arco-augment-3-test-2 / checkpoint-2250 /trainer_state.json
appvoid's picture
Upload folder using huggingface_hub
7cd1ae3 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 5000,
"global_step": 2250,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0044444444444444444,
"grad_norm": 9768.7255859375,
"learning_rate": 1.0000000000000001e-07,
"loss": 16.1729,
"step": 10
},
{
"epoch": 0.008888888888888889,
"grad_norm": 16245.8876953125,
"learning_rate": 1.1e-06,
"loss": 14.043,
"step": 20
},
{
"epoch": 0.013333333333333334,
"grad_norm": 9001.0771484375,
"learning_rate": 2.1000000000000002e-06,
"loss": 8.2782,
"step": 30
},
{
"epoch": 0.017777777777777778,
"grad_norm": 491.5092468261719,
"learning_rate": 3e-06,
"loss": 7.3674,
"step": 40
},
{
"epoch": 0.022222222222222223,
"grad_norm": 2662.317626953125,
"learning_rate": 4.000000000000001e-06,
"loss": 6.5525,
"step": 50
},
{
"epoch": 0.02666666666666667,
"grad_norm": 238.51461791992188,
"learning_rate": 5e-06,
"loss": 6.4309,
"step": 60
},
{
"epoch": 0.03111111111111111,
"grad_norm": 592.76953125,
"learning_rate": 6e-06,
"loss": 5.4059,
"step": 70
},
{
"epoch": 0.035555555555555556,
"grad_norm": 129.07666015625,
"learning_rate": 7.000000000000001e-06,
"loss": 5.1084,
"step": 80
},
{
"epoch": 0.04,
"grad_norm": 763.647216796875,
"learning_rate": 8.000000000000001e-06,
"loss": 4.6757,
"step": 90
},
{
"epoch": 0.044444444444444446,
"grad_norm": 269.35308837890625,
"learning_rate": 9e-06,
"loss": 4.2741,
"step": 100
},
{
"epoch": 0.04888888888888889,
"grad_norm": 121.892822265625,
"learning_rate": 1e-05,
"loss": 3.3332,
"step": 110
},
{
"epoch": 0.05333333333333334,
"grad_norm": 121.66092681884766,
"learning_rate": 1.1000000000000001e-05,
"loss": 3.0875,
"step": 120
},
{
"epoch": 0.057777777777777775,
"grad_norm": 88.0842514038086,
"learning_rate": 1.2e-05,
"loss": 1.9639,
"step": 130
},
{
"epoch": 0.06222222222222222,
"grad_norm": 77.41666412353516,
"learning_rate": 1.3000000000000001e-05,
"loss": 1.645,
"step": 140
},
{
"epoch": 0.06666666666666667,
"grad_norm": 27.421039581298828,
"learning_rate": 1.4000000000000001e-05,
"loss": 1.1254,
"step": 150
},
{
"epoch": 0.07111111111111111,
"grad_norm": 146.31039428710938,
"learning_rate": 1.5e-05,
"loss": 1.1082,
"step": 160
},
{
"epoch": 0.07555555555555556,
"grad_norm": 1123.4139404296875,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.9222,
"step": 170
},
{
"epoch": 0.08,
"grad_norm": 535.9423828125,
"learning_rate": 1.7000000000000003e-05,
"loss": 1.0467,
"step": 180
},
{
"epoch": 0.08444444444444445,
"grad_norm": 36.32695007324219,
"learning_rate": 1.8e-05,
"loss": 0.7194,
"step": 190
},
{
"epoch": 0.08888888888888889,
"grad_norm": 35.27937698364258,
"learning_rate": 1.9e-05,
"loss": 1.1295,
"step": 200
},
{
"epoch": 0.09333333333333334,
"grad_norm": 186.22567749023438,
"learning_rate": 2e-05,
"loss": 0.941,
"step": 210
},
{
"epoch": 0.09777777777777778,
"grad_norm": 11.655800819396973,
"learning_rate": 2.1e-05,
"loss": 1.0712,
"step": 220
},
{
"epoch": 0.10222222222222223,
"grad_norm": 6.5133256912231445,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.799,
"step": 230
},
{
"epoch": 0.10666666666666667,
"grad_norm": 1871.7095947265625,
"learning_rate": 2.3000000000000003e-05,
"loss": 1.4545,
"step": 240
},
{
"epoch": 0.1111111111111111,
"grad_norm": 12.251700401306152,
"learning_rate": 2.4e-05,
"loss": 0.9906,
"step": 250
},
{
"epoch": 0.11555555555555555,
"grad_norm": 76.3839111328125,
"learning_rate": 2.5e-05,
"loss": 1.2341,
"step": 260
},
{
"epoch": 0.12,
"grad_norm": 19.359607696533203,
"learning_rate": 2.6000000000000002e-05,
"loss": 2.9686,
"step": 270
},
{
"epoch": 0.12444444444444444,
"grad_norm": 34.06645584106445,
"learning_rate": 2.7000000000000002e-05,
"loss": 1.0668,
"step": 280
},
{
"epoch": 0.1288888888888889,
"grad_norm": 7.353147983551025,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.9959,
"step": 290
},
{
"epoch": 0.13333333333333333,
"grad_norm": 27.748685836791992,
"learning_rate": 2.9e-05,
"loss": 0.7448,
"step": 300
},
{
"epoch": 0.13777777777777778,
"grad_norm": 2796.3427734375,
"learning_rate": 3e-05,
"loss": 1.4512,
"step": 310
},
{
"epoch": 0.14222222222222222,
"grad_norm": 80.05686950683594,
"learning_rate": 3.1e-05,
"loss": 0.8864,
"step": 320
},
{
"epoch": 0.14666666666666667,
"grad_norm": 27.44098472595215,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.144,
"step": 330
},
{
"epoch": 0.1511111111111111,
"grad_norm": 21.465320587158203,
"learning_rate": 3.3e-05,
"loss": 0.8698,
"step": 340
},
{
"epoch": 0.15555555555555556,
"grad_norm": 10.413846015930176,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.9131,
"step": 350
},
{
"epoch": 0.16,
"grad_norm": 13.890963554382324,
"learning_rate": 3.5e-05,
"loss": 1.1077,
"step": 360
},
{
"epoch": 0.16444444444444445,
"grad_norm": 6.141105651855469,
"learning_rate": 3.6e-05,
"loss": 1.0575,
"step": 370
},
{
"epoch": 0.1688888888888889,
"grad_norm": 2.727337121963501,
"learning_rate": 3.7e-05,
"loss": 0.9563,
"step": 380
},
{
"epoch": 0.17333333333333334,
"grad_norm": 1.5828684568405151,
"learning_rate": 3.8e-05,
"loss": 0.781,
"step": 390
},
{
"epoch": 0.17777777777777778,
"grad_norm": 3.337902545928955,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.8312,
"step": 400
},
{
"epoch": 0.18222222222222223,
"grad_norm": 1.760097622871399,
"learning_rate": 4e-05,
"loss": 0.9048,
"step": 410
},
{
"epoch": 0.18666666666666668,
"grad_norm": 0.9947965741157532,
"learning_rate": 4.1e-05,
"loss": 0.8803,
"step": 420
},
{
"epoch": 0.19111111111111112,
"grad_norm": 18.71548843383789,
"learning_rate": 4.2e-05,
"loss": 1.143,
"step": 430
},
{
"epoch": 0.19555555555555557,
"grad_norm": 12.882355690002441,
"learning_rate": 4.3e-05,
"loss": 0.9267,
"step": 440
},
{
"epoch": 0.2,
"grad_norm": 2.379068613052368,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.7401,
"step": 450
},
{
"epoch": 0.20444444444444446,
"grad_norm": 6.240898609161377,
"learning_rate": 4.5e-05,
"loss": 1.0539,
"step": 460
},
{
"epoch": 0.2088888888888889,
"grad_norm": 14.994612693786621,
"learning_rate": 4.600000000000001e-05,
"loss": 1.119,
"step": 470
},
{
"epoch": 0.21333333333333335,
"grad_norm": 39.39948654174805,
"learning_rate": 4.7e-05,
"loss": 1.027,
"step": 480
},
{
"epoch": 0.21777777777777776,
"grad_norm": 2.395543098449707,
"learning_rate": 4.8e-05,
"loss": 1.0852,
"step": 490
},
{
"epoch": 0.2222222222222222,
"grad_norm": 1.2860183715820312,
"learning_rate": 4.9e-05,
"loss": 0.7519,
"step": 500
},
{
"epoch": 0.22666666666666666,
"grad_norm": 10.799077033996582,
"learning_rate": 5e-05,
"loss": 0.8347,
"step": 510
},
{
"epoch": 0.2311111111111111,
"grad_norm": 1.4125126600265503,
"learning_rate": 4.971428571428572e-05,
"loss": 1.0284,
"step": 520
},
{
"epoch": 0.23555555555555555,
"grad_norm": 3.897629737854004,
"learning_rate": 4.942857142857143e-05,
"loss": 0.8591,
"step": 530
},
{
"epoch": 0.24,
"grad_norm": 3.8170456886291504,
"learning_rate": 4.9142857142857144e-05,
"loss": 0.8344,
"step": 540
},
{
"epoch": 0.24444444444444444,
"grad_norm": 0.6229439377784729,
"learning_rate": 4.885714285714286e-05,
"loss": 0.9252,
"step": 550
},
{
"epoch": 0.24888888888888888,
"grad_norm": 3.2861270904541016,
"learning_rate": 4.8571428571428576e-05,
"loss": 0.9951,
"step": 560
},
{
"epoch": 0.25333333333333335,
"grad_norm": 1.9368836879730225,
"learning_rate": 4.828571428571429e-05,
"loss": 0.9994,
"step": 570
},
{
"epoch": 0.2577777777777778,
"grad_norm": 1.2594083547592163,
"learning_rate": 4.8e-05,
"loss": 0.8287,
"step": 580
},
{
"epoch": 0.26222222222222225,
"grad_norm": 0.7579429149627686,
"learning_rate": 4.771428571428572e-05,
"loss": 1.2831,
"step": 590
},
{
"epoch": 0.26666666666666666,
"grad_norm": 1.412414789199829,
"learning_rate": 4.742857142857143e-05,
"loss": 0.7316,
"step": 600
},
{
"epoch": 0.27111111111111114,
"grad_norm": 1.765723466873169,
"learning_rate": 4.714285714285714e-05,
"loss": 0.6747,
"step": 610
},
{
"epoch": 0.27555555555555555,
"grad_norm": 0.9297116994857788,
"learning_rate": 4.685714285714286e-05,
"loss": 0.7766,
"step": 620
},
{
"epoch": 0.28,
"grad_norm": 0.9512072205543518,
"learning_rate": 4.6571428571428575e-05,
"loss": 0.5614,
"step": 630
},
{
"epoch": 0.28444444444444444,
"grad_norm": 2.3289010524749756,
"learning_rate": 4.628571428571429e-05,
"loss": 1.3121,
"step": 640
},
{
"epoch": 0.28888888888888886,
"grad_norm": 1.013492465019226,
"learning_rate": 4.600000000000001e-05,
"loss": 1.0048,
"step": 650
},
{
"epoch": 0.29333333333333333,
"grad_norm": 0.9352627992630005,
"learning_rate": 4.5714285714285716e-05,
"loss": 0.6874,
"step": 660
},
{
"epoch": 0.29777777777777775,
"grad_norm": 88.00923156738281,
"learning_rate": 4.542857142857143e-05,
"loss": 1.1643,
"step": 670
},
{
"epoch": 0.3022222222222222,
"grad_norm": 0.7422826290130615,
"learning_rate": 4.514285714285714e-05,
"loss": 0.7003,
"step": 680
},
{
"epoch": 0.30666666666666664,
"grad_norm": 1.197748064994812,
"learning_rate": 4.485714285714286e-05,
"loss": 1.2505,
"step": 690
},
{
"epoch": 0.3111111111111111,
"grad_norm": 2.1018965244293213,
"learning_rate": 4.4571428571428574e-05,
"loss": 0.7924,
"step": 700
},
{
"epoch": 0.31555555555555553,
"grad_norm": 1.9967838525772095,
"learning_rate": 4.428571428571428e-05,
"loss": 1.0143,
"step": 710
},
{
"epoch": 0.32,
"grad_norm": 4.196930885314941,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.8882,
"step": 720
},
{
"epoch": 0.3244444444444444,
"grad_norm": 1.986365795135498,
"learning_rate": 4.371428571428572e-05,
"loss": 0.8591,
"step": 730
},
{
"epoch": 0.3288888888888889,
"grad_norm": 3.0498948097229004,
"learning_rate": 4.342857142857143e-05,
"loss": 0.8434,
"step": 740
},
{
"epoch": 0.3333333333333333,
"grad_norm": 0.7130551338195801,
"learning_rate": 4.314285714285715e-05,
"loss": 0.8395,
"step": 750
},
{
"epoch": 0.3377777777777778,
"grad_norm": 0.6148263216018677,
"learning_rate": 4.2857142857142856e-05,
"loss": 0.9217,
"step": 760
},
{
"epoch": 0.3422222222222222,
"grad_norm": 4.150040149688721,
"learning_rate": 4.257142857142857e-05,
"loss": 0.9144,
"step": 770
},
{
"epoch": 0.3466666666666667,
"grad_norm": 1.1592193841934204,
"learning_rate": 4.228571428571429e-05,
"loss": 0.9254,
"step": 780
},
{
"epoch": 0.3511111111111111,
"grad_norm": 1.1033934354782104,
"learning_rate": 4.2e-05,
"loss": 0.7114,
"step": 790
},
{
"epoch": 0.35555555555555557,
"grad_norm": 1.2952511310577393,
"learning_rate": 4.1714285714285714e-05,
"loss": 0.8385,
"step": 800
},
{
"epoch": 0.36,
"grad_norm": 1.5696533918380737,
"learning_rate": 4.1428571428571437e-05,
"loss": 0.6439,
"step": 810
},
{
"epoch": 0.36444444444444446,
"grad_norm": 0.9464730024337769,
"learning_rate": 4.1142857142857146e-05,
"loss": 0.5408,
"step": 820
},
{
"epoch": 0.3688888888888889,
"grad_norm": 2.5423879623413086,
"learning_rate": 4.085714285714286e-05,
"loss": 0.8305,
"step": 830
},
{
"epoch": 0.37333333333333335,
"grad_norm": 1.3495992422103882,
"learning_rate": 4.057142857142857e-05,
"loss": 0.7594,
"step": 840
},
{
"epoch": 0.37777777777777777,
"grad_norm": 1.4968547821044922,
"learning_rate": 4.028571428571429e-05,
"loss": 0.7879,
"step": 850
},
{
"epoch": 0.38222222222222224,
"grad_norm": 23.5468692779541,
"learning_rate": 4e-05,
"loss": 1.0052,
"step": 860
},
{
"epoch": 0.38666666666666666,
"grad_norm": 1.6756787300109863,
"learning_rate": 3.971428571428571e-05,
"loss": 0.7402,
"step": 870
},
{
"epoch": 0.39111111111111113,
"grad_norm": 2.612205743789673,
"learning_rate": 3.942857142857143e-05,
"loss": 0.8477,
"step": 880
},
{
"epoch": 0.39555555555555555,
"grad_norm": 5.494552135467529,
"learning_rate": 3.9142857142857145e-05,
"loss": 1.0808,
"step": 890
},
{
"epoch": 0.4,
"grad_norm": 1.5293407440185547,
"learning_rate": 3.885714285714286e-05,
"loss": 0.8273,
"step": 900
},
{
"epoch": 0.40444444444444444,
"grad_norm": 1.242197871208191,
"learning_rate": 3.857142857142858e-05,
"loss": 0.6873,
"step": 910
},
{
"epoch": 0.4088888888888889,
"grad_norm": 2.009373903274536,
"learning_rate": 3.8285714285714286e-05,
"loss": 0.8726,
"step": 920
},
{
"epoch": 0.41333333333333333,
"grad_norm": 1.1505591869354248,
"learning_rate": 3.8e-05,
"loss": 0.6348,
"step": 930
},
{
"epoch": 0.4177777777777778,
"grad_norm": 0.9240453243255615,
"learning_rate": 3.771428571428572e-05,
"loss": 0.7547,
"step": 940
},
{
"epoch": 0.4222222222222222,
"grad_norm": 4.990575313568115,
"learning_rate": 3.742857142857143e-05,
"loss": 0.8018,
"step": 950
},
{
"epoch": 0.4266666666666667,
"grad_norm": 1.9885175228118896,
"learning_rate": 3.7142857142857143e-05,
"loss": 0.8499,
"step": 960
},
{
"epoch": 0.4311111111111111,
"grad_norm": 1.303685188293457,
"learning_rate": 3.685714285714286e-05,
"loss": 0.9209,
"step": 970
},
{
"epoch": 0.43555555555555553,
"grad_norm": 1.4578043222427368,
"learning_rate": 3.6571428571428576e-05,
"loss": 0.9527,
"step": 980
},
{
"epoch": 0.44,
"grad_norm": 2.819185972213745,
"learning_rate": 3.628571428571429e-05,
"loss": 0.8843,
"step": 990
},
{
"epoch": 0.4444444444444444,
"grad_norm": 0.9243647456169128,
"learning_rate": 3.6e-05,
"loss": 0.496,
"step": 1000
},
{
"epoch": 0.4488888888888889,
"grad_norm": 1.31293785572052,
"learning_rate": 3.571428571428572e-05,
"loss": 0.6839,
"step": 1010
},
{
"epoch": 0.4533333333333333,
"grad_norm": 1.1468777656555176,
"learning_rate": 3.5428571428571426e-05,
"loss": 1.1296,
"step": 1020
},
{
"epoch": 0.4577777777777778,
"grad_norm": 1.786746621131897,
"learning_rate": 3.514285714285714e-05,
"loss": 0.9237,
"step": 1030
},
{
"epoch": 0.4622222222222222,
"grad_norm": 2.120232343673706,
"learning_rate": 3.485714285714286e-05,
"loss": 0.8313,
"step": 1040
},
{
"epoch": 0.4666666666666667,
"grad_norm": 1.00870943069458,
"learning_rate": 3.4571428571428574e-05,
"loss": 0.5811,
"step": 1050
},
{
"epoch": 0.4711111111111111,
"grad_norm": 0.977967381477356,
"learning_rate": 3.428571428571429e-05,
"loss": 0.7529,
"step": 1060
},
{
"epoch": 0.47555555555555556,
"grad_norm": 1.1854398250579834,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.7092,
"step": 1070
},
{
"epoch": 0.48,
"grad_norm": 1.7509541511535645,
"learning_rate": 3.3714285714285716e-05,
"loss": 0.6859,
"step": 1080
},
{
"epoch": 0.48444444444444446,
"grad_norm": 1.652112364768982,
"learning_rate": 3.342857142857143e-05,
"loss": 0.7396,
"step": 1090
},
{
"epoch": 0.4888888888888889,
"grad_norm": 2.1805965900421143,
"learning_rate": 3.314285714285714e-05,
"loss": 0.7982,
"step": 1100
},
{
"epoch": 0.49333333333333335,
"grad_norm": 2.820934534072876,
"learning_rate": 3.285714285714286e-05,
"loss": 0.7424,
"step": 1110
},
{
"epoch": 0.49777777777777776,
"grad_norm": 9.163993835449219,
"learning_rate": 3.257142857142857e-05,
"loss": 0.8498,
"step": 1120
},
{
"epoch": 0.5022222222222222,
"grad_norm": 1.3526314496994019,
"learning_rate": 3.228571428571428e-05,
"loss": 0.7335,
"step": 1130
},
{
"epoch": 0.5066666666666667,
"grad_norm": 3.196364164352417,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.0057,
"step": 1140
},
{
"epoch": 0.5111111111111111,
"grad_norm": 2.5258631706237793,
"learning_rate": 3.1714285714285715e-05,
"loss": 0.7504,
"step": 1150
},
{
"epoch": 0.5155555555555555,
"grad_norm": 18.060762405395508,
"learning_rate": 3.142857142857143e-05,
"loss": 0.8299,
"step": 1160
},
{
"epoch": 0.52,
"grad_norm": 3.3956117630004883,
"learning_rate": 3.114285714285715e-05,
"loss": 0.7396,
"step": 1170
},
{
"epoch": 0.5244444444444445,
"grad_norm": 1.5035347938537598,
"learning_rate": 3.0857142857142856e-05,
"loss": 0.6786,
"step": 1180
},
{
"epoch": 0.5288888888888889,
"grad_norm": 1.8701106309890747,
"learning_rate": 3.057142857142857e-05,
"loss": 1.045,
"step": 1190
},
{
"epoch": 0.5333333333333333,
"grad_norm": 2.3694677352905273,
"learning_rate": 3.0285714285714288e-05,
"loss": 0.7394,
"step": 1200
},
{
"epoch": 0.5377777777777778,
"grad_norm": 3.630218267440796,
"learning_rate": 3e-05,
"loss": 0.8106,
"step": 1210
},
{
"epoch": 0.5422222222222223,
"grad_norm": 1.8953900337219238,
"learning_rate": 2.9714285714285717e-05,
"loss": 0.8347,
"step": 1220
},
{
"epoch": 0.5466666666666666,
"grad_norm": 2.067115545272827,
"learning_rate": 2.9428571428571426e-05,
"loss": 0.9066,
"step": 1230
},
{
"epoch": 0.5511111111111111,
"grad_norm": 2.195612907409668,
"learning_rate": 2.9142857142857146e-05,
"loss": 0.85,
"step": 1240
},
{
"epoch": 0.5555555555555556,
"grad_norm": 6.791778564453125,
"learning_rate": 2.885714285714286e-05,
"loss": 0.6259,
"step": 1250
},
{
"epoch": 0.56,
"grad_norm": 3.0913190841674805,
"learning_rate": 2.857142857142857e-05,
"loss": 0.8132,
"step": 1260
},
{
"epoch": 0.5644444444444444,
"grad_norm": 8.887785911560059,
"learning_rate": 2.8285714285714287e-05,
"loss": 0.626,
"step": 1270
},
{
"epoch": 0.5688888888888889,
"grad_norm": 2.769585132598877,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.5566,
"step": 1280
},
{
"epoch": 0.5733333333333334,
"grad_norm": 2.938758373260498,
"learning_rate": 2.7714285714285716e-05,
"loss": 0.7082,
"step": 1290
},
{
"epoch": 0.5777777777777777,
"grad_norm": 3.9184396266937256,
"learning_rate": 2.742857142857143e-05,
"loss": 0.5574,
"step": 1300
},
{
"epoch": 0.5822222222222222,
"grad_norm": 2.5171377658843994,
"learning_rate": 2.714285714285714e-05,
"loss": 0.497,
"step": 1310
},
{
"epoch": 0.5866666666666667,
"grad_norm": 4.993486404418945,
"learning_rate": 2.6857142857142857e-05,
"loss": 0.6557,
"step": 1320
},
{
"epoch": 0.5911111111111111,
"grad_norm": 5.2871551513671875,
"learning_rate": 2.6571428571428576e-05,
"loss": 0.7234,
"step": 1330
},
{
"epoch": 0.5955555555555555,
"grad_norm": 4.414983749389648,
"learning_rate": 2.6285714285714286e-05,
"loss": 0.8204,
"step": 1340
},
{
"epoch": 0.6,
"grad_norm": 2.0641419887542725,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.5932,
"step": 1350
},
{
"epoch": 0.6044444444444445,
"grad_norm": 4.55308723449707,
"learning_rate": 2.5714285714285714e-05,
"loss": 0.7171,
"step": 1360
},
{
"epoch": 0.6088888888888889,
"grad_norm": 4.960785865783691,
"learning_rate": 2.542857142857143e-05,
"loss": 0.5145,
"step": 1370
},
{
"epoch": 0.6133333333333333,
"grad_norm": 4.376406669616699,
"learning_rate": 2.5142857142857147e-05,
"loss": 0.5864,
"step": 1380
},
{
"epoch": 0.6177777777777778,
"grad_norm": 14.931255340576172,
"learning_rate": 2.485714285714286e-05,
"loss": 0.5942,
"step": 1390
},
{
"epoch": 0.6222222222222222,
"grad_norm": 80.68295288085938,
"learning_rate": 2.4571428571428572e-05,
"loss": 0.7149,
"step": 1400
},
{
"epoch": 0.6266666666666667,
"grad_norm": 6.966264247894287,
"learning_rate": 2.4285714285714288e-05,
"loss": 0.5357,
"step": 1410
},
{
"epoch": 0.6311111111111111,
"grad_norm": 11.523138046264648,
"learning_rate": 2.4e-05,
"loss": 0.5548,
"step": 1420
},
{
"epoch": 0.6355555555555555,
"grad_norm": 5.8682475090026855,
"learning_rate": 2.3714285714285717e-05,
"loss": 0.6273,
"step": 1430
},
{
"epoch": 0.64,
"grad_norm": 5.063971519470215,
"learning_rate": 2.342857142857143e-05,
"loss": 0.5253,
"step": 1440
},
{
"epoch": 0.6444444444444445,
"grad_norm": 6.171313285827637,
"learning_rate": 2.3142857142857145e-05,
"loss": 0.5423,
"step": 1450
},
{
"epoch": 0.6488888888888888,
"grad_norm": 7.615331649780273,
"learning_rate": 2.2857142857142858e-05,
"loss": 0.708,
"step": 1460
},
{
"epoch": 0.6533333333333333,
"grad_norm": 6.465192794799805,
"learning_rate": 2.257142857142857e-05,
"loss": 0.6355,
"step": 1470
},
{
"epoch": 0.6577777777777778,
"grad_norm": 11.557660102844238,
"learning_rate": 2.2285714285714287e-05,
"loss": 0.5724,
"step": 1480
},
{
"epoch": 0.6622222222222223,
"grad_norm": 10.57749080657959,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.6745,
"step": 1490
},
{
"epoch": 0.6666666666666666,
"grad_norm": 7.165240287780762,
"learning_rate": 2.1714285714285715e-05,
"loss": 0.582,
"step": 1500
},
{
"epoch": 0.6711111111111111,
"grad_norm": 4.825045108795166,
"learning_rate": 2.1428571428571428e-05,
"loss": 0.4501,
"step": 1510
},
{
"epoch": 0.6755555555555556,
"grad_norm": 5.933408737182617,
"learning_rate": 2.1142857142857144e-05,
"loss": 0.6209,
"step": 1520
},
{
"epoch": 0.68,
"grad_norm": 3.2412068843841553,
"learning_rate": 2.0857142857142857e-05,
"loss": 0.6279,
"step": 1530
},
{
"epoch": 0.6844444444444444,
"grad_norm": 8.654913902282715,
"learning_rate": 2.0571428571428573e-05,
"loss": 0.5614,
"step": 1540
},
{
"epoch": 0.6888888888888889,
"grad_norm": 3.5298168659210205,
"learning_rate": 2.0285714285714286e-05,
"loss": 0.6737,
"step": 1550
},
{
"epoch": 0.6933333333333334,
"grad_norm": 3.3998289108276367,
"learning_rate": 2e-05,
"loss": 0.669,
"step": 1560
},
{
"epoch": 0.6977777777777778,
"grad_norm": 4.436722278594971,
"learning_rate": 1.9714285714285714e-05,
"loss": 0.7394,
"step": 1570
},
{
"epoch": 0.7022222222222222,
"grad_norm": 5.631706714630127,
"learning_rate": 1.942857142857143e-05,
"loss": 0.5167,
"step": 1580
},
{
"epoch": 0.7066666666666667,
"grad_norm": 4.268092155456543,
"learning_rate": 1.9142857142857143e-05,
"loss": 0.5114,
"step": 1590
},
{
"epoch": 0.7111111111111111,
"grad_norm": 14.461816787719727,
"learning_rate": 1.885714285714286e-05,
"loss": 0.5903,
"step": 1600
},
{
"epoch": 0.7155555555555555,
"grad_norm": 6.177591323852539,
"learning_rate": 1.8571428571428572e-05,
"loss": 0.4619,
"step": 1610
},
{
"epoch": 0.72,
"grad_norm": 3.8775877952575684,
"learning_rate": 1.8285714285714288e-05,
"loss": 0.4254,
"step": 1620
},
{
"epoch": 0.7244444444444444,
"grad_norm": 10.525681495666504,
"learning_rate": 1.8e-05,
"loss": 0.7416,
"step": 1630
},
{
"epoch": 0.7288888888888889,
"grad_norm": 8.446870803833008,
"learning_rate": 1.7714285714285713e-05,
"loss": 0.5597,
"step": 1640
},
{
"epoch": 0.7333333333333333,
"grad_norm": 6.213122367858887,
"learning_rate": 1.742857142857143e-05,
"loss": 0.4531,
"step": 1650
},
{
"epoch": 0.7377777777777778,
"grad_norm": 6.555688858032227,
"learning_rate": 1.7142857142857145e-05,
"loss": 0.6882,
"step": 1660
},
{
"epoch": 0.7422222222222222,
"grad_norm": 5.502016067504883,
"learning_rate": 1.6857142857142858e-05,
"loss": 0.5177,
"step": 1670
},
{
"epoch": 0.7466666666666667,
"grad_norm": 4.0184102058410645,
"learning_rate": 1.657142857142857e-05,
"loss": 0.4499,
"step": 1680
},
{
"epoch": 0.7511111111111111,
"grad_norm": 5.010197639465332,
"learning_rate": 1.6285714285714287e-05,
"loss": 0.5105,
"step": 1690
},
{
"epoch": 0.7555555555555555,
"grad_norm": 6.907636642456055,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.4339,
"step": 1700
},
{
"epoch": 0.76,
"grad_norm": 4.459092617034912,
"learning_rate": 1.5714285714285715e-05,
"loss": 0.5309,
"step": 1710
},
{
"epoch": 0.7644444444444445,
"grad_norm": 6.3801164627075195,
"learning_rate": 1.5428571428571428e-05,
"loss": 0.5354,
"step": 1720
},
{
"epoch": 0.7688888888888888,
"grad_norm": 3.440077066421509,
"learning_rate": 1.5142857142857144e-05,
"loss": 0.4684,
"step": 1730
},
{
"epoch": 0.7733333333333333,
"grad_norm": 8.774897575378418,
"learning_rate": 1.4857142857142858e-05,
"loss": 0.6064,
"step": 1740
},
{
"epoch": 0.7777777777777778,
"grad_norm": 4.872552871704102,
"learning_rate": 1.4571428571428573e-05,
"loss": 0.5877,
"step": 1750
},
{
"epoch": 0.7822222222222223,
"grad_norm": 4.998244762420654,
"learning_rate": 1.4285714285714285e-05,
"loss": 0.3201,
"step": 1760
},
{
"epoch": 0.7866666666666666,
"grad_norm": 9.849549293518066,
"learning_rate": 1.4000000000000001e-05,
"loss": 0.552,
"step": 1770
},
{
"epoch": 0.7911111111111111,
"grad_norm": 3.8695757389068604,
"learning_rate": 1.3714285714285716e-05,
"loss": 0.4807,
"step": 1780
},
{
"epoch": 0.7955555555555556,
"grad_norm": 10.59960651397705,
"learning_rate": 1.3428571428571429e-05,
"loss": 0.5487,
"step": 1790
},
{
"epoch": 0.8,
"grad_norm": 3.5705807209014893,
"learning_rate": 1.3142857142857143e-05,
"loss": 0.4526,
"step": 1800
},
{
"epoch": 0.8044444444444444,
"grad_norm": 3.2554914951324463,
"learning_rate": 1.2857142857142857e-05,
"loss": 0.6035,
"step": 1810
},
{
"epoch": 0.8088888888888889,
"grad_norm": 10.050302505493164,
"learning_rate": 1.2571428571428573e-05,
"loss": 0.6413,
"step": 1820
},
{
"epoch": 0.8133333333333334,
"grad_norm": 3.8750650882720947,
"learning_rate": 1.2285714285714286e-05,
"loss": 0.4818,
"step": 1830
},
{
"epoch": 0.8177777777777778,
"grad_norm": 5.40247917175293,
"learning_rate": 1.2e-05,
"loss": 0.5041,
"step": 1840
},
{
"epoch": 0.8222222222222222,
"grad_norm": 4.115529537200928,
"learning_rate": 1.1714285714285715e-05,
"loss": 0.4337,
"step": 1850
},
{
"epoch": 0.8266666666666667,
"grad_norm": 4.241470813751221,
"learning_rate": 1.1428571428571429e-05,
"loss": 0.5223,
"step": 1860
},
{
"epoch": 0.8311111111111111,
"grad_norm": 25.0269775390625,
"learning_rate": 1.1142857142857143e-05,
"loss": 0.6195,
"step": 1870
},
{
"epoch": 0.8355555555555556,
"grad_norm": 4.397892475128174,
"learning_rate": 1.0857142857142858e-05,
"loss": 0.5594,
"step": 1880
},
{
"epoch": 0.84,
"grad_norm": 15.26313591003418,
"learning_rate": 1.0571428571428572e-05,
"loss": 0.6732,
"step": 1890
},
{
"epoch": 0.8444444444444444,
"grad_norm": 7.27249813079834,
"learning_rate": 1.0285714285714286e-05,
"loss": 0.6866,
"step": 1900
},
{
"epoch": 0.8488888888888889,
"grad_norm": 4.72747278213501,
"learning_rate": 1e-05,
"loss": 0.4916,
"step": 1910
},
{
"epoch": 0.8533333333333334,
"grad_norm": 8.689544677734375,
"learning_rate": 9.714285714285715e-06,
"loss": 0.4455,
"step": 1920
},
{
"epoch": 0.8577777777777778,
"grad_norm": 6.947673797607422,
"learning_rate": 9.42857142857143e-06,
"loss": 0.394,
"step": 1930
},
{
"epoch": 0.8622222222222222,
"grad_norm": 12.597881317138672,
"learning_rate": 9.142857142857144e-06,
"loss": 0.5695,
"step": 1940
},
{
"epoch": 0.8666666666666667,
"grad_norm": 5.3088274002075195,
"learning_rate": 8.857142857142857e-06,
"loss": 0.5589,
"step": 1950
},
{
"epoch": 0.8711111111111111,
"grad_norm": 4.580944061279297,
"learning_rate": 8.571428571428573e-06,
"loss": 0.5902,
"step": 1960
},
{
"epoch": 0.8755555555555555,
"grad_norm": 4.883549213409424,
"learning_rate": 8.285714285714285e-06,
"loss": 0.4635,
"step": 1970
},
{
"epoch": 0.88,
"grad_norm": 20.647493362426758,
"learning_rate": 8.000000000000001e-06,
"loss": 0.5043,
"step": 1980
},
{
"epoch": 0.8844444444444445,
"grad_norm": 5.067135810852051,
"learning_rate": 7.714285714285714e-06,
"loss": 0.4372,
"step": 1990
},
{
"epoch": 0.8888888888888888,
"grad_norm": 8.781386375427246,
"learning_rate": 7.428571428571429e-06,
"loss": 0.4274,
"step": 2000
},
{
"epoch": 0.8933333333333333,
"grad_norm": 4.173491954803467,
"learning_rate": 7.142857142857143e-06,
"loss": 0.422,
"step": 2010
},
{
"epoch": 0.8977777777777778,
"grad_norm": 5.917858600616455,
"learning_rate": 6.857142857142858e-06,
"loss": 0.505,
"step": 2020
},
{
"epoch": 0.9022222222222223,
"grad_norm": 6.02107048034668,
"learning_rate": 6.5714285714285714e-06,
"loss": 0.4933,
"step": 2030
},
{
"epoch": 0.9066666666666666,
"grad_norm": 5.2334794998168945,
"learning_rate": 6.285714285714287e-06,
"loss": 0.4,
"step": 2040
},
{
"epoch": 0.9111111111111111,
"grad_norm": 6.435775279998779,
"learning_rate": 6e-06,
"loss": 0.5269,
"step": 2050
},
{
"epoch": 0.9155555555555556,
"grad_norm": 11.653307914733887,
"learning_rate": 5.7142857142857145e-06,
"loss": 0.5007,
"step": 2060
},
{
"epoch": 0.92,
"grad_norm": 6.596048355102539,
"learning_rate": 5.428571428571429e-06,
"loss": 0.482,
"step": 2070
},
{
"epoch": 0.9244444444444444,
"grad_norm": 11.182780265808105,
"learning_rate": 5.142857142857143e-06,
"loss": 0.498,
"step": 2080
},
{
"epoch": 0.9288888888888889,
"grad_norm": 7.414155960083008,
"learning_rate": 4.857142857142858e-06,
"loss": 0.4041,
"step": 2090
},
{
"epoch": 0.9333333333333333,
"grad_norm": 3.3029086589813232,
"learning_rate": 4.571428571428572e-06,
"loss": 0.4889,
"step": 2100
},
{
"epoch": 0.9377777777777778,
"grad_norm": 4.610305309295654,
"learning_rate": 4.285714285714286e-06,
"loss": 0.3627,
"step": 2110
},
{
"epoch": 0.9422222222222222,
"grad_norm": 13.668721199035645,
"learning_rate": 4.000000000000001e-06,
"loss": 0.5639,
"step": 2120
},
{
"epoch": 0.9466666666666667,
"grad_norm": 11.849321365356445,
"learning_rate": 3.7142857142857146e-06,
"loss": 0.4124,
"step": 2130
},
{
"epoch": 0.9511111111111111,
"grad_norm": 4.347206115722656,
"learning_rate": 3.428571428571429e-06,
"loss": 0.3611,
"step": 2140
},
{
"epoch": 0.9555555555555556,
"grad_norm": 5.468479156494141,
"learning_rate": 3.1428571428571433e-06,
"loss": 0.4312,
"step": 2150
},
{
"epoch": 0.96,
"grad_norm": 5.55856466293335,
"learning_rate": 2.8571428571428573e-06,
"loss": 0.3958,
"step": 2160
},
{
"epoch": 0.9644444444444444,
"grad_norm": 10.76039981842041,
"learning_rate": 2.5714285714285716e-06,
"loss": 0.5161,
"step": 2170
},
{
"epoch": 0.9688888888888889,
"grad_norm": 6.2166547775268555,
"learning_rate": 2.285714285714286e-06,
"loss": 0.4374,
"step": 2180
},
{
"epoch": 0.9733333333333334,
"grad_norm": 8.524560928344727,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.4948,
"step": 2190
},
{
"epoch": 0.9777777777777777,
"grad_norm": 7.957738399505615,
"learning_rate": 1.7142857142857145e-06,
"loss": 0.4129,
"step": 2200
},
{
"epoch": 0.9822222222222222,
"grad_norm": 9.382002830505371,
"learning_rate": 1.4285714285714286e-06,
"loss": 0.3626,
"step": 2210
},
{
"epoch": 0.9866666666666667,
"grad_norm": 5.674395561218262,
"learning_rate": 1.142857142857143e-06,
"loss": 0.5119,
"step": 2220
},
{
"epoch": 0.9911111111111112,
"grad_norm": 4.210872650146484,
"learning_rate": 8.571428571428572e-07,
"loss": 0.4205,
"step": 2230
},
{
"epoch": 0.9955555555555555,
"grad_norm": 5.570230007171631,
"learning_rate": 5.714285714285715e-07,
"loss": 0.5659,
"step": 2240
},
{
"epoch": 1.0,
"grad_norm": 4.3954572677612305,
"learning_rate": 2.8571428571428575e-07,
"loss": 0.4376,
"step": 2250
}
],
"logging_steps": 10,
"max_steps": 2250,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 5000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.74343695220736e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}