LLAMA-2-460m / trainer_state.json
ccore's picture
Upload folder using huggingface_hub
79579c4
raw
history blame
25.1 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9995995194233079,
"eval_steps": 500,
"global_step": 234,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0001,
"loss": 2.3832,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 5.648,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 4.5146,
"step": 3
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 3.6589,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 3.2564,
"step": 5
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 3.0312,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 2.8748,
"step": 7
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 2.8477,
"step": 8
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 2.7413,
"step": 9
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 2.7057,
"step": 10
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 2.7216,
"step": 11
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 2.6576,
"step": 12
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 2.6287,
"step": 13
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 2.572,
"step": 14
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 2.5913,
"step": 15
},
{
"epoch": 0.07,
"learning_rate": 0.0001,
"loss": 2.536,
"step": 16
},
{
"epoch": 0.07,
"learning_rate": 0.0001,
"loss": 2.5511,
"step": 17
},
{
"epoch": 0.08,
"learning_rate": 0.0001,
"loss": 2.4853,
"step": 18
},
{
"epoch": 0.08,
"learning_rate": 0.0001,
"loss": 2.5668,
"step": 19
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 2.535,
"step": 20
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 2.5287,
"step": 21
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 2.5263,
"step": 22
},
{
"epoch": 0.1,
"learning_rate": 0.0001,
"loss": 2.5046,
"step": 23
},
{
"epoch": 0.1,
"learning_rate": 0.0001,
"loss": 2.4366,
"step": 24
},
{
"epoch": 0.11,
"learning_rate": 0.0001,
"loss": 2.4488,
"step": 25
},
{
"epoch": 0.11,
"learning_rate": 0.0001,
"loss": 2.4638,
"step": 26
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 2.4546,
"step": 27
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 2.4169,
"step": 28
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 2.4739,
"step": 29
},
{
"epoch": 0.13,
"learning_rate": 0.0001,
"loss": 2.4074,
"step": 30
},
{
"epoch": 0.13,
"learning_rate": 0.0001,
"loss": 2.4314,
"step": 31
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 2.3819,
"step": 32
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 2.3524,
"step": 33
},
{
"epoch": 0.15,
"learning_rate": 0.0001,
"loss": 2.3943,
"step": 34
},
{
"epoch": 0.15,
"learning_rate": 0.0001,
"loss": 2.4447,
"step": 35
},
{
"epoch": 0.15,
"learning_rate": 0.0001,
"loss": 2.4112,
"step": 36
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 2.3453,
"step": 37
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 2.4186,
"step": 38
},
{
"epoch": 0.17,
"learning_rate": 0.0001,
"loss": 2.3761,
"step": 39
},
{
"epoch": 0.17,
"learning_rate": 0.0001,
"loss": 2.3486,
"step": 40
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 2.4314,
"step": 41
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 2.4059,
"step": 42
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 2.3649,
"step": 43
},
{
"epoch": 0.19,
"learning_rate": 0.0001,
"loss": 2.3544,
"step": 44
},
{
"epoch": 0.19,
"learning_rate": 0.0001,
"loss": 2.3959,
"step": 45
},
{
"epoch": 0.2,
"learning_rate": 0.0001,
"loss": 2.3734,
"step": 46
},
{
"epoch": 0.2,
"learning_rate": 0.0001,
"loss": 2.374,
"step": 47
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 2.3748,
"step": 48
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 2.4016,
"step": 49
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 2.3388,
"step": 50
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 2.3851,
"step": 51
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 2.4123,
"step": 52
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 2.3594,
"step": 53
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 2.3476,
"step": 54
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 2.3593,
"step": 55
},
{
"epoch": 0.24,
"learning_rate": 0.0001,
"loss": 2.3253,
"step": 56
},
{
"epoch": 0.24,
"learning_rate": 0.0001,
"loss": 2.3574,
"step": 57
},
{
"epoch": 0.25,
"learning_rate": 0.0001,
"loss": 2.3721,
"step": 58
},
{
"epoch": 0.25,
"learning_rate": 0.0001,
"loss": 2.3438,
"step": 59
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 2.3575,
"step": 60
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 2.2803,
"step": 61
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 2.3088,
"step": 62
},
{
"epoch": 0.27,
"learning_rate": 0.0001,
"loss": 2.3436,
"step": 63
},
{
"epoch": 0.27,
"learning_rate": 0.0001,
"loss": 2.3629,
"step": 64
},
{
"epoch": 0.28,
"learning_rate": 0.0001,
"loss": 2.3294,
"step": 65
},
{
"epoch": 0.28,
"learning_rate": 0.0001,
"loss": 2.3402,
"step": 66
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 2.3273,
"step": 67
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 2.3335,
"step": 68
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 2.3013,
"step": 69
},
{
"epoch": 0.3,
"learning_rate": 0.0001,
"loss": 2.3396,
"step": 70
},
{
"epoch": 0.3,
"learning_rate": 0.0001,
"loss": 2.327,
"step": 71
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 2.3231,
"step": 72
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 2.3247,
"step": 73
},
{
"epoch": 0.32,
"learning_rate": 0.0001,
"loss": 2.3163,
"step": 74
},
{
"epoch": 0.32,
"learning_rate": 0.0001,
"loss": 2.3301,
"step": 75
},
{
"epoch": 0.32,
"learning_rate": 0.0001,
"loss": 2.3598,
"step": 76
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 2.3115,
"step": 77
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 2.3015,
"step": 78
},
{
"epoch": 0.34,
"learning_rate": 0.0001,
"loss": 2.294,
"step": 79
},
{
"epoch": 0.34,
"learning_rate": 0.0001,
"loss": 2.2731,
"step": 80
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 2.3138,
"step": 81
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 2.3096,
"step": 82
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 2.3133,
"step": 83
},
{
"epoch": 0.36,
"learning_rate": 0.0001,
"loss": 2.2679,
"step": 84
},
{
"epoch": 0.36,
"learning_rate": 0.0001,
"loss": 2.2657,
"step": 85
},
{
"epoch": 0.37,
"learning_rate": 0.0001,
"loss": 2.2958,
"step": 86
},
{
"epoch": 0.37,
"learning_rate": 0.0001,
"loss": 2.297,
"step": 87
},
{
"epoch": 0.38,
"learning_rate": 0.0001,
"loss": 2.2701,
"step": 88
},
{
"epoch": 0.38,
"learning_rate": 0.0001,
"loss": 2.2889,
"step": 89
},
{
"epoch": 0.38,
"learning_rate": 0.0001,
"loss": 2.2585,
"step": 90
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 2.2611,
"step": 91
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 2.2815,
"step": 92
},
{
"epoch": 0.4,
"learning_rate": 0.0001,
"loss": 2.2778,
"step": 93
},
{
"epoch": 0.4,
"learning_rate": 0.0001,
"loss": 2.2803,
"step": 94
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 2.3007,
"step": 95
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 2.3045,
"step": 96
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 2.2858,
"step": 97
},
{
"epoch": 0.42,
"learning_rate": 0.0001,
"loss": 2.2669,
"step": 98
},
{
"epoch": 0.42,
"learning_rate": 0.0001,
"loss": 2.2731,
"step": 99
},
{
"epoch": 0.43,
"learning_rate": 0.0001,
"loss": 2.2707,
"step": 100
},
{
"epoch": 0.43,
"learning_rate": 0.0001,
"loss": 2.2189,
"step": 101
},
{
"epoch": 0.44,
"learning_rate": 0.0001,
"loss": 2.2506,
"step": 102
},
{
"epoch": 0.44,
"learning_rate": 0.0001,
"loss": 2.3119,
"step": 103
},
{
"epoch": 0.44,
"learning_rate": 0.0001,
"loss": 2.2332,
"step": 104
},
{
"epoch": 0.45,
"learning_rate": 0.0001,
"loss": 2.2583,
"step": 105
},
{
"epoch": 0.45,
"learning_rate": 0.0001,
"loss": 2.2416,
"step": 106
},
{
"epoch": 0.46,
"learning_rate": 0.0001,
"loss": 2.3025,
"step": 107
},
{
"epoch": 0.46,
"learning_rate": 0.0001,
"loss": 2.2889,
"step": 108
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 2.2486,
"step": 109
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 2.2369,
"step": 110
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 2.2634,
"step": 111
},
{
"epoch": 0.48,
"learning_rate": 0.0001,
"loss": 2.2911,
"step": 112
},
{
"epoch": 0.48,
"learning_rate": 0.0001,
"loss": 2.3223,
"step": 113
},
{
"epoch": 0.49,
"learning_rate": 0.0001,
"loss": 2.2623,
"step": 114
},
{
"epoch": 0.49,
"learning_rate": 0.0001,
"loss": 2.2075,
"step": 115
},
{
"epoch": 0.5,
"learning_rate": 0.0001,
"loss": 2.2681,
"step": 116
},
{
"epoch": 0.5,
"learning_rate": 0.0001,
"loss": 2.2436,
"step": 117
},
{
"epoch": 0.5,
"learning_rate": 0.0001,
"loss": 2.2396,
"step": 118
},
{
"epoch": 0.51,
"learning_rate": 0.0001,
"loss": 2.2725,
"step": 119
},
{
"epoch": 0.51,
"learning_rate": 0.0001,
"loss": 2.2974,
"step": 120
},
{
"epoch": 0.52,
"learning_rate": 0.0001,
"loss": 2.266,
"step": 121
},
{
"epoch": 0.52,
"learning_rate": 0.0001,
"loss": 2.258,
"step": 122
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 2.2597,
"step": 123
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 2.234,
"step": 124
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 2.2263,
"step": 125
},
{
"epoch": 0.54,
"learning_rate": 0.0001,
"loss": 2.2325,
"step": 126
},
{
"epoch": 0.54,
"learning_rate": 0.0001,
"loss": 2.2024,
"step": 127
},
{
"epoch": 0.55,
"learning_rate": 0.0001,
"loss": 2.2732,
"step": 128
},
{
"epoch": 0.55,
"learning_rate": 0.0001,
"loss": 2.2422,
"step": 129
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 2.2325,
"step": 130
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 2.2492,
"step": 131
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 2.2055,
"step": 132
},
{
"epoch": 0.57,
"learning_rate": 0.0001,
"loss": 2.2735,
"step": 133
},
{
"epoch": 0.57,
"learning_rate": 0.0001,
"loss": 2.202,
"step": 134
},
{
"epoch": 0.58,
"learning_rate": 0.0001,
"loss": 2.195,
"step": 135
},
{
"epoch": 0.58,
"learning_rate": 0.0001,
"loss": 2.1999,
"step": 136
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 2.2033,
"step": 137
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 2.1748,
"step": 138
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 2.2025,
"step": 139
},
{
"epoch": 0.6,
"learning_rate": 0.0001,
"loss": 2.1967,
"step": 140
},
{
"epoch": 0.6,
"learning_rate": 0.0001,
"loss": 2.1796,
"step": 141
},
{
"epoch": 0.61,
"learning_rate": 0.0001,
"loss": 2.1929,
"step": 142
},
{
"epoch": 0.61,
"learning_rate": 0.0001,
"loss": 2.2138,
"step": 143
},
{
"epoch": 0.62,
"learning_rate": 0.0001,
"loss": 2.2058,
"step": 144
},
{
"epoch": 0.62,
"learning_rate": 0.0001,
"loss": 2.2046,
"step": 145
},
{
"epoch": 0.62,
"learning_rate": 0.0001,
"loss": 2.2204,
"step": 146
},
{
"epoch": 0.63,
"learning_rate": 0.0001,
"loss": 2.2028,
"step": 147
},
{
"epoch": 0.63,
"learning_rate": 0.0001,
"loss": 2.2634,
"step": 148
},
{
"epoch": 0.64,
"learning_rate": 0.0001,
"loss": 2.2382,
"step": 149
},
{
"epoch": 0.64,
"learning_rate": 0.0001,
"loss": 2.1955,
"step": 150
},
{
"epoch": 0.65,
"learning_rate": 0.0001,
"loss": 2.1918,
"step": 151
},
{
"epoch": 0.65,
"learning_rate": 0.0001,
"loss": 2.2177,
"step": 152
},
{
"epoch": 0.65,
"learning_rate": 0.0001,
"loss": 2.189,
"step": 153
},
{
"epoch": 0.66,
"learning_rate": 0.0001,
"loss": 2.1829,
"step": 154
},
{
"epoch": 0.66,
"learning_rate": 0.0001,
"loss": 2.2272,
"step": 155
},
{
"epoch": 0.67,
"learning_rate": 0.0001,
"loss": 2.1924,
"step": 156
},
{
"epoch": 0.67,
"learning_rate": 0.0001,
"loss": 2.1877,
"step": 157
},
{
"epoch": 0.67,
"learning_rate": 0.0001,
"loss": 2.1772,
"step": 158
},
{
"epoch": 0.68,
"learning_rate": 0.0001,
"loss": 2.1338,
"step": 159
},
{
"epoch": 0.68,
"learning_rate": 0.0001,
"loss": 2.1817,
"step": 160
},
{
"epoch": 0.69,
"learning_rate": 0.0001,
"loss": 2.211,
"step": 161
},
{
"epoch": 0.69,
"learning_rate": 0.0001,
"loss": 2.1922,
"step": 162
},
{
"epoch": 0.7,
"learning_rate": 0.0001,
"loss": 2.162,
"step": 163
},
{
"epoch": 0.7,
"learning_rate": 0.0001,
"loss": 2.1906,
"step": 164
},
{
"epoch": 0.7,
"learning_rate": 0.0001,
"loss": 2.1931,
"step": 165
},
{
"epoch": 0.71,
"learning_rate": 0.0001,
"loss": 2.1611,
"step": 166
},
{
"epoch": 0.71,
"learning_rate": 0.0001,
"loss": 2.1913,
"step": 167
},
{
"epoch": 0.72,
"learning_rate": 0.0001,
"loss": 2.2342,
"step": 168
},
{
"epoch": 0.72,
"learning_rate": 0.0001,
"loss": 2.1753,
"step": 169
},
{
"epoch": 0.73,
"learning_rate": 0.0001,
"loss": 2.1634,
"step": 170
},
{
"epoch": 0.73,
"learning_rate": 0.0001,
"loss": 2.1628,
"step": 171
},
{
"epoch": 0.73,
"learning_rate": 0.0001,
"loss": 2.1871,
"step": 172
},
{
"epoch": 0.74,
"learning_rate": 0.0001,
"loss": 2.1995,
"step": 173
},
{
"epoch": 0.74,
"learning_rate": 0.0001,
"loss": 2.1537,
"step": 174
},
{
"epoch": 0.75,
"learning_rate": 0.0001,
"loss": 2.2105,
"step": 175
},
{
"epoch": 0.75,
"learning_rate": 0.0001,
"loss": 2.1633,
"step": 176
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 2.1315,
"step": 177
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 2.1628,
"step": 178
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 2.1704,
"step": 179
},
{
"epoch": 0.77,
"learning_rate": 0.0001,
"loss": 2.1696,
"step": 180
},
{
"epoch": 0.77,
"learning_rate": 0.0001,
"loss": 2.1839,
"step": 181
},
{
"epoch": 0.78,
"learning_rate": 0.0001,
"loss": 2.2022,
"step": 182
},
{
"epoch": 0.78,
"learning_rate": 0.0001,
"loss": 2.1568,
"step": 183
},
{
"epoch": 0.79,
"learning_rate": 0.0001,
"loss": 2.1448,
"step": 184
},
{
"epoch": 0.79,
"learning_rate": 0.0001,
"loss": 2.1464,
"step": 185
},
{
"epoch": 0.79,
"learning_rate": 0.0001,
"loss": 2.159,
"step": 186
},
{
"epoch": 0.8,
"learning_rate": 0.0001,
"loss": 2.138,
"step": 187
},
{
"epoch": 0.8,
"learning_rate": 0.0001,
"loss": 2.1726,
"step": 188
},
{
"epoch": 0.81,
"learning_rate": 0.0001,
"loss": 2.107,
"step": 189
},
{
"epoch": 0.81,
"learning_rate": 0.0001,
"loss": 2.1899,
"step": 190
},
{
"epoch": 0.82,
"learning_rate": 0.0001,
"loss": 2.1993,
"step": 191
},
{
"epoch": 0.82,
"learning_rate": 0.0001,
"loss": 2.1387,
"step": 192
},
{
"epoch": 0.82,
"learning_rate": 0.0001,
"loss": 2.1257,
"step": 193
},
{
"epoch": 0.83,
"learning_rate": 0.0001,
"loss": 2.1729,
"step": 194
},
{
"epoch": 0.83,
"learning_rate": 0.0001,
"loss": 2.129,
"step": 195
},
{
"epoch": 0.84,
"learning_rate": 0.0001,
"loss": 2.1368,
"step": 196
},
{
"epoch": 0.84,
"learning_rate": 0.0001,
"loss": 2.1185,
"step": 197
},
{
"epoch": 0.85,
"learning_rate": 0.0001,
"loss": 2.1327,
"step": 198
},
{
"epoch": 0.85,
"learning_rate": 0.0001,
"loss": 2.1498,
"step": 199
},
{
"epoch": 0.85,
"learning_rate": 0.0001,
"loss": 2.1094,
"step": 200
},
{
"epoch": 0.86,
"learning_rate": 0.0001,
"loss": 2.1464,
"step": 201
},
{
"epoch": 0.86,
"learning_rate": 0.0001,
"loss": 2.169,
"step": 202
},
{
"epoch": 0.87,
"learning_rate": 0.0001,
"loss": 2.1436,
"step": 203
},
{
"epoch": 0.87,
"learning_rate": 0.0001,
"loss": 2.1402,
"step": 204
},
{
"epoch": 0.88,
"learning_rate": 0.0001,
"loss": 2.1565,
"step": 205
},
{
"epoch": 0.88,
"learning_rate": 0.0001,
"loss": 2.1457,
"step": 206
},
{
"epoch": 0.88,
"learning_rate": 0.0001,
"loss": 2.1236,
"step": 207
},
{
"epoch": 0.89,
"learning_rate": 0.0001,
"loss": 2.1663,
"step": 208
},
{
"epoch": 0.89,
"learning_rate": 0.0001,
"loss": 2.1648,
"step": 209
},
{
"epoch": 0.9,
"learning_rate": 0.0001,
"loss": 2.1348,
"step": 210
},
{
"epoch": 0.9,
"learning_rate": 0.0001,
"loss": 2.1576,
"step": 211
},
{
"epoch": 0.91,
"learning_rate": 0.0001,
"loss": 2.1683,
"step": 212
},
{
"epoch": 0.91,
"learning_rate": 0.0001,
"loss": 2.1241,
"step": 213
},
{
"epoch": 0.91,
"learning_rate": 0.0001,
"loss": 2.1306,
"step": 214
},
{
"epoch": 0.92,
"learning_rate": 0.0001,
"loss": 2.1476,
"step": 215
},
{
"epoch": 0.92,
"learning_rate": 0.0001,
"loss": 2.1477,
"step": 216
},
{
"epoch": 0.93,
"learning_rate": 0.0001,
"loss": 2.1219,
"step": 217
},
{
"epoch": 0.93,
"learning_rate": 0.0001,
"loss": 2.1511,
"step": 218
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 2.1431,
"step": 219
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 2.1811,
"step": 220
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 2.1417,
"step": 221
},
{
"epoch": 0.95,
"learning_rate": 0.0001,
"loss": 2.1237,
"step": 222
},
{
"epoch": 0.95,
"learning_rate": 0.0001,
"loss": 2.1476,
"step": 223
},
{
"epoch": 0.96,
"learning_rate": 0.0001,
"loss": 2.1791,
"step": 224
},
{
"epoch": 0.96,
"learning_rate": 0.0001,
"loss": 2.1521,
"step": 225
},
{
"epoch": 0.97,
"learning_rate": 0.0001,
"loss": 2.1258,
"step": 226
},
{
"epoch": 0.97,
"learning_rate": 0.0001,
"loss": 2.1568,
"step": 227
},
{
"epoch": 0.97,
"learning_rate": 0.0001,
"loss": 2.1518,
"step": 228
},
{
"epoch": 0.98,
"learning_rate": 0.0001,
"loss": 2.1281,
"step": 229
},
{
"epoch": 0.98,
"learning_rate": 0.0001,
"loss": 2.1377,
"step": 230
},
{
"epoch": 0.99,
"learning_rate": 0.0001,
"loss": 2.1414,
"step": 231
},
{
"epoch": 0.99,
"learning_rate": 0.0001,
"loss": 2.1741,
"step": 232
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 2.1614,
"step": 233
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 2.1615,
"step": 234
},
{
"epoch": 1.0,
"step": 234,
"total_flos": 2.668899657056256e+17,
"train_loss": 2.312185388344985,
"train_runtime": 3320.7115,
"train_samples_per_second": 9.022,
"train_steps_per_second": 0.07
}
],
"logging_steps": 1.0,
"max_steps": 234,
"num_train_epochs": 1,
"save_steps": 100,
"total_flos": 2.668899657056256e+17,
"trial_name": null,
"trial_params": null
}