Menouar's picture
Upload folder using huggingface_hub
56cbd4e verified
raw
history blame contribute delete
No virus
48.9 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 3200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"grad_norm": 9.6875,
"learning_rate": 2.0833333333333333e-07,
"loss": 1.5494,
"step": 10
},
{
"epoch": 0.01,
"grad_norm": 2.375,
"learning_rate": 4.1666666666666667e-07,
"loss": 1.6442,
"step": 20
},
{
"epoch": 0.01,
"grad_norm": 1.78125,
"learning_rate": 6.25e-07,
"loss": 1.5817,
"step": 30
},
{
"epoch": 0.01,
"grad_norm": 1.2734375,
"learning_rate": 8.333333333333333e-07,
"loss": 1.6262,
"step": 40
},
{
"epoch": 0.02,
"grad_norm": 0.9921875,
"learning_rate": 1.0416666666666667e-06,
"loss": 1.6365,
"step": 50
},
{
"epoch": 0.02,
"grad_norm": 0.77734375,
"learning_rate": 1.25e-06,
"loss": 1.5901,
"step": 60
},
{
"epoch": 0.02,
"grad_norm": 0.62109375,
"learning_rate": 1.4583333333333335e-06,
"loss": 1.5757,
"step": 70
},
{
"epoch": 0.03,
"grad_norm": 0.5234375,
"learning_rate": 1.6666666666666667e-06,
"loss": 1.5956,
"step": 80
},
{
"epoch": 0.03,
"grad_norm": 6.75,
"learning_rate": 1.8750000000000003e-06,
"loss": 1.561,
"step": 90
},
{
"epoch": 0.03,
"grad_norm": 4.59375,
"learning_rate": 2.0833333333333334e-06,
"loss": 1.5564,
"step": 100
},
{
"epoch": 0.03,
"grad_norm": 0.546875,
"learning_rate": 2.2916666666666666e-06,
"loss": 1.6172,
"step": 110
},
{
"epoch": 0.04,
"grad_norm": 1.1640625,
"learning_rate": 2.5e-06,
"loss": 1.6872,
"step": 120
},
{
"epoch": 0.04,
"grad_norm": 1.4765625,
"learning_rate": 2.7083333333333334e-06,
"loss": 1.577,
"step": 130
},
{
"epoch": 0.04,
"grad_norm": 2.15625,
"learning_rate": 2.916666666666667e-06,
"loss": 1.56,
"step": 140
},
{
"epoch": 0.05,
"grad_norm": 0.462890625,
"learning_rate": 3.125e-06,
"loss": 1.552,
"step": 150
},
{
"epoch": 0.05,
"grad_norm": 0.416015625,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.5752,
"step": 160
},
{
"epoch": 0.05,
"grad_norm": 0.41796875,
"learning_rate": 3.5416666666666673e-06,
"loss": 1.6739,
"step": 170
},
{
"epoch": 0.06,
"grad_norm": 13.25,
"learning_rate": 3.7500000000000005e-06,
"loss": 1.5538,
"step": 180
},
{
"epoch": 0.06,
"grad_norm": 1.8984375,
"learning_rate": 3.958333333333333e-06,
"loss": 1.6864,
"step": 190
},
{
"epoch": 0.06,
"grad_norm": 11.1875,
"learning_rate": 4.166666666666667e-06,
"loss": 1.5576,
"step": 200
},
{
"epoch": 0.07,
"grad_norm": 1.546875,
"learning_rate": 4.3750000000000005e-06,
"loss": 1.5328,
"step": 210
},
{
"epoch": 0.07,
"grad_norm": 0.357421875,
"learning_rate": 4.583333333333333e-06,
"loss": 1.4953,
"step": 220
},
{
"epoch": 0.07,
"grad_norm": 2.578125,
"learning_rate": 4.791666666666668e-06,
"loss": 1.5663,
"step": 230
},
{
"epoch": 0.07,
"grad_norm": 1.2265625,
"learning_rate": 5e-06,
"loss": 1.5063,
"step": 240
},
{
"epoch": 0.08,
"grad_norm": 0.439453125,
"learning_rate": 5.208333333333334e-06,
"loss": 1.4404,
"step": 250
},
{
"epoch": 0.08,
"grad_norm": 0.443359375,
"learning_rate": 5.416666666666667e-06,
"loss": 1.5304,
"step": 260
},
{
"epoch": 0.08,
"grad_norm": 0.44921875,
"learning_rate": 5.625e-06,
"loss": 1.5536,
"step": 270
},
{
"epoch": 0.09,
"grad_norm": 1.4140625,
"learning_rate": 5.833333333333334e-06,
"loss": 1.5385,
"step": 280
},
{
"epoch": 0.09,
"grad_norm": 0.4609375,
"learning_rate": 6.041666666666667e-06,
"loss": 1.513,
"step": 290
},
{
"epoch": 0.09,
"grad_norm": 0.50390625,
"learning_rate": 6.25e-06,
"loss": 1.4549,
"step": 300
},
{
"epoch": 0.1,
"grad_norm": 0.6328125,
"learning_rate": 6.458333333333334e-06,
"loss": 1.4931,
"step": 310
},
{
"epoch": 0.1,
"grad_norm": 0.48046875,
"learning_rate": 6.666666666666667e-06,
"loss": 1.4201,
"step": 320
},
{
"epoch": 0.1,
"grad_norm": 0.392578125,
"learning_rate": 6.875e-06,
"loss": 1.5471,
"step": 330
},
{
"epoch": 0.11,
"grad_norm": 0.95703125,
"learning_rate": 7.083333333333335e-06,
"loss": 1.4287,
"step": 340
},
{
"epoch": 0.11,
"grad_norm": 0.388671875,
"learning_rate": 7.291666666666667e-06,
"loss": 1.4475,
"step": 350
},
{
"epoch": 0.11,
"grad_norm": 0.33984375,
"learning_rate": 7.500000000000001e-06,
"loss": 1.477,
"step": 360
},
{
"epoch": 0.12,
"grad_norm": 1.296875,
"learning_rate": 7.708333333333334e-06,
"loss": 1.4533,
"step": 370
},
{
"epoch": 0.12,
"grad_norm": 0.400390625,
"learning_rate": 7.916666666666667e-06,
"loss": 1.3663,
"step": 380
},
{
"epoch": 0.12,
"grad_norm": 0.375,
"learning_rate": 8.125000000000001e-06,
"loss": 1.3953,
"step": 390
},
{
"epoch": 0.12,
"grad_norm": 1.4921875,
"learning_rate": 8.333333333333334e-06,
"loss": 1.471,
"step": 400
},
{
"epoch": 0.13,
"grad_norm": 0.392578125,
"learning_rate": 8.541666666666666e-06,
"loss": 1.4374,
"step": 410
},
{
"epoch": 0.13,
"grad_norm": 2.046875,
"learning_rate": 8.750000000000001e-06,
"loss": 1.4224,
"step": 420
},
{
"epoch": 0.13,
"grad_norm": 0.5546875,
"learning_rate": 8.958333333333334e-06,
"loss": 1.3261,
"step": 430
},
{
"epoch": 0.14,
"grad_norm": 0.2578125,
"learning_rate": 9.166666666666666e-06,
"loss": 1.4033,
"step": 440
},
{
"epoch": 0.14,
"grad_norm": 1.546875,
"learning_rate": 9.375000000000001e-06,
"loss": 1.4237,
"step": 450
},
{
"epoch": 0.14,
"grad_norm": 0.435546875,
"learning_rate": 9.583333333333335e-06,
"loss": 1.4083,
"step": 460
},
{
"epoch": 0.15,
"grad_norm": 0.2255859375,
"learning_rate": 9.791666666666666e-06,
"loss": 1.3245,
"step": 470
},
{
"epoch": 0.15,
"grad_norm": 0.333984375,
"learning_rate": 1e-05,
"loss": 1.3771,
"step": 480
},
{
"epoch": 0.15,
"grad_norm": 0.5546875,
"learning_rate": 1.0208333333333334e-05,
"loss": 1.3789,
"step": 490
},
{
"epoch": 0.16,
"grad_norm": 0.7578125,
"learning_rate": 1.0416666666666668e-05,
"loss": 1.4275,
"step": 500
},
{
"epoch": 0.16,
"grad_norm": 0.3359375,
"learning_rate": 1.0625e-05,
"loss": 1.3739,
"step": 510
},
{
"epoch": 0.16,
"grad_norm": 1.0625,
"learning_rate": 1.0833333333333334e-05,
"loss": 1.3758,
"step": 520
},
{
"epoch": 0.17,
"grad_norm": 2.140625,
"learning_rate": 1.1041666666666668e-05,
"loss": 1.412,
"step": 530
},
{
"epoch": 0.17,
"grad_norm": 0.279296875,
"learning_rate": 1.125e-05,
"loss": 1.4025,
"step": 540
},
{
"epoch": 0.17,
"grad_norm": 2.3125,
"learning_rate": 1.1458333333333333e-05,
"loss": 1.4138,
"step": 550
},
{
"epoch": 0.17,
"grad_norm": 0.259765625,
"learning_rate": 1.1666666666666668e-05,
"loss": 1.2598,
"step": 560
},
{
"epoch": 0.18,
"grad_norm": 2.625,
"learning_rate": 1.1875e-05,
"loss": 1.3543,
"step": 570
},
{
"epoch": 0.18,
"grad_norm": 1.2734375,
"learning_rate": 1.2083333333333333e-05,
"loss": 1.273,
"step": 580
},
{
"epoch": 0.18,
"grad_norm": 2.328125,
"learning_rate": 1.2291666666666668e-05,
"loss": 1.2361,
"step": 590
},
{
"epoch": 0.19,
"grad_norm": 0.384765625,
"learning_rate": 1.25e-05,
"loss": 1.2996,
"step": 600
},
{
"epoch": 0.19,
"grad_norm": 1.2734375,
"learning_rate": 1.2708333333333333e-05,
"loss": 1.235,
"step": 610
},
{
"epoch": 0.19,
"grad_norm": 1.2109375,
"learning_rate": 1.2916666666666668e-05,
"loss": 1.3838,
"step": 620
},
{
"epoch": 0.2,
"grad_norm": 0.9765625,
"learning_rate": 1.3125e-05,
"loss": 1.2292,
"step": 630
},
{
"epoch": 0.2,
"grad_norm": 0.8125,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.2698,
"step": 640
},
{
"epoch": 0.2,
"grad_norm": 0.28515625,
"learning_rate": 1.3541666666666668e-05,
"loss": 1.3358,
"step": 650
},
{
"epoch": 0.21,
"grad_norm": 0.216796875,
"learning_rate": 1.375e-05,
"loss": 1.237,
"step": 660
},
{
"epoch": 0.21,
"grad_norm": 0.73046875,
"learning_rate": 1.3958333333333333e-05,
"loss": 1.2976,
"step": 670
},
{
"epoch": 0.21,
"grad_norm": 0.466796875,
"learning_rate": 1.416666666666667e-05,
"loss": 1.2324,
"step": 680
},
{
"epoch": 0.22,
"grad_norm": 0.302734375,
"learning_rate": 1.4375e-05,
"loss": 1.2436,
"step": 690
},
{
"epoch": 0.22,
"grad_norm": 1.125,
"learning_rate": 1.4583333333333333e-05,
"loss": 1.2607,
"step": 700
},
{
"epoch": 0.22,
"grad_norm": 0.25,
"learning_rate": 1.479166666666667e-05,
"loss": 1.2724,
"step": 710
},
{
"epoch": 0.23,
"grad_norm": 0.439453125,
"learning_rate": 1.5000000000000002e-05,
"loss": 1.2314,
"step": 720
},
{
"epoch": 0.23,
"grad_norm": 1.375,
"learning_rate": 1.5208333333333333e-05,
"loss": 1.2632,
"step": 730
},
{
"epoch": 0.23,
"grad_norm": 0.7890625,
"learning_rate": 1.5416666666666668e-05,
"loss": 1.3291,
"step": 740
},
{
"epoch": 0.23,
"grad_norm": 0.89453125,
"learning_rate": 1.5625e-05,
"loss": 1.2816,
"step": 750
},
{
"epoch": 0.24,
"grad_norm": 0.2197265625,
"learning_rate": 1.5833333333333333e-05,
"loss": 1.2163,
"step": 760
},
{
"epoch": 0.24,
"grad_norm": 0.216796875,
"learning_rate": 1.604166666666667e-05,
"loss": 1.2693,
"step": 770
},
{
"epoch": 0.24,
"grad_norm": 0.41015625,
"learning_rate": 1.6250000000000002e-05,
"loss": 1.2114,
"step": 780
},
{
"epoch": 0.25,
"grad_norm": 0.77734375,
"learning_rate": 1.6458333333333335e-05,
"loss": 1.1689,
"step": 790
},
{
"epoch": 0.25,
"grad_norm": 0.271484375,
"learning_rate": 1.6666666666666667e-05,
"loss": 1.2469,
"step": 800
},
{
"epoch": 0.25,
"grad_norm": 0.88671875,
"learning_rate": 1.6875e-05,
"loss": 1.2159,
"step": 810
},
{
"epoch": 0.26,
"grad_norm": 0.359375,
"learning_rate": 1.7083333333333333e-05,
"loss": 1.2198,
"step": 820
},
{
"epoch": 0.26,
"grad_norm": 0.2099609375,
"learning_rate": 1.729166666666667e-05,
"loss": 1.2687,
"step": 830
},
{
"epoch": 0.26,
"grad_norm": 1.109375,
"learning_rate": 1.7500000000000002e-05,
"loss": 1.2719,
"step": 840
},
{
"epoch": 0.27,
"grad_norm": 0.2216796875,
"learning_rate": 1.7708333333333335e-05,
"loss": 1.2074,
"step": 850
},
{
"epoch": 0.27,
"grad_norm": 0.2578125,
"learning_rate": 1.7916666666666667e-05,
"loss": 1.1637,
"step": 860
},
{
"epoch": 0.27,
"grad_norm": 0.3515625,
"learning_rate": 1.8125e-05,
"loss": 1.1775,
"step": 870
},
{
"epoch": 0.28,
"grad_norm": 6.09375,
"learning_rate": 1.8333333333333333e-05,
"loss": 1.1949,
"step": 880
},
{
"epoch": 0.28,
"grad_norm": 0.294921875,
"learning_rate": 1.854166666666667e-05,
"loss": 1.1488,
"step": 890
},
{
"epoch": 0.28,
"grad_norm": 0.328125,
"learning_rate": 1.8750000000000002e-05,
"loss": 1.2244,
"step": 900
},
{
"epoch": 0.28,
"grad_norm": 0.361328125,
"learning_rate": 1.8958333333333334e-05,
"loss": 1.1557,
"step": 910
},
{
"epoch": 0.29,
"grad_norm": 0.1943359375,
"learning_rate": 1.916666666666667e-05,
"loss": 1.1331,
"step": 920
},
{
"epoch": 0.29,
"grad_norm": 0.1630859375,
"learning_rate": 1.9375e-05,
"loss": 1.235,
"step": 930
},
{
"epoch": 0.29,
"grad_norm": 0.28515625,
"learning_rate": 1.9583333333333333e-05,
"loss": 1.1916,
"step": 940
},
{
"epoch": 0.3,
"grad_norm": 0.244140625,
"learning_rate": 1.979166666666667e-05,
"loss": 1.1931,
"step": 950
},
{
"epoch": 0.3,
"grad_norm": 0.455078125,
"learning_rate": 2e-05,
"loss": 1.1947,
"step": 960
},
{
"epoch": 0.3,
"grad_norm": 0.27734375,
"learning_rate": 1.9999933893861945e-05,
"loss": 1.123,
"step": 970
},
{
"epoch": 0.31,
"grad_norm": 0.609375,
"learning_rate": 1.9999735576321776e-05,
"loss": 1.2481,
"step": 980
},
{
"epoch": 0.31,
"grad_norm": 1.203125,
"learning_rate": 1.99994050500015e-05,
"loss": 1.2567,
"step": 990
},
{
"epoch": 0.31,
"grad_norm": 0.4453125,
"learning_rate": 1.9998942319271076e-05,
"loss": 1.1169,
"step": 1000
},
{
"epoch": 0.32,
"grad_norm": 0.1767578125,
"learning_rate": 1.9998347390248377e-05,
"loss": 1.1375,
"step": 1010
},
{
"epoch": 0.32,
"grad_norm": 0.357421875,
"learning_rate": 1.999762027079909e-05,
"loss": 1.2387,
"step": 1020
},
{
"epoch": 0.32,
"grad_norm": 0.2109375,
"learning_rate": 1.9996760970536635e-05,
"loss": 1.239,
"step": 1030
},
{
"epoch": 0.33,
"grad_norm": 0.193359375,
"learning_rate": 1.9995769500822007e-05,
"loss": 1.1548,
"step": 1040
},
{
"epoch": 0.33,
"grad_norm": 0.2060546875,
"learning_rate": 1.9994645874763657e-05,
"loss": 1.1675,
"step": 1050
},
{
"epoch": 0.33,
"grad_norm": 0.15234375,
"learning_rate": 1.9993390107217302e-05,
"loss": 1.1675,
"step": 1060
},
{
"epoch": 0.33,
"grad_norm": 0.71875,
"learning_rate": 1.999200221478573e-05,
"loss": 1.1909,
"step": 1070
},
{
"epoch": 0.34,
"grad_norm": 0.32421875,
"learning_rate": 1.999048221581858e-05,
"loss": 1.1468,
"step": 1080
},
{
"epoch": 0.34,
"grad_norm": 0.271484375,
"learning_rate": 1.9988830130412106e-05,
"loss": 1.2334,
"step": 1090
},
{
"epoch": 0.34,
"grad_norm": 0.62109375,
"learning_rate": 1.9987045980408907e-05,
"loss": 1.2107,
"step": 1100
},
{
"epoch": 0.35,
"grad_norm": 0.24609375,
"learning_rate": 1.9985129789397633e-05,
"loss": 1.1329,
"step": 1110
},
{
"epoch": 0.35,
"grad_norm": 1.3125,
"learning_rate": 1.9983081582712684e-05,
"loss": 1.2072,
"step": 1120
},
{
"epoch": 0.35,
"grad_norm": 0.25390625,
"learning_rate": 1.9980901387433866e-05,
"loss": 1.1971,
"step": 1130
},
{
"epoch": 0.36,
"grad_norm": 0.66796875,
"learning_rate": 1.9978589232386036e-05,
"loss": 1.2553,
"step": 1140
},
{
"epoch": 0.36,
"grad_norm": 0.423828125,
"learning_rate": 1.9976145148138727e-05,
"loss": 1.1773,
"step": 1150
},
{
"epoch": 0.36,
"grad_norm": 0.15234375,
"learning_rate": 1.9973569167005725e-05,
"loss": 1.2301,
"step": 1160
},
{
"epoch": 0.37,
"grad_norm": 0.271484375,
"learning_rate": 1.9970861323044667e-05,
"loss": 1.1788,
"step": 1170
},
{
"epoch": 0.37,
"grad_norm": 0.1875,
"learning_rate": 1.9968021652056578e-05,
"loss": 1.2372,
"step": 1180
},
{
"epoch": 0.37,
"grad_norm": 0.2275390625,
"learning_rate": 1.9965050191585388e-05,
"loss": 1.1555,
"step": 1190
},
{
"epoch": 0.38,
"grad_norm": 0.166015625,
"learning_rate": 1.9961946980917457e-05,
"loss": 1.1395,
"step": 1200
},
{
"epoch": 0.38,
"grad_norm": 0.28515625,
"learning_rate": 1.995871206108104e-05,
"loss": 1.2342,
"step": 1210
},
{
"epoch": 0.38,
"grad_norm": 0.31640625,
"learning_rate": 1.995534547484574e-05,
"loss": 1.1636,
"step": 1220
},
{
"epoch": 0.38,
"grad_norm": 0.26171875,
"learning_rate": 1.995184726672197e-05,
"loss": 1.0984,
"step": 1230
},
{
"epoch": 0.39,
"grad_norm": 0.65234375,
"learning_rate": 1.9948217482960334e-05,
"loss": 1.186,
"step": 1240
},
{
"epoch": 0.39,
"grad_norm": 0.6328125,
"learning_rate": 1.9944456171551024e-05,
"loss": 1.2151,
"step": 1250
},
{
"epoch": 0.39,
"grad_norm": 0.25390625,
"learning_rate": 1.9940563382223196e-05,
"loss": 1.1904,
"step": 1260
},
{
"epoch": 0.4,
"grad_norm": 0.462890625,
"learning_rate": 1.993653916644431e-05,
"loss": 1.1485,
"step": 1270
},
{
"epoch": 0.4,
"grad_norm": 0.173828125,
"learning_rate": 1.9932383577419432e-05,
"loss": 1.1406,
"step": 1280
},
{
"epoch": 0.4,
"grad_norm": 1.40625,
"learning_rate": 1.9928096670090552e-05,
"loss": 1.1583,
"step": 1290
},
{
"epoch": 0.41,
"grad_norm": 0.2255859375,
"learning_rate": 1.992367850113585e-05,
"loss": 1.1775,
"step": 1300
},
{
"epoch": 0.41,
"grad_norm": 0.203125,
"learning_rate": 1.9919129128968938e-05,
"loss": 1.173,
"step": 1310
},
{
"epoch": 0.41,
"grad_norm": 0.1845703125,
"learning_rate": 1.9914448613738107e-05,
"loss": 1.1648,
"step": 1320
},
{
"epoch": 0.42,
"grad_norm": 0.58203125,
"learning_rate": 1.9909637017325508e-05,
"loss": 1.0632,
"step": 1330
},
{
"epoch": 0.42,
"grad_norm": 0.2470703125,
"learning_rate": 1.9904694403346362e-05,
"loss": 1.1756,
"step": 1340
},
{
"epoch": 0.42,
"grad_norm": 0.16015625,
"learning_rate": 1.989962083714808e-05,
"loss": 1.154,
"step": 1350
},
{
"epoch": 0.42,
"grad_norm": 0.291015625,
"learning_rate": 1.9894416385809444e-05,
"loss": 1.1659,
"step": 1360
},
{
"epoch": 0.43,
"grad_norm": 0.1884765625,
"learning_rate": 1.9889081118139694e-05,
"loss": 1.1852,
"step": 1370
},
{
"epoch": 0.43,
"grad_norm": 0.2373046875,
"learning_rate": 1.988361510467761e-05,
"loss": 1.1686,
"step": 1380
},
{
"epoch": 0.43,
"grad_norm": 0.267578125,
"learning_rate": 1.9878018417690602e-05,
"loss": 1.2461,
"step": 1390
},
{
"epoch": 0.44,
"grad_norm": 3.09375,
"learning_rate": 1.9872291131173743e-05,
"loss": 1.1913,
"step": 1400
},
{
"epoch": 0.44,
"grad_norm": 0.271484375,
"learning_rate": 1.9866433320848793e-05,
"loss": 1.2264,
"step": 1410
},
{
"epoch": 0.44,
"grad_norm": 0.953125,
"learning_rate": 1.9860445064163193e-05,
"loss": 1.151,
"step": 1420
},
{
"epoch": 0.45,
"grad_norm": 0.1875,
"learning_rate": 1.985432644028905e-05,
"loss": 1.1306,
"step": 1430
},
{
"epoch": 0.45,
"grad_norm": 1.265625,
"learning_rate": 1.9848077530122083e-05,
"loss": 1.19,
"step": 1440
},
{
"epoch": 0.45,
"grad_norm": 0.255859375,
"learning_rate": 1.9841698416280554e-05,
"loss": 1.0554,
"step": 1450
},
{
"epoch": 0.46,
"grad_norm": 0.291015625,
"learning_rate": 1.983518918310418e-05,
"loss": 1.1399,
"step": 1460
},
{
"epoch": 0.46,
"grad_norm": 1.6015625,
"learning_rate": 1.9828549916653013e-05,
"loss": 1.1098,
"step": 1470
},
{
"epoch": 0.46,
"grad_norm": 0.193359375,
"learning_rate": 1.982178070470631e-05,
"loss": 1.1319,
"step": 1480
},
{
"epoch": 0.47,
"grad_norm": 0.52734375,
"learning_rate": 1.9814881636761355e-05,
"loss": 1.2344,
"step": 1490
},
{
"epoch": 0.47,
"grad_norm": 0.578125,
"learning_rate": 1.9807852804032306e-05,
"loss": 1.1336,
"step": 1500
},
{
"epoch": 0.47,
"grad_norm": 0.16796875,
"learning_rate": 1.980069429944895e-05,
"loss": 1.1052,
"step": 1510
},
{
"epoch": 0.47,
"grad_norm": 0.19921875,
"learning_rate": 1.9793406217655516e-05,
"loss": 1.1314,
"step": 1520
},
{
"epoch": 0.48,
"grad_norm": 0.169921875,
"learning_rate": 1.9785988655009386e-05,
"loss": 1.1783,
"step": 1530
},
{
"epoch": 0.48,
"grad_norm": 0.490234375,
"learning_rate": 1.977844170957984e-05,
"loss": 1.1526,
"step": 1540
},
{
"epoch": 0.48,
"grad_norm": 0.33984375,
"learning_rate": 1.977076548114677e-05,
"loss": 1.1069,
"step": 1550
},
{
"epoch": 0.49,
"grad_norm": 0.3828125,
"learning_rate": 1.9762960071199334e-05,
"loss": 1.2254,
"step": 1560
},
{
"epoch": 0.49,
"grad_norm": 0.640625,
"learning_rate": 1.975502558293464e-05,
"loss": 1.1648,
"step": 1570
},
{
"epoch": 0.49,
"grad_norm": 0.279296875,
"learning_rate": 1.974696212125635e-05,
"loss": 1.1854,
"step": 1580
},
{
"epoch": 0.5,
"grad_norm": 0.3046875,
"learning_rate": 1.9738769792773338e-05,
"loss": 1.2473,
"step": 1590
},
{
"epoch": 0.5,
"grad_norm": 0.326171875,
"learning_rate": 1.973044870579824e-05,
"loss": 1.1984,
"step": 1600
},
{
"epoch": 0.5,
"grad_norm": 0.224609375,
"learning_rate": 1.972199897034604e-05,
"loss": 1.1372,
"step": 1610
},
{
"epoch": 0.51,
"grad_norm": 0.5703125,
"learning_rate": 1.9713420698132614e-05,
"loss": 1.123,
"step": 1620
},
{
"epoch": 0.51,
"grad_norm": 0.427734375,
"learning_rate": 1.9704714002573255e-05,
"loss": 1.1167,
"step": 1630
},
{
"epoch": 0.51,
"grad_norm": 0.2177734375,
"learning_rate": 1.9695878998781162e-05,
"loss": 1.1196,
"step": 1640
},
{
"epoch": 0.52,
"grad_norm": 0.2451171875,
"learning_rate": 1.9686915803565934e-05,
"loss": 1.1106,
"step": 1650
},
{
"epoch": 0.52,
"grad_norm": 0.193359375,
"learning_rate": 1.9677824535432012e-05,
"loss": 1.1101,
"step": 1660
},
{
"epoch": 0.52,
"grad_norm": 0.1982421875,
"learning_rate": 1.9668605314577124e-05,
"loss": 1.1876,
"step": 1670
},
{
"epoch": 0.53,
"grad_norm": 0.2080078125,
"learning_rate": 1.9659258262890683e-05,
"loss": 1.1827,
"step": 1680
},
{
"epoch": 0.53,
"grad_norm": 0.291015625,
"learning_rate": 1.9649783503952196e-05,
"loss": 1.1399,
"step": 1690
},
{
"epoch": 0.53,
"grad_norm": 0.5546875,
"learning_rate": 1.9640181163029597e-05,
"loss": 1.13,
"step": 1700
},
{
"epoch": 0.53,
"grad_norm": 0.2294921875,
"learning_rate": 1.963045136707763e-05,
"loss": 1.1582,
"step": 1710
},
{
"epoch": 0.54,
"grad_norm": 0.2294921875,
"learning_rate": 1.9620594244736133e-05,
"loss": 1.2255,
"step": 1720
},
{
"epoch": 0.54,
"grad_norm": 2.8125,
"learning_rate": 1.9610609926328373e-05,
"loss": 1.1538,
"step": 1730
},
{
"epoch": 0.54,
"grad_norm": 0.2197265625,
"learning_rate": 1.960049854385929e-05,
"loss": 1.1813,
"step": 1740
},
{
"epoch": 0.55,
"grad_norm": 0.38671875,
"learning_rate": 1.9590260231013774e-05,
"loss": 1.202,
"step": 1750
},
{
"epoch": 0.55,
"grad_norm": 1.0625,
"learning_rate": 1.957989512315489e-05,
"loss": 1.1095,
"step": 1760
},
{
"epoch": 0.55,
"grad_norm": 0.318359375,
"learning_rate": 1.956940335732209e-05,
"loss": 1.1931,
"step": 1770
},
{
"epoch": 0.56,
"grad_norm": 0.287109375,
"learning_rate": 1.9558785072229395e-05,
"loss": 1.1645,
"step": 1780
},
{
"epoch": 0.56,
"grad_norm": 0.181640625,
"learning_rate": 1.9548040408263575e-05,
"loss": 1.1852,
"step": 1790
},
{
"epoch": 0.56,
"grad_norm": 0.369140625,
"learning_rate": 1.953716950748227e-05,
"loss": 1.0633,
"step": 1800
},
{
"epoch": 0.57,
"grad_norm": 0.2041015625,
"learning_rate": 1.952617251361214e-05,
"loss": 1.1748,
"step": 1810
},
{
"epoch": 0.57,
"grad_norm": 0.2158203125,
"learning_rate": 1.951504957204694e-05,
"loss": 1.075,
"step": 1820
},
{
"epoch": 0.57,
"grad_norm": 0.16796875,
"learning_rate": 1.9503800829845613e-05,
"loss": 1.1498,
"step": 1830
},
{
"epoch": 0.57,
"grad_norm": 0.68359375,
"learning_rate": 1.949242643573034e-05,
"loss": 1.1333,
"step": 1840
},
{
"epoch": 0.58,
"grad_norm": 0.55078125,
"learning_rate": 1.9480926540084578e-05,
"loss": 1.1932,
"step": 1850
},
{
"epoch": 0.58,
"grad_norm": 0.9453125,
"learning_rate": 1.946930129495106e-05,
"loss": 1.2105,
"step": 1860
},
{
"epoch": 0.58,
"grad_norm": 0.1669921875,
"learning_rate": 1.9457550854029797e-05,
"loss": 1.0915,
"step": 1870
},
{
"epoch": 0.59,
"grad_norm": 0.2041015625,
"learning_rate": 1.944567537267605e-05,
"loss": 1.105,
"step": 1880
},
{
"epoch": 0.59,
"grad_norm": 0.27734375,
"learning_rate": 1.9433675007898255e-05,
"loss": 1.1275,
"step": 1890
},
{
"epoch": 0.59,
"grad_norm": 0.1884765625,
"learning_rate": 1.9421549918355965e-05,
"loss": 1.1369,
"step": 1900
},
{
"epoch": 0.6,
"grad_norm": 0.3046875,
"learning_rate": 1.9409300264357757e-05,
"loss": 1.134,
"step": 1910
},
{
"epoch": 0.6,
"grad_norm": 0.2001953125,
"learning_rate": 1.9396926207859085e-05,
"loss": 1.0956,
"step": 1920
},
{
"epoch": 0.6,
"grad_norm": 0.2060546875,
"learning_rate": 1.9384427912460172e-05,
"loss": 1.1498,
"step": 1930
},
{
"epoch": 0.61,
"grad_norm": 0.2216796875,
"learning_rate": 1.9371805543403826e-05,
"loss": 1.1962,
"step": 1940
},
{
"epoch": 0.61,
"grad_norm": 0.29296875,
"learning_rate": 1.935905926757326e-05,
"loss": 1.1103,
"step": 1950
},
{
"epoch": 0.61,
"grad_norm": 0.1953125,
"learning_rate": 1.9346189253489888e-05,
"loss": 1.0858,
"step": 1960
},
{
"epoch": 0.62,
"grad_norm": 0.2734375,
"learning_rate": 1.9333195671311093e-05,
"loss": 1.1537,
"step": 1970
},
{
"epoch": 0.62,
"grad_norm": 0.2119140625,
"learning_rate": 1.932007869282799e-05,
"loss": 1.1339,
"step": 1980
},
{
"epoch": 0.62,
"grad_norm": 0.3046875,
"learning_rate": 1.9306838491463126e-05,
"loss": 1.0732,
"step": 1990
},
{
"epoch": 0.62,
"grad_norm": 0.203125,
"learning_rate": 1.9293475242268224e-05,
"loss": 1.1001,
"step": 2000
},
{
"epoch": 0.63,
"grad_norm": 0.193359375,
"learning_rate": 1.9279989121921846e-05,
"loss": 1.1295,
"step": 2010
},
{
"epoch": 0.63,
"grad_norm": 0.61328125,
"learning_rate": 1.9266380308727054e-05,
"loss": 1.1069,
"step": 2020
},
{
"epoch": 0.63,
"grad_norm": 0.34765625,
"learning_rate": 1.9252648982609065e-05,
"loss": 1.1003,
"step": 2030
},
{
"epoch": 0.64,
"grad_norm": 0.255859375,
"learning_rate": 1.9238795325112867e-05,
"loss": 1.098,
"step": 2040
},
{
"epoch": 0.64,
"grad_norm": 0.66796875,
"learning_rate": 1.9224819519400825e-05,
"loss": 1.1447,
"step": 2050
},
{
"epoch": 0.64,
"grad_norm": 0.91796875,
"learning_rate": 1.9210721750250237e-05,
"loss": 1.0511,
"step": 2060
},
{
"epoch": 0.65,
"grad_norm": 0.2119140625,
"learning_rate": 1.9196502204050925e-05,
"loss": 1.1048,
"step": 2070
},
{
"epoch": 0.65,
"grad_norm": 0.30859375,
"learning_rate": 1.9182161068802742e-05,
"loss": 1.2156,
"step": 2080
},
{
"epoch": 0.65,
"grad_norm": 0.16015625,
"learning_rate": 1.9167698534113105e-05,
"loss": 1.0455,
"step": 2090
},
{
"epoch": 0.66,
"grad_norm": 0.20703125,
"learning_rate": 1.9153114791194475e-05,
"loss": 1.2662,
"step": 2100
},
{
"epoch": 0.66,
"grad_norm": 0.212890625,
"learning_rate": 1.9138410032861833e-05,
"loss": 1.1073,
"step": 2110
},
{
"epoch": 0.66,
"grad_norm": 0.20703125,
"learning_rate": 1.9123584453530145e-05,
"loss": 1.1808,
"step": 2120
},
{
"epoch": 0.67,
"grad_norm": 0.2041015625,
"learning_rate": 1.910863824921176e-05,
"loss": 1.0918,
"step": 2130
},
{
"epoch": 0.67,
"grad_norm": 0.2158203125,
"learning_rate": 1.9093571617513853e-05,
"loss": 1.1115,
"step": 2140
},
{
"epoch": 0.67,
"grad_norm": 0.31640625,
"learning_rate": 1.907838475763579e-05,
"loss": 1.1847,
"step": 2150
},
{
"epoch": 0.68,
"grad_norm": 0.251953125,
"learning_rate": 1.9063077870366504e-05,
"loss": 1.1355,
"step": 2160
},
{
"epoch": 0.68,
"grad_norm": 0.18359375,
"learning_rate": 1.9047651158081827e-05,
"loss": 1.1227,
"step": 2170
},
{
"epoch": 0.68,
"grad_norm": 1.0625,
"learning_rate": 1.9032104824741843e-05,
"loss": 1.156,
"step": 2180
},
{
"epoch": 0.68,
"grad_norm": 0.205078125,
"learning_rate": 1.901643907588816e-05,
"loss": 1.1995,
"step": 2190
},
{
"epoch": 0.69,
"grad_norm": 0.2060546875,
"learning_rate": 1.900065411864121e-05,
"loss": 1.1294,
"step": 2200
},
{
"epoch": 0.69,
"grad_norm": 0.1591796875,
"learning_rate": 1.898475016169751e-05,
"loss": 1.1487,
"step": 2210
},
{
"epoch": 0.69,
"grad_norm": 0.248046875,
"learning_rate": 1.8968727415326885e-05,
"loss": 1.1438,
"step": 2220
},
{
"epoch": 0.7,
"grad_norm": 0.2294921875,
"learning_rate": 1.895258609136972e-05,
"loss": 1.1341,
"step": 2230
},
{
"epoch": 0.7,
"grad_norm": 0.9765625,
"learning_rate": 1.8936326403234125e-05,
"loss": 1.1479,
"step": 2240
},
{
"epoch": 0.7,
"grad_norm": 0.169921875,
"learning_rate": 1.8919948565893144e-05,
"loss": 1.2063,
"step": 2250
},
{
"epoch": 0.71,
"grad_norm": 0.1923828125,
"learning_rate": 1.8903452795881893e-05,
"loss": 1.1608,
"step": 2260
},
{
"epoch": 0.71,
"grad_norm": 0.2099609375,
"learning_rate": 1.8886839311294695e-05,
"loss": 1.1145,
"step": 2270
},
{
"epoch": 0.71,
"grad_norm": 0.201171875,
"learning_rate": 1.887010833178222e-05,
"loss": 1.0683,
"step": 2280
},
{
"epoch": 0.72,
"grad_norm": 0.19140625,
"learning_rate": 1.885326007854855e-05,
"loss": 1.1338,
"step": 2290
},
{
"epoch": 0.72,
"grad_norm": 0.19921875,
"learning_rate": 1.883629477434828e-05,
"loss": 1.1307,
"step": 2300
},
{
"epoch": 0.72,
"grad_norm": 0.173828125,
"learning_rate": 1.881921264348355e-05,
"loss": 1.1751,
"step": 2310
},
{
"epoch": 0.72,
"grad_norm": 0.1953125,
"learning_rate": 1.880201391180111e-05,
"loss": 1.1072,
"step": 2320
},
{
"epoch": 0.73,
"grad_norm": 0.201171875,
"learning_rate": 1.8784698806689308e-05,
"loss": 1.1771,
"step": 2330
},
{
"epoch": 0.73,
"grad_norm": 0.1552734375,
"learning_rate": 1.876726755707508e-05,
"loss": 1.1182,
"step": 2340
},
{
"epoch": 0.73,
"grad_norm": 0.38671875,
"learning_rate": 1.8749720393420948e-05,
"loss": 1.2228,
"step": 2350
},
{
"epoch": 0.74,
"grad_norm": 0.20703125,
"learning_rate": 1.8732057547721962e-05,
"loss": 1.1807,
"step": 2360
},
{
"epoch": 0.74,
"grad_norm": 0.205078125,
"learning_rate": 1.8714279253502616e-05,
"loss": 1.0115,
"step": 2370
},
{
"epoch": 0.74,
"grad_norm": 0.328125,
"learning_rate": 1.8696385745813793e-05,
"loss": 1.0663,
"step": 2380
},
{
"epoch": 0.75,
"grad_norm": 0.251953125,
"learning_rate": 1.8678377261229624e-05,
"loss": 1.1894,
"step": 2390
},
{
"epoch": 0.75,
"grad_norm": 0.26171875,
"learning_rate": 1.866025403784439e-05,
"loss": 1.2207,
"step": 2400
},
{
"epoch": 0.75,
"grad_norm": 0.287109375,
"learning_rate": 1.8642016315269345e-05,
"loss": 1.092,
"step": 2410
},
{
"epoch": 0.76,
"grad_norm": 0.1982421875,
"learning_rate": 1.8623664334629576e-05,
"loss": 1.1397,
"step": 2420
},
{
"epoch": 0.76,
"grad_norm": 0.291015625,
"learning_rate": 1.860519833856079e-05,
"loss": 1.1003,
"step": 2430
},
{
"epoch": 0.76,
"grad_norm": 0.267578125,
"learning_rate": 1.8586618571206133e-05,
"loss": 1.1145,
"step": 2440
},
{
"epoch": 0.77,
"grad_norm": 0.5703125,
"learning_rate": 1.856792527821293e-05,
"loss": 1.1072,
"step": 2450
},
{
"epoch": 0.77,
"grad_norm": 0.271484375,
"learning_rate": 1.854911870672947e-05,
"loss": 1.2103,
"step": 2460
},
{
"epoch": 0.77,
"grad_norm": 0.173828125,
"learning_rate": 1.8530199105401705e-05,
"loss": 1.2184,
"step": 2470
},
{
"epoch": 0.78,
"grad_norm": 0.1669921875,
"learning_rate": 1.8511166724369997e-05,
"loss": 1.1892,
"step": 2480
},
{
"epoch": 0.78,
"grad_norm": 0.28125,
"learning_rate": 1.849202181526579e-05,
"loss": 1.1147,
"step": 2490
},
{
"epoch": 0.78,
"grad_norm": 0.177734375,
"learning_rate": 1.847276463120828e-05,
"loss": 1.1493,
"step": 2500
},
{
"epoch": 0.78,
"grad_norm": 0.1630859375,
"learning_rate": 1.8453395426801083e-05,
"loss": 1.1848,
"step": 2510
},
{
"epoch": 0.79,
"grad_norm": 0.216796875,
"learning_rate": 1.843391445812886e-05,
"loss": 1.1074,
"step": 2520
},
{
"epoch": 0.79,
"grad_norm": 0.24609375,
"learning_rate": 1.841432198275393e-05,
"loss": 1.1532,
"step": 2530
},
{
"epoch": 0.79,
"grad_norm": 0.197265625,
"learning_rate": 1.8394618259712866e-05,
"loss": 1.1678,
"step": 2540
},
{
"epoch": 0.8,
"grad_norm": 0.2138671875,
"learning_rate": 1.837480354951308e-05,
"loss": 1.1779,
"step": 2550
},
{
"epoch": 0.8,
"grad_norm": 0.1943359375,
"learning_rate": 1.8354878114129368e-05,
"loss": 1.2235,
"step": 2560
},
{
"epoch": 0.8,
"grad_norm": 0.18359375,
"learning_rate": 1.833484221700044e-05,
"loss": 1.128,
"step": 2570
},
{
"epoch": 0.81,
"grad_norm": 0.216796875,
"learning_rate": 1.8314696123025456e-05,
"loss": 1.0884,
"step": 2580
},
{
"epoch": 0.81,
"grad_norm": 0.1728515625,
"learning_rate": 1.8294440098560508e-05,
"loss": 1.152,
"step": 2590
},
{
"epoch": 0.81,
"grad_norm": 0.1962890625,
"learning_rate": 1.8274074411415104e-05,
"loss": 1.1352,
"step": 2600
},
{
"epoch": 0.82,
"grad_norm": 0.419921875,
"learning_rate": 1.8253599330848638e-05,
"loss": 1.129,
"step": 2610
},
{
"epoch": 0.82,
"grad_norm": 0.271484375,
"learning_rate": 1.8233015127566805e-05,
"loss": 1.1701,
"step": 2620
},
{
"epoch": 0.82,
"grad_norm": 0.302734375,
"learning_rate": 1.8212322073718042e-05,
"loss": 1.1856,
"step": 2630
},
{
"epoch": 0.82,
"grad_norm": 0.255859375,
"learning_rate": 1.819152044288992e-05,
"loss": 1.1635,
"step": 2640
},
{
"epoch": 0.83,
"grad_norm": 1.0625,
"learning_rate": 1.817061051010554e-05,
"loss": 1.1203,
"step": 2650
},
{
"epoch": 0.83,
"grad_norm": 0.19140625,
"learning_rate": 1.8149592551819883e-05,
"loss": 1.1662,
"step": 2660
},
{
"epoch": 0.83,
"grad_norm": 0.2353515625,
"learning_rate": 1.8128466845916156e-05,
"loss": 1.1825,
"step": 2670
},
{
"epoch": 0.84,
"grad_norm": 0.201171875,
"learning_rate": 1.8107233671702123e-05,
"loss": 1.1868,
"step": 2680
},
{
"epoch": 0.84,
"grad_norm": 0.212890625,
"learning_rate": 1.808589330990642e-05,
"loss": 1.1071,
"step": 2690
},
{
"epoch": 0.84,
"grad_norm": 0.1943359375,
"learning_rate": 1.806444604267483e-05,
"loss": 1.1734,
"step": 2700
},
{
"epoch": 0.85,
"grad_norm": 0.193359375,
"learning_rate": 1.8042892153566543e-05,
"loss": 1.213,
"step": 2710
},
{
"epoch": 0.85,
"grad_norm": 0.61328125,
"learning_rate": 1.802123192755044e-05,
"loss": 1.1722,
"step": 2720
},
{
"epoch": 0.85,
"grad_norm": 0.220703125,
"learning_rate": 1.7999465651001297e-05,
"loss": 1.0755,
"step": 2730
},
{
"epoch": 0.86,
"grad_norm": 0.6875,
"learning_rate": 1.7977593611696017e-05,
"loss": 1.1852,
"step": 2740
},
{
"epoch": 0.86,
"grad_norm": 0.19921875,
"learning_rate": 1.79556160988098e-05,
"loss": 1.1037,
"step": 2750
},
{
"epoch": 0.86,
"grad_norm": 0.166015625,
"learning_rate": 1.7933533402912354e-05,
"loss": 1.2323,
"step": 2760
},
{
"epoch": 0.87,
"grad_norm": 0.2099609375,
"learning_rate": 1.791134581596402e-05,
"loss": 1.1885,
"step": 2770
},
{
"epoch": 0.87,
"grad_norm": 0.29296875,
"learning_rate": 1.7889053631311947e-05,
"loss": 1.1541,
"step": 2780
},
{
"epoch": 0.87,
"grad_norm": 0.2373046875,
"learning_rate": 1.786665714368617e-05,
"loss": 1.1488,
"step": 2790
},
{
"epoch": 0.88,
"grad_norm": 0.75,
"learning_rate": 1.784415664919576e-05,
"loss": 1.1424,
"step": 2800
},
{
"epoch": 0.88,
"grad_norm": 1.03125,
"learning_rate": 1.782155244532487e-05,
"loss": 1.1235,
"step": 2810
},
{
"epoch": 0.88,
"grad_norm": 0.388671875,
"learning_rate": 1.7798844830928818e-05,
"loss": 1.3127,
"step": 2820
},
{
"epoch": 0.88,
"grad_norm": 0.4609375,
"learning_rate": 1.7776034106230156e-05,
"loss": 1.1475,
"step": 2830
},
{
"epoch": 0.89,
"grad_norm": 0.1650390625,
"learning_rate": 1.775312057281466e-05,
"loss": 1.1558,
"step": 2840
},
{
"epoch": 0.89,
"grad_norm": 0.171875,
"learning_rate": 1.773010453362737e-05,
"loss": 1.0776,
"step": 2850
},
{
"epoch": 0.89,
"grad_norm": 0.236328125,
"learning_rate": 1.770698629296858e-05,
"loss": 1.1442,
"step": 2860
},
{
"epoch": 0.9,
"grad_norm": 0.498046875,
"learning_rate": 1.7683766156489817e-05,
"loss": 1.1917,
"step": 2870
},
{
"epoch": 0.9,
"grad_norm": 0.1826171875,
"learning_rate": 1.766044443118978e-05,
"loss": 1.2439,
"step": 2880
},
{
"epoch": 0.9,
"grad_norm": 0.2177734375,
"learning_rate": 1.763702142541032e-05,
"loss": 1.129,
"step": 2890
},
{
"epoch": 0.91,
"grad_norm": 0.2314453125,
"learning_rate": 1.761349744883231e-05,
"loss": 1.1861,
"step": 2900
},
{
"epoch": 0.91,
"grad_norm": 0.291015625,
"learning_rate": 1.758987281247162e-05,
"loss": 1.1001,
"step": 2910
},
{
"epoch": 0.91,
"grad_norm": 0.17578125,
"learning_rate": 1.756614782867493e-05,
"loss": 1.2019,
"step": 2920
},
{
"epoch": 0.92,
"grad_norm": 0.1552734375,
"learning_rate": 1.7542322811115657e-05,
"loss": 1.1267,
"step": 2930
},
{
"epoch": 0.92,
"grad_norm": 0.158203125,
"learning_rate": 1.7518398074789776e-05,
"loss": 1.1625,
"step": 2940
},
{
"epoch": 0.92,
"grad_norm": 0.1728515625,
"learning_rate": 1.7494373936011674e-05,
"loss": 1.1846,
"step": 2950
},
{
"epoch": 0.93,
"grad_norm": 0.26171875,
"learning_rate": 1.7470250712409963e-05,
"loss": 1.0803,
"step": 2960
},
{
"epoch": 0.93,
"grad_norm": 0.2021484375,
"learning_rate": 1.7446028722923266e-05,
"loss": 1.1674,
"step": 2970
},
{
"epoch": 0.93,
"grad_norm": 0.240234375,
"learning_rate": 1.7421708287796017e-05,
"loss": 1.1976,
"step": 2980
},
{
"epoch": 0.93,
"grad_norm": 0.23828125,
"learning_rate": 1.7397289728574234e-05,
"loss": 1.1307,
"step": 2990
},
{
"epoch": 0.94,
"grad_norm": 0.61328125,
"learning_rate": 1.737277336810124e-05,
"loss": 1.1122,
"step": 3000
},
{
"epoch": 0.94,
"grad_norm": 0.1845703125,
"learning_rate": 1.7348159530513424e-05,
"loss": 1.1558,
"step": 3010
},
{
"epoch": 0.94,
"grad_norm": 0.1826171875,
"learning_rate": 1.7323448541235922e-05,
"loss": 1.1335,
"step": 3020
},
{
"epoch": 0.95,
"grad_norm": 0.2109375,
"learning_rate": 1.7298640726978357e-05,
"loss": 1.1388,
"step": 3030
},
{
"epoch": 0.95,
"grad_norm": 0.2578125,
"learning_rate": 1.7273736415730488e-05,
"loss": 1.207,
"step": 3040
},
{
"epoch": 0.95,
"grad_norm": 0.25,
"learning_rate": 1.7248735936757882e-05,
"loss": 1.113,
"step": 3050
},
{
"epoch": 0.96,
"grad_norm": 0.201171875,
"learning_rate": 1.7223639620597556e-05,
"loss": 1.1843,
"step": 3060
},
{
"epoch": 0.96,
"grad_norm": 0.189453125,
"learning_rate": 1.719844779905363e-05,
"loss": 1.1279,
"step": 3070
},
{
"epoch": 0.96,
"grad_norm": 0.18359375,
"learning_rate": 1.7173160805192895e-05,
"loss": 1.1639,
"step": 3080
},
{
"epoch": 0.97,
"grad_norm": 0.2041015625,
"learning_rate": 1.7147778973340466e-05,
"loss": 1.1434,
"step": 3090
},
{
"epoch": 0.97,
"grad_norm": 0.2158203125,
"learning_rate": 1.7122302639075313e-05,
"loss": 1.1951,
"step": 3100
},
{
"epoch": 0.97,
"grad_norm": 2.046875,
"learning_rate": 1.7096732139225853e-05,
"loss": 1.1432,
"step": 3110
},
{
"epoch": 0.97,
"grad_norm": 0.2060546875,
"learning_rate": 1.7071067811865477e-05,
"loss": 1.1327,
"step": 3120
},
{
"epoch": 0.98,
"grad_norm": 0.314453125,
"learning_rate": 1.7045309996308107e-05,
"loss": 1.1622,
"step": 3130
},
{
"epoch": 0.98,
"grad_norm": 0.1904296875,
"learning_rate": 1.7019459033103684e-05,
"loss": 1.1804,
"step": 3140
},
{
"epoch": 0.98,
"grad_norm": 0.1708984375,
"learning_rate": 1.699351526403367e-05,
"loss": 1.0703,
"step": 3150
},
{
"epoch": 0.99,
"grad_norm": 0.30859375,
"learning_rate": 1.6967479032106552e-05,
"loss": 1.1724,
"step": 3160
},
{
"epoch": 0.99,
"grad_norm": 0.1953125,
"learning_rate": 1.694135068155327e-05,
"loss": 1.1547,
"step": 3170
},
{
"epoch": 0.99,
"grad_norm": 0.2314453125,
"learning_rate": 1.6915130557822698e-05,
"loss": 1.1062,
"step": 3180
},
{
"epoch": 1.0,
"grad_norm": 0.392578125,
"learning_rate": 1.6888819007577054e-05,
"loss": 1.1308,
"step": 3190
},
{
"epoch": 1.0,
"grad_norm": 0.546875,
"learning_rate": 1.686241637868734e-05,
"loss": 1.0832,
"step": 3200
}
],
"logging_steps": 10,
"max_steps": 9600,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 9.386039555779461e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}