akkky02's picture
Upload folder using huggingface_hub
14b8326 verified
raw
history blame
No virus
43 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9990726429675425,
"eval_steps": 500,
"global_step": 404,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0003,
"loss": 1.7194,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 0.0003,
"loss": 1.5941,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 1.6227,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 1.6363,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 1.4752,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 1.4016,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 1.3052,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 1.2636,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 1.1788,
"step": 9
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 1.0782,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 1.0597,
"step": 11
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 1.0015,
"step": 12
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 0.9441,
"step": 13
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 0.9357,
"step": 14
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 0.9028,
"step": 15
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 0.9042,
"step": 16
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 0.8833,
"step": 17
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 0.8826,
"step": 18
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 0.9081,
"step": 19
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 0.909,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 0.8979,
"step": 21
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 0.9265,
"step": 22
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 0.9184,
"step": 23
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 0.8515,
"step": 24
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 0.8342,
"step": 25
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 0.8402,
"step": 26
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 0.9189,
"step": 27
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 0.8512,
"step": 28
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 0.8487,
"step": 29
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 0.8354,
"step": 30
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 0.8592,
"step": 31
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 0.8842,
"step": 32
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 0.8588,
"step": 33
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 0.8925,
"step": 34
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 0.8386,
"step": 35
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 0.8773,
"step": 36
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 0.8517,
"step": 37
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 0.8459,
"step": 38
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 0.8601,
"step": 39
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 0.8276,
"step": 40
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 0.8774,
"step": 41
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 0.8536,
"step": 42
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 0.8416,
"step": 43
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 0.8515,
"step": 44
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 0.8248,
"step": 45
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 0.8666,
"step": 46
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 0.8353,
"step": 47
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 0.842,
"step": 48
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 0.8508,
"step": 49
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 0.8769,
"step": 50
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 0.8201,
"step": 51
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 0.8267,
"step": 52
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 0.8309,
"step": 53
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 0.8337,
"step": 54
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 0.8515,
"step": 55
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 0.8438,
"step": 56
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 0.8862,
"step": 57
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 0.8204,
"step": 58
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 0.8138,
"step": 59
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 0.8372,
"step": 60
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 0.8315,
"step": 61
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 0.8407,
"step": 62
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 0.8324,
"step": 63
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 0.8391,
"step": 64
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 0.8466,
"step": 65
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 0.8328,
"step": 66
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 0.8416,
"step": 67
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 0.8876,
"step": 68
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 0.8113,
"step": 69
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 0.8487,
"step": 70
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 0.8477,
"step": 71
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 0.7847,
"step": 72
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 0.841,
"step": 73
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 0.8401,
"step": 74
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 0.8436,
"step": 75
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 0.8339,
"step": 76
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 0.8379,
"step": 77
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 0.8391,
"step": 78
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 0.8246,
"step": 79
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 0.8197,
"step": 80
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 0.793,
"step": 81
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 0.8377,
"step": 82
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 0.8351,
"step": 83
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 0.8269,
"step": 84
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 0.8137,
"step": 85
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 0.8478,
"step": 86
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 0.8258,
"step": 87
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 0.8443,
"step": 88
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 0.8392,
"step": 89
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 0.8415,
"step": 90
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 0.8166,
"step": 91
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 0.8365,
"step": 92
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 0.8592,
"step": 93
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 0.8245,
"step": 94
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 0.8118,
"step": 95
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 0.8285,
"step": 96
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 0.8324,
"step": 97
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 0.8096,
"step": 98
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 0.8569,
"step": 99
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 0.838,
"step": 100
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 0.8456,
"step": 101
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 0.7865,
"step": 102
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 0.8116,
"step": 103
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 0.8347,
"step": 104
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 0.8161,
"step": 105
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 0.8432,
"step": 106
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 0.8343,
"step": 107
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 0.8439,
"step": 108
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 0.8054,
"step": 109
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 0.8206,
"step": 110
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 0.8343,
"step": 111
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 0.8441,
"step": 112
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 0.8266,
"step": 113
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 0.7953,
"step": 114
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 0.77,
"step": 115
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 0.8267,
"step": 116
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 0.7804,
"step": 117
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 0.8249,
"step": 118
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 0.8161,
"step": 119
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 0.8344,
"step": 120
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 0.8275,
"step": 121
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 0.8261,
"step": 122
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 0.8369,
"step": 123
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 0.8129,
"step": 124
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 0.8453,
"step": 125
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 0.8479,
"step": 126
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 0.8147,
"step": 127
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 0.8153,
"step": 128
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 0.8123,
"step": 129
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 0.8065,
"step": 130
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 0.8779,
"step": 131
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 0.858,
"step": 132
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 0.7778,
"step": 133
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 0.7964,
"step": 134
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 0.8367,
"step": 135
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 0.821,
"step": 136
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 0.789,
"step": 137
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 0.8593,
"step": 138
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 0.8206,
"step": 139
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.8253,
"step": 140
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.8285,
"step": 141
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.8459,
"step": 142
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.7973,
"step": 143
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 0.788,
"step": 144
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 0.8206,
"step": 145
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 0.8466,
"step": 146
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 0.8011,
"step": 147
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 0.853,
"step": 148
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 0.7929,
"step": 149
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 0.8195,
"step": 150
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 0.8021,
"step": 151
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 0.8344,
"step": 152
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 0.8125,
"step": 153
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 0.8431,
"step": 154
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 0.8153,
"step": 155
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.8259,
"step": 156
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.7858,
"step": 157
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.8018,
"step": 158
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.8205,
"step": 159
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 0.7985,
"step": 160
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 0.8172,
"step": 161
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 0.8689,
"step": 162
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 0.7981,
"step": 163
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.8014,
"step": 164
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.7899,
"step": 165
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.8245,
"step": 166
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.8475,
"step": 167
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.8509,
"step": 168
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.8367,
"step": 169
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.8063,
"step": 170
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.8381,
"step": 171
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.791,
"step": 172
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.8393,
"step": 173
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.8257,
"step": 174
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.8175,
"step": 175
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.8208,
"step": 176
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.845,
"step": 177
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.8445,
"step": 178
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.8169,
"step": 179
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.8208,
"step": 180
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.7784,
"step": 181
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.8121,
"step": 182
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.8374,
"step": 183
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.8493,
"step": 184
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.8501,
"step": 185
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.8344,
"step": 186
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.819,
"step": 187
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.8242,
"step": 188
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.8456,
"step": 189
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.8438,
"step": 190
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.7943,
"step": 191
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.8304,
"step": 192
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.8383,
"step": 193
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.842,
"step": 194
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.8291,
"step": 195
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.8129,
"step": 196
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.8395,
"step": 197
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.779,
"step": 198
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.8177,
"step": 199
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.7797,
"step": 200
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.811,
"step": 201
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.799,
"step": 202
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.819,
"step": 203
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.8409,
"step": 204
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.8493,
"step": 205
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.8184,
"step": 206
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.8576,
"step": 207
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.8146,
"step": 208
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.8048,
"step": 209
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.8131,
"step": 210
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.7773,
"step": 211
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.829,
"step": 212
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 0.8182,
"step": 213
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 0.8743,
"step": 214
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 0.815,
"step": 215
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 0.8289,
"step": 216
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.8044,
"step": 217
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.8156,
"step": 218
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.788,
"step": 219
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.8059,
"step": 220
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 0.854,
"step": 221
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 0.8238,
"step": 222
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 0.8615,
"step": 223
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 0.8098,
"step": 224
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.8186,
"step": 225
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.8106,
"step": 226
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.8231,
"step": 227
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.7982,
"step": 228
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.8382,
"step": 229
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.8128,
"step": 230
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.8337,
"step": 231
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.8273,
"step": 232
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.815,
"step": 233
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.8141,
"step": 234
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.7875,
"step": 235
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.8061,
"step": 236
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 0.8286,
"step": 237
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 0.8449,
"step": 238
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 0.8285,
"step": 239
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 0.8611,
"step": 240
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.8041,
"step": 241
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.8099,
"step": 242
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.8171,
"step": 243
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.8045,
"step": 244
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.824,
"step": 245
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.8209,
"step": 246
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.841,
"step": 247
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.8132,
"step": 248
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.8069,
"step": 249
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.7605,
"step": 250
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.825,
"step": 251
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.8283,
"step": 252
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.8266,
"step": 253
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.8227,
"step": 254
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.8168,
"step": 255
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.8285,
"step": 256
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.7928,
"step": 257
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.8012,
"step": 258
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.8251,
"step": 259
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.779,
"step": 260
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.7967,
"step": 261
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.8655,
"step": 262
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.8114,
"step": 263
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.8317,
"step": 264
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.7692,
"step": 265
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.8038,
"step": 266
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.7747,
"step": 267
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.8063,
"step": 268
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.8232,
"step": 269
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.8524,
"step": 270
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.778,
"step": 271
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.7871,
"step": 272
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.7761,
"step": 273
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.8191,
"step": 274
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.8141,
"step": 275
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.8145,
"step": 276
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.7848,
"step": 277
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.8237,
"step": 278
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.8374,
"step": 279
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.8033,
"step": 280
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.8068,
"step": 281
},
{
"epoch": 0.7,
"learning_rate": 0.0003,
"loss": 0.8134,
"step": 282
},
{
"epoch": 0.7,
"learning_rate": 0.0003,
"loss": 0.8018,
"step": 283
},
{
"epoch": 0.7,
"learning_rate": 0.0003,
"loss": 0.7842,
"step": 284
},
{
"epoch": 0.7,
"learning_rate": 0.0003,
"loss": 0.8068,
"step": 285
},
{
"epoch": 0.71,
"learning_rate": 0.0003,
"loss": 0.803,
"step": 286
},
{
"epoch": 0.71,
"learning_rate": 0.0003,
"loss": 0.8121,
"step": 287
},
{
"epoch": 0.71,
"learning_rate": 0.0003,
"loss": 0.8321,
"step": 288
},
{
"epoch": 0.71,
"learning_rate": 0.0003,
"loss": 0.7839,
"step": 289
},
{
"epoch": 0.72,
"learning_rate": 0.0003,
"loss": 0.8022,
"step": 290
},
{
"epoch": 0.72,
"learning_rate": 0.0003,
"loss": 0.7578,
"step": 291
},
{
"epoch": 0.72,
"learning_rate": 0.0003,
"loss": 0.7962,
"step": 292
},
{
"epoch": 0.72,
"learning_rate": 0.0003,
"loss": 0.8076,
"step": 293
},
{
"epoch": 0.73,
"learning_rate": 0.0003,
"loss": 0.7988,
"step": 294
},
{
"epoch": 0.73,
"learning_rate": 0.0003,
"loss": 0.8184,
"step": 295
},
{
"epoch": 0.73,
"learning_rate": 0.0003,
"loss": 0.7914,
"step": 296
},
{
"epoch": 0.73,
"learning_rate": 0.0003,
"loss": 0.8245,
"step": 297
},
{
"epoch": 0.74,
"learning_rate": 0.0003,
"loss": 0.793,
"step": 298
},
{
"epoch": 0.74,
"learning_rate": 0.0003,
"loss": 0.8215,
"step": 299
},
{
"epoch": 0.74,
"learning_rate": 0.0003,
"loss": 0.8245,
"step": 300
},
{
"epoch": 0.74,
"learning_rate": 0.0003,
"loss": 0.7999,
"step": 301
},
{
"epoch": 0.75,
"learning_rate": 0.0003,
"loss": 0.7887,
"step": 302
},
{
"epoch": 0.75,
"learning_rate": 0.0003,
"loss": 0.8281,
"step": 303
},
{
"epoch": 0.75,
"learning_rate": 0.0003,
"loss": 0.7986,
"step": 304
},
{
"epoch": 0.75,
"learning_rate": 0.0003,
"loss": 0.7991,
"step": 305
},
{
"epoch": 0.76,
"learning_rate": 0.0003,
"loss": 0.8281,
"step": 306
},
{
"epoch": 0.76,
"learning_rate": 0.0003,
"loss": 0.8088,
"step": 307
},
{
"epoch": 0.76,
"learning_rate": 0.0003,
"loss": 0.8355,
"step": 308
},
{
"epoch": 0.76,
"learning_rate": 0.0003,
"loss": 0.836,
"step": 309
},
{
"epoch": 0.77,
"learning_rate": 0.0003,
"loss": 0.8246,
"step": 310
},
{
"epoch": 0.77,
"learning_rate": 0.0003,
"loss": 0.8125,
"step": 311
},
{
"epoch": 0.77,
"learning_rate": 0.0003,
"loss": 0.7693,
"step": 312
},
{
"epoch": 0.77,
"learning_rate": 0.0003,
"loss": 0.8056,
"step": 313
},
{
"epoch": 0.78,
"learning_rate": 0.0003,
"loss": 0.8255,
"step": 314
},
{
"epoch": 0.78,
"learning_rate": 0.0003,
"loss": 0.8055,
"step": 315
},
{
"epoch": 0.78,
"learning_rate": 0.0003,
"loss": 0.815,
"step": 316
},
{
"epoch": 0.78,
"learning_rate": 0.0003,
"loss": 0.8487,
"step": 317
},
{
"epoch": 0.79,
"learning_rate": 0.0003,
"loss": 0.8004,
"step": 318
},
{
"epoch": 0.79,
"learning_rate": 0.0003,
"loss": 0.7659,
"step": 319
},
{
"epoch": 0.79,
"learning_rate": 0.0003,
"loss": 0.7746,
"step": 320
},
{
"epoch": 0.79,
"learning_rate": 0.0003,
"loss": 0.8239,
"step": 321
},
{
"epoch": 0.8,
"learning_rate": 0.0003,
"loss": 0.8295,
"step": 322
},
{
"epoch": 0.8,
"learning_rate": 0.0003,
"loss": 0.8423,
"step": 323
},
{
"epoch": 0.8,
"learning_rate": 0.0003,
"loss": 0.8059,
"step": 324
},
{
"epoch": 0.8,
"learning_rate": 0.0003,
"loss": 0.8106,
"step": 325
},
{
"epoch": 0.81,
"learning_rate": 0.0003,
"loss": 0.8058,
"step": 326
},
{
"epoch": 0.81,
"learning_rate": 0.0003,
"loss": 0.8203,
"step": 327
},
{
"epoch": 0.81,
"learning_rate": 0.0003,
"loss": 0.7953,
"step": 328
},
{
"epoch": 0.81,
"learning_rate": 0.0003,
"loss": 0.7907,
"step": 329
},
{
"epoch": 0.82,
"learning_rate": 0.0003,
"loss": 0.7948,
"step": 330
},
{
"epoch": 0.82,
"learning_rate": 0.0003,
"loss": 0.7885,
"step": 331
},
{
"epoch": 0.82,
"learning_rate": 0.0003,
"loss": 0.841,
"step": 332
},
{
"epoch": 0.82,
"learning_rate": 0.0003,
"loss": 0.7947,
"step": 333
},
{
"epoch": 0.83,
"learning_rate": 0.0003,
"loss": 0.8183,
"step": 334
},
{
"epoch": 0.83,
"learning_rate": 0.0003,
"loss": 0.7873,
"step": 335
},
{
"epoch": 0.83,
"learning_rate": 0.0003,
"loss": 0.8261,
"step": 336
},
{
"epoch": 0.83,
"learning_rate": 0.0003,
"loss": 0.781,
"step": 337
},
{
"epoch": 0.84,
"learning_rate": 0.0003,
"loss": 0.813,
"step": 338
},
{
"epoch": 0.84,
"learning_rate": 0.0003,
"loss": 0.8064,
"step": 339
},
{
"epoch": 0.84,
"learning_rate": 0.0003,
"loss": 0.8317,
"step": 340
},
{
"epoch": 0.84,
"learning_rate": 0.0003,
"loss": 0.7971,
"step": 341
},
{
"epoch": 0.85,
"learning_rate": 0.0003,
"loss": 0.8128,
"step": 342
},
{
"epoch": 0.85,
"learning_rate": 0.0003,
"loss": 0.8213,
"step": 343
},
{
"epoch": 0.85,
"learning_rate": 0.0003,
"loss": 0.829,
"step": 344
},
{
"epoch": 0.85,
"learning_rate": 0.0003,
"loss": 0.8115,
"step": 345
},
{
"epoch": 0.86,
"learning_rate": 0.0003,
"loss": 0.8323,
"step": 346
},
{
"epoch": 0.86,
"learning_rate": 0.0003,
"loss": 0.8099,
"step": 347
},
{
"epoch": 0.86,
"learning_rate": 0.0003,
"loss": 0.8108,
"step": 348
},
{
"epoch": 0.86,
"learning_rate": 0.0003,
"loss": 0.8044,
"step": 349
},
{
"epoch": 0.87,
"learning_rate": 0.0003,
"loss": 0.801,
"step": 350
},
{
"epoch": 0.87,
"learning_rate": 0.0003,
"loss": 0.8017,
"step": 351
},
{
"epoch": 0.87,
"learning_rate": 0.0003,
"loss": 0.7843,
"step": 352
},
{
"epoch": 0.87,
"learning_rate": 0.0003,
"loss": 0.8088,
"step": 353
},
{
"epoch": 0.88,
"learning_rate": 0.0003,
"loss": 0.8133,
"step": 354
},
{
"epoch": 0.88,
"learning_rate": 0.0003,
"loss": 0.8235,
"step": 355
},
{
"epoch": 0.88,
"learning_rate": 0.0003,
"loss": 0.8167,
"step": 356
},
{
"epoch": 0.88,
"learning_rate": 0.0003,
"loss": 0.854,
"step": 357
},
{
"epoch": 0.89,
"learning_rate": 0.0003,
"loss": 0.7992,
"step": 358
},
{
"epoch": 0.89,
"learning_rate": 0.0003,
"loss": 0.7892,
"step": 359
},
{
"epoch": 0.89,
"learning_rate": 0.0003,
"loss": 0.7866,
"step": 360
},
{
"epoch": 0.89,
"learning_rate": 0.0003,
"loss": 0.8542,
"step": 361
},
{
"epoch": 0.9,
"learning_rate": 0.0003,
"loss": 0.8012,
"step": 362
},
{
"epoch": 0.9,
"learning_rate": 0.0003,
"loss": 0.7737,
"step": 363
},
{
"epoch": 0.9,
"learning_rate": 0.0003,
"loss": 0.7984,
"step": 364
},
{
"epoch": 0.9,
"learning_rate": 0.0003,
"loss": 0.8194,
"step": 365
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.8079,
"step": 366
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.8056,
"step": 367
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.8256,
"step": 368
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.8433,
"step": 369
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.8153,
"step": 370
},
{
"epoch": 0.92,
"learning_rate": 0.0003,
"loss": 0.8097,
"step": 371
},
{
"epoch": 0.92,
"learning_rate": 0.0003,
"loss": 0.7818,
"step": 372
},
{
"epoch": 0.92,
"learning_rate": 0.0003,
"loss": 0.7962,
"step": 373
},
{
"epoch": 0.92,
"learning_rate": 0.0003,
"loss": 0.8045,
"step": 374
},
{
"epoch": 0.93,
"learning_rate": 0.0003,
"loss": 0.7956,
"step": 375
},
{
"epoch": 0.93,
"learning_rate": 0.0003,
"loss": 0.802,
"step": 376
},
{
"epoch": 0.93,
"learning_rate": 0.0003,
"loss": 0.8449,
"step": 377
},
{
"epoch": 0.93,
"learning_rate": 0.0003,
"loss": 0.7775,
"step": 378
},
{
"epoch": 0.94,
"learning_rate": 0.0003,
"loss": 0.7988,
"step": 379
},
{
"epoch": 0.94,
"learning_rate": 0.0003,
"loss": 0.8193,
"step": 380
},
{
"epoch": 0.94,
"learning_rate": 0.0003,
"loss": 0.8197,
"step": 381
},
{
"epoch": 0.94,
"learning_rate": 0.0003,
"loss": 0.8213,
"step": 382
},
{
"epoch": 0.95,
"learning_rate": 0.0003,
"loss": 0.8168,
"step": 383
},
{
"epoch": 0.95,
"learning_rate": 0.0003,
"loss": 0.8144,
"step": 384
},
{
"epoch": 0.95,
"learning_rate": 0.0003,
"loss": 0.8058,
"step": 385
},
{
"epoch": 0.95,
"learning_rate": 0.0003,
"loss": 0.8189,
"step": 386
},
{
"epoch": 0.96,
"learning_rate": 0.0003,
"loss": 0.7832,
"step": 387
},
{
"epoch": 0.96,
"learning_rate": 0.0003,
"loss": 0.7697,
"step": 388
},
{
"epoch": 0.96,
"learning_rate": 0.0003,
"loss": 0.7869,
"step": 389
},
{
"epoch": 0.96,
"learning_rate": 0.0003,
"loss": 0.8478,
"step": 390
},
{
"epoch": 0.97,
"learning_rate": 0.0003,
"loss": 0.803,
"step": 391
},
{
"epoch": 0.97,
"learning_rate": 0.0003,
"loss": 0.8309,
"step": 392
},
{
"epoch": 0.97,
"learning_rate": 0.0003,
"loss": 0.795,
"step": 393
},
{
"epoch": 0.97,
"learning_rate": 0.0003,
"loss": 0.8193,
"step": 394
},
{
"epoch": 0.98,
"learning_rate": 0.0003,
"loss": 0.7853,
"step": 395
},
{
"epoch": 0.98,
"learning_rate": 0.0003,
"loss": 0.8157,
"step": 396
},
{
"epoch": 0.98,
"learning_rate": 0.0003,
"loss": 0.8198,
"step": 397
},
{
"epoch": 0.98,
"learning_rate": 0.0003,
"loss": 0.813,
"step": 398
},
{
"epoch": 0.99,
"learning_rate": 0.0003,
"loss": 0.8178,
"step": 399
},
{
"epoch": 0.99,
"learning_rate": 0.0003,
"loss": 0.7883,
"step": 400
},
{
"epoch": 0.99,
"learning_rate": 0.0003,
"loss": 0.802,
"step": 401
},
{
"epoch": 0.99,
"learning_rate": 0.0003,
"loss": 0.7938,
"step": 402
},
{
"epoch": 1.0,
"learning_rate": 0.0003,
"loss": 0.8183,
"step": 403
},
{
"epoch": 1.0,
"learning_rate": 0.0003,
"loss": 0.8004,
"step": 404
},
{
"epoch": 1.0,
"step": 404,
"total_flos": 4.5406536857338675e+17,
"train_loss": 0.8388028397123413,
"train_runtime": 5878.3336,
"train_samples_per_second": 8.805,
"train_steps_per_second": 0.069
}
],
"logging_steps": 1,
"max_steps": 404,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"total_flos": 4.5406536857338675e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}