Weyaxi's picture
Upload folder using huggingface_hub
8946471
raw
history blame
7.14 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9927611168562565,
"eval_steps": 500,
"global_step": 60,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 4.000000000000001e-06,
"loss": 0.643,
"step": 1
},
{
"epoch": 0.03,
"learning_rate": 8.000000000000001e-06,
"loss": 0.6409,
"step": 2
},
{
"epoch": 0.05,
"learning_rate": 1.2e-05,
"loss": 0.5779,
"step": 3
},
{
"epoch": 0.07,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.6641,
"step": 4
},
{
"epoch": 0.08,
"learning_rate": 2e-05,
"loss": 0.61,
"step": 5
},
{
"epoch": 0.1,
"learning_rate": 2.4e-05,
"loss": 0.6653,
"step": 6
},
{
"epoch": 0.12,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.6101,
"step": 7
},
{
"epoch": 0.13,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.7479,
"step": 8
},
{
"epoch": 0.15,
"learning_rate": 3.6e-05,
"loss": 0.6357,
"step": 9
},
{
"epoch": 0.17,
"learning_rate": 4e-05,
"loss": 0.6214,
"step": 10
},
{
"epoch": 0.18,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.6257,
"step": 11
},
{
"epoch": 0.2,
"learning_rate": 4.8e-05,
"loss": 0.6228,
"step": 12
},
{
"epoch": 0.22,
"learning_rate": 5.2000000000000004e-05,
"loss": 0.6295,
"step": 13
},
{
"epoch": 0.23,
"learning_rate": 5.6000000000000006e-05,
"loss": 0.6345,
"step": 14
},
{
"epoch": 0.25,
"learning_rate": 6e-05,
"loss": 0.6282,
"step": 15
},
{
"epoch": 0.26,
"learning_rate": 6.400000000000001e-05,
"loss": 0.6231,
"step": 16
},
{
"epoch": 0.28,
"learning_rate": 6.800000000000001e-05,
"loss": 0.6282,
"step": 17
},
{
"epoch": 0.3,
"learning_rate": 7.2e-05,
"loss": 0.6423,
"step": 18
},
{
"epoch": 0.31,
"learning_rate": 7.6e-05,
"loss": 0.6055,
"step": 19
},
{
"epoch": 0.33,
"learning_rate": 8e-05,
"loss": 0.6244,
"step": 20
},
{
"epoch": 0.35,
"learning_rate": 8.4e-05,
"loss": 0.5443,
"step": 21
},
{
"epoch": 0.36,
"learning_rate": 8.800000000000001e-05,
"loss": 0.6479,
"step": 22
},
{
"epoch": 0.38,
"learning_rate": 9.200000000000001e-05,
"loss": 0.5565,
"step": 23
},
{
"epoch": 0.4,
"learning_rate": 9.6e-05,
"loss": 0.6131,
"step": 24
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 0.6696,
"step": 25
},
{
"epoch": 0.43,
"learning_rate": 0.00010400000000000001,
"loss": 0.5886,
"step": 26
},
{
"epoch": 0.45,
"learning_rate": 0.00010800000000000001,
"loss": 0.5999,
"step": 27
},
{
"epoch": 0.46,
"learning_rate": 0.00011200000000000001,
"loss": 0.7083,
"step": 28
},
{
"epoch": 0.48,
"learning_rate": 0.000116,
"loss": 0.6178,
"step": 29
},
{
"epoch": 0.5,
"learning_rate": 0.00012,
"loss": 0.6466,
"step": 30
},
{
"epoch": 0.51,
"learning_rate": 0.000124,
"loss": 0.5462,
"step": 31
},
{
"epoch": 0.53,
"learning_rate": 0.00012800000000000002,
"loss": 0.6239,
"step": 32
},
{
"epoch": 0.55,
"learning_rate": 0.000132,
"loss": 0.6646,
"step": 33
},
{
"epoch": 0.56,
"learning_rate": 0.00013600000000000003,
"loss": 0.6293,
"step": 34
},
{
"epoch": 0.58,
"learning_rate": 0.00014,
"loss": 0.5853,
"step": 35
},
{
"epoch": 0.6,
"learning_rate": 0.000144,
"loss": 0.6881,
"step": 36
},
{
"epoch": 0.61,
"learning_rate": 0.000148,
"loss": 0.6398,
"step": 37
},
{
"epoch": 0.63,
"learning_rate": 0.000152,
"loss": 0.6054,
"step": 38
},
{
"epoch": 0.65,
"learning_rate": 0.00015600000000000002,
"loss": 0.6332,
"step": 39
},
{
"epoch": 0.66,
"learning_rate": 0.00016,
"loss": 0.5941,
"step": 40
},
{
"epoch": 0.68,
"learning_rate": 0.000164,
"loss": 0.6127,
"step": 41
},
{
"epoch": 0.69,
"learning_rate": 0.000168,
"loss": 0.6475,
"step": 42
},
{
"epoch": 0.71,
"learning_rate": 0.000172,
"loss": 0.5668,
"step": 43
},
{
"epoch": 0.73,
"learning_rate": 0.00017600000000000002,
"loss": 0.6348,
"step": 44
},
{
"epoch": 0.74,
"learning_rate": 0.00018,
"loss": 0.6379,
"step": 45
},
{
"epoch": 0.76,
"learning_rate": 0.00018400000000000003,
"loss": 0.5992,
"step": 46
},
{
"epoch": 0.78,
"learning_rate": 0.000188,
"loss": 0.6435,
"step": 47
},
{
"epoch": 0.79,
"learning_rate": 0.000192,
"loss": 0.5909,
"step": 48
},
{
"epoch": 0.81,
"learning_rate": 0.000196,
"loss": 0.6596,
"step": 49
},
{
"epoch": 0.83,
"learning_rate": 0.0002,
"loss": 0.6426,
"step": 50
},
{
"epoch": 0.84,
"learning_rate": 0.00020400000000000003,
"loss": 0.5908,
"step": 51
},
{
"epoch": 0.86,
"learning_rate": 0.00020800000000000001,
"loss": 0.5486,
"step": 52
},
{
"epoch": 0.88,
"learning_rate": 0.00021200000000000003,
"loss": 0.6184,
"step": 53
},
{
"epoch": 0.89,
"learning_rate": 0.00021600000000000002,
"loss": 0.6977,
"step": 54
},
{
"epoch": 0.91,
"learning_rate": 0.00022000000000000003,
"loss": 0.6308,
"step": 55
},
{
"epoch": 0.93,
"learning_rate": 0.00022400000000000002,
"loss": 0.5394,
"step": 56
},
{
"epoch": 0.94,
"learning_rate": 0.00022799999999999999,
"loss": 0.5426,
"step": 57
},
{
"epoch": 0.96,
"learning_rate": 0.000232,
"loss": 0.5429,
"step": 58
},
{
"epoch": 0.98,
"learning_rate": 0.000236,
"loss": 0.5822,
"step": 59
},
{
"epoch": 0.99,
"learning_rate": 0.00024,
"loss": 0.5793,
"step": 60
}
],
"logging_steps": 1,
"max_steps": 180,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 10,
"total_flos": 2.07429203165184e+17,
"trial_name": null,
"trial_params": null
}