Undi95's picture
Upload folder using huggingface_hub
557a9c3
raw
history blame
12.6 kB
{
"best_metric": 1.6143836975097656,
"best_model_checkpoint": "./lora-out/checkpoint-100",
"epoch": 0.3110419906687403,
"eval_steps": 50,
"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": 2e-05,
"loss": 1.7924,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 4e-05,
"loss": 1.8083,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 6e-05,
"loss": 1.8177,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 8e-05,
"loss": 1.7595,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 1.6598,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 0.00012,
"loss": 1.6919,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 0.00014,
"loss": 1.6706,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 0.00016,
"loss": 1.6879,
"step": 8
},
{
"epoch": 0.03,
"learning_rate": 0.00018,
"loss": 1.7051,
"step": 9
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.7022,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 0.000199999456645141,
"loss": 1.6809,
"step": 11
},
{
"epoch": 0.04,
"learning_rate": 0.00019999782658646859,
"loss": 1.6098,
"step": 12
},
{
"epoch": 0.04,
"learning_rate": 0.0001999951098416968,
"loss": 1.7014,
"step": 13
},
{
"epoch": 0.04,
"learning_rate": 0.00019999130644034888,
"loss": 1.5885,
"step": 14
},
{
"epoch": 0.05,
"learning_rate": 0.00019998641642375657,
"loss": 1.6243,
"step": 15
},
{
"epoch": 0.05,
"learning_rate": 0.00019998043984506027,
"loss": 1.6484,
"step": 16
},
{
"epoch": 0.05,
"learning_rate": 0.00019997337676920803,
"loss": 1.6093,
"step": 17
},
{
"epoch": 0.06,
"learning_rate": 0.00019996522727295496,
"loss": 1.6173,
"step": 18
},
{
"epoch": 0.06,
"learning_rate": 0.00019995599144486247,
"loss": 1.646,
"step": 19
},
{
"epoch": 0.06,
"learning_rate": 0.00019994566938529712,
"loss": 1.6469,
"step": 20
},
{
"epoch": 0.07,
"learning_rate": 0.00019993426120642983,
"loss": 1.6564,
"step": 21
},
{
"epoch": 0.07,
"learning_rate": 0.00019992176703223432,
"loss": 1.5901,
"step": 22
},
{
"epoch": 0.07,
"learning_rate": 0.000199908186998486,
"loss": 1.664,
"step": 23
},
{
"epoch": 0.07,
"learning_rate": 0.00019989352125276047,
"loss": 1.6275,
"step": 24
},
{
"epoch": 0.08,
"learning_rate": 0.00019987776995443178,
"loss": 1.5839,
"step": 25
},
{
"epoch": 0.08,
"learning_rate": 0.00019986093327467076,
"loss": 1.5611,
"step": 26
},
{
"epoch": 0.08,
"learning_rate": 0.00019984301139644334,
"loss": 1.669,
"step": 27
},
{
"epoch": 0.09,
"learning_rate": 0.0001998240045145083,
"loss": 1.5641,
"step": 28
},
{
"epoch": 0.09,
"learning_rate": 0.00019980391283541522,
"loss": 1.6023,
"step": 29
},
{
"epoch": 0.09,
"learning_rate": 0.00019978273657750238,
"loss": 1.6309,
"step": 30
},
{
"epoch": 0.1,
"learning_rate": 0.0001997604759708942,
"loss": 1.6353,
"step": 31
},
{
"epoch": 0.1,
"learning_rate": 0.00019973713125749884,
"loss": 1.6328,
"step": 32
},
{
"epoch": 0.1,
"learning_rate": 0.00019971270269100564,
"loss": 1.5683,
"step": 33
},
{
"epoch": 0.11,
"learning_rate": 0.00019968719053688213,
"loss": 1.6217,
"step": 34
},
{
"epoch": 0.11,
"learning_rate": 0.0001996605950723714,
"loss": 1.5734,
"step": 35
},
{
"epoch": 0.11,
"learning_rate": 0.00019963291658648896,
"loss": 1.6162,
"step": 36
},
{
"epoch": 0.12,
"learning_rate": 0.00019960415538001957,
"loss": 1.5922,
"step": 37
},
{
"epoch": 0.12,
"learning_rate": 0.0001995743117655141,
"loss": 1.5806,
"step": 38
},
{
"epoch": 0.12,
"learning_rate": 0.000199543386067286,
"loss": 1.5938,
"step": 39
},
{
"epoch": 0.12,
"learning_rate": 0.00019951137862140778,
"loss": 1.6386,
"step": 40
},
{
"epoch": 0.13,
"learning_rate": 0.00019947828977570756,
"loss": 1.6476,
"step": 41
},
{
"epoch": 0.13,
"learning_rate": 0.00019944411988976496,
"loss": 1.6557,
"step": 42
},
{
"epoch": 0.13,
"learning_rate": 0.00019940886933490749,
"loss": 1.5836,
"step": 43
},
{
"epoch": 0.14,
"learning_rate": 0.00019937253849420635,
"loss": 1.6421,
"step": 44
},
{
"epoch": 0.14,
"learning_rate": 0.0001993351277624723,
"loss": 1.629,
"step": 45
},
{
"epoch": 0.14,
"learning_rate": 0.00019929663754625145,
"loss": 1.6392,
"step": 46
},
{
"epoch": 0.15,
"learning_rate": 0.00019925706826382064,
"loss": 1.5677,
"step": 47
},
{
"epoch": 0.15,
"learning_rate": 0.00019921642034518317,
"loss": 1.6144,
"step": 48
},
{
"epoch": 0.15,
"learning_rate": 0.00019917469423206389,
"loss": 1.6068,
"step": 49
},
{
"epoch": 0.16,
"learning_rate": 0.00019913189037790456,
"loss": 1.6421,
"step": 50
},
{
"epoch": 0.16,
"eval_loss": 1.621693730354309,
"eval_runtime": 233.7603,
"eval_samples_per_second": 16.354,
"eval_steps_per_second": 4.09,
"step": 50
},
{
"epoch": 0.16,
"learning_rate": 0.0001990880092478588,
"loss": 1.6172,
"step": 51
},
{
"epoch": 0.16,
"learning_rate": 0.0001990430513187871,
"loss": 1.6095,
"step": 52
},
{
"epoch": 0.16,
"learning_rate": 0.00019899701707925166,
"loss": 1.5967,
"step": 53
},
{
"epoch": 0.17,
"learning_rate": 0.00019894990702951106,
"loss": 1.617,
"step": 54
},
{
"epoch": 0.17,
"learning_rate": 0.00019890172168151473,
"loss": 1.5932,
"step": 55
},
{
"epoch": 0.17,
"learning_rate": 0.0001988524615588976,
"loss": 1.6548,
"step": 56
},
{
"epoch": 0.18,
"learning_rate": 0.00019880212719697413,
"loss": 1.6033,
"step": 57
},
{
"epoch": 0.18,
"learning_rate": 0.00019875071914273278,
"loss": 1.6063,
"step": 58
},
{
"epoch": 0.18,
"learning_rate": 0.00019869823795482986,
"loss": 1.6107,
"step": 59
},
{
"epoch": 0.19,
"learning_rate": 0.00019864468420358354,
"loss": 1.5758,
"step": 60
},
{
"epoch": 0.19,
"learning_rate": 0.00019859005847096763,
"loss": 1.5723,
"step": 61
},
{
"epoch": 0.19,
"learning_rate": 0.00019853436135060527,
"loss": 1.542,
"step": 62
},
{
"epoch": 0.2,
"learning_rate": 0.00019847759344776252,
"loss": 1.5611,
"step": 63
},
{
"epoch": 0.2,
"learning_rate": 0.00019841975537934162,
"loss": 1.6157,
"step": 64
},
{
"epoch": 0.2,
"learning_rate": 0.00019836084777387458,
"loss": 1.5589,
"step": 65
},
{
"epoch": 0.21,
"learning_rate": 0.00019830087127151598,
"loss": 1.6077,
"step": 66
},
{
"epoch": 0.21,
"learning_rate": 0.00019823982652403634,
"loss": 1.5473,
"step": 67
},
{
"epoch": 0.21,
"learning_rate": 0.00019817771419481487,
"loss": 1.6265,
"step": 68
},
{
"epoch": 0.21,
"learning_rate": 0.0001981145349588323,
"loss": 1.6074,
"step": 69
},
{
"epoch": 0.22,
"learning_rate": 0.00019805028950266348,
"loss": 1.6195,
"step": 70
},
{
"epoch": 0.22,
"learning_rate": 0.00019798497852447006,
"loss": 1.5876,
"step": 71
},
{
"epoch": 0.22,
"learning_rate": 0.0001979186027339928,
"loss": 1.5978,
"step": 72
},
{
"epoch": 0.23,
"learning_rate": 0.00019785116285254381,
"loss": 1.533,
"step": 73
},
{
"epoch": 0.23,
"learning_rate": 0.00019778265961299888,
"loss": 1.5888,
"step": 74
},
{
"epoch": 0.23,
"learning_rate": 0.0001977130937597894,
"loss": 1.6211,
"step": 75
},
{
"epoch": 0.24,
"learning_rate": 0.00019764246604889415,
"loss": 1.6091,
"step": 76
},
{
"epoch": 0.24,
"learning_rate": 0.00019757077724783147,
"loss": 1.6012,
"step": 77
},
{
"epoch": 0.24,
"learning_rate": 0.0001974980281356504,
"loss": 1.6401,
"step": 78
},
{
"epoch": 0.25,
"learning_rate": 0.0001974242195029227,
"loss": 1.6111,
"step": 79
},
{
"epoch": 0.25,
"learning_rate": 0.00019734935215173392,
"loss": 1.6208,
"step": 80
},
{
"epoch": 0.25,
"learning_rate": 0.00019727342689567482,
"loss": 1.6038,
"step": 81
},
{
"epoch": 0.26,
"learning_rate": 0.00019719644455983256,
"loss": 1.5915,
"step": 82
},
{
"epoch": 0.26,
"learning_rate": 0.0001971184059807817,
"loss": 1.5872,
"step": 83
},
{
"epoch": 0.26,
"learning_rate": 0.000197039312006575,
"loss": 1.5984,
"step": 84
},
{
"epoch": 0.26,
"learning_rate": 0.0001969591634967344,
"loss": 1.5996,
"step": 85
},
{
"epoch": 0.27,
"learning_rate": 0.00019687796132224152,
"loss": 1.6056,
"step": 86
},
{
"epoch": 0.27,
"learning_rate": 0.0001967957063655283,
"loss": 1.6099,
"step": 87
},
{
"epoch": 0.27,
"learning_rate": 0.0001967123995204674,
"loss": 1.6295,
"step": 88
},
{
"epoch": 0.28,
"learning_rate": 0.00019662804169236225,
"loss": 1.5482,
"step": 89
},
{
"epoch": 0.28,
"learning_rate": 0.00019654263379793773,
"loss": 1.5781,
"step": 90
},
{
"epoch": 0.28,
"learning_rate": 0.00019645617676532963,
"loss": 1.5954,
"step": 91
},
{
"epoch": 0.29,
"learning_rate": 0.000196368671534075,
"loss": 1.619,
"step": 92
},
{
"epoch": 0.29,
"learning_rate": 0.0001962801190551016,
"loss": 1.6153,
"step": 93
},
{
"epoch": 0.29,
"learning_rate": 0.0001961905202907179,
"loss": 1.6008,
"step": 94
},
{
"epoch": 0.3,
"learning_rate": 0.00019609987621460232,
"loss": 1.5891,
"step": 95
},
{
"epoch": 0.3,
"learning_rate": 0.0001960081878117929,
"loss": 1.6438,
"step": 96
},
{
"epoch": 0.3,
"learning_rate": 0.0001959154560786764,
"loss": 1.5576,
"step": 97
},
{
"epoch": 0.3,
"learning_rate": 0.00019582168202297758,
"loss": 1.646,
"step": 98
},
{
"epoch": 0.31,
"learning_rate": 0.00019572686666374822,
"loss": 1.6269,
"step": 99
},
{
"epoch": 0.31,
"learning_rate": 0.00019563101103135602,
"loss": 1.6288,
"step": 100
},
{
"epoch": 0.31,
"eval_loss": 1.6143836975097656,
"eval_runtime": 233.6412,
"eval_samples_per_second": 16.363,
"eval_steps_per_second": 4.092,
"step": 100
}
],
"logging_steps": 1,
"max_steps": 963,
"num_train_epochs": 3,
"save_steps": 50,
"total_flos": 2.804271657517056e+17,
"trial_name": null,
"trial_params": null
}