ToastyPigeon's picture
Training in progress, step 293, checkpoint
fdafaee verified
raw
history blame
50.9 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.5008547008547009,
"eval_steps": 30,
"global_step": 293,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0017094017094017094,
"grad_norm": 0.71875,
"learning_rate": 1.5e-06,
"loss": 2.3076,
"step": 1
},
{
"epoch": 0.0017094017094017094,
"eval_loss": 2.248321533203125,
"eval_runtime": 152.6229,
"eval_samples_per_second": 1.677,
"eval_steps_per_second": 0.282,
"step": 1
},
{
"epoch": 0.003418803418803419,
"grad_norm": 0.671875,
"learning_rate": 3e-06,
"loss": 2.3377,
"step": 2
},
{
"epoch": 0.005128205128205128,
"grad_norm": 0.65625,
"learning_rate": 4.5e-06,
"loss": 2.3576,
"step": 3
},
{
"epoch": 0.006837606837606838,
"grad_norm": 0.6796875,
"learning_rate": 6e-06,
"loss": 2.2635,
"step": 4
},
{
"epoch": 0.008547008547008548,
"grad_norm": 0.7265625,
"learning_rate": 7.5e-06,
"loss": 2.4173,
"step": 5
},
{
"epoch": 0.010256410256410256,
"grad_norm": 0.64453125,
"learning_rate": 9e-06,
"loss": 2.2549,
"step": 6
},
{
"epoch": 0.011965811965811967,
"grad_norm": 0.65234375,
"learning_rate": 1.05e-05,
"loss": 2.4147,
"step": 7
},
{
"epoch": 0.013675213675213675,
"grad_norm": 0.6328125,
"learning_rate": 1.2e-05,
"loss": 2.3563,
"step": 8
},
{
"epoch": 0.015384615384615385,
"grad_norm": 0.5390625,
"learning_rate": 1.3500000000000001e-05,
"loss": 2.3558,
"step": 9
},
{
"epoch": 0.017094017094017096,
"grad_norm": 0.88671875,
"learning_rate": 1.5e-05,
"loss": 2.3426,
"step": 10
},
{
"epoch": 0.018803418803418803,
"grad_norm": 0.498046875,
"learning_rate": 1.65e-05,
"loss": 2.3699,
"step": 11
},
{
"epoch": 0.020512820512820513,
"grad_norm": 0.515625,
"learning_rate": 1.8e-05,
"loss": 2.2644,
"step": 12
},
{
"epoch": 0.022222222222222223,
"grad_norm": 0.5859375,
"learning_rate": 1.95e-05,
"loss": 2.2842,
"step": 13
},
{
"epoch": 0.023931623931623933,
"grad_norm": 0.640625,
"learning_rate": 2.1e-05,
"loss": 2.2977,
"step": 14
},
{
"epoch": 0.02564102564102564,
"grad_norm": 0.62109375,
"learning_rate": 2.25e-05,
"loss": 2.2834,
"step": 15
},
{
"epoch": 0.02735042735042735,
"grad_norm": 0.7265625,
"learning_rate": 2.4e-05,
"loss": 2.3457,
"step": 16
},
{
"epoch": 0.02905982905982906,
"grad_norm": 0.734375,
"learning_rate": 2.55e-05,
"loss": 2.1915,
"step": 17
},
{
"epoch": 0.03076923076923077,
"grad_norm": 0.62109375,
"learning_rate": 2.7000000000000002e-05,
"loss": 2.264,
"step": 18
},
{
"epoch": 0.03247863247863248,
"grad_norm": 0.55078125,
"learning_rate": 2.8499999999999998e-05,
"loss": 2.2251,
"step": 19
},
{
"epoch": 0.03418803418803419,
"grad_norm": 0.55859375,
"learning_rate": 3e-05,
"loss": 2.2482,
"step": 20
},
{
"epoch": 0.035897435897435895,
"grad_norm": 0.578125,
"learning_rate": 2.9999946827306146e-05,
"loss": 2.3187,
"step": 21
},
{
"epoch": 0.037606837606837605,
"grad_norm": 0.57421875,
"learning_rate": 2.9999787309621396e-05,
"loss": 2.329,
"step": 22
},
{
"epoch": 0.039316239316239315,
"grad_norm": 0.55859375,
"learning_rate": 2.9999521448136205e-05,
"loss": 2.1736,
"step": 23
},
{
"epoch": 0.041025641025641026,
"grad_norm": 0.53515625,
"learning_rate": 2.999914924483466e-05,
"loss": 2.2928,
"step": 24
},
{
"epoch": 0.042735042735042736,
"grad_norm": 0.5390625,
"learning_rate": 2.999867070249444e-05,
"loss": 2.3343,
"step": 25
},
{
"epoch": 0.044444444444444446,
"grad_norm": 0.5078125,
"learning_rate": 2.9998085824686838e-05,
"loss": 2.3226,
"step": 26
},
{
"epoch": 0.046153846153846156,
"grad_norm": 0.53125,
"learning_rate": 2.9997394615776692e-05,
"loss": 2.2437,
"step": 27
},
{
"epoch": 0.04786324786324787,
"grad_norm": 0.5234375,
"learning_rate": 2.999659708092239e-05,
"loss": 2.2302,
"step": 28
},
{
"epoch": 0.04957264957264957,
"grad_norm": 0.546875,
"learning_rate": 2.9995693226075796e-05,
"loss": 2.1686,
"step": 29
},
{
"epoch": 0.05128205128205128,
"grad_norm": 0.5,
"learning_rate": 2.9994683057982227e-05,
"loss": 2.2699,
"step": 30
},
{
"epoch": 0.05128205128205128,
"eval_loss": 2.2213175296783447,
"eval_runtime": 153.4952,
"eval_samples_per_second": 1.668,
"eval_steps_per_second": 0.28,
"step": 30
},
{
"epoch": 0.05299145299145299,
"grad_norm": 0.53125,
"learning_rate": 2.9993566584180403e-05,
"loss": 2.2601,
"step": 31
},
{
"epoch": 0.0547008547008547,
"grad_norm": 0.52734375,
"learning_rate": 2.9992343813002384e-05,
"loss": 2.3567,
"step": 32
},
{
"epoch": 0.05641025641025641,
"grad_norm": 0.5625,
"learning_rate": 2.99910147535735e-05,
"loss": 2.3461,
"step": 33
},
{
"epoch": 0.05811965811965812,
"grad_norm": 0.5,
"learning_rate": 2.9989579415812313e-05,
"loss": 2.2736,
"step": 34
},
{
"epoch": 0.05982905982905983,
"grad_norm": 0.5546875,
"learning_rate": 2.998803781043051e-05,
"loss": 2.4475,
"step": 35
},
{
"epoch": 0.06153846153846154,
"grad_norm": 0.48828125,
"learning_rate": 2.9986389948932825e-05,
"loss": 2.2864,
"step": 36
},
{
"epoch": 0.06324786324786325,
"grad_norm": 0.53515625,
"learning_rate": 2.998463584361699e-05,
"loss": 2.2971,
"step": 37
},
{
"epoch": 0.06495726495726496,
"grad_norm": 0.52734375,
"learning_rate": 2.9982775507573586e-05,
"loss": 2.1686,
"step": 38
},
{
"epoch": 0.06666666666666667,
"grad_norm": 0.51171875,
"learning_rate": 2.9980808954686005e-05,
"loss": 2.2225,
"step": 39
},
{
"epoch": 0.06837606837606838,
"grad_norm": 0.51171875,
"learning_rate": 2.9978736199630297e-05,
"loss": 2.1414,
"step": 40
},
{
"epoch": 0.07008547008547009,
"grad_norm": 0.59375,
"learning_rate": 2.99765572578751e-05,
"loss": 2.2085,
"step": 41
},
{
"epoch": 0.07179487179487179,
"grad_norm": 0.625,
"learning_rate": 2.9974272145681487e-05,
"loss": 2.3185,
"step": 42
},
{
"epoch": 0.0735042735042735,
"grad_norm": 0.494140625,
"learning_rate": 2.997188088010287e-05,
"loss": 2.1781,
"step": 43
},
{
"epoch": 0.07521367521367521,
"grad_norm": 0.53125,
"learning_rate": 2.9969383478984875e-05,
"loss": 2.1979,
"step": 44
},
{
"epoch": 0.07692307692307693,
"grad_norm": 0.52734375,
"learning_rate": 2.9966779960965186e-05,
"loss": 2.1786,
"step": 45
},
{
"epoch": 0.07863247863247863,
"grad_norm": 0.5234375,
"learning_rate": 2.9964070345473427e-05,
"loss": 2.2664,
"step": 46
},
{
"epoch": 0.08034188034188035,
"grad_norm": 0.59765625,
"learning_rate": 2.9961254652731014e-05,
"loss": 2.1936,
"step": 47
},
{
"epoch": 0.08205128205128205,
"grad_norm": 0.6171875,
"learning_rate": 2.9958332903750987e-05,
"loss": 2.3133,
"step": 48
},
{
"epoch": 0.08376068376068375,
"grad_norm": 0.53125,
"learning_rate": 2.9955305120337887e-05,
"loss": 2.2156,
"step": 49
},
{
"epoch": 0.08547008547008547,
"grad_norm": 0.51953125,
"learning_rate": 2.9952171325087547e-05,
"loss": 2.4135,
"step": 50
},
{
"epoch": 0.08717948717948718,
"grad_norm": 0.921875,
"learning_rate": 2.994893154138697e-05,
"loss": 2.2793,
"step": 51
},
{
"epoch": 0.08888888888888889,
"grad_norm": 0.5546875,
"learning_rate": 2.9945585793414117e-05,
"loss": 2.2301,
"step": 52
},
{
"epoch": 0.0905982905982906,
"grad_norm": 0.5234375,
"learning_rate": 2.9942134106137754e-05,
"loss": 2.2878,
"step": 53
},
{
"epoch": 0.09230769230769231,
"grad_norm": 1.1328125,
"learning_rate": 2.9938576505317253e-05,
"loss": 2.3196,
"step": 54
},
{
"epoch": 0.09401709401709402,
"grad_norm": 0.5078125,
"learning_rate": 2.99349130175024e-05,
"loss": 2.3061,
"step": 55
},
{
"epoch": 0.09572649572649573,
"grad_norm": 0.515625,
"learning_rate": 2.9931143670033195e-05,
"loss": 2.1972,
"step": 56
},
{
"epoch": 0.09743589743589744,
"grad_norm": 0.490234375,
"learning_rate": 2.9927268491039653e-05,
"loss": 2.3351,
"step": 57
},
{
"epoch": 0.09914529914529914,
"grad_norm": 0.482421875,
"learning_rate": 2.992328750944159e-05,
"loss": 2.2107,
"step": 58
},
{
"epoch": 0.10085470085470086,
"grad_norm": 0.5546875,
"learning_rate": 2.9919200754948417e-05,
"loss": 2.2458,
"step": 59
},
{
"epoch": 0.10256410256410256,
"grad_norm": 0.5546875,
"learning_rate": 2.99150082580589e-05,
"loss": 2.1415,
"step": 60
},
{
"epoch": 0.10256410256410256,
"eval_loss": 2.194425106048584,
"eval_runtime": 153.5382,
"eval_samples_per_second": 1.667,
"eval_steps_per_second": 0.28,
"step": 60
},
{
"epoch": 0.10427350427350428,
"grad_norm": 0.486328125,
"learning_rate": 2.9910710050060954e-05,
"loss": 2.23,
"step": 61
},
{
"epoch": 0.10598290598290598,
"grad_norm": 0.5078125,
"learning_rate": 2.9906306163031388e-05,
"loss": 2.1581,
"step": 62
},
{
"epoch": 0.1076923076923077,
"grad_norm": 0.54296875,
"learning_rate": 2.9901796629835686e-05,
"loss": 2.1723,
"step": 63
},
{
"epoch": 0.1094017094017094,
"grad_norm": 0.5703125,
"learning_rate": 2.9897181484127743e-05,
"loss": 2.2641,
"step": 64
},
{
"epoch": 0.1111111111111111,
"grad_norm": 0.55078125,
"learning_rate": 2.9892460760349624e-05,
"loss": 2.2183,
"step": 65
},
{
"epoch": 0.11282051282051282,
"grad_norm": 0.53515625,
"learning_rate": 2.9887634493731312e-05,
"loss": 2.2151,
"step": 66
},
{
"epoch": 0.11452991452991453,
"grad_norm": 0.54296875,
"learning_rate": 2.988270272029043e-05,
"loss": 2.206,
"step": 67
},
{
"epoch": 0.11623931623931624,
"grad_norm": 0.51953125,
"learning_rate": 2.987766547683199e-05,
"loss": 2.1754,
"step": 68
},
{
"epoch": 0.11794871794871795,
"grad_norm": 0.671875,
"learning_rate": 2.9872522800948106e-05,
"loss": 2.2236,
"step": 69
},
{
"epoch": 0.11965811965811966,
"grad_norm": 0.578125,
"learning_rate": 2.9867274731017714e-05,
"loss": 2.222,
"step": 70
},
{
"epoch": 0.12136752136752137,
"grad_norm": 0.51171875,
"learning_rate": 2.9861921306206287e-05,
"loss": 2.0767,
"step": 71
},
{
"epoch": 0.12307692307692308,
"grad_norm": 0.51171875,
"learning_rate": 2.9856462566465556e-05,
"loss": 2.2204,
"step": 72
},
{
"epoch": 0.12478632478632479,
"grad_norm": 0.5703125,
"learning_rate": 2.9850898552533175e-05,
"loss": 2.3901,
"step": 73
},
{
"epoch": 0.1264957264957265,
"grad_norm": 0.5234375,
"learning_rate": 2.984522930593247e-05,
"loss": 2.1304,
"step": 74
},
{
"epoch": 0.1282051282051282,
"grad_norm": 0.515625,
"learning_rate": 2.9839454868972085e-05,
"loss": 2.1427,
"step": 75
},
{
"epoch": 0.12991452991452992,
"grad_norm": 0.51171875,
"learning_rate": 2.9833575284745687e-05,
"loss": 2.235,
"step": 76
},
{
"epoch": 0.13162393162393163,
"grad_norm": 0.5546875,
"learning_rate": 2.9827590597131636e-05,
"loss": 2.316,
"step": 77
},
{
"epoch": 0.13333333333333333,
"grad_norm": 0.703125,
"learning_rate": 2.9821500850792668e-05,
"loss": 2.2714,
"step": 78
},
{
"epoch": 0.13504273504273503,
"grad_norm": 0.546875,
"learning_rate": 2.981530609117554e-05,
"loss": 2.2249,
"step": 79
},
{
"epoch": 0.13675213675213677,
"grad_norm": 0.5234375,
"learning_rate": 2.980900636451073e-05,
"loss": 2.1681,
"step": 80
},
{
"epoch": 0.13846153846153847,
"grad_norm": 0.52734375,
"learning_rate": 2.9802601717812045e-05,
"loss": 2.3345,
"step": 81
},
{
"epoch": 0.14017094017094017,
"grad_norm": 0.5234375,
"learning_rate": 2.9796092198876305e-05,
"loss": 2.1506,
"step": 82
},
{
"epoch": 0.14188034188034188,
"grad_norm": 0.5546875,
"learning_rate": 2.9789477856282968e-05,
"loss": 2.2908,
"step": 83
},
{
"epoch": 0.14358974358974358,
"grad_norm": 0.57421875,
"learning_rate": 2.978275873939378e-05,
"loss": 2.2495,
"step": 84
},
{
"epoch": 0.1452991452991453,
"grad_norm": 0.59375,
"learning_rate": 2.977593489835239e-05,
"loss": 2.186,
"step": 85
},
{
"epoch": 0.147008547008547,
"grad_norm": 0.6484375,
"learning_rate": 2.9769006384084e-05,
"loss": 2.1442,
"step": 86
},
{
"epoch": 0.14871794871794872,
"grad_norm": 0.51171875,
"learning_rate": 2.976197324829496e-05,
"loss": 2.1663,
"step": 87
},
{
"epoch": 0.15042735042735042,
"grad_norm": 0.515625,
"learning_rate": 2.9754835543472396e-05,
"loss": 2.3458,
"step": 88
},
{
"epoch": 0.15213675213675212,
"grad_norm": 0.55078125,
"learning_rate": 2.9747593322883817e-05,
"loss": 2.1568,
"step": 89
},
{
"epoch": 0.15384615384615385,
"grad_norm": 0.5625,
"learning_rate": 2.9740246640576713e-05,
"loss": 2.2196,
"step": 90
},
{
"epoch": 0.15384615384615385,
"eval_loss": 2.1906561851501465,
"eval_runtime": 153.5179,
"eval_samples_per_second": 1.668,
"eval_steps_per_second": 0.28,
"step": 90
},
{
"epoch": 0.15555555555555556,
"grad_norm": 0.52734375,
"learning_rate": 2.9732795551378154e-05,
"loss": 2.1843,
"step": 91
},
{
"epoch": 0.15726495726495726,
"grad_norm": 0.5546875,
"learning_rate": 2.972524011089439e-05,
"loss": 2.2099,
"step": 92
},
{
"epoch": 0.15897435897435896,
"grad_norm": 0.62109375,
"learning_rate": 2.971758037551042e-05,
"loss": 2.1464,
"step": 93
},
{
"epoch": 0.1606837606837607,
"grad_norm": 0.6015625,
"learning_rate": 2.9709816402389573e-05,
"loss": 2.2127,
"step": 94
},
{
"epoch": 0.1623931623931624,
"grad_norm": 0.55859375,
"learning_rate": 2.9701948249473103e-05,
"loss": 2.2087,
"step": 95
},
{
"epoch": 0.1641025641025641,
"grad_norm": 0.59765625,
"learning_rate": 2.9693975975479723e-05,
"loss": 2.297,
"step": 96
},
{
"epoch": 0.1658119658119658,
"grad_norm": 0.59765625,
"learning_rate": 2.968589963990519e-05,
"loss": 2.1285,
"step": 97
},
{
"epoch": 0.1675213675213675,
"grad_norm": 0.56640625,
"learning_rate": 2.9677719303021867e-05,
"loss": 2.1603,
"step": 98
},
{
"epoch": 0.16923076923076924,
"grad_norm": 0.53125,
"learning_rate": 2.9669435025878246e-05,
"loss": 2.1093,
"step": 99
},
{
"epoch": 0.17094017094017094,
"grad_norm": 0.5703125,
"learning_rate": 2.966104687029851e-05,
"loss": 2.325,
"step": 100
},
{
"epoch": 0.17264957264957265,
"grad_norm": 0.67578125,
"learning_rate": 2.9652554898882082e-05,
"loss": 2.0521,
"step": 101
},
{
"epoch": 0.17435897435897435,
"grad_norm": 0.58203125,
"learning_rate": 2.9643959175003137e-05,
"loss": 2.3031,
"step": 102
},
{
"epoch": 0.17606837606837608,
"grad_norm": 0.51953125,
"learning_rate": 2.963525976281013e-05,
"loss": 2.1553,
"step": 103
},
{
"epoch": 0.17777777777777778,
"grad_norm": 0.6015625,
"learning_rate": 2.9626456727225336e-05,
"loss": 2.1681,
"step": 104
},
{
"epoch": 0.1794871794871795,
"grad_norm": 0.56640625,
"learning_rate": 2.961755013394435e-05,
"loss": 2.2048,
"step": 105
},
{
"epoch": 0.1811965811965812,
"grad_norm": 0.5703125,
"learning_rate": 2.9608540049435603e-05,
"loss": 2.2213,
"step": 106
},
{
"epoch": 0.1829059829059829,
"grad_norm": 0.59375,
"learning_rate": 2.959942654093986e-05,
"loss": 2.1712,
"step": 107
},
{
"epoch": 0.18461538461538463,
"grad_norm": 0.63671875,
"learning_rate": 2.9590209676469725e-05,
"loss": 2.1191,
"step": 108
},
{
"epoch": 0.18632478632478633,
"grad_norm": 0.56640625,
"learning_rate": 2.958088952480913e-05,
"loss": 2.1237,
"step": 109
},
{
"epoch": 0.18803418803418803,
"grad_norm": 0.578125,
"learning_rate": 2.9571466155512816e-05,
"loss": 2.1009,
"step": 110
},
{
"epoch": 0.18974358974358974,
"grad_norm": 0.59375,
"learning_rate": 2.956193963890583e-05,
"loss": 2.1874,
"step": 111
},
{
"epoch": 0.19145299145299147,
"grad_norm": 0.56640625,
"learning_rate": 2.9552310046082996e-05,
"loss": 2.1853,
"step": 112
},
{
"epoch": 0.19316239316239317,
"grad_norm": 0.78515625,
"learning_rate": 2.954257744890835e-05,
"loss": 2.1964,
"step": 113
},
{
"epoch": 0.19487179487179487,
"grad_norm": 0.61328125,
"learning_rate": 2.9532741920014666e-05,
"loss": 2.1841,
"step": 114
},
{
"epoch": 0.19658119658119658,
"grad_norm": 0.5546875,
"learning_rate": 2.9522803532802863e-05,
"loss": 2.1514,
"step": 115
},
{
"epoch": 0.19829059829059828,
"grad_norm": 0.546875,
"learning_rate": 2.9512762361441473e-05,
"loss": 2.1976,
"step": 116
},
{
"epoch": 0.2,
"grad_norm": 0.61328125,
"learning_rate": 2.9502618480866093e-05,
"loss": 2.2175,
"step": 117
},
{
"epoch": 0.20170940170940171,
"grad_norm": 0.5390625,
"learning_rate": 2.9492371966778828e-05,
"loss": 2.3224,
"step": 118
},
{
"epoch": 0.20341880341880342,
"grad_norm": 0.6171875,
"learning_rate": 2.948202289564771e-05,
"loss": 2.0922,
"step": 119
},
{
"epoch": 0.20512820512820512,
"grad_norm": 0.5625,
"learning_rate": 2.947157134470614e-05,
"loss": 2.1286,
"step": 120
},
{
"epoch": 0.20512820512820512,
"eval_loss": 2.1840789318084717,
"eval_runtime": 153.5679,
"eval_samples_per_second": 1.667,
"eval_steps_per_second": 0.28,
"step": 120
},
{
"epoch": 0.20683760683760682,
"grad_norm": 0.58984375,
"learning_rate": 2.946101739195231e-05,
"loss": 2.3025,
"step": 121
},
{
"epoch": 0.20854700854700856,
"grad_norm": 0.578125,
"learning_rate": 2.945036111614863e-05,
"loss": 2.2483,
"step": 122
},
{
"epoch": 0.21025641025641026,
"grad_norm": 0.5625,
"learning_rate": 2.9439602596821103e-05,
"loss": 2.1793,
"step": 123
},
{
"epoch": 0.21196581196581196,
"grad_norm": 0.546875,
"learning_rate": 2.9428741914258788e-05,
"loss": 2.1217,
"step": 124
},
{
"epoch": 0.21367521367521367,
"grad_norm": 0.5625,
"learning_rate": 2.941777914951315e-05,
"loss": 2.2512,
"step": 125
},
{
"epoch": 0.2153846153846154,
"grad_norm": 0.58203125,
"learning_rate": 2.9406714384397493e-05,
"loss": 2.1602,
"step": 126
},
{
"epoch": 0.2170940170940171,
"grad_norm": 0.61328125,
"learning_rate": 2.9395547701486322e-05,
"loss": 2.1697,
"step": 127
},
{
"epoch": 0.2188034188034188,
"grad_norm": 0.6015625,
"learning_rate": 2.938427918411474e-05,
"loss": 2.1518,
"step": 128
},
{
"epoch": 0.2205128205128205,
"grad_norm": 0.59765625,
"learning_rate": 2.937290891637782e-05,
"loss": 2.1246,
"step": 129
},
{
"epoch": 0.2222222222222222,
"grad_norm": 0.5859375,
"learning_rate": 2.9361436983129985e-05,
"loss": 2.1706,
"step": 130
},
{
"epoch": 0.22393162393162394,
"grad_norm": 0.5859375,
"learning_rate": 2.934986346998438e-05,
"loss": 2.1758,
"step": 131
},
{
"epoch": 0.22564102564102564,
"grad_norm": 0.6328125,
"learning_rate": 2.933818846331221e-05,
"loss": 2.1348,
"step": 132
},
{
"epoch": 0.22735042735042735,
"grad_norm": 0.5859375,
"learning_rate": 2.9326412050242115e-05,
"loss": 2.133,
"step": 133
},
{
"epoch": 0.22905982905982905,
"grad_norm": 0.5703125,
"learning_rate": 2.9314534318659512e-05,
"loss": 2.1673,
"step": 134
},
{
"epoch": 0.23076923076923078,
"grad_norm": 0.62890625,
"learning_rate": 2.930255535720594e-05,
"loss": 2.1968,
"step": 135
},
{
"epoch": 0.23247863247863249,
"grad_norm": 0.55859375,
"learning_rate": 2.929047525527841e-05,
"loss": 2.1598,
"step": 136
},
{
"epoch": 0.2341880341880342,
"grad_norm": 0.578125,
"learning_rate": 2.927829410302871e-05,
"loss": 2.2926,
"step": 137
},
{
"epoch": 0.2358974358974359,
"grad_norm": 0.625,
"learning_rate": 2.926601199136277e-05,
"loss": 2.2654,
"step": 138
},
{
"epoch": 0.2376068376068376,
"grad_norm": 0.64453125,
"learning_rate": 2.9253629011939953e-05,
"loss": 2.1086,
"step": 139
},
{
"epoch": 0.23931623931623933,
"grad_norm": 0.6015625,
"learning_rate": 2.9241145257172376e-05,
"loss": 2.1793,
"step": 140
},
{
"epoch": 0.24102564102564103,
"grad_norm": 0.58203125,
"learning_rate": 2.9228560820224233e-05,
"loss": 2.1496,
"step": 141
},
{
"epoch": 0.24273504273504273,
"grad_norm": 0.5625,
"learning_rate": 2.9215875795011088e-05,
"loss": 2.1907,
"step": 142
},
{
"epoch": 0.24444444444444444,
"grad_norm": 0.5859375,
"learning_rate": 2.9203090276199183e-05,
"loss": 2.1389,
"step": 143
},
{
"epoch": 0.24615384615384617,
"grad_norm": 0.5625,
"learning_rate": 2.9190204359204736e-05,
"loss": 2.1267,
"step": 144
},
{
"epoch": 0.24786324786324787,
"grad_norm": 0.62109375,
"learning_rate": 2.9177218140193194e-05,
"loss": 2.2647,
"step": 145
},
{
"epoch": 0.24957264957264957,
"grad_norm": 0.63671875,
"learning_rate": 2.916413171607856e-05,
"loss": 2.1353,
"step": 146
},
{
"epoch": 0.2512820512820513,
"grad_norm": 0.5703125,
"learning_rate": 2.9150945184522657e-05,
"loss": 2.1386,
"step": 147
},
{
"epoch": 0.252991452991453,
"grad_norm": 0.6015625,
"learning_rate": 2.9137658643934374e-05,
"loss": 2.13,
"step": 148
},
{
"epoch": 0.2547008547008547,
"grad_norm": 0.546875,
"learning_rate": 2.9124272193468964e-05,
"loss": 2.2023,
"step": 149
},
{
"epoch": 0.2564102564102564,
"grad_norm": 0.73828125,
"learning_rate": 2.911078593302729e-05,
"loss": 2.1163,
"step": 150
},
{
"epoch": 0.2564102564102564,
"eval_loss": 2.1831252574920654,
"eval_runtime": 153.5476,
"eval_samples_per_second": 1.667,
"eval_steps_per_second": 0.28,
"step": 150
},
{
"epoch": 0.25811965811965815,
"grad_norm": 0.55859375,
"learning_rate": 2.9097199963255074e-05,
"loss": 2.1386,
"step": 151
},
{
"epoch": 0.25982905982905985,
"grad_norm": 0.65234375,
"learning_rate": 2.9083514385542162e-05,
"loss": 2.1316,
"step": 152
},
{
"epoch": 0.26153846153846155,
"grad_norm": 0.5703125,
"learning_rate": 2.9069729302021747e-05,
"loss": 2.2437,
"step": 153
},
{
"epoch": 0.26324786324786326,
"grad_norm": 0.62890625,
"learning_rate": 2.905584481556962e-05,
"loss": 2.1822,
"step": 154
},
{
"epoch": 0.26495726495726496,
"grad_norm": 0.64453125,
"learning_rate": 2.9041861029803407e-05,
"loss": 2.2614,
"step": 155
},
{
"epoch": 0.26666666666666666,
"grad_norm": 0.55859375,
"learning_rate": 2.9027778049081785e-05,
"loss": 2.2387,
"step": 156
},
{
"epoch": 0.26837606837606837,
"grad_norm": 0.60546875,
"learning_rate": 2.9013595978503695e-05,
"loss": 2.124,
"step": 157
},
{
"epoch": 0.27008547008547007,
"grad_norm": 0.5703125,
"learning_rate": 2.8999314923907584e-05,
"loss": 2.0662,
"step": 158
},
{
"epoch": 0.2717948717948718,
"grad_norm": 0.62109375,
"learning_rate": 2.8984934991870598e-05,
"loss": 2.1483,
"step": 159
},
{
"epoch": 0.27350427350427353,
"grad_norm": 0.56640625,
"learning_rate": 2.8970456289707778e-05,
"loss": 2.1428,
"step": 160
},
{
"epoch": 0.27521367521367524,
"grad_norm": 0.578125,
"learning_rate": 2.895587892547129e-05,
"loss": 2.1845,
"step": 161
},
{
"epoch": 0.27692307692307694,
"grad_norm": 0.65625,
"learning_rate": 2.8941203007949575e-05,
"loss": 1.8986,
"step": 162
},
{
"epoch": 0.27863247863247864,
"grad_norm": 0.59375,
"learning_rate": 2.8926428646666576e-05,
"loss": 2.1513,
"step": 163
},
{
"epoch": 0.28034188034188035,
"grad_norm": 0.5703125,
"learning_rate": 2.891155595188091e-05,
"loss": 2.1334,
"step": 164
},
{
"epoch": 0.28205128205128205,
"grad_norm": 0.66796875,
"learning_rate": 2.8896585034585022e-05,
"loss": 2.08,
"step": 165
},
{
"epoch": 0.28376068376068375,
"grad_norm": 0.60546875,
"learning_rate": 2.8881516006504388e-05,
"loss": 2.0936,
"step": 166
},
{
"epoch": 0.28547008547008546,
"grad_norm": 0.609375,
"learning_rate": 2.886634898009668e-05,
"loss": 2.1244,
"step": 167
},
{
"epoch": 0.28717948717948716,
"grad_norm": 0.55859375,
"learning_rate": 2.885108406855088e-05,
"loss": 2.1053,
"step": 168
},
{
"epoch": 0.28888888888888886,
"grad_norm": 0.61328125,
"learning_rate": 2.8835721385786506e-05,
"loss": 2.067,
"step": 169
},
{
"epoch": 0.2905982905982906,
"grad_norm": 0.609375,
"learning_rate": 2.882026104645271e-05,
"loss": 2.1022,
"step": 170
},
{
"epoch": 0.2923076923076923,
"grad_norm": 0.59765625,
"learning_rate": 2.8804703165927433e-05,
"loss": 2.1366,
"step": 171
},
{
"epoch": 0.294017094017094,
"grad_norm": 0.60546875,
"learning_rate": 2.878904786031658e-05,
"loss": 1.9787,
"step": 172
},
{
"epoch": 0.29572649572649573,
"grad_norm": 0.5859375,
"learning_rate": 2.877329524645308e-05,
"loss": 2.1275,
"step": 173
},
{
"epoch": 0.29743589743589743,
"grad_norm": 0.64453125,
"learning_rate": 2.8757445441896086e-05,
"loss": 2.0948,
"step": 174
},
{
"epoch": 0.29914529914529914,
"grad_norm": 0.58984375,
"learning_rate": 2.8741498564930065e-05,
"loss": 2.0375,
"step": 175
},
{
"epoch": 0.30085470085470084,
"grad_norm": 0.5859375,
"learning_rate": 2.8725454734563908e-05,
"loss": 2.0992,
"step": 176
},
{
"epoch": 0.30256410256410254,
"grad_norm": 0.58984375,
"learning_rate": 2.8709314070530077e-05,
"loss": 2.0009,
"step": 177
},
{
"epoch": 0.30427350427350425,
"grad_norm": 0.69921875,
"learning_rate": 2.8693076693283656e-05,
"loss": 2.0853,
"step": 178
},
{
"epoch": 0.305982905982906,
"grad_norm": 0.60546875,
"learning_rate": 2.8676742724001504e-05,
"loss": 2.1654,
"step": 179
},
{
"epoch": 0.3076923076923077,
"grad_norm": 0.5703125,
"learning_rate": 2.8660312284581332e-05,
"loss": 2.0999,
"step": 180
},
{
"epoch": 0.3076923076923077,
"eval_loss": 2.1848390102386475,
"eval_runtime": 153.653,
"eval_samples_per_second": 1.666,
"eval_steps_per_second": 0.28,
"step": 180
},
{
"epoch": 0.3094017094017094,
"grad_norm": 0.67578125,
"learning_rate": 2.8643785497640778e-05,
"loss": 2.0686,
"step": 181
},
{
"epoch": 0.3111111111111111,
"grad_norm": 0.6328125,
"learning_rate": 2.8627162486516516e-05,
"loss": 2.1621,
"step": 182
},
{
"epoch": 0.3128205128205128,
"grad_norm": 0.63671875,
"learning_rate": 2.8610443375263328e-05,
"loss": 2.2083,
"step": 183
},
{
"epoch": 0.3145299145299145,
"grad_norm": 0.62109375,
"learning_rate": 2.8593628288653162e-05,
"loss": 2.1462,
"step": 184
},
{
"epoch": 0.3162393162393162,
"grad_norm": 0.58203125,
"learning_rate": 2.857671735217423e-05,
"loss": 2.0359,
"step": 185
},
{
"epoch": 0.31794871794871793,
"grad_norm": 0.59375,
"learning_rate": 2.8559710692030032e-05,
"loss": 2.06,
"step": 186
},
{
"epoch": 0.31965811965811963,
"grad_norm": 0.65625,
"learning_rate": 2.8542608435138472e-05,
"loss": 2.0161,
"step": 187
},
{
"epoch": 0.3213675213675214,
"grad_norm": 0.59375,
"learning_rate": 2.8525410709130844e-05,
"loss": 2.0891,
"step": 188
},
{
"epoch": 0.3230769230769231,
"grad_norm": 0.6328125,
"learning_rate": 2.8508117642350934e-05,
"loss": 2.161,
"step": 189
},
{
"epoch": 0.3247863247863248,
"grad_norm": 4.71875,
"learning_rate": 2.849072936385403e-05,
"loss": 2.114,
"step": 190
},
{
"epoch": 0.3264957264957265,
"grad_norm": 0.625,
"learning_rate": 2.8473246003405977e-05,
"loss": 2.0737,
"step": 191
},
{
"epoch": 0.3282051282051282,
"grad_norm": 0.7421875,
"learning_rate": 2.8455667691482186e-05,
"loss": 2.1467,
"step": 192
},
{
"epoch": 0.3299145299145299,
"grad_norm": 0.66796875,
"learning_rate": 2.8437994559266685e-05,
"loss": 2.3981,
"step": 193
},
{
"epoch": 0.3316239316239316,
"grad_norm": 0.6796875,
"learning_rate": 2.8420226738651142e-05,
"loss": 2.1642,
"step": 194
},
{
"epoch": 0.3333333333333333,
"grad_norm": 0.60546875,
"learning_rate": 2.8402364362233846e-05,
"loss": 2.0835,
"step": 195
},
{
"epoch": 0.335042735042735,
"grad_norm": 0.6484375,
"learning_rate": 2.8384407563318758e-05,
"loss": 2.1733,
"step": 196
},
{
"epoch": 0.3367521367521368,
"grad_norm": 0.6484375,
"learning_rate": 2.8366356475914487e-05,
"loss": 2.1804,
"step": 197
},
{
"epoch": 0.3384615384615385,
"grad_norm": 0.5703125,
"learning_rate": 2.834821123473331e-05,
"loss": 2.0218,
"step": 198
},
{
"epoch": 0.3401709401709402,
"grad_norm": 0.65234375,
"learning_rate": 2.8329971975190146e-05,
"loss": 2.137,
"step": 199
},
{
"epoch": 0.3418803418803419,
"grad_norm": 0.640625,
"learning_rate": 2.831163883340157e-05,
"loss": 2.1711,
"step": 200
},
{
"epoch": 0.3435897435897436,
"grad_norm": 0.5859375,
"learning_rate": 2.8293211946184787e-05,
"loss": 2.2119,
"step": 201
},
{
"epoch": 0.3452991452991453,
"grad_norm": 0.59375,
"learning_rate": 2.827469145105659e-05,
"loss": 2.1208,
"step": 202
},
{
"epoch": 0.347008547008547,
"grad_norm": 0.60546875,
"learning_rate": 2.8256077486232368e-05,
"loss": 2.1377,
"step": 203
},
{
"epoch": 0.3487179487179487,
"grad_norm": 0.56640625,
"learning_rate": 2.8237370190625056e-05,
"loss": 2.0869,
"step": 204
},
{
"epoch": 0.3504273504273504,
"grad_norm": 0.62109375,
"learning_rate": 2.8218569703844104e-05,
"loss": 2.066,
"step": 205
},
{
"epoch": 0.35213675213675216,
"grad_norm": 0.5859375,
"learning_rate": 2.819967616619442e-05,
"loss": 2.1472,
"step": 206
},
{
"epoch": 0.35384615384615387,
"grad_norm": 0.71484375,
"learning_rate": 2.818068971867535e-05,
"loss": 2.3903,
"step": 207
},
{
"epoch": 0.35555555555555557,
"grad_norm": 0.63671875,
"learning_rate": 2.8161610502979598e-05,
"loss": 2.154,
"step": 208
},
{
"epoch": 0.3572649572649573,
"grad_norm": 0.66015625,
"learning_rate": 2.8142438661492194e-05,
"loss": 2.143,
"step": 209
},
{
"epoch": 0.358974358974359,
"grad_norm": 0.59765625,
"learning_rate": 2.8123174337289405e-05,
"loss": 2.0984,
"step": 210
},
{
"epoch": 0.358974358974359,
"eval_loss": 2.177856683731079,
"eval_runtime": 153.5529,
"eval_samples_per_second": 1.667,
"eval_steps_per_second": 0.28,
"step": 210
},
{
"epoch": 0.3606837606837607,
"grad_norm": 0.5703125,
"learning_rate": 2.8103817674137697e-05,
"loss": 2.0901,
"step": 211
},
{
"epoch": 0.3623931623931624,
"grad_norm": 0.58984375,
"learning_rate": 2.8084368816492643e-05,
"loss": 2.1651,
"step": 212
},
{
"epoch": 0.3641025641025641,
"grad_norm": 0.6640625,
"learning_rate": 2.8064827909497826e-05,
"loss": 2.0036,
"step": 213
},
{
"epoch": 0.3658119658119658,
"grad_norm": 0.65234375,
"learning_rate": 2.8045195098983813e-05,
"loss": 2.0947,
"step": 214
},
{
"epoch": 0.36752136752136755,
"grad_norm": 0.59765625,
"learning_rate": 2.8025470531467e-05,
"loss": 2.124,
"step": 215
},
{
"epoch": 0.36923076923076925,
"grad_norm": 0.58984375,
"learning_rate": 2.8005654354148578e-05,
"loss": 2.0957,
"step": 216
},
{
"epoch": 0.37094017094017095,
"grad_norm": 0.6484375,
"learning_rate": 2.7985746714913383e-05,
"loss": 2.1268,
"step": 217
},
{
"epoch": 0.37264957264957266,
"grad_norm": 0.64453125,
"learning_rate": 2.796574776232883e-05,
"loss": 2.1524,
"step": 218
},
{
"epoch": 0.37435897435897436,
"grad_norm": 0.6015625,
"learning_rate": 2.7945657645643788e-05,
"loss": 2.0742,
"step": 219
},
{
"epoch": 0.37606837606837606,
"grad_norm": 0.60546875,
"learning_rate": 2.7925476514787462e-05,
"loss": 2.0809,
"step": 220
},
{
"epoch": 0.37777777777777777,
"grad_norm": 0.66015625,
"learning_rate": 2.7905204520368297e-05,
"loss": 2.0084,
"step": 221
},
{
"epoch": 0.37948717948717947,
"grad_norm": 0.68359375,
"learning_rate": 2.7884841813672812e-05,
"loss": 2.1647,
"step": 222
},
{
"epoch": 0.3811965811965812,
"grad_norm": 0.6328125,
"learning_rate": 2.7864388546664528e-05,
"loss": 2.101,
"step": 223
},
{
"epoch": 0.38290598290598293,
"grad_norm": 0.5859375,
"learning_rate": 2.7843844871982773e-05,
"loss": 2.2433,
"step": 224
},
{
"epoch": 0.38461538461538464,
"grad_norm": 0.62890625,
"learning_rate": 2.7823210942941592e-05,
"loss": 2.3129,
"step": 225
},
{
"epoch": 0.38632478632478634,
"grad_norm": 0.59375,
"learning_rate": 2.7802486913528573e-05,
"loss": 2.069,
"step": 226
},
{
"epoch": 0.38803418803418804,
"grad_norm": 0.6015625,
"learning_rate": 2.7781672938403715e-05,
"loss": 2.1515,
"step": 227
},
{
"epoch": 0.38974358974358975,
"grad_norm": 0.63671875,
"learning_rate": 2.776076917289826e-05,
"loss": 2.1224,
"step": 228
},
{
"epoch": 0.39145299145299145,
"grad_norm": 0.671875,
"learning_rate": 2.7739775773013553e-05,
"loss": 2.0911,
"step": 229
},
{
"epoch": 0.39316239316239315,
"grad_norm": 0.58984375,
"learning_rate": 2.771869289541985e-05,
"loss": 2.03,
"step": 230
},
{
"epoch": 0.39487179487179486,
"grad_norm": 0.6640625,
"learning_rate": 2.7697520697455174e-05,
"loss": 2.1555,
"step": 231
},
{
"epoch": 0.39658119658119656,
"grad_norm": 0.87890625,
"learning_rate": 2.7676259337124127e-05,
"loss": 2.1044,
"step": 232
},
{
"epoch": 0.39829059829059826,
"grad_norm": 0.65234375,
"learning_rate": 2.765490897309672e-05,
"loss": 2.0823,
"step": 233
},
{
"epoch": 0.4,
"grad_norm": 0.6484375,
"learning_rate": 2.7633469764707173e-05,
"loss": 2.22,
"step": 234
},
{
"epoch": 0.4017094017094017,
"grad_norm": 0.6171875,
"learning_rate": 2.761194187195275e-05,
"loss": 2.1114,
"step": 235
},
{
"epoch": 0.40341880341880343,
"grad_norm": 0.63671875,
"learning_rate": 2.7590325455492544e-05,
"loss": 2.1627,
"step": 236
},
{
"epoch": 0.40512820512820513,
"grad_norm": 0.6328125,
"learning_rate": 2.756862067664629e-05,
"loss": 2.0677,
"step": 237
},
{
"epoch": 0.40683760683760684,
"grad_norm": 0.6328125,
"learning_rate": 2.754682769739315e-05,
"loss": 2.2179,
"step": 238
},
{
"epoch": 0.40854700854700854,
"grad_norm": 0.59375,
"learning_rate": 2.7524946680370525e-05,
"loss": 2.1264,
"step": 239
},
{
"epoch": 0.41025641025641024,
"grad_norm": 0.62890625,
"learning_rate": 2.7502977788872803e-05,
"loss": 2.0791,
"step": 240
},
{
"epoch": 0.41025641025641024,
"eval_loss": 2.1732006072998047,
"eval_runtime": 153.5496,
"eval_samples_per_second": 1.667,
"eval_steps_per_second": 0.28,
"step": 240
},
{
"epoch": 0.41196581196581195,
"grad_norm": 0.609375,
"learning_rate": 2.748092118685019e-05,
"loss": 2.1464,
"step": 241
},
{
"epoch": 0.41367521367521365,
"grad_norm": 0.69140625,
"learning_rate": 2.7458777038907448e-05,
"loss": 2.1003,
"step": 242
},
{
"epoch": 0.4153846153846154,
"grad_norm": 0.64453125,
"learning_rate": 2.7436545510302684e-05,
"loss": 2.1369,
"step": 243
},
{
"epoch": 0.4170940170940171,
"grad_norm": 0.65625,
"learning_rate": 2.7414226766946108e-05,
"loss": 2.1722,
"step": 244
},
{
"epoch": 0.4188034188034188,
"grad_norm": 0.58203125,
"learning_rate": 2.7391820975398797e-05,
"loss": 2.0298,
"step": 245
},
{
"epoch": 0.4205128205128205,
"grad_norm": 0.66796875,
"learning_rate": 2.7369328302871473e-05,
"loss": 2.2088,
"step": 246
},
{
"epoch": 0.4222222222222222,
"grad_norm": 0.640625,
"learning_rate": 2.7346748917223208e-05,
"loss": 1.8934,
"step": 247
},
{
"epoch": 0.4239316239316239,
"grad_norm": 0.72265625,
"learning_rate": 2.732408298696022e-05,
"loss": 2.0064,
"step": 248
},
{
"epoch": 0.4256410256410256,
"grad_norm": 0.625,
"learning_rate": 2.730133068123459e-05,
"loss": 2.3159,
"step": 249
},
{
"epoch": 0.42735042735042733,
"grad_norm": 0.6328125,
"learning_rate": 2.7278492169843002e-05,
"loss": 2.091,
"step": 250
},
{
"epoch": 0.42905982905982903,
"grad_norm": 0.625,
"learning_rate": 2.7255567623225484e-05,
"loss": 2.1577,
"step": 251
},
{
"epoch": 0.4307692307692308,
"grad_norm": 0.66015625,
"learning_rate": 2.723255721246412e-05,
"loss": 2.185,
"step": 252
},
{
"epoch": 0.4324786324786325,
"grad_norm": 0.66015625,
"learning_rate": 2.72094611092818e-05,
"loss": 2.1338,
"step": 253
},
{
"epoch": 0.4341880341880342,
"grad_norm": 0.62890625,
"learning_rate": 2.7186279486040902e-05,
"loss": 2.058,
"step": 254
},
{
"epoch": 0.4358974358974359,
"grad_norm": 0.62109375,
"learning_rate": 2.7163012515742044e-05,
"loss": 2.0945,
"step": 255
},
{
"epoch": 0.4376068376068376,
"grad_norm": 0.6015625,
"learning_rate": 2.713966037202277e-05,
"loss": 2.0251,
"step": 256
},
{
"epoch": 0.4393162393162393,
"grad_norm": 0.66015625,
"learning_rate": 2.711622322915626e-05,
"loss": 2.1224,
"step": 257
},
{
"epoch": 0.441025641025641,
"grad_norm": 0.6015625,
"learning_rate": 2.7092701262050017e-05,
"loss": 2.1081,
"step": 258
},
{
"epoch": 0.4427350427350427,
"grad_norm": 0.609375,
"learning_rate": 2.706909464624459e-05,
"loss": 2.2308,
"step": 259
},
{
"epoch": 0.4444444444444444,
"grad_norm": 0.67578125,
"learning_rate": 2.7045403557912232e-05,
"loss": 2.1526,
"step": 260
},
{
"epoch": 0.4461538461538462,
"grad_norm": 0.62109375,
"learning_rate": 2.7021628173855615e-05,
"loss": 2.0584,
"step": 261
},
{
"epoch": 0.4478632478632479,
"grad_norm": 0.69921875,
"learning_rate": 2.699776867150648e-05,
"loss": 2.2188,
"step": 262
},
{
"epoch": 0.4495726495726496,
"grad_norm": 0.671875,
"learning_rate": 2.697382522892435e-05,
"loss": 2.2346,
"step": 263
},
{
"epoch": 0.4512820512820513,
"grad_norm": 0.625,
"learning_rate": 2.6949798024795157e-05,
"loss": 2.1916,
"step": 264
},
{
"epoch": 0.452991452991453,
"grad_norm": 3.375,
"learning_rate": 2.6925687238429946e-05,
"loss": 2.068,
"step": 265
},
{
"epoch": 0.4547008547008547,
"grad_norm": 0.6640625,
"learning_rate": 2.690149304976352e-05,
"loss": 2.3094,
"step": 266
},
{
"epoch": 0.4564102564102564,
"grad_norm": 0.69140625,
"learning_rate": 2.68772156393531e-05,
"loss": 2.138,
"step": 267
},
{
"epoch": 0.4581196581196581,
"grad_norm": 0.63671875,
"learning_rate": 2.685285518837697e-05,
"loss": 2.0336,
"step": 268
},
{
"epoch": 0.4598290598290598,
"grad_norm": 0.65234375,
"learning_rate": 2.6828411878633143e-05,
"loss": 2.1164,
"step": 269
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.6484375,
"learning_rate": 2.6803885892537985e-05,
"loss": 2.1127,
"step": 270
},
{
"epoch": 0.46153846153846156,
"eval_loss": 2.1717300415039062,
"eval_runtime": 153.5734,
"eval_samples_per_second": 1.667,
"eval_steps_per_second": 0.28,
"step": 270
},
{
"epoch": 0.46324786324786327,
"grad_norm": 0.8984375,
"learning_rate": 2.677927741312486e-05,
"loss": 2.1996,
"step": 271
},
{
"epoch": 0.46495726495726497,
"grad_norm": 0.62109375,
"learning_rate": 2.6754586624042777e-05,
"loss": 2.0878,
"step": 272
},
{
"epoch": 0.4666666666666667,
"grad_norm": 0.60546875,
"learning_rate": 2.6729813709555e-05,
"loss": 2.165,
"step": 273
},
{
"epoch": 0.4683760683760684,
"grad_norm": 0.65234375,
"learning_rate": 2.6704958854537677e-05,
"loss": 2.0755,
"step": 274
},
{
"epoch": 0.4700854700854701,
"grad_norm": 0.73828125,
"learning_rate": 2.6680022244478478e-05,
"loss": 2.1522,
"step": 275
},
{
"epoch": 0.4717948717948718,
"grad_norm": 0.65625,
"learning_rate": 2.6655004065475192e-05,
"loss": 2.0565,
"step": 276
},
{
"epoch": 0.4735042735042735,
"grad_norm": 0.9765625,
"learning_rate": 2.6629904504234338e-05,
"loss": 2.0979,
"step": 277
},
{
"epoch": 0.4752136752136752,
"grad_norm": 0.61328125,
"learning_rate": 2.6604723748069774e-05,
"loss": 2.056,
"step": 278
},
{
"epoch": 0.47692307692307695,
"grad_norm": 0.7109375,
"learning_rate": 2.657946198490132e-05,
"loss": 2.087,
"step": 279
},
{
"epoch": 0.47863247863247865,
"grad_norm": 0.63671875,
"learning_rate": 2.655411940325332e-05,
"loss": 2.13,
"step": 280
},
{
"epoch": 0.48034188034188036,
"grad_norm": 0.703125,
"learning_rate": 2.652869619225326e-05,
"loss": 2.1566,
"step": 281
},
{
"epoch": 0.48205128205128206,
"grad_norm": 0.64453125,
"learning_rate": 2.6503192541630355e-05,
"loss": 2.1701,
"step": 282
},
{
"epoch": 0.48376068376068376,
"grad_norm": 0.93359375,
"learning_rate": 2.6477608641714113e-05,
"loss": 2.0952,
"step": 283
},
{
"epoch": 0.48547008547008547,
"grad_norm": 0.69140625,
"learning_rate": 2.645194468343295e-05,
"loss": 1.9035,
"step": 284
},
{
"epoch": 0.48717948717948717,
"grad_norm": 0.73828125,
"learning_rate": 2.6426200858312717e-05,
"loss": 2.0392,
"step": 285
},
{
"epoch": 0.4888888888888889,
"grad_norm": 0.74609375,
"learning_rate": 2.6400377358475323e-05,
"loss": 2.0303,
"step": 286
},
{
"epoch": 0.4905982905982906,
"grad_norm": 0.65625,
"learning_rate": 2.6374474376637264e-05,
"loss": 2.0651,
"step": 287
},
{
"epoch": 0.49230769230769234,
"grad_norm": 0.7265625,
"learning_rate": 2.63484921061082e-05,
"loss": 2.0559,
"step": 288
},
{
"epoch": 0.49401709401709404,
"grad_norm": 0.73046875,
"learning_rate": 2.6322430740789513e-05,
"loss": 2.0077,
"step": 289
},
{
"epoch": 0.49572649572649574,
"grad_norm": 0.69140625,
"learning_rate": 2.629629047517284e-05,
"loss": 2.1017,
"step": 290
},
{
"epoch": 0.49743589743589745,
"grad_norm": 0.78515625,
"learning_rate": 2.6270071504338662e-05,
"loss": 2.1471,
"step": 291
},
{
"epoch": 0.49914529914529915,
"grad_norm": 0.625,
"learning_rate": 2.6243774023954807e-05,
"loss": 2.0882,
"step": 292
},
{
"epoch": 0.5008547008547009,
"grad_norm": 0.59375,
"learning_rate": 2.6217398230275006e-05,
"loss": 2.162,
"step": 293
}
],
"logging_steps": 1,
"max_steps": 1170,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 293,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.5504892596518912e+17,
"train_batch_size": 6,
"trial_name": null,
"trial_params": null
}