ToolAlpaca-7B / trainer_state.json
TangQiaoYu's picture
upload
be35992
raw
history blame
10.2 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"global_step": 93,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 0.0,
"loss": 0.6543,
"step": 1
},
{
"epoch": 0.06,
"learning_rate": 1.2618595071429148e-05,
"loss": 0.3535,
"step": 2
},
{
"epoch": 0.1,
"learning_rate": 2e-05,
"loss": 0.3599,
"step": 3
},
{
"epoch": 0.13,
"learning_rate": 2e-05,
"loss": 0.2832,
"step": 4
},
{
"epoch": 0.16,
"learning_rate": 2e-05,
"loss": 0.2739,
"step": 5
},
{
"epoch": 0.19,
"learning_rate": 2e-05,
"loss": 0.2388,
"step": 6
},
{
"epoch": 0.23,
"learning_rate": 2e-05,
"loss": 0.2554,
"step": 7
},
{
"epoch": 0.26,
"learning_rate": 2e-05,
"loss": 0.2375,
"step": 8
},
{
"epoch": 0.29,
"learning_rate": 2e-05,
"loss": 0.2207,
"step": 9
},
{
"epoch": 0.32,
"learning_rate": 2e-05,
"loss": 0.2139,
"step": 10
},
{
"epoch": 0.35,
"learning_rate": 2e-05,
"loss": 0.2019,
"step": 11
},
{
"epoch": 0.39,
"learning_rate": 2e-05,
"loss": 0.1963,
"step": 12
},
{
"epoch": 0.42,
"learning_rate": 2e-05,
"loss": 0.1826,
"step": 13
},
{
"epoch": 0.45,
"learning_rate": 2e-05,
"loss": 0.2029,
"step": 14
},
{
"epoch": 0.48,
"learning_rate": 2e-05,
"loss": 0.186,
"step": 15
},
{
"epoch": 0.52,
"learning_rate": 2e-05,
"loss": 0.197,
"step": 16
},
{
"epoch": 0.55,
"learning_rate": 2e-05,
"loss": 0.1863,
"step": 17
},
{
"epoch": 0.58,
"learning_rate": 2e-05,
"loss": 0.1787,
"step": 18
},
{
"epoch": 0.61,
"learning_rate": 2e-05,
"loss": 0.1902,
"step": 19
},
{
"epoch": 0.65,
"learning_rate": 2e-05,
"loss": 0.1775,
"step": 20
},
{
"epoch": 0.68,
"learning_rate": 2e-05,
"loss": 0.1707,
"step": 21
},
{
"epoch": 0.71,
"learning_rate": 2e-05,
"loss": 0.1785,
"step": 22
},
{
"epoch": 0.74,
"learning_rate": 2e-05,
"loss": 0.1836,
"step": 23
},
{
"epoch": 0.77,
"learning_rate": 2e-05,
"loss": 0.1655,
"step": 24
},
{
"epoch": 0.81,
"learning_rate": 2e-05,
"loss": 0.1707,
"step": 25
},
{
"epoch": 0.84,
"learning_rate": 2e-05,
"loss": 0.1687,
"step": 26
},
{
"epoch": 0.87,
"learning_rate": 2e-05,
"loss": 0.1765,
"step": 27
},
{
"epoch": 0.9,
"learning_rate": 2e-05,
"loss": 0.1567,
"step": 28
},
{
"epoch": 0.94,
"learning_rate": 2e-05,
"loss": 0.1694,
"step": 29
},
{
"epoch": 0.97,
"learning_rate": 2e-05,
"loss": 0.1572,
"step": 30
},
{
"epoch": 1.0,
"learning_rate": 2e-05,
"loss": 0.1743,
"step": 31
},
{
"epoch": 1.03,
"learning_rate": 2e-05,
"loss": 0.1055,
"step": 32
},
{
"epoch": 1.06,
"learning_rate": 2e-05,
"loss": 0.1014,
"step": 33
},
{
"epoch": 1.1,
"learning_rate": 2e-05,
"loss": 0.0975,
"step": 34
},
{
"epoch": 1.13,
"learning_rate": 2e-05,
"loss": 0.0986,
"step": 35
},
{
"epoch": 1.16,
"learning_rate": 2e-05,
"loss": 0.0856,
"step": 36
},
{
"epoch": 1.19,
"learning_rate": 2e-05,
"loss": 0.0837,
"step": 37
},
{
"epoch": 1.23,
"learning_rate": 2e-05,
"loss": 0.0979,
"step": 38
},
{
"epoch": 1.26,
"learning_rate": 2e-05,
"loss": 0.0898,
"step": 39
},
{
"epoch": 1.29,
"learning_rate": 2e-05,
"loss": 0.0828,
"step": 40
},
{
"epoch": 1.32,
"learning_rate": 2e-05,
"loss": 0.0923,
"step": 41
},
{
"epoch": 1.35,
"learning_rate": 2e-05,
"loss": 0.1002,
"step": 42
},
{
"epoch": 1.39,
"learning_rate": 2e-05,
"loss": 0.0935,
"step": 43
},
{
"epoch": 1.42,
"learning_rate": 2e-05,
"loss": 0.0826,
"step": 44
},
{
"epoch": 1.45,
"learning_rate": 2e-05,
"loss": 0.082,
"step": 45
},
{
"epoch": 1.48,
"learning_rate": 2e-05,
"loss": 0.0864,
"step": 46
},
{
"epoch": 1.52,
"learning_rate": 2e-05,
"loss": 0.0906,
"step": 47
},
{
"epoch": 1.55,
"learning_rate": 2e-05,
"loss": 0.0852,
"step": 48
},
{
"epoch": 1.58,
"learning_rate": 2e-05,
"loss": 0.0894,
"step": 49
},
{
"epoch": 1.61,
"learning_rate": 2e-05,
"loss": 0.0775,
"step": 50
},
{
"epoch": 1.65,
"learning_rate": 2e-05,
"loss": 0.0885,
"step": 51
},
{
"epoch": 1.68,
"learning_rate": 2e-05,
"loss": 0.0818,
"step": 52
},
{
"epoch": 1.71,
"learning_rate": 2e-05,
"loss": 0.0753,
"step": 53
},
{
"epoch": 1.74,
"learning_rate": 2e-05,
"loss": 0.0786,
"step": 54
},
{
"epoch": 1.77,
"learning_rate": 2e-05,
"loss": 0.0797,
"step": 55
},
{
"epoch": 1.81,
"learning_rate": 2e-05,
"loss": 0.0863,
"step": 56
},
{
"epoch": 1.84,
"learning_rate": 2e-05,
"loss": 0.0851,
"step": 57
},
{
"epoch": 1.87,
"learning_rate": 2e-05,
"loss": 0.089,
"step": 58
},
{
"epoch": 1.9,
"learning_rate": 2e-05,
"loss": 0.0887,
"step": 59
},
{
"epoch": 1.94,
"learning_rate": 2e-05,
"loss": 0.0801,
"step": 60
},
{
"epoch": 1.97,
"learning_rate": 2e-05,
"loss": 0.0938,
"step": 61
},
{
"epoch": 2.0,
"learning_rate": 2e-05,
"loss": 0.0868,
"step": 62
},
{
"epoch": 2.03,
"learning_rate": 2e-05,
"loss": 0.0435,
"step": 63
},
{
"epoch": 2.06,
"learning_rate": 2e-05,
"loss": 0.0484,
"step": 64
},
{
"epoch": 2.1,
"learning_rate": 2e-05,
"loss": 0.0419,
"step": 65
},
{
"epoch": 2.13,
"learning_rate": 2e-05,
"loss": 0.0395,
"step": 66
},
{
"epoch": 2.16,
"learning_rate": 2e-05,
"loss": 0.0421,
"step": 67
},
{
"epoch": 2.19,
"learning_rate": 2e-05,
"loss": 0.0357,
"step": 68
},
{
"epoch": 2.23,
"learning_rate": 2e-05,
"loss": 0.0459,
"step": 69
},
{
"epoch": 2.26,
"learning_rate": 2e-05,
"loss": 0.041,
"step": 70
},
{
"epoch": 2.29,
"learning_rate": 2e-05,
"loss": 0.0411,
"step": 71
},
{
"epoch": 2.32,
"learning_rate": 2e-05,
"loss": 0.0444,
"step": 72
},
{
"epoch": 2.35,
"learning_rate": 2e-05,
"loss": 0.0406,
"step": 73
},
{
"epoch": 2.39,
"learning_rate": 2e-05,
"loss": 0.0412,
"step": 74
},
{
"epoch": 2.42,
"learning_rate": 2e-05,
"loss": 0.0448,
"step": 75
},
{
"epoch": 2.45,
"learning_rate": 2e-05,
"loss": 0.0374,
"step": 76
},
{
"epoch": 2.48,
"learning_rate": 2e-05,
"loss": 0.0446,
"step": 77
},
{
"epoch": 2.52,
"learning_rate": 2e-05,
"loss": 0.0411,
"step": 78
},
{
"epoch": 2.55,
"learning_rate": 2e-05,
"loss": 0.041,
"step": 79
},
{
"epoch": 2.58,
"learning_rate": 2e-05,
"loss": 0.0406,
"step": 80
},
{
"epoch": 2.61,
"learning_rate": 2e-05,
"loss": 0.0444,
"step": 81
},
{
"epoch": 2.65,
"learning_rate": 2e-05,
"loss": 0.0439,
"step": 82
},
{
"epoch": 2.68,
"learning_rate": 2e-05,
"loss": 0.0433,
"step": 83
},
{
"epoch": 2.71,
"learning_rate": 2e-05,
"loss": 0.0443,
"step": 84
},
{
"epoch": 2.74,
"learning_rate": 2e-05,
"loss": 0.0422,
"step": 85
},
{
"epoch": 2.77,
"learning_rate": 2e-05,
"loss": 0.0411,
"step": 86
},
{
"epoch": 2.81,
"learning_rate": 2e-05,
"loss": 0.0463,
"step": 87
},
{
"epoch": 2.84,
"learning_rate": 2e-05,
"loss": 0.0408,
"step": 88
},
{
"epoch": 2.87,
"learning_rate": 2e-05,
"loss": 0.0425,
"step": 89
},
{
"epoch": 2.9,
"learning_rate": 2e-05,
"loss": 0.0441,
"step": 90
},
{
"epoch": 2.94,
"learning_rate": 2e-05,
"loss": 0.0441,
"step": 91
},
{
"epoch": 2.97,
"learning_rate": 2e-05,
"loss": 0.0475,
"step": 92
},
{
"epoch": 3.0,
"learning_rate": 2e-05,
"loss": 0.0456,
"step": 93
},
{
"epoch": 3.0,
"step": 93,
"total_flos": 38440796160000.0,
"train_loss": 0.1174569078671035,
"train_runtime": 5368.2591,
"train_samples_per_second": 2.2,
"train_steps_per_second": 0.017
}
],
"max_steps": 93,
"num_train_epochs": 3,
"total_flos": 38440796160000.0,
"trial_name": null,
"trial_params": null
}