pythia-adapter / trainer_state.json
TinyPixel's picture
Upload folder using huggingface_hub
ab8d5d1 verified
raw
history blame
10.9 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9972041006523766,
"eval_steps": 500,
"global_step": 201,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 2.2476,
"step": 2
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 2.2095,
"step": 4
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 1.7971,
"step": 6
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 1.7855,
"step": 8
},
{
"epoch": 0.15,
"learning_rate": 0.0002,
"loss": 1.5748,
"step": 10
},
{
"epoch": 0.18,
"learning_rate": 0.0002,
"loss": 1.514,
"step": 12
},
{
"epoch": 0.21,
"learning_rate": 0.0002,
"loss": 2.0154,
"step": 14
},
{
"epoch": 0.24,
"learning_rate": 0.0002,
"loss": 2.0265,
"step": 16
},
{
"epoch": 0.27,
"learning_rate": 0.0002,
"loss": 2.2248,
"step": 18
},
{
"epoch": 0.3,
"learning_rate": 0.0002,
"loss": 1.6516,
"step": 20
},
{
"epoch": 0.33,
"learning_rate": 0.0002,
"loss": 1.7012,
"step": 22
},
{
"epoch": 0.36,
"learning_rate": 0.0002,
"loss": 1.7529,
"step": 24
},
{
"epoch": 0.39,
"learning_rate": 0.0002,
"loss": 1.6224,
"step": 26
},
{
"epoch": 0.42,
"learning_rate": 0.0002,
"loss": 1.5869,
"step": 28
},
{
"epoch": 0.45,
"learning_rate": 0.0002,
"loss": 1.7821,
"step": 30
},
{
"epoch": 0.48,
"learning_rate": 0.0002,
"loss": 1.8414,
"step": 32
},
{
"epoch": 0.51,
"learning_rate": 0.0002,
"loss": 2.5965,
"step": 34
},
{
"epoch": 0.54,
"learning_rate": 0.0002,
"loss": 1.8098,
"step": 36
},
{
"epoch": 0.57,
"learning_rate": 0.0002,
"loss": 1.6632,
"step": 38
},
{
"epoch": 0.6,
"learning_rate": 0.0002,
"loss": 1.7756,
"step": 40
},
{
"epoch": 0.63,
"learning_rate": 0.0002,
"loss": 1.5594,
"step": 42
},
{
"epoch": 0.66,
"learning_rate": 0.0002,
"loss": 1.6928,
"step": 44
},
{
"epoch": 0.69,
"learning_rate": 0.0002,
"loss": 1.7223,
"step": 46
},
{
"epoch": 0.72,
"learning_rate": 0.0002,
"loss": 1.5006,
"step": 48
},
{
"epoch": 0.75,
"learning_rate": 0.0002,
"loss": 2.3682,
"step": 50
},
{
"epoch": 0.78,
"learning_rate": 0.0002,
"loss": 1.9393,
"step": 52
},
{
"epoch": 0.81,
"learning_rate": 0.0002,
"loss": 1.823,
"step": 54
},
{
"epoch": 0.84,
"learning_rate": 0.0002,
"loss": 1.6966,
"step": 56
},
{
"epoch": 0.86,
"learning_rate": 0.0002,
"loss": 1.5331,
"step": 58
},
{
"epoch": 0.89,
"learning_rate": 0.0002,
"loss": 1.5971,
"step": 60
},
{
"epoch": 0.92,
"learning_rate": 0.0002,
"loss": 1.7346,
"step": 62
},
{
"epoch": 0.95,
"learning_rate": 0.0002,
"loss": 1.6502,
"step": 64
},
{
"epoch": 0.98,
"learning_rate": 0.0002,
"loss": 1.7093,
"step": 66
},
{
"epoch": 1.01,
"learning_rate": 0.0002,
"loss": 1.9674,
"step": 68
},
{
"epoch": 1.04,
"learning_rate": 0.0002,
"loss": 2.1178,
"step": 70
},
{
"epoch": 1.07,
"learning_rate": 0.0002,
"loss": 1.6422,
"step": 72
},
{
"epoch": 1.1,
"learning_rate": 0.0002,
"loss": 1.5777,
"step": 74
},
{
"epoch": 1.13,
"learning_rate": 0.0002,
"loss": 1.6813,
"step": 76
},
{
"epoch": 1.16,
"learning_rate": 0.0002,
"loss": 1.4568,
"step": 78
},
{
"epoch": 1.19,
"learning_rate": 0.0002,
"loss": 1.4511,
"step": 80
},
{
"epoch": 1.22,
"learning_rate": 0.0002,
"loss": 1.6265,
"step": 82
},
{
"epoch": 1.25,
"learning_rate": 0.0002,
"loss": 1.2337,
"step": 84
},
{
"epoch": 1.28,
"learning_rate": 0.0002,
"loss": 2.0693,
"step": 86
},
{
"epoch": 1.31,
"learning_rate": 0.0002,
"loss": 1.6134,
"step": 88
},
{
"epoch": 1.34,
"learning_rate": 0.0002,
"loss": 1.5955,
"step": 90
},
{
"epoch": 1.37,
"learning_rate": 0.0002,
"loss": 1.4866,
"step": 92
},
{
"epoch": 1.4,
"learning_rate": 0.0002,
"loss": 1.4122,
"step": 94
},
{
"epoch": 1.43,
"learning_rate": 0.0002,
"loss": 1.4224,
"step": 96
},
{
"epoch": 1.46,
"learning_rate": 0.0002,
"loss": 1.5695,
"step": 98
},
{
"epoch": 1.49,
"learning_rate": 0.0002,
"loss": 1.7786,
"step": 100
},
{
"epoch": 1.52,
"learning_rate": 0.0002,
"loss": 2.3576,
"step": 102
},
{
"epoch": 1.55,
"learning_rate": 0.0002,
"loss": 1.6475,
"step": 104
},
{
"epoch": 1.58,
"learning_rate": 0.0002,
"loss": 1.7765,
"step": 106
},
{
"epoch": 1.61,
"learning_rate": 0.0002,
"loss": 1.5304,
"step": 108
},
{
"epoch": 1.64,
"learning_rate": 0.0002,
"loss": 1.33,
"step": 110
},
{
"epoch": 1.67,
"learning_rate": 0.0002,
"loss": 1.4141,
"step": 112
},
{
"epoch": 1.7,
"learning_rate": 0.0002,
"loss": 1.5615,
"step": 114
},
{
"epoch": 1.73,
"learning_rate": 0.0002,
"loss": 1.5599,
"step": 116
},
{
"epoch": 1.76,
"learning_rate": 0.0002,
"loss": 2.1615,
"step": 118
},
{
"epoch": 1.79,
"learning_rate": 0.0002,
"loss": 1.6991,
"step": 120
},
{
"epoch": 1.82,
"learning_rate": 0.0002,
"loss": 1.6502,
"step": 122
},
{
"epoch": 1.85,
"learning_rate": 0.0002,
"loss": 1.5974,
"step": 124
},
{
"epoch": 1.88,
"learning_rate": 0.0002,
"loss": 1.2396,
"step": 126
},
{
"epoch": 1.91,
"learning_rate": 0.0002,
"loss": 1.3839,
"step": 128
},
{
"epoch": 1.94,
"learning_rate": 0.0002,
"loss": 1.5737,
"step": 130
},
{
"epoch": 1.97,
"learning_rate": 0.0002,
"loss": 1.5733,
"step": 132
},
{
"epoch": 2.0,
"learning_rate": 0.0002,
"loss": 1.369,
"step": 134
},
{
"epoch": 2.03,
"learning_rate": 0.0002,
"loss": 2.2205,
"step": 136
},
{
"epoch": 2.06,
"learning_rate": 0.0002,
"loss": 2.0597,
"step": 138
},
{
"epoch": 2.09,
"learning_rate": 0.0002,
"loss": 1.5924,
"step": 140
},
{
"epoch": 2.12,
"learning_rate": 0.0002,
"loss": 1.5504,
"step": 142
},
{
"epoch": 2.15,
"learning_rate": 0.0002,
"loss": 1.4464,
"step": 144
},
{
"epoch": 2.18,
"learning_rate": 0.0002,
"loss": 1.3526,
"step": 146
},
{
"epoch": 2.21,
"learning_rate": 0.0002,
"loss": 1.2872,
"step": 148
},
{
"epoch": 2.24,
"learning_rate": 0.0002,
"loss": 1.139,
"step": 150
},
{
"epoch": 2.27,
"learning_rate": 0.0002,
"loss": 2.0427,
"step": 152
},
{
"epoch": 2.3,
"learning_rate": 0.0002,
"loss": 1.7152,
"step": 154
},
{
"epoch": 2.33,
"learning_rate": 0.0002,
"loss": 1.6782,
"step": 156
},
{
"epoch": 2.36,
"learning_rate": 0.0002,
"loss": 1.5993,
"step": 158
},
{
"epoch": 2.39,
"learning_rate": 0.0002,
"loss": 1.5009,
"step": 160
},
{
"epoch": 2.42,
"learning_rate": 0.0002,
"loss": 1.2242,
"step": 162
},
{
"epoch": 2.45,
"learning_rate": 0.0002,
"loss": 1.3298,
"step": 164
},
{
"epoch": 2.48,
"learning_rate": 0.0002,
"loss": 1.159,
"step": 166
},
{
"epoch": 2.51,
"learning_rate": 0.0002,
"loss": 2.0425,
"step": 168
},
{
"epoch": 2.53,
"learning_rate": 0.0002,
"loss": 1.7428,
"step": 170
},
{
"epoch": 2.56,
"learning_rate": 0.0002,
"loss": 1.6052,
"step": 172
},
{
"epoch": 2.59,
"learning_rate": 0.0002,
"loss": 1.5935,
"step": 174
},
{
"epoch": 2.62,
"learning_rate": 0.0002,
"loss": 1.3055,
"step": 176
},
{
"epoch": 2.65,
"learning_rate": 0.0002,
"loss": 1.1967,
"step": 178
},
{
"epoch": 2.68,
"learning_rate": 0.0002,
"loss": 1.3355,
"step": 180
},
{
"epoch": 2.71,
"learning_rate": 0.0002,
"loss": 1.0649,
"step": 182
},
{
"epoch": 2.74,
"learning_rate": 0.0002,
"loss": 2.3474,
"step": 184
},
{
"epoch": 2.77,
"learning_rate": 0.0002,
"loss": 1.6763,
"step": 186
},
{
"epoch": 2.8,
"learning_rate": 0.0002,
"loss": 1.5105,
"step": 188
},
{
"epoch": 2.83,
"learning_rate": 0.0002,
"loss": 1.5544,
"step": 190
},
{
"epoch": 2.86,
"learning_rate": 0.0002,
"loss": 1.1297,
"step": 192
},
{
"epoch": 2.89,
"learning_rate": 0.0002,
"loss": 1.2825,
"step": 194
},
{
"epoch": 2.92,
"learning_rate": 0.0002,
"loss": 1.3587,
"step": 196
},
{
"epoch": 2.95,
"learning_rate": 0.0002,
"loss": 1.2585,
"step": 198
},
{
"epoch": 2.98,
"learning_rate": 0.0002,
"loss": 1.3599,
"step": 200
}
],
"logging_steps": 2,
"max_steps": 201,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 8906354934939648.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}