HH2-temp / checkpoint-75 /trainer_state.json
nRuaif
Upload folder using huggingface_hub
1e9bec5
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.348314606741573,
"eval_steps": 500,
"global_step": 75,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 1e-05,
"loss": 1.6702,
"step": 1
},
{
"epoch": 0.04,
"learning_rate": 1.5e-05,
"loss": 1.5262,
"step": 2
},
{
"epoch": 0.05,
"learning_rate": 2e-05,
"loss": 1.8831,
"step": 3
},
{
"epoch": 0.07,
"learning_rate": 2.5e-05,
"loss": 1.6531,
"step": 4
},
{
"epoch": 0.09,
"learning_rate": 3e-05,
"loss": 1.6833,
"step": 5
},
{
"epoch": 0.11,
"learning_rate": 3.5e-05,
"loss": 1.7288,
"step": 6
},
{
"epoch": 0.13,
"learning_rate": 4e-05,
"loss": 1.5015,
"step": 7
},
{
"epoch": 0.14,
"learning_rate": 4.5e-05,
"loss": 1.6876,
"step": 8
},
{
"epoch": 0.16,
"learning_rate": 5e-05,
"loss": 1.6648,
"step": 9
},
{
"epoch": 0.18,
"learning_rate": 4.998766400914329e-05,
"loss": 1.8044,
"step": 10
},
{
"epoch": 0.2,
"learning_rate": 4.995066821070679e-05,
"loss": 1.6566,
"step": 11
},
{
"epoch": 0.22,
"learning_rate": 4.9889049115077005e-05,
"loss": 1.6917,
"step": 12
},
{
"epoch": 0.23,
"learning_rate": 4.980286753286195e-05,
"loss": 1.6271,
"step": 13
},
{
"epoch": 0.25,
"learning_rate": 4.9692208514878444e-05,
"loss": 1.7478,
"step": 14
},
{
"epoch": 0.27,
"learning_rate": 4.9557181268217227e-05,
"loss": 1.606,
"step": 15
},
{
"epoch": 0.29,
"learning_rate": 4.939791904846869e-05,
"loss": 1.6176,
"step": 16
},
{
"epoch": 0.31,
"learning_rate": 4.9214579028215776e-05,
"loss": 1.7205,
"step": 17
},
{
"epoch": 0.32,
"learning_rate": 4.900734214192358e-05,
"loss": 1.5682,
"step": 18
},
{
"epoch": 0.34,
"learning_rate": 4.877641290737884e-05,
"loss": 1.6807,
"step": 19
},
{
"epoch": 0.36,
"learning_rate": 4.852201922385564e-05,
"loss": 1.6137,
"step": 20
},
{
"epoch": 0.38,
"learning_rate": 4.8244412147206284e-05,
"loss": 1.6352,
"step": 21
},
{
"epoch": 0.4,
"learning_rate": 4.794386564209953e-05,
"loss": 1.5979,
"step": 22
},
{
"epoch": 0.41,
"learning_rate": 4.762067631165049e-05,
"loss": 1.6163,
"step": 23
},
{
"epoch": 0.43,
"learning_rate": 4.72751631047092e-08,
"loss": 1.6513,
"step": 24
},
{
"epoch": 0.45,
"learning_rate": 1.5667160778366258e-05,
"loss": 1.5181,
"step": 25
},
{
"epoch": 0.47,
"learning_rate": 3.102787330029076e-05,
"loss": 1.544,
"step": 26
},
{
"epoch": 0.49,
"learning_rate": 4.610819813755038e-05,
"loss": 1.4473,
"step": 27
},
{
"epoch": 0.5,
"learning_rate": 4.567701435686404e-05,
"loss": 1.6461,
"step": 28
},
{
"epoch": 0.52,
"learning_rate": 4.522542485937369e-05,
"loss": 1.519,
"step": 29
},
{
"epoch": 0.54,
"learning_rate": 4.4753875309392266e-05,
"loss": 1.5967,
"step": 30
},
{
"epoch": 0.56,
"learning_rate": 4.426283106939474e-05,
"loss": 1.6351,
"step": 31
},
{
"epoch": 0.58,
"learning_rate": 4.375277674076149e-05,
"loss": 1.5408,
"step": 32
},
{
"epoch": 0.59,
"learning_rate": 4.3224215685535294e-05,
"loss": 1.6087,
"step": 33
},
{
"epoch": 0.61,
"learning_rate": 4.267766952966369e-05,
"loss": 1.5753,
"step": 34
},
{
"epoch": 0.63,
"learning_rate": 4.211367764821722e-05,
"loss": 1.6771,
"step": 35
},
{
"epoch": 0.65,
"learning_rate": 4.1532796633091296e-05,
"loss": 1.5738,
"step": 36
},
{
"epoch": 0.67,
"learning_rate": 4.093559974371725e-05,
"loss": 1.5405,
"step": 37
},
{
"epoch": 0.68,
"learning_rate": 4.0322676341324415e-05,
"loss": 1.614,
"step": 38
},
{
"epoch": 0.7,
"learning_rate": 3.969463130731183e-05,
"loss": 1.6264,
"step": 39
},
{
"epoch": 0.72,
"learning_rate": 3.905208444630327e-05,
"loss": 1.5959,
"step": 40
},
{
"epoch": 0.74,
"learning_rate": 3.8395669874474915e-05,
"loss": 1.5935,
"step": 41
},
{
"epoch": 0.76,
"learning_rate": 3.7726035393759285e-05,
"loss": 1.502,
"step": 42
},
{
"epoch": 0.77,
"learning_rate": 3.704384185254288e-05,
"loss": 1.6214,
"step": 43
},
{
"epoch": 0.79,
"learning_rate": 3.634976249348867e-05,
"loss": 1.5852,
"step": 44
},
{
"epoch": 0.81,
"learning_rate": 3.564448228912682e-05,
"loss": 1.7603,
"step": 45
},
{
"epoch": 0.83,
"learning_rate": 3.4928697265869515e-05,
"loss": 1.4935,
"step": 46
},
{
"epoch": 0.84,
"learning_rate": 3.4203113817116957e-05,
"loss": 1.5517,
"step": 47
},
{
"epoch": 0.86,
"learning_rate": 3.346844800613229e-05,
"loss": 1.6087,
"step": 48
},
{
"epoch": 0.88,
"learning_rate": 3.2725424859373694e-08,
"loss": 1.5613,
"step": 49
},
{
"epoch": 0.9,
"learning_rate": 1.0679575735427564e-05,
"loss": 1.597,
"step": 50
},
{
"epoch": 0.92,
"learning_rate": 2.0821903868473956e-05,
"loss": 1.5146,
"step": 51
},
{
"epoch": 0.93,
"learning_rate": 3.045358103491357e-05,
"loss": 1.5927,
"step": 52
},
{
"epoch": 0.95,
"learning_rate": 2.9684532864643122e-05,
"loss": 1.6061,
"step": 53
},
{
"epoch": 0.97,
"learning_rate": 2.8910861626005776e-05,
"loss": 1.5321,
"step": 54
},
{
"epoch": 0.99,
"learning_rate": 2.8133330839107608e-05,
"loss": 1.4788,
"step": 55
},
{
"epoch": 1.01,
"learning_rate": 2.7352707832962865e-05,
"loss": 1.499,
"step": 56
},
{
"epoch": 1.02,
"learning_rate": 2.656976298823284e-05,
"loss": 1.5762,
"step": 57
},
{
"epoch": 1.04,
"learning_rate": 2.578526897695321e-05,
"loss": 1.5178,
"step": 58
},
{
"epoch": 1.06,
"learning_rate": 2.5e-05,
"loss": 1.5249,
"step": 59
},
{
"epoch": 1.08,
"learning_rate": 2.4214731023046793e-05,
"loss": 1.5864,
"step": 60
},
{
"epoch": 1.1,
"learning_rate": 2.3430237011767167e-05,
"loss": 1.4421,
"step": 61
},
{
"epoch": 1.11,
"learning_rate": 2.2647292167037144e-05,
"loss": 1.6576,
"step": 62
},
{
"epoch": 1.13,
"learning_rate": 2.186666916089239e-05,
"loss": 1.5909,
"step": 63
},
{
"epoch": 1.15,
"learning_rate": 2.1089138373994223e-05,
"loss": 1.6872,
"step": 64
},
{
"epoch": 1.17,
"learning_rate": 2.031546713535688e-05,
"loss": 1.5855,
"step": 65
},
{
"epoch": 1.19,
"learning_rate": 1.9546418965086442e-05,
"loss": 1.4649,
"step": 66
},
{
"epoch": 1.2,
"learning_rate": 1.8782752820878634e-05,
"loss": 1.5359,
"step": 67
},
{
"epoch": 1.22,
"learning_rate": 1.802522234901927e-05,
"loss": 1.5669,
"step": 68
},
{
"epoch": 1.24,
"learning_rate": 1.7274575140626318e-05,
"loss": 1.5668,
"step": 69
},
{
"epoch": 1.26,
"learning_rate": 1.6531551993867717e-05,
"loss": 1.5836,
"step": 70
},
{
"epoch": 1.28,
"learning_rate": 1.5796886182883053e-05,
"loss": 1.6105,
"step": 71
},
{
"epoch": 1.29,
"learning_rate": 1.5071302734130489e-05,
"loss": 1.7016,
"step": 72
},
{
"epoch": 1.31,
"learning_rate": 1.4355517710873184e-05,
"loss": 1.5267,
"step": 73
},
{
"epoch": 1.33,
"learning_rate": 1.3650237506511332e-08,
"loss": 1.5548,
"step": 74
},
{
"epoch": 1.35,
"learning_rate": 4.327356821250675e-06,
"loss": 1.4613,
"step": 75
}
],
"logging_steps": 1,
"max_steps": 110,
"num_train_epochs": 2,
"save_steps": 25,
"total_flos": 2.6572405131313152e+17,
"trial_name": null,
"trial_params": null
}