CodeGeneration / trainer_state.json
SushantGautam's picture
End of training
e2541a4
raw
history blame
8.76 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"global_step": 70,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.14,
"learning_rate": 4.928571428571429e-05,
"loss": 3.0215,
"step": 1
},
{
"epoch": 0.29,
"learning_rate": 4.8571428571428576e-05,
"loss": 3.396,
"step": 2
},
{
"epoch": 0.43,
"learning_rate": 4.785714285714286e-05,
"loss": 2.7081,
"step": 3
},
{
"epoch": 0.57,
"learning_rate": 4.714285714285714e-05,
"loss": 2.81,
"step": 4
},
{
"epoch": 0.71,
"learning_rate": 4.642857142857143e-05,
"loss": 2.7994,
"step": 5
},
{
"epoch": 0.86,
"learning_rate": 4.5714285714285716e-05,
"loss": 2.5904,
"step": 6
},
{
"epoch": 1.0,
"learning_rate": 4.5e-05,
"loss": 3.1253,
"step": 7
},
{
"epoch": 1.14,
"learning_rate": 4.428571428571428e-05,
"loss": 2.7843,
"step": 8
},
{
"epoch": 1.29,
"learning_rate": 4.3571428571428576e-05,
"loss": 2.6066,
"step": 9
},
{
"epoch": 1.43,
"learning_rate": 4.2857142857142856e-05,
"loss": 2.6174,
"step": 10
},
{
"epoch": 1.57,
"learning_rate": 4.214285714285714e-05,
"loss": 2.619,
"step": 11
},
{
"epoch": 1.71,
"learning_rate": 4.1428571428571437e-05,
"loss": 2.7048,
"step": 12
},
{
"epoch": 1.86,
"learning_rate": 4.0714285714285717e-05,
"loss": 2.5045,
"step": 13
},
{
"epoch": 2.0,
"learning_rate": 4e-05,
"loss": 2.6195,
"step": 14
},
{
"epoch": 2.14,
"learning_rate": 3.928571428571429e-05,
"loss": 2.276,
"step": 15
},
{
"epoch": 2.29,
"learning_rate": 3.857142857142858e-05,
"loss": 2.4503,
"step": 16
},
{
"epoch": 2.43,
"learning_rate": 3.785714285714286e-05,
"loss": 2.5767,
"step": 17
},
{
"epoch": 2.57,
"learning_rate": 3.7142857142857143e-05,
"loss": 2.4256,
"step": 18
},
{
"epoch": 2.71,
"learning_rate": 3.642857142857143e-05,
"loss": 2.6956,
"step": 19
},
{
"epoch": 2.86,
"learning_rate": 3.571428571428572e-05,
"loss": 2.5666,
"step": 20
},
{
"epoch": 3.0,
"learning_rate": 3.5e-05,
"loss": 2.5238,
"step": 21
},
{
"epoch": 3.14,
"learning_rate": 3.428571428571429e-05,
"loss": 2.4623,
"step": 22
},
{
"epoch": 3.29,
"learning_rate": 3.357142857142857e-05,
"loss": 2.5452,
"step": 23
},
{
"epoch": 3.43,
"learning_rate": 3.285714285714286e-05,
"loss": 2.4905,
"step": 24
},
{
"epoch": 3.57,
"learning_rate": 3.2142857142857144e-05,
"loss": 2.5106,
"step": 25
},
{
"epoch": 3.71,
"learning_rate": 3.142857142857143e-05,
"loss": 2.2134,
"step": 26
},
{
"epoch": 3.86,
"learning_rate": 3.071428571428572e-05,
"loss": 2.3214,
"step": 27
},
{
"epoch": 4.0,
"learning_rate": 3e-05,
"loss": 1.8621,
"step": 28
},
{
"epoch": 4.14,
"learning_rate": 2.9285714285714288e-05,
"loss": 2.4828,
"step": 29
},
{
"epoch": 4.29,
"learning_rate": 2.857142857142857e-05,
"loss": 2.3785,
"step": 30
},
{
"epoch": 4.43,
"learning_rate": 2.785714285714286e-05,
"loss": 2.2715,
"step": 31
},
{
"epoch": 4.57,
"learning_rate": 2.714285714285714e-05,
"loss": 2.1797,
"step": 32
},
{
"epoch": 4.71,
"learning_rate": 2.642857142857143e-05,
"loss": 2.22,
"step": 33
},
{
"epoch": 4.86,
"learning_rate": 2.5714285714285714e-05,
"loss": 2.4549,
"step": 34
},
{
"epoch": 5.0,
"learning_rate": 2.5e-05,
"loss": 2.207,
"step": 35
},
{
"epoch": 5.14,
"learning_rate": 2.4285714285714288e-05,
"loss": 2.3845,
"step": 36
},
{
"epoch": 5.29,
"learning_rate": 2.357142857142857e-05,
"loss": 2.2862,
"step": 37
},
{
"epoch": 5.43,
"learning_rate": 2.2857142857142858e-05,
"loss": 2.2408,
"step": 38
},
{
"epoch": 5.57,
"learning_rate": 2.214285714285714e-05,
"loss": 2.4339,
"step": 39
},
{
"epoch": 5.71,
"learning_rate": 2.1428571428571428e-05,
"loss": 1.9903,
"step": 40
},
{
"epoch": 5.86,
"learning_rate": 2.0714285714285718e-05,
"loss": 2.2583,
"step": 41
},
{
"epoch": 6.0,
"learning_rate": 2e-05,
"loss": 2.6031,
"step": 42
},
{
"epoch": 6.14,
"learning_rate": 1.928571428571429e-05,
"loss": 2.1461,
"step": 43
},
{
"epoch": 6.29,
"learning_rate": 1.8571428571428572e-05,
"loss": 2.1812,
"step": 44
},
{
"epoch": 6.43,
"learning_rate": 1.785714285714286e-05,
"loss": 2.1179,
"step": 45
},
{
"epoch": 6.57,
"learning_rate": 1.7142857142857145e-05,
"loss": 2.3383,
"step": 46
},
{
"epoch": 6.71,
"learning_rate": 1.642857142857143e-05,
"loss": 2.3931,
"step": 47
},
{
"epoch": 6.86,
"learning_rate": 1.5714285714285715e-05,
"loss": 2.1934,
"step": 48
},
{
"epoch": 7.0,
"learning_rate": 1.5e-05,
"loss": 2.189,
"step": 49
},
{
"epoch": 7.14,
"learning_rate": 1.4285714285714285e-05,
"loss": 2.0834,
"step": 50
},
{
"epoch": 7.29,
"learning_rate": 1.357142857142857e-05,
"loss": 2.1371,
"step": 51
},
{
"epoch": 7.43,
"learning_rate": 1.2857142857142857e-05,
"loss": 2.0772,
"step": 52
},
{
"epoch": 7.57,
"learning_rate": 1.2142857142857144e-05,
"loss": 2.3063,
"step": 53
},
{
"epoch": 7.71,
"learning_rate": 1.1428571428571429e-05,
"loss": 2.2691,
"step": 54
},
{
"epoch": 7.86,
"learning_rate": 1.0714285714285714e-05,
"loss": 2.2412,
"step": 55
},
{
"epoch": 8.0,
"learning_rate": 1e-05,
"loss": 2.5235,
"step": 56
},
{
"epoch": 8.14,
"learning_rate": 9.285714285714286e-06,
"loss": 2.239,
"step": 57
},
{
"epoch": 8.29,
"learning_rate": 8.571428571428573e-06,
"loss": 2.1908,
"step": 58
},
{
"epoch": 8.43,
"learning_rate": 7.857142857142858e-06,
"loss": 2.1594,
"step": 59
},
{
"epoch": 8.57,
"learning_rate": 7.142857142857143e-06,
"loss": 2.2055,
"step": 60
},
{
"epoch": 8.71,
"learning_rate": 6.428571428571429e-06,
"loss": 1.975,
"step": 61
},
{
"epoch": 8.86,
"learning_rate": 5.7142857142857145e-06,
"loss": 2.2883,
"step": 62
},
{
"epoch": 9.0,
"learning_rate": 5e-06,
"loss": 1.9735,
"step": 63
},
{
"epoch": 9.14,
"learning_rate": 4.285714285714286e-06,
"loss": 2.189,
"step": 64
},
{
"epoch": 9.29,
"learning_rate": 3.5714285714285714e-06,
"loss": 2.3047,
"step": 65
},
{
"epoch": 9.43,
"learning_rate": 2.8571428571428573e-06,
"loss": 1.908,
"step": 66
},
{
"epoch": 9.57,
"learning_rate": 2.142857142857143e-06,
"loss": 2.0436,
"step": 67
},
{
"epoch": 9.71,
"learning_rate": 1.4285714285714286e-06,
"loss": 2.2566,
"step": 68
},
{
"epoch": 9.86,
"learning_rate": 7.142857142857143e-07,
"loss": 2.2008,
"step": 69
},
{
"epoch": 10.0,
"learning_rate": 0.0,
"loss": 2.3549,
"step": 70
},
{
"epoch": 10.0,
"step": 70,
"total_flos": 256066191360000.0,
"train_loss": 2.381487710135324,
"train_runtime": 18.165,
"train_samples_per_second": 26.975,
"train_steps_per_second": 3.854
}
],
"max_steps": 70,
"num_train_epochs": 10,
"total_flos": 256066191360000.0,
"trial_name": null,
"trial_params": null
}