xp163 / checkpoint-228 /trainer_state.json
ugaoo's picture
Upload folder using huggingface_hub
2453d7e verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 228,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.013157894736842105,
"grad_norm": 30.562854766845703,
"learning_rate": 5.0000000000000004e-08,
"loss": 2.2022,
"step": 1
},
{
"epoch": 0.02631578947368421,
"grad_norm": 31.231891632080078,
"learning_rate": 1.0000000000000001e-07,
"loss": 2.2332,
"step": 2
},
{
"epoch": 0.039473684210526314,
"grad_norm": 30.672441482543945,
"learning_rate": 1.5000000000000002e-07,
"loss": 2.1838,
"step": 3
},
{
"epoch": 0.05263157894736842,
"grad_norm": 30.322587966918945,
"learning_rate": 2.0000000000000002e-07,
"loss": 2.1722,
"step": 4
},
{
"epoch": 0.06578947368421052,
"grad_norm": 30.77847671508789,
"learning_rate": 2.5000000000000004e-07,
"loss": 2.1905,
"step": 5
},
{
"epoch": 0.07894736842105263,
"grad_norm": 30.271461486816406,
"learning_rate": 3.0000000000000004e-07,
"loss": 2.152,
"step": 6
},
{
"epoch": 0.09210526315789473,
"grad_norm": 30.211917877197266,
"learning_rate": 3.5000000000000004e-07,
"loss": 2.1535,
"step": 7
},
{
"epoch": 0.10526315789473684,
"grad_norm": 30.876808166503906,
"learning_rate": 4.0000000000000003e-07,
"loss": 2.1821,
"step": 8
},
{
"epoch": 0.11842105263157894,
"grad_norm": 30.311782836914062,
"learning_rate": 4.5000000000000003e-07,
"loss": 2.1493,
"step": 9
},
{
"epoch": 0.13157894736842105,
"grad_norm": 29.994876861572266,
"learning_rate": 5.000000000000001e-07,
"loss": 2.1006,
"step": 10
},
{
"epoch": 0.14473684210526316,
"grad_norm": 30.387903213500977,
"learning_rate": 5.5e-07,
"loss": 2.1116,
"step": 11
},
{
"epoch": 0.15789473684210525,
"grad_norm": 29.694482803344727,
"learning_rate": 6.000000000000001e-07,
"loss": 2.0657,
"step": 12
},
{
"epoch": 0.17105263157894737,
"grad_norm": 29.319564819335938,
"learning_rate": 6.5e-07,
"loss": 2.0295,
"step": 13
},
{
"epoch": 0.18421052631578946,
"grad_norm": 29.47940444946289,
"learning_rate": 7.000000000000001e-07,
"loss": 2.0205,
"step": 14
},
{
"epoch": 0.19736842105263158,
"grad_norm": 28.094648361206055,
"learning_rate": 7.5e-07,
"loss": 1.9182,
"step": 15
},
{
"epoch": 0.21052631578947367,
"grad_norm": 27.290010452270508,
"learning_rate": 8.000000000000001e-07,
"loss": 1.8242,
"step": 16
},
{
"epoch": 0.2236842105263158,
"grad_norm": 27.355669021606445,
"learning_rate": 8.500000000000001e-07,
"loss": 1.8095,
"step": 17
},
{
"epoch": 0.23684210526315788,
"grad_norm": 26.473133087158203,
"learning_rate": 9.000000000000001e-07,
"loss": 1.7021,
"step": 18
},
{
"epoch": 0.25,
"grad_norm": 25.996793746948242,
"learning_rate": 9.500000000000001e-07,
"loss": 1.6026,
"step": 19
},
{
"epoch": 0.2631578947368421,
"grad_norm": 25.409788131713867,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.4958,
"step": 20
},
{
"epoch": 0.27631578947368424,
"grad_norm": 25.045166015625,
"learning_rate": 1.0500000000000001e-06,
"loss": 1.3705,
"step": 21
},
{
"epoch": 0.2894736842105263,
"grad_norm": 24.878185272216797,
"learning_rate": 1.1e-06,
"loss": 1.2165,
"step": 22
},
{
"epoch": 0.3026315789473684,
"grad_norm": 24.428897857666016,
"learning_rate": 1.1500000000000002e-06,
"loss": 1.0541,
"step": 23
},
{
"epoch": 0.3157894736842105,
"grad_norm": 23.59629249572754,
"learning_rate": 1.2000000000000002e-06,
"loss": 0.8731,
"step": 24
},
{
"epoch": 0.32894736842105265,
"grad_norm": 22.640525817871094,
"learning_rate": 1.25e-06,
"loss": 0.6974,
"step": 25
},
{
"epoch": 0.34210526315789475,
"grad_norm": 20.182687759399414,
"learning_rate": 1.3e-06,
"loss": 0.5304,
"step": 26
},
{
"epoch": 0.35526315789473684,
"grad_norm": 16.674095153808594,
"learning_rate": 1.3500000000000002e-06,
"loss": 0.3994,
"step": 27
},
{
"epoch": 0.3684210526315789,
"grad_norm": 11.497395515441895,
"learning_rate": 1.4000000000000001e-06,
"loss": 0.2574,
"step": 28
},
{
"epoch": 0.3815789473684211,
"grad_norm": 7.353602886199951,
"learning_rate": 1.45e-06,
"loss": 0.192,
"step": 29
},
{
"epoch": 0.39473684210526316,
"grad_norm": 5.207138538360596,
"learning_rate": 1.5e-06,
"loss": 0.1373,
"step": 30
},
{
"epoch": 0.40789473684210525,
"grad_norm": 3.827702522277832,
"learning_rate": 1.5500000000000002e-06,
"loss": 0.1182,
"step": 31
},
{
"epoch": 0.42105263157894735,
"grad_norm": 2.3438303470611572,
"learning_rate": 1.6000000000000001e-06,
"loss": 0.0889,
"step": 32
},
{
"epoch": 0.4342105263157895,
"grad_norm": 1.3860067129135132,
"learning_rate": 1.6500000000000003e-06,
"loss": 0.079,
"step": 33
},
{
"epoch": 0.4473684210526316,
"grad_norm": 1.272938847541809,
"learning_rate": 1.7000000000000002e-06,
"loss": 0.0716,
"step": 34
},
{
"epoch": 0.4605263157894737,
"grad_norm": 1.0202291011810303,
"learning_rate": 1.75e-06,
"loss": 0.0669,
"step": 35
},
{
"epoch": 0.47368421052631576,
"grad_norm": 0.7427852153778076,
"learning_rate": 1.8000000000000001e-06,
"loss": 0.0553,
"step": 36
},
{
"epoch": 0.4868421052631579,
"grad_norm": 0.633512020111084,
"learning_rate": 1.85e-06,
"loss": 0.059,
"step": 37
},
{
"epoch": 0.5,
"grad_norm": 0.4689115285873413,
"learning_rate": 1.9000000000000002e-06,
"loss": 0.0513,
"step": 38
},
{
"epoch": 0.5131578947368421,
"grad_norm": 0.5156136751174927,
"learning_rate": 1.9500000000000004e-06,
"loss": 0.0447,
"step": 39
},
{
"epoch": 0.5263157894736842,
"grad_norm": 0.4687592387199402,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.0478,
"step": 40
},
{
"epoch": 0.5394736842105263,
"grad_norm": 0.6448376774787903,
"learning_rate": 2.05e-06,
"loss": 0.0453,
"step": 41
},
{
"epoch": 0.5526315789473685,
"grad_norm": 0.526674211025238,
"learning_rate": 2.1000000000000002e-06,
"loss": 0.0479,
"step": 42
},
{
"epoch": 0.5657894736842105,
"grad_norm": 0.5008970499038696,
"learning_rate": 2.15e-06,
"loss": 0.0413,
"step": 43
},
{
"epoch": 0.5789473684210527,
"grad_norm": 0.47381266951560974,
"learning_rate": 2.2e-06,
"loss": 0.0454,
"step": 44
},
{
"epoch": 0.5921052631578947,
"grad_norm": 0.5133708715438843,
"learning_rate": 2.25e-06,
"loss": 0.0405,
"step": 45
},
{
"epoch": 0.6052631578947368,
"grad_norm": 0.3338497579097748,
"learning_rate": 2.3000000000000004e-06,
"loss": 0.0399,
"step": 46
},
{
"epoch": 0.618421052631579,
"grad_norm": 0.36396729946136475,
"learning_rate": 2.35e-06,
"loss": 0.0376,
"step": 47
},
{
"epoch": 0.631578947368421,
"grad_norm": 0.24808718264102936,
"learning_rate": 2.4000000000000003e-06,
"loss": 0.0398,
"step": 48
},
{
"epoch": 0.6447368421052632,
"grad_norm": 0.4498325288295746,
"learning_rate": 2.4500000000000003e-06,
"loss": 0.0379,
"step": 49
},
{
"epoch": 0.6578947368421053,
"grad_norm": 0.3247833251953125,
"learning_rate": 2.5e-06,
"loss": 0.0347,
"step": 50
},
{
"epoch": 0.6710526315789473,
"grad_norm": 0.5700550675392151,
"learning_rate": 2.55e-06,
"loss": 0.0401,
"step": 51
},
{
"epoch": 0.6842105263157895,
"grad_norm": 0.40577009320259094,
"learning_rate": 2.6e-06,
"loss": 0.0445,
"step": 52
},
{
"epoch": 0.6973684210526315,
"grad_norm": 0.26929962635040283,
"learning_rate": 2.6500000000000005e-06,
"loss": 0.0374,
"step": 53
},
{
"epoch": 0.7105263157894737,
"grad_norm": 0.2586027979850769,
"learning_rate": 2.7000000000000004e-06,
"loss": 0.0367,
"step": 54
},
{
"epoch": 0.7236842105263158,
"grad_norm": 0.37353914976119995,
"learning_rate": 2.7500000000000004e-06,
"loss": 0.0374,
"step": 55
},
{
"epoch": 0.7368421052631579,
"grad_norm": 0.24289675056934357,
"learning_rate": 2.8000000000000003e-06,
"loss": 0.0367,
"step": 56
},
{
"epoch": 0.75,
"grad_norm": 0.3887583315372467,
"learning_rate": 2.85e-06,
"loss": 0.0341,
"step": 57
},
{
"epoch": 0.7631578947368421,
"grad_norm": 0.2641527056694031,
"learning_rate": 2.9e-06,
"loss": 0.0396,
"step": 58
},
{
"epoch": 0.7763157894736842,
"grad_norm": 0.3535292446613312,
"learning_rate": 2.95e-06,
"loss": 0.0353,
"step": 59
},
{
"epoch": 0.7894736842105263,
"grad_norm": 0.28277266025543213,
"learning_rate": 3e-06,
"loss": 0.0297,
"step": 60
},
{
"epoch": 0.8026315789473685,
"grad_norm": 0.3220183253288269,
"learning_rate": 3.05e-06,
"loss": 0.034,
"step": 61
},
{
"epoch": 0.8157894736842105,
"grad_norm": 0.35354799032211304,
"learning_rate": 3.1000000000000004e-06,
"loss": 0.0334,
"step": 62
},
{
"epoch": 0.8289473684210527,
"grad_norm": 0.290508896112442,
"learning_rate": 3.1500000000000003e-06,
"loss": 0.0326,
"step": 63
},
{
"epoch": 0.8421052631578947,
"grad_norm": 0.37485048174858093,
"learning_rate": 3.2000000000000003e-06,
"loss": 0.0341,
"step": 64
},
{
"epoch": 0.8552631578947368,
"grad_norm": 0.30379700660705566,
"learning_rate": 3.2500000000000002e-06,
"loss": 0.0312,
"step": 65
},
{
"epoch": 0.868421052631579,
"grad_norm": 0.4121778905391693,
"learning_rate": 3.3000000000000006e-06,
"loss": 0.0307,
"step": 66
},
{
"epoch": 0.881578947368421,
"grad_norm": 0.4124625325202942,
"learning_rate": 3.3500000000000005e-06,
"loss": 0.034,
"step": 67
},
{
"epoch": 0.8947368421052632,
"grad_norm": 0.47734567523002625,
"learning_rate": 3.4000000000000005e-06,
"loss": 0.0341,
"step": 68
},
{
"epoch": 0.9078947368421053,
"grad_norm": 0.24404998123645782,
"learning_rate": 3.45e-06,
"loss": 0.0304,
"step": 69
},
{
"epoch": 0.9210526315789473,
"grad_norm": 0.3431500196456909,
"learning_rate": 3.5e-06,
"loss": 0.0334,
"step": 70
},
{
"epoch": 0.9342105263157895,
"grad_norm": 0.19714811444282532,
"learning_rate": 3.5500000000000003e-06,
"loss": 0.0302,
"step": 71
},
{
"epoch": 0.9473684210526315,
"grad_norm": 0.3125874996185303,
"learning_rate": 3.6000000000000003e-06,
"loss": 0.0286,
"step": 72
},
{
"epoch": 0.9605263157894737,
"grad_norm": 0.2595495879650116,
"learning_rate": 3.65e-06,
"loss": 0.0316,
"step": 73
},
{
"epoch": 0.9736842105263158,
"grad_norm": 0.2165302336215973,
"learning_rate": 3.7e-06,
"loss": 0.0289,
"step": 74
},
{
"epoch": 0.9868421052631579,
"grad_norm": 0.268668532371521,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.0279,
"step": 75
},
{
"epoch": 1.0,
"grad_norm": 0.32586586475372314,
"learning_rate": 3.8000000000000005e-06,
"loss": 0.0304,
"step": 76
},
{
"epoch": 1.013157894736842,
"grad_norm": 0.2914262115955353,
"learning_rate": 3.85e-06,
"loss": 0.028,
"step": 77
},
{
"epoch": 1.0263157894736843,
"grad_norm": 0.22661137580871582,
"learning_rate": 3.900000000000001e-06,
"loss": 0.0298,
"step": 78
},
{
"epoch": 1.0394736842105263,
"grad_norm": 0.3464835286140442,
"learning_rate": 3.95e-06,
"loss": 0.0264,
"step": 79
},
{
"epoch": 1.0526315789473684,
"grad_norm": 0.3589572012424469,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0267,
"step": 80
},
{
"epoch": 1.0657894736842106,
"grad_norm": 0.404414564371109,
"learning_rate": 4.05e-06,
"loss": 0.0285,
"step": 81
},
{
"epoch": 1.0789473684210527,
"grad_norm": 0.3761513829231262,
"learning_rate": 4.1e-06,
"loss": 0.0282,
"step": 82
},
{
"epoch": 1.0921052631578947,
"grad_norm": 0.2694334089756012,
"learning_rate": 4.15e-06,
"loss": 0.0288,
"step": 83
},
{
"epoch": 1.1052631578947367,
"grad_norm": 0.2726658582687378,
"learning_rate": 4.2000000000000004e-06,
"loss": 0.0237,
"step": 84
},
{
"epoch": 1.118421052631579,
"grad_norm": 0.3058425188064575,
"learning_rate": 4.25e-06,
"loss": 0.0249,
"step": 85
},
{
"epoch": 1.131578947368421,
"grad_norm": 0.3472772240638733,
"learning_rate": 4.3e-06,
"loss": 0.0245,
"step": 86
},
{
"epoch": 1.1447368421052633,
"grad_norm": 0.2989756166934967,
"learning_rate": 4.350000000000001e-06,
"loss": 0.0241,
"step": 87
},
{
"epoch": 1.1578947368421053,
"grad_norm": 0.2575015425682068,
"learning_rate": 4.4e-06,
"loss": 0.0247,
"step": 88
},
{
"epoch": 1.1710526315789473,
"grad_norm": 0.41998928785324097,
"learning_rate": 4.450000000000001e-06,
"loss": 0.0251,
"step": 89
},
{
"epoch": 1.1842105263157894,
"grad_norm": 0.38380005955696106,
"learning_rate": 4.5e-06,
"loss": 0.0266,
"step": 90
},
{
"epoch": 1.1973684210526316,
"grad_norm": 0.4818059504032135,
"learning_rate": 4.5500000000000005e-06,
"loss": 0.0245,
"step": 91
},
{
"epoch": 1.2105263157894737,
"grad_norm": 0.2347942441701889,
"learning_rate": 4.600000000000001e-06,
"loss": 0.0206,
"step": 92
},
{
"epoch": 1.2236842105263157,
"grad_norm": 0.22905026376247406,
"learning_rate": 4.65e-06,
"loss": 0.0243,
"step": 93
},
{
"epoch": 1.236842105263158,
"grad_norm": 0.2179802507162094,
"learning_rate": 4.7e-06,
"loss": 0.02,
"step": 94
},
{
"epoch": 1.25,
"grad_norm": 0.44029659032821655,
"learning_rate": 4.75e-06,
"loss": 0.0226,
"step": 95
},
{
"epoch": 1.263157894736842,
"grad_norm": 0.23579446971416473,
"learning_rate": 4.800000000000001e-06,
"loss": 0.0222,
"step": 96
},
{
"epoch": 1.2763157894736843,
"grad_norm": 0.26277050375938416,
"learning_rate": 4.85e-06,
"loss": 0.0185,
"step": 97
},
{
"epoch": 1.2894736842105263,
"grad_norm": 0.2147447168827057,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.0214,
"step": 98
},
{
"epoch": 1.3026315789473684,
"grad_norm": 0.2472253143787384,
"learning_rate": 4.95e-06,
"loss": 0.0202,
"step": 99
},
{
"epoch": 1.3157894736842106,
"grad_norm": 0.3486703932285309,
"learning_rate": 5e-06,
"loss": 0.0258,
"step": 100
},
{
"epoch": 1.3289473684210527,
"grad_norm": 0.20332910120487213,
"learning_rate": 4.999902656502973e-06,
"loss": 0.0227,
"step": 101
},
{
"epoch": 1.3421052631578947,
"grad_norm": 0.2204633206129074,
"learning_rate": 4.9996106335924965e-06,
"loss": 0.023,
"step": 102
},
{
"epoch": 1.3552631578947367,
"grad_norm": 0.23998253047466278,
"learning_rate": 4.999123954009797e-06,
"loss": 0.0174,
"step": 103
},
{
"epoch": 1.368421052631579,
"grad_norm": 0.2601929008960724,
"learning_rate": 4.998442655654946e-06,
"loss": 0.02,
"step": 104
},
{
"epoch": 1.381578947368421,
"grad_norm": 0.2718435823917389,
"learning_rate": 4.997566791583916e-06,
"loss": 0.0166,
"step": 105
},
{
"epoch": 1.3947368421052633,
"grad_norm": 0.3064010441303253,
"learning_rate": 4.996496430004446e-06,
"loss": 0.0213,
"step": 106
},
{
"epoch": 1.4078947368421053,
"grad_norm": 0.2788292467594147,
"learning_rate": 4.995231654270726e-06,
"loss": 0.0181,
"step": 107
},
{
"epoch": 1.4210526315789473,
"grad_norm": 0.22800594568252563,
"learning_rate": 4.993772562876909e-06,
"loss": 0.0171,
"step": 108
},
{
"epoch": 1.4342105263157894,
"grad_norm": 0.23220059275627136,
"learning_rate": 4.992119269449445e-06,
"loss": 0.0156,
"step": 109
},
{
"epoch": 1.4473684210526316,
"grad_norm": 0.27420574426651,
"learning_rate": 4.990271902738223e-06,
"loss": 0.0206,
"step": 110
},
{
"epoch": 1.4605263157894737,
"grad_norm": 0.2498057335615158,
"learning_rate": 4.988230606606552e-06,
"loss": 0.0151,
"step": 111
},
{
"epoch": 1.4736842105263157,
"grad_norm": 0.25992438197135925,
"learning_rate": 4.985995540019956e-06,
"loss": 0.0196,
"step": 112
},
{
"epoch": 1.486842105263158,
"grad_norm": 0.2115156501531601,
"learning_rate": 4.983566877033791e-06,
"loss": 0.0163,
"step": 113
},
{
"epoch": 1.5,
"grad_norm": 0.2592470943927765,
"learning_rate": 4.980944806779698e-06,
"loss": 0.019,
"step": 114
},
{
"epoch": 1.513157894736842,
"grad_norm": 0.270512193441391,
"learning_rate": 4.9781295334508664e-06,
"loss": 0.0169,
"step": 115
},
{
"epoch": 1.526315789473684,
"grad_norm": 0.19861334562301636,
"learning_rate": 4.975121276286136e-06,
"loss": 0.0166,
"step": 116
},
{
"epoch": 1.5394736842105263,
"grad_norm": 0.2240753024816513,
"learning_rate": 4.9719202695529265e-06,
"loss": 0.0121,
"step": 117
},
{
"epoch": 1.5526315789473686,
"grad_norm": 0.22006243467330933,
"learning_rate": 4.968526762528988e-06,
"loss": 0.0128,
"step": 118
},
{
"epoch": 1.5657894736842106,
"grad_norm": 0.28461605310440063,
"learning_rate": 4.964941019482995e-06,
"loss": 0.0159,
"step": 119
},
{
"epoch": 1.5789473684210527,
"grad_norm": 0.25858908891677856,
"learning_rate": 4.961163319653959e-06,
"loss": 0.0152,
"step": 120
},
{
"epoch": 1.5921052631578947,
"grad_norm": 0.3055003881454468,
"learning_rate": 4.9571939572294914e-06,
"loss": 0.0146,
"step": 121
},
{
"epoch": 1.6052631578947367,
"grad_norm": 0.20667505264282227,
"learning_rate": 4.953033241322887e-06,
"loss": 0.0124,
"step": 122
},
{
"epoch": 1.618421052631579,
"grad_norm": 0.27322497963905334,
"learning_rate": 4.948681495949055e-06,
"loss": 0.011,
"step": 123
},
{
"epoch": 1.631578947368421,
"grad_norm": 0.1962827891111374,
"learning_rate": 4.944139059999286e-06,
"loss": 0.0109,
"step": 124
},
{
"epoch": 1.6447368421052633,
"grad_norm": 0.28328728675842285,
"learning_rate": 4.939406287214861e-06,
"loss": 0.0133,
"step": 125
},
{
"epoch": 1.6578947368421053,
"grad_norm": 0.28026294708251953,
"learning_rate": 4.9344835461595016e-06,
"loss": 0.0102,
"step": 126
},
{
"epoch": 1.6710526315789473,
"grad_norm": 0.3398573100566864,
"learning_rate": 4.929371220190671e-06,
"loss": 0.0119,
"step": 127
},
{
"epoch": 1.6842105263157894,
"grad_norm": 0.2361363172531128,
"learning_rate": 4.9240697074297205e-06,
"loss": 0.0129,
"step": 128
},
{
"epoch": 1.6973684210526314,
"grad_norm": 0.32814645767211914,
"learning_rate": 4.918579420730884e-06,
"loss": 0.0127,
"step": 129
},
{
"epoch": 1.7105263157894737,
"grad_norm": 0.22548508644104004,
"learning_rate": 4.912900787649124e-06,
"loss": 0.0124,
"step": 130
},
{
"epoch": 1.723684210526316,
"grad_norm": 0.2327754944562912,
"learning_rate": 4.907034250406846e-06,
"loss": 0.0101,
"step": 131
},
{
"epoch": 1.736842105263158,
"grad_norm": 0.27854445576667786,
"learning_rate": 4.900980265859449e-06,
"loss": 0.01,
"step": 132
},
{
"epoch": 1.75,
"grad_norm": 0.23271694779396057,
"learning_rate": 4.894739305459754e-06,
"loss": 0.0115,
"step": 133
},
{
"epoch": 1.763157894736842,
"grad_norm": 0.25155016779899597,
"learning_rate": 4.88831185522129e-06,
"loss": 0.0109,
"step": 134
},
{
"epoch": 1.776315789473684,
"grad_norm": 0.19088079035282135,
"learning_rate": 4.881698415680442e-06,
"loss": 0.0078,
"step": 135
},
{
"epoch": 1.7894736842105263,
"grad_norm": 0.23603218793869019,
"learning_rate": 4.874899501857477e-06,
"loss": 0.008,
"step": 136
},
{
"epoch": 1.8026315789473686,
"grad_norm": 0.18059666454792023,
"learning_rate": 4.867915643216434e-06,
"loss": 0.0089,
"step": 137
},
{
"epoch": 1.8157894736842106,
"grad_norm": 0.15945391356945038,
"learning_rate": 4.860747383623889e-06,
"loss": 0.0098,
"step": 138
},
{
"epoch": 1.8289473684210527,
"grad_norm": 0.18949876725673676,
"learning_rate": 4.85339528130661e-06,
"loss": 0.0086,
"step": 139
},
{
"epoch": 1.8421052631578947,
"grad_norm": 0.29193180799484253,
"learning_rate": 4.845859908808074e-06,
"loss": 0.01,
"step": 140
},
{
"epoch": 1.8552631578947367,
"grad_norm": 0.24959662556648254,
"learning_rate": 4.838141852943891e-06,
"loss": 0.0076,
"step": 141
},
{
"epoch": 1.868421052631579,
"grad_norm": 0.2785402834415436,
"learning_rate": 4.830241714756099e-06,
"loss": 0.0096,
"step": 142
},
{
"epoch": 1.881578947368421,
"grad_norm": 0.19859325885772705,
"learning_rate": 4.822160109466361e-06,
"loss": 0.0069,
"step": 143
},
{
"epoch": 1.8947368421052633,
"grad_norm": 0.19538483023643494,
"learning_rate": 4.813897666428054e-06,
"loss": 0.0084,
"step": 144
},
{
"epoch": 1.9078947368421053,
"grad_norm": 0.17871639132499695,
"learning_rate": 4.805455029077255e-06,
"loss": 0.0061,
"step": 145
},
{
"epoch": 1.9210526315789473,
"grad_norm": 0.1562146097421646,
"learning_rate": 4.79683285488264e-06,
"loss": 0.0039,
"step": 146
},
{
"epoch": 1.9342105263157894,
"grad_norm": 0.19822978973388672,
"learning_rate": 4.788031815294282e-06,
"loss": 0.0047,
"step": 147
},
{
"epoch": 1.9473684210526314,
"grad_norm": 0.20769113302230835,
"learning_rate": 4.779052595691355e-06,
"loss": 0.0081,
"step": 148
},
{
"epoch": 1.9605263157894737,
"grad_norm": 0.2603056728839874,
"learning_rate": 4.76989589532877e-06,
"loss": 0.0061,
"step": 149
},
{
"epoch": 1.973684210526316,
"grad_norm": 0.22610457241535187,
"learning_rate": 4.7605624272827125e-06,
"loss": 0.0062,
"step": 150
},
{
"epoch": 1.986842105263158,
"grad_norm": 0.29966941475868225,
"learning_rate": 4.75105291839512e-06,
"loss": 0.0066,
"step": 151
},
{
"epoch": 2.0,
"grad_norm": 0.20590010285377502,
"learning_rate": 4.741368109217072e-06,
"loss": 0.0054,
"step": 152
},
{
"epoch": 2.013157894736842,
"grad_norm": 0.12020114809274673,
"learning_rate": 4.7315087539511225e-06,
"loss": 0.0025,
"step": 153
},
{
"epoch": 2.026315789473684,
"grad_norm": 0.15393255650997162,
"learning_rate": 4.721475620392567e-06,
"loss": 0.0032,
"step": 154
},
{
"epoch": 2.039473684210526,
"grad_norm": 0.29606589674949646,
"learning_rate": 4.711269489869654e-06,
"loss": 0.0026,
"step": 155
},
{
"epoch": 2.0526315789473686,
"grad_norm": 0.19793158769607544,
"learning_rate": 4.700891157182729e-06,
"loss": 0.004,
"step": 156
},
{
"epoch": 2.0657894736842106,
"grad_norm": 0.1712222695350647,
"learning_rate": 4.690341430542351e-06,
"loss": 0.0032,
"step": 157
},
{
"epoch": 2.0789473684210527,
"grad_norm": 0.1618899554014206,
"learning_rate": 4.679621131506347e-06,
"loss": 0.0034,
"step": 158
},
{
"epoch": 2.0921052631578947,
"grad_norm": 0.28481054306030273,
"learning_rate": 4.668731094915835e-06,
"loss": 0.0021,
"step": 159
},
{
"epoch": 2.1052631578947367,
"grad_norm": 0.20630034804344177,
"learning_rate": 4.657672168830211e-06,
"loss": 0.0029,
"step": 160
},
{
"epoch": 2.1184210526315788,
"grad_norm": 0.15455815196037292,
"learning_rate": 4.646445214461105e-06,
"loss": 0.0035,
"step": 161
},
{
"epoch": 2.1315789473684212,
"grad_norm": 0.1995575726032257,
"learning_rate": 4.635051106105316e-06,
"loss": 0.0033,
"step": 162
},
{
"epoch": 2.1447368421052633,
"grad_norm": 0.1014007031917572,
"learning_rate": 4.623490731076728e-06,
"loss": 0.0018,
"step": 163
},
{
"epoch": 2.1578947368421053,
"grad_norm": 0.14722265303134918,
"learning_rate": 4.6117649896372055e-06,
"loss": 0.0049,
"step": 164
},
{
"epoch": 2.1710526315789473,
"grad_norm": 0.18898749351501465,
"learning_rate": 4.59987479492649e-06,
"loss": 0.0046,
"step": 165
},
{
"epoch": 2.1842105263157894,
"grad_norm": 0.13396897912025452,
"learning_rate": 4.587821072891089e-06,
"loss": 0.003,
"step": 166
},
{
"epoch": 2.1973684210526314,
"grad_norm": 0.07628808170557022,
"learning_rate": 4.5756047622121665e-06,
"loss": 0.002,
"step": 167
},
{
"epoch": 2.2105263157894735,
"grad_norm": 0.11752250790596008,
"learning_rate": 4.563226814232444e-06,
"loss": 0.0026,
"step": 168
},
{
"epoch": 2.223684210526316,
"grad_norm": 0.16660097241401672,
"learning_rate": 4.550688192882115e-06,
"loss": 0.0035,
"step": 169
},
{
"epoch": 2.236842105263158,
"grad_norm": 0.1427406370639801,
"learning_rate": 4.53798987460378e-06,
"loss": 0.0023,
"step": 170
},
{
"epoch": 2.25,
"grad_norm": 0.13983683288097382,
"learning_rate": 4.525132848276405e-06,
"loss": 0.0021,
"step": 171
},
{
"epoch": 2.263157894736842,
"grad_norm": 0.138810396194458,
"learning_rate": 4.512118115138315e-06,
"loss": 0.0026,
"step": 172
},
{
"epoch": 2.276315789473684,
"grad_norm": 0.09332790225744247,
"learning_rate": 4.498946688709216e-06,
"loss": 0.0016,
"step": 173
},
{
"epoch": 2.2894736842105265,
"grad_norm": 0.11120238155126572,
"learning_rate": 4.485619594711278e-06,
"loss": 0.0022,
"step": 174
},
{
"epoch": 2.3026315789473686,
"grad_norm": 0.23101334273815155,
"learning_rate": 4.4721378709892475e-06,
"loss": 0.0027,
"step": 175
},
{
"epoch": 2.3157894736842106,
"grad_norm": 0.17137247323989868,
"learning_rate": 4.4585025674296315e-06,
"loss": 0.0017,
"step": 176
},
{
"epoch": 2.3289473684210527,
"grad_norm": 0.19652289152145386,
"learning_rate": 4.444714745878936e-06,
"loss": 0.0023,
"step": 177
},
{
"epoch": 2.3421052631578947,
"grad_norm": 0.13559234142303467,
"learning_rate": 4.430775480060973e-06,
"loss": 0.0023,
"step": 178
},
{
"epoch": 2.3552631578947367,
"grad_norm": 0.15922801196575165,
"learning_rate": 4.416685855493246e-06,
"loss": 0.0021,
"step": 179
},
{
"epoch": 2.3684210526315788,
"grad_norm": 0.20893222093582153,
"learning_rate": 4.4024469694024194e-06,
"loss": 0.0031,
"step": 180
},
{
"epoch": 2.3815789473684212,
"grad_norm": 0.12193958461284637,
"learning_rate": 4.388059930638865e-06,
"loss": 0.0012,
"step": 181
},
{
"epoch": 2.3947368421052633,
"grad_norm": 0.2393576055765152,
"learning_rate": 4.373525859590313e-06,
"loss": 0.0016,
"step": 182
},
{
"epoch": 2.4078947368421053,
"grad_norm": 0.16970235109329224,
"learning_rate": 4.358845888094607e-06,
"loss": 0.0011,
"step": 183
},
{
"epoch": 2.4210526315789473,
"grad_norm": 0.2883284091949463,
"learning_rate": 4.3440211593515556e-06,
"loss": 0.0022,
"step": 184
},
{
"epoch": 2.4342105263157894,
"grad_norm": 0.18665015697479248,
"learning_rate": 4.32905282783391e-06,
"loss": 0.0026,
"step": 185
},
{
"epoch": 2.4473684210526314,
"grad_norm": 0.1786370724439621,
"learning_rate": 4.313942059197457e-06,
"loss": 0.0014,
"step": 186
},
{
"epoch": 2.4605263157894735,
"grad_norm": 0.11455212533473969,
"learning_rate": 4.298690030190247e-06,
"loss": 0.0009,
"step": 187
},
{
"epoch": 2.473684210526316,
"grad_norm": 0.10696641355752945,
"learning_rate": 4.283297928560951e-06,
"loss": 0.001,
"step": 188
},
{
"epoch": 2.486842105263158,
"grad_norm": 0.10494012385606766,
"learning_rate": 4.267766952966369e-06,
"loss": 0.0011,
"step": 189
},
{
"epoch": 2.5,
"grad_norm": 0.2017836719751358,
"learning_rate": 4.252098312878083e-06,
"loss": 0.0011,
"step": 190
},
{
"epoch": 2.513157894736842,
"grad_norm": 0.26616591215133667,
"learning_rate": 4.236293228488267e-06,
"loss": 0.0023,
"step": 191
},
{
"epoch": 2.526315789473684,
"grad_norm": 0.23929062485694885,
"learning_rate": 4.220352930614672e-06,
"loss": 0.0034,
"step": 192
},
{
"epoch": 2.5394736842105265,
"grad_norm": 0.5802208781242371,
"learning_rate": 4.204278660604767e-06,
"loss": 0.0014,
"step": 193
},
{
"epoch": 2.5526315789473686,
"grad_norm": 0.5981740355491638,
"learning_rate": 4.1880716702390764e-06,
"loss": 0.0011,
"step": 194
},
{
"epoch": 2.5657894736842106,
"grad_norm": 0.1276736855506897,
"learning_rate": 4.171733221633695e-06,
"loss": 0.0019,
"step": 195
},
{
"epoch": 2.5789473684210527,
"grad_norm": 0.13732750713825226,
"learning_rate": 4.155264587142002e-06,
"loss": 0.0014,
"step": 196
},
{
"epoch": 2.5921052631578947,
"grad_norm": 0.0735265240073204,
"learning_rate": 4.138667049255574e-06,
"loss": 0.001,
"step": 197
},
{
"epoch": 2.6052631578947367,
"grad_norm": 0.10450134426355362,
"learning_rate": 4.121941900504316e-06,
"loss": 0.0006,
"step": 198
},
{
"epoch": 2.6184210526315788,
"grad_norm": 0.08921566605567932,
"learning_rate": 4.105090443355801e-06,
"loss": 0.0013,
"step": 199
},
{
"epoch": 2.6315789473684212,
"grad_norm": 0.09669087827205658,
"learning_rate": 4.088113990113846e-06,
"loss": 0.0012,
"step": 200
},
{
"epoch": 2.6447368421052633,
"grad_norm": 0.14158889651298523,
"learning_rate": 4.071013862816311e-06,
"loss": 0.0021,
"step": 201
},
{
"epoch": 2.6578947368421053,
"grad_norm": 0.11639536172151566,
"learning_rate": 4.0537913931321495e-06,
"loss": 0.0015,
"step": 202
},
{
"epoch": 2.6710526315789473,
"grad_norm": 0.09123487025499344,
"learning_rate": 4.036447922257699e-06,
"loss": 0.002,
"step": 203
},
{
"epoch": 2.6842105263157894,
"grad_norm": 0.02566586434841156,
"learning_rate": 4.018984800812248e-06,
"loss": 0.0002,
"step": 204
},
{
"epoch": 2.6973684210526314,
"grad_norm": 0.1402742564678192,
"learning_rate": 4.001403388732842e-06,
"loss": 0.0011,
"step": 205
},
{
"epoch": 2.7105263157894735,
"grad_norm": 0.1250494420528412,
"learning_rate": 3.983705055168391e-06,
"loss": 0.0006,
"step": 206
},
{
"epoch": 2.723684210526316,
"grad_norm": 0.30169546604156494,
"learning_rate": 3.965891178373038e-06,
"loss": 0.0018,
"step": 207
},
{
"epoch": 2.736842105263158,
"grad_norm": 0.09584180265665054,
"learning_rate": 3.947963145598833e-06,
"loss": 0.0015,
"step": 208
},
{
"epoch": 2.75,
"grad_norm": 0.08999550342559814,
"learning_rate": 3.929922352987702e-06,
"loss": 0.0012,
"step": 209
},
{
"epoch": 2.763157894736842,
"grad_norm": 0.059366654604673386,
"learning_rate": 3.911770205462717e-06,
"loss": 0.0006,
"step": 210
},
{
"epoch": 2.776315789473684,
"grad_norm": 0.09513477981090546,
"learning_rate": 3.8935081166186935e-06,
"loss": 0.0014,
"step": 211
},
{
"epoch": 2.7894736842105265,
"grad_norm": 0.14668132364749908,
"learning_rate": 3.875137508612104e-06,
"loss": 0.0013,
"step": 212
},
{
"epoch": 2.8026315789473686,
"grad_norm": 0.12972496449947357,
"learning_rate": 3.856659812050328e-06,
"loss": 0.0007,
"step": 213
},
{
"epoch": 2.8157894736842106,
"grad_norm": 0.06435713171958923,
"learning_rate": 3.838076465880248e-06,
"loss": 0.0007,
"step": 214
},
{
"epoch": 2.8289473684210527,
"grad_norm": 0.07473474740982056,
"learning_rate": 3.819388917276186e-06,
"loss": 0.0008,
"step": 215
},
{
"epoch": 2.8421052631578947,
"grad_norm": 0.08037233352661133,
"learning_rate": 3.8005986215272056e-06,
"loss": 0.0007,
"step": 216
},
{
"epoch": 2.8552631578947367,
"grad_norm": 0.08691643178462982,
"learning_rate": 3.7817070419237866e-06,
"loss": 0.0006,
"step": 217
},
{
"epoch": 2.8684210526315788,
"grad_norm": 0.05137595161795616,
"learning_rate": 3.7627156496438686e-06,
"loss": 0.0004,
"step": 218
},
{
"epoch": 2.8815789473684212,
"grad_norm": 0.05121254175901413,
"learning_rate": 3.7436259236382797e-06,
"loss": 0.0003,
"step": 219
},
{
"epoch": 2.8947368421052633,
"grad_norm": 0.07157135009765625,
"learning_rate": 3.7244393505155713e-06,
"loss": 0.0006,
"step": 220
},
{
"epoch": 2.9078947368421053,
"grad_norm": 0.10179968178272247,
"learning_rate": 3.7051574244262412e-06,
"loss": 0.0002,
"step": 221
},
{
"epoch": 2.9210526315789473,
"grad_norm": 0.04186256229877472,
"learning_rate": 3.6857816469463806e-06,
"loss": 0.0003,
"step": 222
},
{
"epoch": 2.9342105263157894,
"grad_norm": 0.12561319768428802,
"learning_rate": 3.6663135269607413e-06,
"loss": 0.0004,
"step": 223
},
{
"epoch": 2.9473684210526314,
"grad_norm": 0.030656659975647926,
"learning_rate": 3.6467545805452266e-06,
"loss": 0.0001,
"step": 224
},
{
"epoch": 2.9605263157894735,
"grad_norm": 0.04994300380349159,
"learning_rate": 3.6271063308488298e-06,
"loss": 0.0002,
"step": 225
},
{
"epoch": 2.973684210526316,
"grad_norm": 0.035699985921382904,
"learning_rate": 3.6073703079750204e-06,
"loss": 0.0001,
"step": 226
},
{
"epoch": 2.986842105263158,
"grad_norm": 0.025821536779403687,
"learning_rate": 3.5875480488625847e-06,
"loss": 0.0002,
"step": 227
},
{
"epoch": 3.0,
"grad_norm": 0.0367676243185997,
"learning_rate": 3.5676410971659404e-06,
"loss": 0.0001,
"step": 228
}
],
"logging_steps": 1,
"max_steps": 456,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 76,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.4667657840936616e+19,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}