scarlett-13b / trainer_state.json
ajibawa-2023's picture
Upload folder using huggingface_hub
88f385a
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9361702127659575,
"global_step": 69,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04,
"learning_rate": 6.666666666666667e-06,
"loss": 1.6279,
"step": 1
},
{
"epoch": 0.09,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.6133,
"step": 2
},
{
"epoch": 0.13,
"learning_rate": 2e-05,
"loss": 1.6035,
"step": 3
},
{
"epoch": 0.17,
"learning_rate": 1.9988673391830082e-05,
"loss": 1.3525,
"step": 4
},
{
"epoch": 0.21,
"learning_rate": 1.9954719225730847e-05,
"loss": 1.543,
"step": 5
},
{
"epoch": 0.26,
"learning_rate": 1.989821441880933e-05,
"loss": 1.2588,
"step": 6
},
{
"epoch": 0.3,
"learning_rate": 1.9819286972627066e-05,
"loss": 1.2148,
"step": 7
},
{
"epoch": 0.34,
"learning_rate": 1.9718115683235418e-05,
"loss": 1.2109,
"step": 8
},
{
"epoch": 0.38,
"learning_rate": 1.9594929736144978e-05,
"loss": 1.1846,
"step": 9
},
{
"epoch": 0.43,
"learning_rate": 1.9450008187146685e-05,
"loss": 1.1768,
"step": 10
},
{
"epoch": 0.47,
"learning_rate": 1.9283679330160726e-05,
"loss": 1.1709,
"step": 11
},
{
"epoch": 0.51,
"learning_rate": 1.9096319953545186e-05,
"loss": 1.1211,
"step": 12
},
{
"epoch": 0.55,
"learning_rate": 1.8888354486549238e-05,
"loss": 1.123,
"step": 13
},
{
"epoch": 0.6,
"learning_rate": 1.866025403784439e-05,
"loss": 1.1162,
"step": 14
},
{
"epoch": 0.64,
"learning_rate": 1.8412535328311813e-05,
"loss": 1.1084,
"step": 15
},
{
"epoch": 0.68,
"learning_rate": 1.814575952050336e-05,
"loss": 1.1094,
"step": 16
},
{
"epoch": 0.72,
"learning_rate": 1.7860530947427878e-05,
"loss": 1.1104,
"step": 17
},
{
"epoch": 0.77,
"learning_rate": 1.7557495743542586e-05,
"loss": 1.0801,
"step": 18
},
{
"epoch": 0.81,
"learning_rate": 1.72373403810507e-05,
"loss": 1.0967,
"step": 19
},
{
"epoch": 0.85,
"learning_rate": 1.6900790114821122e-05,
"loss": 1.083,
"step": 20
},
{
"epoch": 0.89,
"learning_rate": 1.6548607339452853e-05,
"loss": 1.0723,
"step": 21
},
{
"epoch": 0.94,
"learning_rate": 1.6181589862206053e-05,
"loss": 1.0742,
"step": 22
},
{
"epoch": 0.98,
"learning_rate": 1.5800569095711983e-05,
"loss": 1.0654,
"step": 23
},
{
"epoch": 1.02,
"learning_rate": 1.5406408174555978e-05,
"loss": 1.0283,
"step": 24
},
{
"epoch": 1.06,
"learning_rate": 1.5000000000000002e-05,
"loss": 1.0342,
"step": 25
},
{
"epoch": 1.11,
"learning_rate": 1.4582265217274105e-05,
"loss": 1.0156,
"step": 26
},
{
"epoch": 1.15,
"learning_rate": 1.4154150130018867e-05,
"loss": 0.9907,
"step": 27
},
{
"epoch": 1.19,
"learning_rate": 1.3716624556603275e-05,
"loss": 1.0205,
"step": 28
},
{
"epoch": 1.23,
"learning_rate": 1.3270679633174219e-05,
"loss": 1.0063,
"step": 29
},
{
"epoch": 1.28,
"learning_rate": 1.2817325568414299e-05,
"loss": 0.9663,
"step": 30
},
{
"epoch": 1.32,
"learning_rate": 1.2357589355094275e-05,
"loss": 0.9868,
"step": 31
},
{
"epoch": 1.36,
"learning_rate": 1.1892512443604103e-05,
"loss": 0.999,
"step": 32
},
{
"epoch": 1.4,
"learning_rate": 1.1423148382732854e-05,
"loss": 0.9854,
"step": 33
},
{
"epoch": 1.45,
"learning_rate": 1.0950560433041825e-05,
"loss": 0.9878,
"step": 34
},
{
"epoch": 1.49,
"learning_rate": 1.0475819158237426e-05,
"loss": 0.9805,
"step": 35
},
{
"epoch": 1.53,
"learning_rate": 1e-05,
"loss": 0.9756,
"step": 36
},
{
"epoch": 1.57,
"learning_rate": 9.524180841762577e-06,
"loss": 0.978,
"step": 37
},
{
"epoch": 1.62,
"learning_rate": 9.049439566958176e-06,
"loss": 0.9795,
"step": 38
},
{
"epoch": 1.66,
"learning_rate": 8.576851617267151e-06,
"loss": 0.9727,
"step": 39
},
{
"epoch": 1.7,
"learning_rate": 8.107487556395902e-06,
"loss": 1.002,
"step": 40
},
{
"epoch": 1.74,
"learning_rate": 7.642410644905726e-06,
"loss": 0.9893,
"step": 41
},
{
"epoch": 1.79,
"learning_rate": 7.182674431585703e-06,
"loss": 0.9814,
"step": 42
},
{
"epoch": 1.83,
"learning_rate": 6.729320366825785e-06,
"loss": 0.9697,
"step": 43
},
{
"epoch": 1.87,
"learning_rate": 6.283375443396726e-06,
"loss": 0.9712,
"step": 44
},
{
"epoch": 1.91,
"learning_rate": 5.845849869981137e-06,
"loss": 0.98,
"step": 45
},
{
"epoch": 1.96,
"learning_rate": 5.417734782725896e-06,
"loss": 0.9746,
"step": 46
},
{
"epoch": 2.0,
"learning_rate": 5.000000000000003e-06,
"loss": 0.9512,
"step": 47
},
{
"epoch": 2.04,
"learning_rate": 4.593591825444028e-06,
"loss": 0.9146,
"step": 48
},
{
"epoch": 2.09,
"learning_rate": 4.19943090428802e-06,
"loss": 0.9546,
"step": 49
},
{
"epoch": 2.13,
"learning_rate": 3.818410137793947e-06,
"loss": 0.9434,
"step": 50
},
{
"epoch": 2.17,
"learning_rate": 3.4513926605471504e-06,
"loss": 0.9438,
"step": 51
},
{
"epoch": 2.21,
"learning_rate": 3.099209885178882e-06,
"loss": 0.9346,
"step": 52
},
{
"epoch": 2.26,
"learning_rate": 2.7626596189492983e-06,
"loss": 0.9292,
"step": 53
},
{
"epoch": 2.3,
"learning_rate": 2.4425042564574186e-06,
"loss": 0.9443,
"step": 54
},
{
"epoch": 2.34,
"learning_rate": 2.1394690525721275e-06,
"loss": 0.9263,
"step": 55
},
{
"epoch": 2.38,
"learning_rate": 1.854240479496643e-06,
"loss": 0.937,
"step": 56
},
{
"epoch": 2.43,
"learning_rate": 1.587464671688187e-06,
"loss": 0.9478,
"step": 57
},
{
"epoch": 2.47,
"learning_rate": 1.339745962155613e-06,
"loss": 0.9351,
"step": 58
},
{
"epoch": 2.51,
"learning_rate": 1.1116455134507665e-06,
"loss": 0.9268,
"step": 59
},
{
"epoch": 2.55,
"learning_rate": 9.036800464548157e-07,
"loss": 0.9209,
"step": 60
},
{
"epoch": 2.6,
"learning_rate": 7.163206698392744e-07,
"loss": 0.9307,
"step": 61
},
{
"epoch": 2.64,
"learning_rate": 5.499918128533155e-07,
"loss": 0.9229,
"step": 62
},
{
"epoch": 2.68,
"learning_rate": 4.0507026385502747e-07,
"loss": 0.9258,
"step": 63
},
{
"epoch": 2.72,
"learning_rate": 2.818843167645835e-07,
"loss": 0.9336,
"step": 64
},
{
"epoch": 2.77,
"learning_rate": 1.8071302737293294e-07,
"loss": 0.9199,
"step": 65
},
{
"epoch": 2.81,
"learning_rate": 1.0178558119067316e-07,
"loss": 0.9307,
"step": 66
},
{
"epoch": 2.85,
"learning_rate": 4.528077426915412e-08,
"loss": 0.9292,
"step": 67
},
{
"epoch": 2.89,
"learning_rate": 1.1326608169920373e-08,
"loss": 0.9414,
"step": 68
},
{
"epoch": 2.94,
"learning_rate": 0.0,
"loss": 0.9287,
"step": 69
},
{
"epoch": 2.94,
"step": 69,
"total_flos": 88957161308160.0,
"train_loss": 1.0487644361413044,
"train_runtime": 7514.7793,
"train_samples_per_second": 2.386,
"train_steps_per_second": 0.009
}
],
"max_steps": 69,
"num_train_epochs": 3,
"total_flos": 88957161308160.0,
"trial_name": null,
"trial_params": null
}