pythia-exp / trainer_state.json
TinyPixel's picture
Upload folder using huggingface_hub
df625f2
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": 2.7611,
"step": 2
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 2.0534,
"step": 4
},
{
"epoch": 0.09,
"learning_rate": 0.0002,
"loss": 1.8546,
"step": 6
},
{
"epoch": 0.12,
"learning_rate": 0.0002,
"loss": 1.7224,
"step": 8
},
{
"epoch": 0.15,
"learning_rate": 0.0002,
"loss": 1.5704,
"step": 10
},
{
"epoch": 0.18,
"learning_rate": 0.0002,
"loss": 1.701,
"step": 12
},
{
"epoch": 0.21,
"learning_rate": 0.0002,
"loss": 2.1142,
"step": 14
},
{
"epoch": 0.24,
"learning_rate": 0.0002,
"loss": 2.1463,
"step": 16
},
{
"epoch": 0.27,
"learning_rate": 0.0002,
"loss": 2.28,
"step": 18
},
{
"epoch": 0.3,
"learning_rate": 0.0002,
"loss": 1.9174,
"step": 20
},
{
"epoch": 0.33,
"learning_rate": 0.0002,
"loss": 1.8062,
"step": 22
},
{
"epoch": 0.36,
"learning_rate": 0.0002,
"loss": 1.7627,
"step": 24
},
{
"epoch": 0.39,
"learning_rate": 0.0002,
"loss": 1.6455,
"step": 26
},
{
"epoch": 0.42,
"learning_rate": 0.0002,
"loss": 1.7599,
"step": 28
},
{
"epoch": 0.45,
"learning_rate": 0.0002,
"loss": 1.9044,
"step": 30
},
{
"epoch": 0.48,
"learning_rate": 0.0002,
"loss": 1.8191,
"step": 32
},
{
"epoch": 0.51,
"learning_rate": 0.0002,
"loss": 2.2867,
"step": 34
},
{
"epoch": 0.54,
"learning_rate": 0.0002,
"loss": 1.8142,
"step": 36
},
{
"epoch": 0.57,
"learning_rate": 0.0002,
"loss": 1.7659,
"step": 38
},
{
"epoch": 0.6,
"learning_rate": 0.0002,
"loss": 1.7533,
"step": 40
},
{
"epoch": 0.63,
"learning_rate": 0.0002,
"loss": 1.4815,
"step": 42
},
{
"epoch": 0.66,
"learning_rate": 0.0002,
"loss": 1.6431,
"step": 44
},
{
"epoch": 0.69,
"learning_rate": 0.0002,
"loss": 1.7396,
"step": 46
},
{
"epoch": 0.72,
"learning_rate": 0.0002,
"loss": 1.657,
"step": 48
},
{
"epoch": 0.75,
"learning_rate": 0.0002,
"loss": 2.4034,
"step": 50
},
{
"epoch": 0.78,
"learning_rate": 0.0002,
"loss": 1.6792,
"step": 52
},
{
"epoch": 0.81,
"learning_rate": 0.0002,
"loss": 1.7176,
"step": 54
},
{
"epoch": 0.84,
"learning_rate": 0.0002,
"loss": 1.6806,
"step": 56
},
{
"epoch": 0.86,
"learning_rate": 0.0002,
"loss": 1.4216,
"step": 58
},
{
"epoch": 0.89,
"learning_rate": 0.0002,
"loss": 1.5723,
"step": 60
},
{
"epoch": 0.92,
"learning_rate": 0.0002,
"loss": 1.6799,
"step": 62
},
{
"epoch": 0.95,
"learning_rate": 0.0002,
"loss": 1.7065,
"step": 64
},
{
"epoch": 0.98,
"learning_rate": 0.0002,
"loss": 1.7307,
"step": 66
},
{
"epoch": 1.01,
"learning_rate": 0.0002,
"loss": 1.9236,
"step": 68
},
{
"epoch": 1.04,
"learning_rate": 0.0002,
"loss": 2.078,
"step": 70
},
{
"epoch": 1.07,
"learning_rate": 0.0002,
"loss": 1.7343,
"step": 72
},
{
"epoch": 1.1,
"learning_rate": 0.0002,
"loss": 1.7106,
"step": 74
},
{
"epoch": 1.13,
"learning_rate": 0.0002,
"loss": 1.491,
"step": 76
},
{
"epoch": 1.16,
"learning_rate": 0.0002,
"loss": 1.4934,
"step": 78
},
{
"epoch": 1.19,
"learning_rate": 0.0002,
"loss": 1.5139,
"step": 80
},
{
"epoch": 1.22,
"learning_rate": 0.0002,
"loss": 1.5726,
"step": 82
},
{
"epoch": 1.25,
"learning_rate": 0.0002,
"loss": 1.7851,
"step": 84
},
{
"epoch": 1.28,
"learning_rate": 0.0002,
"loss": 2.2004,
"step": 86
},
{
"epoch": 1.31,
"learning_rate": 0.0002,
"loss": 1.614,
"step": 88
},
{
"epoch": 1.34,
"learning_rate": 0.0002,
"loss": 1.6361,
"step": 90
},
{
"epoch": 1.37,
"learning_rate": 0.0002,
"loss": 1.5856,
"step": 92
},
{
"epoch": 1.4,
"learning_rate": 0.0002,
"loss": 1.3014,
"step": 94
},
{
"epoch": 1.43,
"learning_rate": 0.0002,
"loss": 1.5709,
"step": 96
},
{
"epoch": 1.46,
"learning_rate": 0.0002,
"loss": 1.6687,
"step": 98
},
{
"epoch": 1.49,
"learning_rate": 0.0002,
"loss": 1.7529,
"step": 100
},
{
"epoch": 1.52,
"learning_rate": 0.0002,
"loss": 2.0307,
"step": 102
},
{
"epoch": 1.55,
"learning_rate": 0.0002,
"loss": 1.6563,
"step": 104
},
{
"epoch": 1.58,
"learning_rate": 0.0002,
"loss": 1.5444,
"step": 106
},
{
"epoch": 1.61,
"learning_rate": 0.0002,
"loss": 1.5678,
"step": 108
},
{
"epoch": 1.64,
"learning_rate": 0.0002,
"loss": 1.2937,
"step": 110
},
{
"epoch": 1.67,
"learning_rate": 0.0002,
"loss": 1.4848,
"step": 112
},
{
"epoch": 1.7,
"learning_rate": 0.0002,
"loss": 1.6739,
"step": 114
},
{
"epoch": 1.73,
"learning_rate": 0.0002,
"loss": 1.6185,
"step": 116
},
{
"epoch": 1.76,
"learning_rate": 0.0002,
"loss": 1.9855,
"step": 118
},
{
"epoch": 1.79,
"learning_rate": 0.0002,
"loss": 1.6515,
"step": 120
},
{
"epoch": 1.82,
"learning_rate": 0.0002,
"loss": 1.6412,
"step": 122
},
{
"epoch": 1.85,
"learning_rate": 0.0002,
"loss": 1.6263,
"step": 124
},
{
"epoch": 1.88,
"learning_rate": 0.0002,
"loss": 1.3411,
"step": 126
},
{
"epoch": 1.91,
"learning_rate": 0.0002,
"loss": 1.5003,
"step": 128
},
{
"epoch": 1.94,
"learning_rate": 0.0002,
"loss": 1.6156,
"step": 130
},
{
"epoch": 1.97,
"learning_rate": 0.0002,
"loss": 1.6351,
"step": 132
},
{
"epoch": 2.0,
"learning_rate": 0.0002,
"loss": 1.4533,
"step": 134
},
{
"epoch": 2.03,
"learning_rate": 0.0002,
"loss": 2.065,
"step": 136
},
{
"epoch": 2.06,
"learning_rate": 0.0002,
"loss": 1.9513,
"step": 138
},
{
"epoch": 2.09,
"learning_rate": 0.0002,
"loss": 1.5904,
"step": 140
},
{
"epoch": 2.12,
"learning_rate": 0.0002,
"loss": 1.5137,
"step": 142
},
{
"epoch": 2.15,
"learning_rate": 0.0002,
"loss": 1.3142,
"step": 144
},
{
"epoch": 2.18,
"learning_rate": 0.0002,
"loss": 1.2811,
"step": 146
},
{
"epoch": 2.21,
"learning_rate": 0.0002,
"loss": 1.307,
"step": 148
},
{
"epoch": 2.24,
"learning_rate": 0.0002,
"loss": 1.3048,
"step": 150
},
{
"epoch": 2.27,
"learning_rate": 0.0002,
"loss": 2.1982,
"step": 152
},
{
"epoch": 2.3,
"learning_rate": 0.0002,
"loss": 1.792,
"step": 154
},
{
"epoch": 2.33,
"learning_rate": 0.0002,
"loss": 1.6401,
"step": 156
},
{
"epoch": 2.36,
"learning_rate": 0.0002,
"loss": 1.5942,
"step": 158
},
{
"epoch": 2.39,
"learning_rate": 0.0002,
"loss": 1.3007,
"step": 160
},
{
"epoch": 2.42,
"learning_rate": 0.0002,
"loss": 1.2533,
"step": 162
},
{
"epoch": 2.45,
"learning_rate": 0.0002,
"loss": 1.4146,
"step": 164
},
{
"epoch": 2.48,
"learning_rate": 0.0002,
"loss": 1.1527,
"step": 166
},
{
"epoch": 2.51,
"learning_rate": 0.0002,
"loss": 2.0213,
"step": 168
},
{
"epoch": 2.53,
"learning_rate": 0.0002,
"loss": 1.617,
"step": 170
},
{
"epoch": 2.56,
"learning_rate": 0.0002,
"loss": 1.5848,
"step": 172
},
{
"epoch": 2.59,
"learning_rate": 0.0002,
"loss": 1.553,
"step": 174
},
{
"epoch": 2.62,
"learning_rate": 0.0002,
"loss": 1.425,
"step": 176
},
{
"epoch": 2.65,
"learning_rate": 0.0002,
"loss": 1.2844,
"step": 178
},
{
"epoch": 2.68,
"learning_rate": 0.0002,
"loss": 1.2933,
"step": 180
},
{
"epoch": 2.71,
"learning_rate": 0.0002,
"loss": 1.1767,
"step": 182
},
{
"epoch": 2.74,
"learning_rate": 0.0002,
"loss": 2.1534,
"step": 184
},
{
"epoch": 2.77,
"learning_rate": 0.0002,
"loss": 1.7644,
"step": 186
},
{
"epoch": 2.8,
"learning_rate": 0.0002,
"loss": 1.6005,
"step": 188
},
{
"epoch": 2.83,
"learning_rate": 0.0002,
"loss": 1.6655,
"step": 190
},
{
"epoch": 2.86,
"learning_rate": 0.0002,
"loss": 1.3768,
"step": 192
},
{
"epoch": 2.89,
"learning_rate": 0.0002,
"loss": 1.2941,
"step": 194
},
{
"epoch": 2.92,
"learning_rate": 0.0002,
"loss": 1.3398,
"step": 196
},
{
"epoch": 2.95,
"learning_rate": 0.0002,
"loss": 1.2624,
"step": 198
},
{
"epoch": 2.98,
"learning_rate": 0.0002,
"loss": 1.884,
"step": 200
}
],
"logging_steps": 2,
"max_steps": 201,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 8822423073988608.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}