Kevin Ni
upload the model
8533dc5
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.96,
"eval_steps": 37,
"global_step": 111,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 1.6666666666666667e-06,
"loss": 0.6112,
"step": 1
},
{
"epoch": 0.05,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.6303,
"step": 2
},
{
"epoch": 0.08,
"learning_rate": 5e-06,
"loss": 0.5761,
"step": 3
},
{
"epoch": 0.11,
"learning_rate": 6.666666666666667e-06,
"loss": 0.5203,
"step": 4
},
{
"epoch": 0.13,
"learning_rate": 8.333333333333334e-06,
"loss": 0.5136,
"step": 5
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 0.535,
"step": 6
},
{
"epoch": 0.19,
"learning_rate": 1.1666666666666668e-05,
"loss": 0.5001,
"step": 7
},
{
"epoch": 0.21,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.5683,
"step": 8
},
{
"epoch": 0.24,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.5901,
"step": 9
},
{
"epoch": 0.27,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.483,
"step": 10
},
{
"epoch": 0.29,
"learning_rate": 1.8333333333333333e-05,
"loss": 0.5924,
"step": 11
},
{
"epoch": 0.32,
"learning_rate": 2e-05,
"loss": 0.4826,
"step": 12
},
{
"epoch": 0.35,
"learning_rate": 1.9994965423831853e-05,
"loss": 0.6382,
"step": 13
},
{
"epoch": 0.37,
"learning_rate": 1.9979866764718846e-05,
"loss": 0.6642,
"step": 14
},
{
"epoch": 0.4,
"learning_rate": 1.9954719225730847e-05,
"loss": 1.0157,
"step": 15
},
{
"epoch": 0.43,
"learning_rate": 1.9919548128307954e-05,
"loss": 0.8049,
"step": 16
},
{
"epoch": 0.45,
"learning_rate": 1.9874388886763944e-05,
"loss": 0.5901,
"step": 17
},
{
"epoch": 0.48,
"learning_rate": 1.9819286972627066e-05,
"loss": 0.5374,
"step": 18
},
{
"epoch": 0.51,
"learning_rate": 1.9754297868854075e-05,
"loss": 0.6478,
"step": 19
},
{
"epoch": 0.53,
"learning_rate": 1.9679487013963566e-05,
"loss": 0.5887,
"step": 20
},
{
"epoch": 0.56,
"learning_rate": 1.9594929736144978e-05,
"loss": 0.617,
"step": 21
},
{
"epoch": 0.59,
"learning_rate": 1.9500711177409456e-05,
"loss": 0.5248,
"step": 22
},
{
"epoch": 0.61,
"learning_rate": 1.9396926207859085e-05,
"loss": 0.6107,
"step": 23
},
{
"epoch": 0.64,
"learning_rate": 1.9283679330160726e-05,
"loss": 0.5962,
"step": 24
},
{
"epoch": 0.67,
"learning_rate": 1.9161084574320696e-05,
"loss": 0.5956,
"step": 25
},
{
"epoch": 0.69,
"learning_rate": 1.9029265382866216e-05,
"loss": 0.596,
"step": 26
},
{
"epoch": 0.72,
"learning_rate": 1.8888354486549238e-05,
"loss": 0.5287,
"step": 27
},
{
"epoch": 0.75,
"learning_rate": 1.873849377069785e-05,
"loss": 0.5219,
"step": 28
},
{
"epoch": 0.77,
"learning_rate": 1.8579834132349773e-05,
"loss": 0.5725,
"step": 29
},
{
"epoch": 0.8,
"learning_rate": 1.8412535328311813e-05,
"loss": 0.5125,
"step": 30
},
{
"epoch": 0.83,
"learning_rate": 1.8236765814298328e-05,
"loss": 0.684,
"step": 31
},
{
"epoch": 0.85,
"learning_rate": 1.8052702575310588e-05,
"loss": 0.6122,
"step": 32
},
{
"epoch": 0.88,
"learning_rate": 1.7860530947427878e-05,
"loss": 0.58,
"step": 33
},
{
"epoch": 0.91,
"learning_rate": 1.766044443118978e-05,
"loss": 0.5345,
"step": 34
},
{
"epoch": 0.93,
"learning_rate": 1.745264449675755e-05,
"loss": 0.6006,
"step": 35
},
{
"epoch": 0.96,
"learning_rate": 1.72373403810507e-05,
"loss": 0.5205,
"step": 36
},
{
"epoch": 0.99,
"learning_rate": 1.7014748877063212e-05,
"loss": 0.5162,
"step": 37
},
{
"epoch": 0.99,
"eval_loss": 0.5430402755737305,
"eval_runtime": 104.5069,
"eval_samples_per_second": 4.306,
"eval_steps_per_second": 0.545,
"step": 37
},
{
"epoch": 1.01,
"learning_rate": 1.6785094115571323e-05,
"loss": 0.4366,
"step": 38
},
{
"epoch": 1.04,
"learning_rate": 1.6548607339452853e-05,
"loss": 0.2943,
"step": 39
},
{
"epoch": 1.07,
"learning_rate": 1.6305526670845225e-05,
"loss": 0.3252,
"step": 40
},
{
"epoch": 1.09,
"learning_rate": 1.6056096871376667e-05,
"loss": 0.2371,
"step": 41
},
{
"epoch": 1.12,
"learning_rate": 1.5800569095711983e-05,
"loss": 0.2612,
"step": 42
},
{
"epoch": 1.15,
"learning_rate": 1.5539200638661106e-05,
"loss": 0.2848,
"step": 43
},
{
"epoch": 1.17,
"learning_rate": 1.5272254676105026e-05,
"loss": 0.3492,
"step": 44
},
{
"epoch": 1.2,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.3187,
"step": 45
},
{
"epoch": 1.23,
"learning_rate": 1.472271074772683e-05,
"loss": 0.2717,
"step": 46
},
{
"epoch": 1.25,
"learning_rate": 1.4440666126057743e-05,
"loss": 0.2904,
"step": 47
},
{
"epoch": 1.28,
"learning_rate": 1.4154150130018867e-05,
"loss": 0.3491,
"step": 48
},
{
"epoch": 1.31,
"learning_rate": 1.3863451256931286e-05,
"loss": 0.2594,
"step": 49
},
{
"epoch": 1.33,
"learning_rate": 1.356886221591872e-05,
"loss": 0.2274,
"step": 50
},
{
"epoch": 1.36,
"learning_rate": 1.3270679633174219e-05,
"loss": 0.258,
"step": 51
},
{
"epoch": 1.39,
"learning_rate": 1.296920375328275e-05,
"loss": 0.2805,
"step": 52
},
{
"epoch": 1.41,
"learning_rate": 1.266473813690035e-05,
"loss": 0.3149,
"step": 53
},
{
"epoch": 1.44,
"learning_rate": 1.2357589355094275e-05,
"loss": 0.2612,
"step": 54
},
{
"epoch": 1.47,
"learning_rate": 1.2048066680651908e-05,
"loss": 0.2585,
"step": 55
},
{
"epoch": 1.49,
"learning_rate": 1.1736481776669307e-05,
"loss": 0.2456,
"step": 56
},
{
"epoch": 1.52,
"learning_rate": 1.1423148382732854e-05,
"loss": 0.2848,
"step": 57
},
{
"epoch": 1.55,
"learning_rate": 1.1108381999010111e-05,
"loss": 0.2913,
"step": 58
},
{
"epoch": 1.57,
"learning_rate": 1.0792499568567885e-05,
"loss": 0.2446,
"step": 59
},
{
"epoch": 1.6,
"learning_rate": 1.0475819158237426e-05,
"loss": 0.4025,
"step": 60
},
{
"epoch": 1.63,
"learning_rate": 1.015865963834808e-05,
"loss": 0.282,
"step": 61
},
{
"epoch": 1.65,
"learning_rate": 9.841340361651921e-06,
"loss": 0.256,
"step": 62
},
{
"epoch": 1.68,
"learning_rate": 9.524180841762577e-06,
"loss": 0.2738,
"step": 63
},
{
"epoch": 1.71,
"learning_rate": 9.207500431432115e-06,
"loss": 0.2426,
"step": 64
},
{
"epoch": 1.73,
"learning_rate": 8.89161800098989e-06,
"loss": 0.2979,
"step": 65
},
{
"epoch": 1.76,
"learning_rate": 8.576851617267151e-06,
"loss": 0.2517,
"step": 66
},
{
"epoch": 1.79,
"learning_rate": 8.263518223330698e-06,
"loss": 0.245,
"step": 67
},
{
"epoch": 1.81,
"learning_rate": 7.951933319348095e-06,
"loss": 0.2405,
"step": 68
},
{
"epoch": 1.84,
"learning_rate": 7.642410644905726e-06,
"loss": 0.2171,
"step": 69
},
{
"epoch": 1.87,
"learning_rate": 7.335261863099652e-06,
"loss": 0.2534,
"step": 70
},
{
"epoch": 1.89,
"learning_rate": 7.0307962467172555e-06,
"loss": 0.257,
"step": 71
},
{
"epoch": 1.92,
"learning_rate": 6.729320366825785e-06,
"loss": 0.2736,
"step": 72
},
{
"epoch": 1.95,
"learning_rate": 6.431137784081283e-06,
"loss": 0.2773,
"step": 73
},
{
"epoch": 1.97,
"learning_rate": 6.136548743068713e-06,
"loss": 0.2686,
"step": 74
},
{
"epoch": 1.97,
"eval_loss": 0.5483924150466919,
"eval_runtime": 104.141,
"eval_samples_per_second": 4.321,
"eval_steps_per_second": 0.547,
"step": 74
},
{
"epoch": 2.0,
"learning_rate": 5.845849869981137e-06,
"loss": 0.3391,
"step": 75
},
{
"epoch": 2.03,
"learning_rate": 5.559333873942259e-06,
"loss": 0.1271,
"step": 76
},
{
"epoch": 2.05,
"learning_rate": 5.277289252273175e-06,
"loss": 0.1226,
"step": 77
},
{
"epoch": 2.08,
"learning_rate": 5.000000000000003e-06,
"loss": 0.1008,
"step": 78
},
{
"epoch": 2.11,
"learning_rate": 4.727745323894976e-06,
"loss": 0.1086,
"step": 79
},
{
"epoch": 2.13,
"learning_rate": 4.460799361338898e-06,
"loss": 0.1104,
"step": 80
},
{
"epoch": 2.16,
"learning_rate": 4.19943090428802e-06,
"loss": 0.0931,
"step": 81
},
{
"epoch": 2.19,
"learning_rate": 3.943903128623336e-06,
"loss": 0.1212,
"step": 82
},
{
"epoch": 2.21,
"learning_rate": 3.6944733291547784e-06,
"loss": 0.0952,
"step": 83
},
{
"epoch": 2.24,
"learning_rate": 3.4513926605471504e-06,
"loss": 0.0924,
"step": 84
},
{
"epoch": 2.27,
"learning_rate": 3.2149058844286796e-06,
"loss": 0.094,
"step": 85
},
{
"epoch": 2.29,
"learning_rate": 2.9852511229367862e-06,
"loss": 0.101,
"step": 86
},
{
"epoch": 2.32,
"learning_rate": 2.7626596189492983e-06,
"loss": 0.0979,
"step": 87
},
{
"epoch": 2.35,
"learning_rate": 2.5473555032424534e-06,
"loss": 0.0972,
"step": 88
},
{
"epoch": 2.37,
"learning_rate": 2.339555568810221e-06,
"loss": 0.0847,
"step": 89
},
{
"epoch": 2.4,
"learning_rate": 2.1394690525721275e-06,
"loss": 0.0818,
"step": 90
},
{
"epoch": 2.43,
"learning_rate": 1.947297424689414e-06,
"loss": 0.1019,
"step": 91
},
{
"epoch": 2.45,
"learning_rate": 1.7632341857016733e-06,
"loss": 0.0849,
"step": 92
},
{
"epoch": 2.48,
"learning_rate": 1.587464671688187e-06,
"loss": 0.0616,
"step": 93
},
{
"epoch": 2.51,
"learning_rate": 1.4201658676502294e-06,
"loss": 0.0966,
"step": 94
},
{
"epoch": 2.53,
"learning_rate": 1.2615062293021508e-06,
"loss": 0.0712,
"step": 95
},
{
"epoch": 2.56,
"learning_rate": 1.1116455134507665e-06,
"loss": 0.0874,
"step": 96
},
{
"epoch": 2.59,
"learning_rate": 9.707346171337895e-07,
"loss": 0.0894,
"step": 97
},
{
"epoch": 2.61,
"learning_rate": 8.389154256793042e-07,
"loss": 0.0853,
"step": 98
},
{
"epoch": 2.64,
"learning_rate": 7.163206698392744e-07,
"loss": 0.0827,
"step": 99
},
{
"epoch": 2.67,
"learning_rate": 6.030737921409169e-07,
"loss": 0.0785,
"step": 100
},
{
"epoch": 2.69,
"learning_rate": 4.992888225905467e-07,
"loss": 0.0735,
"step": 101
},
{
"epoch": 2.72,
"learning_rate": 4.0507026385502747e-07,
"loss": 0.0906,
"step": 102
},
{
"epoch": 2.75,
"learning_rate": 3.2051298603643754e-07,
"loss": 0.0717,
"step": 103
},
{
"epoch": 2.77,
"learning_rate": 2.4570213114592957e-07,
"loss": 0.0638,
"step": 104
},
{
"epoch": 2.8,
"learning_rate": 1.8071302737293294e-07,
"loss": 0.0785,
"step": 105
},
{
"epoch": 2.83,
"learning_rate": 1.2561111323605714e-07,
"loss": 0.0735,
"step": 106
},
{
"epoch": 2.85,
"learning_rate": 8.04518716920466e-08,
"loss": 0.11,
"step": 107
},
{
"epoch": 2.88,
"learning_rate": 4.528077426915412e-08,
"loss": 0.0849,
"step": 108
},
{
"epoch": 2.91,
"learning_rate": 2.013323528115674e-08,
"loss": 0.0885,
"step": 109
},
{
"epoch": 2.93,
"learning_rate": 5.034576168149175e-09,
"loss": 0.061,
"step": 110
},
{
"epoch": 2.96,
"learning_rate": 0.0,
"loss": 0.0889,
"step": 111
},
{
"epoch": 2.96,
"eval_loss": 0.6206281185150146,
"eval_runtime": 104.1508,
"eval_samples_per_second": 4.321,
"eval_steps_per_second": 0.547,
"step": 111
},
{
"epoch": 2.96,
"step": 111,
"total_flos": 3.879485131928371e+16,
"train_loss": 0.3224217994725919,
"train_runtime": 3175.6121,
"train_samples_per_second": 0.567,
"train_steps_per_second": 0.035
}
],
"logging_steps": 1.0,
"max_steps": 111,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 37,
"total_flos": 3.879485131928371e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}