opencsg-codeLlama-7b-v0.2 / trainer_state.json
TomPei's picture
Upload folder using huggingface_hub
da91231 verified
raw
history blame
21.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.3071895424836601,
"eval_steps": 500,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.0,
"loss": 0.5341,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 4.075900941810124e-06,
"loss": 0.4805,
"step": 2
},
{
"epoch": 0.02,
"learning_rate": 6.46015014942309e-06,
"loss": 0.4839,
"step": 3
},
{
"epoch": 0.03,
"learning_rate": 8.151801883620247e-06,
"loss": 0.4227,
"step": 4
},
{
"epoch": 0.03,
"learning_rate": 9.463948908766788e-06,
"loss": 0.4289,
"step": 5
},
{
"epoch": 0.04,
"learning_rate": 1.0536051091233212e-05,
"loss": 0.3633,
"step": 6
},
{
"epoch": 0.05,
"learning_rate": 1.1442500570809876e-05,
"loss": 0.3749,
"step": 7
},
{
"epoch": 0.05,
"learning_rate": 1.222770282543037e-05,
"loss": 0.3379,
"step": 8
},
{
"epoch": 0.06,
"learning_rate": 1.292030029884618e-05,
"loss": 0.3637,
"step": 9
},
{
"epoch": 0.07,
"learning_rate": 1.3539849850576912e-05,
"loss": 0.3716,
"step": 10
},
{
"epoch": 0.07,
"learning_rate": 1.4100300592531481e-05,
"loss": 0.3544,
"step": 11
},
{
"epoch": 0.08,
"learning_rate": 1.4611952033043337e-05,
"loss": 0.3463,
"step": 12
},
{
"epoch": 0.08,
"learning_rate": 1.5082625732282867e-05,
"loss": 0.3121,
"step": 13
},
{
"epoch": 0.09,
"learning_rate": 1.551840151262e-05,
"loss": 0.3364,
"step": 14
},
{
"epoch": 0.1,
"learning_rate": 1.5924099058189875e-05,
"loss": 0.3259,
"step": 15
},
{
"epoch": 0.1,
"learning_rate": 1.6303603767240495e-05,
"loss": 0.3348,
"step": 16
},
{
"epoch": 0.11,
"learning_rate": 1.6660093644266146e-05,
"loss": 0.3125,
"step": 17
},
{
"epoch": 0.12,
"learning_rate": 1.6996201240656302e-05,
"loss": 0.3377,
"step": 18
},
{
"epoch": 0.12,
"learning_rate": 1.7314131752785847e-05,
"loss": 0.3086,
"step": 19
},
{
"epoch": 0.13,
"learning_rate": 1.7615750792387035e-05,
"loss": 0.3012,
"step": 20
},
{
"epoch": 0.14,
"learning_rate": 1.7902650720232966e-05,
"loss": 0.3212,
"step": 21
},
{
"epoch": 0.14,
"learning_rate": 1.8176201534341607e-05,
"loss": 0.3179,
"step": 22
},
{
"epoch": 0.15,
"learning_rate": 1.8437590437029225e-05,
"loss": 0.3196,
"step": 23
},
{
"epoch": 0.16,
"learning_rate": 1.868785297485346e-05,
"loss": 0.3175,
"step": 24
},
{
"epoch": 0.16,
"learning_rate": 1.8927897817533575e-05,
"loss": 0.3312,
"step": 25
},
{
"epoch": 0.17,
"learning_rate": 1.915852667409299e-05,
"loss": 0.2915,
"step": 26
},
{
"epoch": 0.18,
"learning_rate": 1.9380450448269272e-05,
"loss": 0.3208,
"step": 27
},
{
"epoch": 0.18,
"learning_rate": 1.9594302454430122e-05,
"loss": 0.2906,
"step": 28
},
{
"epoch": 0.19,
"learning_rate": 1.9800649313336155e-05,
"loss": 0.2998,
"step": 29
},
{
"epoch": 0.2,
"learning_rate": 2e-05,
"loss": 0.3057,
"step": 30
},
{
"epoch": 0.2,
"learning_rate": 2e-05,
"loss": 0.2943,
"step": 31
},
{
"epoch": 0.21,
"learning_rate": 2e-05,
"loss": 0.3099,
"step": 32
},
{
"epoch": 0.22,
"learning_rate": 2e-05,
"loss": 0.2935,
"step": 33
},
{
"epoch": 0.22,
"learning_rate": 2e-05,
"loss": 0.2903,
"step": 34
},
{
"epoch": 0.23,
"learning_rate": 2e-05,
"loss": 0.2782,
"step": 35
},
{
"epoch": 0.24,
"learning_rate": 2e-05,
"loss": 0.3099,
"step": 36
},
{
"epoch": 0.24,
"learning_rate": 2e-05,
"loss": 0.2966,
"step": 37
},
{
"epoch": 0.25,
"learning_rate": 2e-05,
"loss": 0.2939,
"step": 38
},
{
"epoch": 0.25,
"learning_rate": 2e-05,
"loss": 0.2949,
"step": 39
},
{
"epoch": 0.26,
"learning_rate": 2e-05,
"loss": 0.2842,
"step": 40
},
{
"epoch": 0.27,
"learning_rate": 2e-05,
"loss": 0.279,
"step": 41
},
{
"epoch": 0.27,
"learning_rate": 2e-05,
"loss": 0.3078,
"step": 42
},
{
"epoch": 0.28,
"learning_rate": 2e-05,
"loss": 0.3019,
"step": 43
},
{
"epoch": 0.29,
"learning_rate": 2e-05,
"loss": 0.3208,
"step": 44
},
{
"epoch": 0.29,
"learning_rate": 2e-05,
"loss": 0.312,
"step": 45
},
{
"epoch": 0.3,
"learning_rate": 2e-05,
"loss": 0.2994,
"step": 46
},
{
"epoch": 0.31,
"learning_rate": 2e-05,
"loss": 0.3032,
"step": 47
},
{
"epoch": 0.31,
"learning_rate": 2e-05,
"loss": 0.3176,
"step": 48
},
{
"epoch": 0.32,
"learning_rate": 2e-05,
"loss": 0.3116,
"step": 49
},
{
"epoch": 0.33,
"learning_rate": 2e-05,
"loss": 0.3035,
"step": 50
},
{
"epoch": 0.33,
"learning_rate": 2e-05,
"loss": 0.3081,
"step": 51
},
{
"epoch": 0.34,
"learning_rate": 2e-05,
"loss": 0.2975,
"step": 52
},
{
"epoch": 0.35,
"learning_rate": 2e-05,
"loss": 0.2893,
"step": 53
},
{
"epoch": 0.35,
"learning_rate": 2e-05,
"loss": 0.2919,
"step": 54
},
{
"epoch": 0.36,
"learning_rate": 2e-05,
"loss": 0.2922,
"step": 55
},
{
"epoch": 0.37,
"learning_rate": 2e-05,
"loss": 0.3126,
"step": 56
},
{
"epoch": 0.37,
"learning_rate": 2e-05,
"loss": 0.2758,
"step": 57
},
{
"epoch": 0.38,
"learning_rate": 2e-05,
"loss": 0.2856,
"step": 58
},
{
"epoch": 0.39,
"learning_rate": 2e-05,
"loss": 0.2936,
"step": 59
},
{
"epoch": 0.39,
"learning_rate": 2e-05,
"loss": 0.2778,
"step": 60
},
{
"epoch": 0.4,
"learning_rate": 2e-05,
"loss": 0.2777,
"step": 61
},
{
"epoch": 0.41,
"learning_rate": 2e-05,
"loss": 0.2757,
"step": 62
},
{
"epoch": 0.41,
"learning_rate": 2e-05,
"loss": 0.2961,
"step": 63
},
{
"epoch": 0.42,
"learning_rate": 2e-05,
"loss": 0.2864,
"step": 64
},
{
"epoch": 0.42,
"learning_rate": 2e-05,
"loss": 0.2746,
"step": 65
},
{
"epoch": 0.43,
"learning_rate": 2e-05,
"loss": 0.2824,
"step": 66
},
{
"epoch": 0.44,
"learning_rate": 2e-05,
"loss": 0.2719,
"step": 67
},
{
"epoch": 0.44,
"learning_rate": 2e-05,
"loss": 0.2786,
"step": 68
},
{
"epoch": 0.45,
"learning_rate": 2e-05,
"loss": 0.2739,
"step": 69
},
{
"epoch": 0.46,
"learning_rate": 2e-05,
"loss": 0.2846,
"step": 70
},
{
"epoch": 0.46,
"learning_rate": 2e-05,
"loss": 0.2762,
"step": 71
},
{
"epoch": 0.47,
"learning_rate": 2e-05,
"loss": 0.2834,
"step": 72
},
{
"epoch": 0.48,
"learning_rate": 2e-05,
"loss": 0.2827,
"step": 73
},
{
"epoch": 0.48,
"learning_rate": 2e-05,
"loss": 0.2697,
"step": 74
},
{
"epoch": 0.49,
"learning_rate": 2e-05,
"loss": 0.2873,
"step": 75
},
{
"epoch": 0.5,
"learning_rate": 2e-05,
"loss": 0.2596,
"step": 76
},
{
"epoch": 0.5,
"learning_rate": 2e-05,
"loss": 0.2791,
"step": 77
},
{
"epoch": 0.51,
"learning_rate": 2e-05,
"loss": 0.2683,
"step": 78
},
{
"epoch": 0.52,
"learning_rate": 2e-05,
"loss": 0.2771,
"step": 79
},
{
"epoch": 0.52,
"learning_rate": 2e-05,
"loss": 0.2836,
"step": 80
},
{
"epoch": 0.53,
"learning_rate": 2e-05,
"loss": 0.2656,
"step": 81
},
{
"epoch": 0.54,
"learning_rate": 2e-05,
"loss": 0.2832,
"step": 82
},
{
"epoch": 0.54,
"learning_rate": 2e-05,
"loss": 0.2572,
"step": 83
},
{
"epoch": 0.55,
"learning_rate": 2e-05,
"loss": 0.2691,
"step": 84
},
{
"epoch": 0.56,
"learning_rate": 2e-05,
"loss": 0.2811,
"step": 85
},
{
"epoch": 0.56,
"learning_rate": 2e-05,
"loss": 0.2757,
"step": 86
},
{
"epoch": 0.57,
"learning_rate": 2e-05,
"loss": 0.2752,
"step": 87
},
{
"epoch": 0.58,
"learning_rate": 2e-05,
"loss": 0.275,
"step": 88
},
{
"epoch": 0.58,
"learning_rate": 2e-05,
"loss": 0.2871,
"step": 89
},
{
"epoch": 0.59,
"learning_rate": 2e-05,
"loss": 0.2601,
"step": 90
},
{
"epoch": 0.59,
"learning_rate": 2e-05,
"loss": 0.2832,
"step": 91
},
{
"epoch": 0.6,
"learning_rate": 2e-05,
"loss": 0.2717,
"step": 92
},
{
"epoch": 0.61,
"learning_rate": 2e-05,
"loss": 0.2845,
"step": 93
},
{
"epoch": 0.61,
"learning_rate": 2e-05,
"loss": 0.2825,
"step": 94
},
{
"epoch": 0.62,
"learning_rate": 2e-05,
"loss": 0.2886,
"step": 95
},
{
"epoch": 0.63,
"learning_rate": 2e-05,
"loss": 0.2713,
"step": 96
},
{
"epoch": 0.63,
"learning_rate": 2e-05,
"loss": 0.2771,
"step": 97
},
{
"epoch": 0.64,
"learning_rate": 2e-05,
"loss": 0.2577,
"step": 98
},
{
"epoch": 0.65,
"learning_rate": 2e-05,
"loss": 0.2648,
"step": 99
},
{
"epoch": 0.65,
"learning_rate": 2e-05,
"loss": 0.2794,
"step": 100
},
{
"epoch": 0.66,
"learning_rate": 2e-05,
"loss": 0.2868,
"step": 101
},
{
"epoch": 0.67,
"learning_rate": 2e-05,
"loss": 0.2822,
"step": 102
},
{
"epoch": 0.67,
"learning_rate": 2e-05,
"loss": 0.2802,
"step": 103
},
{
"epoch": 0.68,
"learning_rate": 2e-05,
"loss": 0.2764,
"step": 104
},
{
"epoch": 0.69,
"learning_rate": 2e-05,
"loss": 0.2716,
"step": 105
},
{
"epoch": 0.69,
"learning_rate": 2e-05,
"loss": 0.2679,
"step": 106
},
{
"epoch": 0.7,
"learning_rate": 2e-05,
"loss": 0.2825,
"step": 107
},
{
"epoch": 0.71,
"learning_rate": 2e-05,
"loss": 0.2852,
"step": 108
},
{
"epoch": 0.71,
"learning_rate": 2e-05,
"loss": 0.277,
"step": 109
},
{
"epoch": 0.72,
"learning_rate": 2e-05,
"loss": 0.2666,
"step": 110
},
{
"epoch": 0.73,
"learning_rate": 2e-05,
"loss": 0.2815,
"step": 111
},
{
"epoch": 0.73,
"learning_rate": 2e-05,
"loss": 0.2722,
"step": 112
},
{
"epoch": 0.74,
"learning_rate": 2e-05,
"loss": 0.2648,
"step": 113
},
{
"epoch": 0.75,
"learning_rate": 2e-05,
"loss": 0.2826,
"step": 114
},
{
"epoch": 0.75,
"learning_rate": 2e-05,
"loss": 0.2667,
"step": 115
},
{
"epoch": 0.76,
"learning_rate": 2e-05,
"loss": 0.2724,
"step": 116
},
{
"epoch": 0.76,
"learning_rate": 2e-05,
"loss": 0.2757,
"step": 117
},
{
"epoch": 0.77,
"learning_rate": 2e-05,
"loss": 0.2748,
"step": 118
},
{
"epoch": 0.78,
"learning_rate": 2e-05,
"loss": 0.2708,
"step": 119
},
{
"epoch": 0.78,
"learning_rate": 2e-05,
"loss": 0.2774,
"step": 120
},
{
"epoch": 0.79,
"learning_rate": 2e-05,
"loss": 0.2737,
"step": 121
},
{
"epoch": 0.8,
"learning_rate": 2e-05,
"loss": 0.2603,
"step": 122
},
{
"epoch": 0.8,
"learning_rate": 2e-05,
"loss": 0.2792,
"step": 123
},
{
"epoch": 0.81,
"learning_rate": 2e-05,
"loss": 0.2788,
"step": 124
},
{
"epoch": 0.82,
"learning_rate": 2e-05,
"loss": 0.2803,
"step": 125
},
{
"epoch": 0.82,
"learning_rate": 2e-05,
"loss": 0.2862,
"step": 126
},
{
"epoch": 0.83,
"learning_rate": 2e-05,
"loss": 0.2892,
"step": 127
},
{
"epoch": 0.84,
"learning_rate": 2e-05,
"loss": 0.2794,
"step": 128
},
{
"epoch": 0.84,
"learning_rate": 2e-05,
"loss": 0.2721,
"step": 129
},
{
"epoch": 0.85,
"learning_rate": 2e-05,
"loss": 0.2714,
"step": 130
},
{
"epoch": 0.86,
"learning_rate": 2e-05,
"loss": 0.2693,
"step": 131
},
{
"epoch": 0.86,
"learning_rate": 2e-05,
"loss": 0.2851,
"step": 132
},
{
"epoch": 0.87,
"learning_rate": 2e-05,
"loss": 0.2804,
"step": 133
},
{
"epoch": 0.88,
"learning_rate": 2e-05,
"loss": 0.2772,
"step": 134
},
{
"epoch": 0.88,
"learning_rate": 2e-05,
"loss": 0.271,
"step": 135
},
{
"epoch": 0.89,
"learning_rate": 2e-05,
"loss": 0.2752,
"step": 136
},
{
"epoch": 0.9,
"learning_rate": 2e-05,
"loss": 0.2527,
"step": 137
},
{
"epoch": 0.9,
"learning_rate": 2e-05,
"loss": 0.2707,
"step": 138
},
{
"epoch": 0.91,
"learning_rate": 2e-05,
"loss": 0.2579,
"step": 139
},
{
"epoch": 0.92,
"learning_rate": 2e-05,
"loss": 0.2707,
"step": 140
},
{
"epoch": 0.92,
"learning_rate": 2e-05,
"loss": 0.2584,
"step": 141
},
{
"epoch": 0.93,
"learning_rate": 2e-05,
"loss": 0.2652,
"step": 142
},
{
"epoch": 0.93,
"learning_rate": 2e-05,
"loss": 0.269,
"step": 143
},
{
"epoch": 0.94,
"learning_rate": 2e-05,
"loss": 0.2666,
"step": 144
},
{
"epoch": 0.95,
"learning_rate": 2e-05,
"loss": 0.2685,
"step": 145
},
{
"epoch": 0.95,
"learning_rate": 2e-05,
"loss": 0.2818,
"step": 146
},
{
"epoch": 0.96,
"learning_rate": 2e-05,
"loss": 0.2583,
"step": 147
},
{
"epoch": 0.97,
"learning_rate": 2e-05,
"loss": 0.2834,
"step": 148
},
{
"epoch": 0.97,
"learning_rate": 2e-05,
"loss": 0.2691,
"step": 149
},
{
"epoch": 0.98,
"learning_rate": 2e-05,
"loss": 0.2617,
"step": 150
},
{
"epoch": 0.99,
"learning_rate": 2e-05,
"loss": 0.2772,
"step": 151
},
{
"epoch": 0.99,
"learning_rate": 2e-05,
"loss": 0.2785,
"step": 152
},
{
"epoch": 1.0,
"learning_rate": 2e-05,
"loss": 0.2714,
"step": 153
},
{
"epoch": 1.01,
"learning_rate": 2e-05,
"loss": 0.215,
"step": 154
},
{
"epoch": 1.01,
"learning_rate": 2e-05,
"loss": 0.2257,
"step": 155
},
{
"epoch": 1.02,
"learning_rate": 2e-05,
"loss": 0.2122,
"step": 156
},
{
"epoch": 1.03,
"learning_rate": 2e-05,
"loss": 0.2267,
"step": 157
},
{
"epoch": 1.03,
"learning_rate": 2e-05,
"loss": 0.2159,
"step": 158
},
{
"epoch": 1.04,
"learning_rate": 2e-05,
"loss": 0.2114,
"step": 159
},
{
"epoch": 1.05,
"learning_rate": 2e-05,
"loss": 0.2124,
"step": 160
},
{
"epoch": 1.05,
"learning_rate": 2e-05,
"loss": 0.2085,
"step": 161
},
{
"epoch": 1.06,
"learning_rate": 2e-05,
"loss": 0.221,
"step": 162
},
{
"epoch": 1.07,
"learning_rate": 2e-05,
"loss": 0.2177,
"step": 163
},
{
"epoch": 1.07,
"learning_rate": 2e-05,
"loss": 0.2226,
"step": 164
},
{
"epoch": 1.08,
"learning_rate": 2e-05,
"loss": 0.2198,
"step": 165
},
{
"epoch": 1.08,
"learning_rate": 2e-05,
"loss": 0.2179,
"step": 166
},
{
"epoch": 1.09,
"learning_rate": 2e-05,
"loss": 0.215,
"step": 167
},
{
"epoch": 1.1,
"learning_rate": 2e-05,
"loss": 0.2223,
"step": 168
},
{
"epoch": 1.1,
"learning_rate": 2e-05,
"loss": 0.2168,
"step": 169
},
{
"epoch": 1.11,
"learning_rate": 2e-05,
"loss": 0.2081,
"step": 170
},
{
"epoch": 1.12,
"learning_rate": 2e-05,
"loss": 0.2101,
"step": 171
},
{
"epoch": 1.12,
"learning_rate": 2e-05,
"loss": 0.2091,
"step": 172
},
{
"epoch": 1.13,
"learning_rate": 2e-05,
"loss": 0.2459,
"step": 173
},
{
"epoch": 1.14,
"learning_rate": 2e-05,
"loss": 0.2135,
"step": 174
},
{
"epoch": 1.14,
"learning_rate": 2e-05,
"loss": 0.2182,
"step": 175
},
{
"epoch": 1.15,
"learning_rate": 2e-05,
"loss": 0.2165,
"step": 176
},
{
"epoch": 1.16,
"learning_rate": 2e-05,
"loss": 0.2239,
"step": 177
},
{
"epoch": 1.16,
"learning_rate": 2e-05,
"loss": 0.2184,
"step": 178
},
{
"epoch": 1.17,
"learning_rate": 2e-05,
"loss": 0.2272,
"step": 179
},
{
"epoch": 1.18,
"learning_rate": 2e-05,
"loss": 0.2066,
"step": 180
},
{
"epoch": 1.18,
"learning_rate": 2e-05,
"loss": 0.2123,
"step": 181
},
{
"epoch": 1.19,
"learning_rate": 2e-05,
"loss": 0.2059,
"step": 182
},
{
"epoch": 1.2,
"learning_rate": 2e-05,
"loss": 0.2192,
"step": 183
},
{
"epoch": 1.2,
"learning_rate": 2e-05,
"loss": 0.2102,
"step": 184
},
{
"epoch": 1.21,
"learning_rate": 2e-05,
"loss": 0.2192,
"step": 185
},
{
"epoch": 1.22,
"learning_rate": 2e-05,
"loss": 0.2156,
"step": 186
},
{
"epoch": 1.22,
"learning_rate": 2e-05,
"loss": 0.22,
"step": 187
},
{
"epoch": 1.23,
"learning_rate": 2e-05,
"loss": 0.2154,
"step": 188
},
{
"epoch": 1.24,
"learning_rate": 2e-05,
"loss": 0.2045,
"step": 189
},
{
"epoch": 1.24,
"learning_rate": 2e-05,
"loss": 0.2153,
"step": 190
},
{
"epoch": 1.25,
"learning_rate": 2e-05,
"loss": 0.2242,
"step": 191
},
{
"epoch": 1.25,
"learning_rate": 2e-05,
"loss": 0.2119,
"step": 192
},
{
"epoch": 1.26,
"learning_rate": 2e-05,
"loss": 0.2163,
"step": 193
},
{
"epoch": 1.27,
"learning_rate": 2e-05,
"loss": 0.2172,
"step": 194
},
{
"epoch": 1.27,
"learning_rate": 2e-05,
"loss": 0.2002,
"step": 195
},
{
"epoch": 1.28,
"learning_rate": 2e-05,
"loss": 0.2138,
"step": 196
},
{
"epoch": 1.29,
"learning_rate": 2e-05,
"loss": 0.2247,
"step": 197
},
{
"epoch": 1.29,
"learning_rate": 2e-05,
"loss": 0.2208,
"step": 198
},
{
"epoch": 1.3,
"learning_rate": 2e-05,
"loss": 0.2188,
"step": 199
},
{
"epoch": 1.31,
"learning_rate": 2e-05,
"loss": 0.2129,
"step": 200
}
],
"logging_steps": 1.0,
"max_steps": 306,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 100,
"total_flos": 5.340257905864081e+18,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}