LLAMA-2-460m / checkpoint-100 /trainer_state.json
ccore's picture
Upload folder using huggingface_hub
79579c4
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.42717928180483244,
"eval_steps": 500,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0001,
"loss": 2.3832,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 5.648,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 4.5146,
"step": 3
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 3.6589,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 3.2564,
"step": 5
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 3.0312,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 2.8748,
"step": 7
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 2.8477,
"step": 8
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 2.7413,
"step": 9
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 2.7057,
"step": 10
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 2.7216,
"step": 11
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 2.6576,
"step": 12
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 2.6287,
"step": 13
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 2.572,
"step": 14
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 2.5913,
"step": 15
},
{
"epoch": 0.07,
"learning_rate": 0.0001,
"loss": 2.536,
"step": 16
},
{
"epoch": 0.07,
"learning_rate": 0.0001,
"loss": 2.5511,
"step": 17
},
{
"epoch": 0.08,
"learning_rate": 0.0001,
"loss": 2.4853,
"step": 18
},
{
"epoch": 0.08,
"learning_rate": 0.0001,
"loss": 2.5668,
"step": 19
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 2.535,
"step": 20
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 2.5287,
"step": 21
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 2.5263,
"step": 22
},
{
"epoch": 0.1,
"learning_rate": 0.0001,
"loss": 2.5046,
"step": 23
},
{
"epoch": 0.1,
"learning_rate": 0.0001,
"loss": 2.4366,
"step": 24
},
{
"epoch": 0.11,
"learning_rate": 0.0001,
"loss": 2.4488,
"step": 25
},
{
"epoch": 0.11,
"learning_rate": 0.0001,
"loss": 2.4638,
"step": 26
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 2.4546,
"step": 27
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 2.4169,
"step": 28
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 2.4739,
"step": 29
},
{
"epoch": 0.13,
"learning_rate": 0.0001,
"loss": 2.4074,
"step": 30
},
{
"epoch": 0.13,
"learning_rate": 0.0001,
"loss": 2.4314,
"step": 31
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 2.3819,
"step": 32
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 2.3524,
"step": 33
},
{
"epoch": 0.15,
"learning_rate": 0.0001,
"loss": 2.3943,
"step": 34
},
{
"epoch": 0.15,
"learning_rate": 0.0001,
"loss": 2.4447,
"step": 35
},
{
"epoch": 0.15,
"learning_rate": 0.0001,
"loss": 2.4112,
"step": 36
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 2.3453,
"step": 37
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 2.4186,
"step": 38
},
{
"epoch": 0.17,
"learning_rate": 0.0001,
"loss": 2.3761,
"step": 39
},
{
"epoch": 0.17,
"learning_rate": 0.0001,
"loss": 2.3486,
"step": 40
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 2.4314,
"step": 41
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 2.4059,
"step": 42
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 2.3649,
"step": 43
},
{
"epoch": 0.19,
"learning_rate": 0.0001,
"loss": 2.3544,
"step": 44
},
{
"epoch": 0.19,
"learning_rate": 0.0001,
"loss": 2.3959,
"step": 45
},
{
"epoch": 0.2,
"learning_rate": 0.0001,
"loss": 2.3734,
"step": 46
},
{
"epoch": 0.2,
"learning_rate": 0.0001,
"loss": 2.374,
"step": 47
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 2.3748,
"step": 48
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 2.4016,
"step": 49
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 2.3388,
"step": 50
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 2.3851,
"step": 51
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 2.4123,
"step": 52
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 2.3594,
"step": 53
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 2.3476,
"step": 54
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 2.3593,
"step": 55
},
{
"epoch": 0.24,
"learning_rate": 0.0001,
"loss": 2.3253,
"step": 56
},
{
"epoch": 0.24,
"learning_rate": 0.0001,
"loss": 2.3574,
"step": 57
},
{
"epoch": 0.25,
"learning_rate": 0.0001,
"loss": 2.3721,
"step": 58
},
{
"epoch": 0.25,
"learning_rate": 0.0001,
"loss": 2.3438,
"step": 59
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 2.3575,
"step": 60
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 2.2803,
"step": 61
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 2.3088,
"step": 62
},
{
"epoch": 0.27,
"learning_rate": 0.0001,
"loss": 2.3436,
"step": 63
},
{
"epoch": 0.27,
"learning_rate": 0.0001,
"loss": 2.3629,
"step": 64
},
{
"epoch": 0.28,
"learning_rate": 0.0001,
"loss": 2.3294,
"step": 65
},
{
"epoch": 0.28,
"learning_rate": 0.0001,
"loss": 2.3402,
"step": 66
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 2.3273,
"step": 67
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 2.3335,
"step": 68
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 2.3013,
"step": 69
},
{
"epoch": 0.3,
"learning_rate": 0.0001,
"loss": 2.3396,
"step": 70
},
{
"epoch": 0.3,
"learning_rate": 0.0001,
"loss": 2.327,
"step": 71
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 2.3231,
"step": 72
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 2.3247,
"step": 73
},
{
"epoch": 0.32,
"learning_rate": 0.0001,
"loss": 2.3163,
"step": 74
},
{
"epoch": 0.32,
"learning_rate": 0.0001,
"loss": 2.3301,
"step": 75
},
{
"epoch": 0.32,
"learning_rate": 0.0001,
"loss": 2.3598,
"step": 76
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 2.3115,
"step": 77
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 2.3015,
"step": 78
},
{
"epoch": 0.34,
"learning_rate": 0.0001,
"loss": 2.294,
"step": 79
},
{
"epoch": 0.34,
"learning_rate": 0.0001,
"loss": 2.2731,
"step": 80
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 2.3138,
"step": 81
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 2.3096,
"step": 82
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 2.3133,
"step": 83
},
{
"epoch": 0.36,
"learning_rate": 0.0001,
"loss": 2.2679,
"step": 84
},
{
"epoch": 0.36,
"learning_rate": 0.0001,
"loss": 2.2657,
"step": 85
},
{
"epoch": 0.37,
"learning_rate": 0.0001,
"loss": 2.2958,
"step": 86
},
{
"epoch": 0.37,
"learning_rate": 0.0001,
"loss": 2.297,
"step": 87
},
{
"epoch": 0.38,
"learning_rate": 0.0001,
"loss": 2.2701,
"step": 88
},
{
"epoch": 0.38,
"learning_rate": 0.0001,
"loss": 2.2889,
"step": 89
},
{
"epoch": 0.38,
"learning_rate": 0.0001,
"loss": 2.2585,
"step": 90
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 2.2611,
"step": 91
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 2.2815,
"step": 92
},
{
"epoch": 0.4,
"learning_rate": 0.0001,
"loss": 2.2778,
"step": 93
},
{
"epoch": 0.4,
"learning_rate": 0.0001,
"loss": 2.2803,
"step": 94
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 2.3007,
"step": 95
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 2.3045,
"step": 96
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 2.2858,
"step": 97
},
{
"epoch": 0.42,
"learning_rate": 0.0001,
"loss": 2.2669,
"step": 98
},
{
"epoch": 0.42,
"learning_rate": 0.0001,
"loss": 2.2731,
"step": 99
},
{
"epoch": 0.43,
"learning_rate": 0.0001,
"loss": 2.2707,
"step": 100
}
],
"logging_steps": 1.0,
"max_steps": 234,
"num_train_epochs": 1,
"save_steps": 100,
"total_flos": 1.1405554089984e+17,
"trial_name": null,
"trial_params": null
}