 }, { "epoch": 0.12, "grad_norm": 66.5, "learning_rate": 8.538983050847457e-07, "loss": 1.4546, "step": 4810 }, { "epoch": 0.12, "grad_norm": 65.5, "learning_rate": 8.535593220338983e-07, "loss": 1.4745, "step": 4820 }, { "epoch": 0.12, "grad_norm": 68.5, "learning_rate": 8.532203389830508e-07, "loss": 1.488, "step": 4830 }, { "epoch": 0.12, "grad_norm": 66.5, "learning_rate": 8.528813559322033e-07, "loss": 1.4607, "step": 4840 }, { "epoch": 0.12, "grad_norm": 67.0, "learning_rate": 8.525423728813558e-07, "loss": 1.4884, "step": 4850 }, { "epoch": 0.12, "grad_norm": 70.5, "learning_rate": 8.522033898305085e-07, "loss": 1.4927, "step": 4860 }, { "epoch": 0.12, "grad_norm": 66.0, "learning_rate": 8.51864406779661e-07, "loss": 1.498, "step": 4870 }, { "epoch": 0.12, "grad_norm": 69.5, "learning_rate": 8.515254237288135e-07, "loss": 1.4846, "step": 4880 }, { "epoch": 0.12, "grad_norm": 65.5, "learning_rate": 8.511864406779661e-07, "loss": 1.5013, "step": 4890 }, { "epoch": 0.12, "grad_norm": 68.0, "learning_rate": 8.508474576271186e-07, "loss": 1.4643, "step": 4900 }, { "epoch": 0.12, "grad_norm": 68.0, "learning_rate": 8.505084745762712e-07, "loss": 1.465, "step": 4910 }, { "epoch": 0.12, "grad_norm": 69.0, "learning_rate": 8.501694915254238e-07, "loss": 1.4796, "step": 4920 }, { "epoch": 0.12, "grad_norm": 64.5, "learning_rate": 8.498305084745763e-07, "loss": 1.4816, "step": 4930 }, { "epoch": 0.12, "grad_norm": 64.0, "learning_rate": 8.494915254237288e-07, "loss": 1.48, "step": 4940 }, { "epoch": 0.12, "grad_norm": 66.5, "learning_rate": 8.491525423728813e-07, "loss": 1.4097, "step": 4950 }, { "epoch": 0.12, "grad_norm": 66.5, "learning_rate": 8.488135593220339e-07, "loss": 1.488, "step": 4960 }, { "epoch": 0.12, "grad_norm": 66.5, "learning_rate": 8.484745762711864e-07, "loss": 1.4347, "step": 4970 }, { "epoch": 0.12, "grad_norm": 69.0, "learning_rate": 8.481355932203389e-07, "loss": 1.4901, "step": 4980 }, { "epoch": 0.12, "grad_norm": 63.0, "learning_rate": 8.477966101694914e-07, "loss": 1.471, "step": 4990 }, { "epoch": 0.12, "grad_norm": 65.5, "learning_rate": 8.47457627118644e-07, "loss": 1.423, "step": 5000 }, { "epoch": 0.12, "eval_loss": 1.4716249704360962, "eval_runtime": 68.0492, "eval_samples_per_second": 14.695, "eval_steps_per_second": 14.695, "step": 5000 } ], "logging_steps": 10, "max_steps": 30000, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 5000, "total_flos": 8.06961020928e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }