video-ckpt-v2-e1 / checkpoint-100 /trainer_state.json
si0wang
Update
8f07e0f
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.7782101167315175,
"eval_steps": 500,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 2.5e-06,
"loss": 2.0738,
"step": 1
},
{
"epoch": 0.02,
"learning_rate": 5e-06,
"loss": 2.0648,
"step": 2
},
{
"epoch": 0.02,
"learning_rate": 7.500000000000001e-06,
"loss": 2.0442,
"step": 3
},
{
"epoch": 0.03,
"learning_rate": 1e-05,
"loss": 1.9734,
"step": 4
},
{
"epoch": 0.04,
"learning_rate": 9.998395376482152e-06,
"loss": 1.9491,
"step": 5
},
{
"epoch": 0.05,
"learning_rate": 9.993582535855265e-06,
"loss": 2.0878,
"step": 6
},
{
"epoch": 0.05,
"learning_rate": 9.985564567238237e-06,
"loss": 2.0244,
"step": 7
},
{
"epoch": 0.06,
"learning_rate": 9.974346616959476e-06,
"loss": 2.0044,
"step": 8
},
{
"epoch": 0.07,
"learning_rate": 9.959935885253715e-06,
"loss": 1.9516,
"step": 9
},
{
"epoch": 0.08,
"learning_rate": 9.942341621640558e-06,
"loss": 1.8856,
"step": 10
},
{
"epoch": 0.09,
"learning_rate": 9.921575118987672e-06,
"loss": 1.8866,
"step": 11
},
{
"epoch": 0.09,
"learning_rate": 9.897649706262474e-06,
"loss": 1.8785,
"step": 12
},
{
"epoch": 0.1,
"learning_rate": 9.870580739976936e-06,
"loss": 1.8429,
"step": 13
},
{
"epoch": 0.11,
"learning_rate": 9.840385594331022e-06,
"loss": 1.8444,
"step": 14
},
{
"epoch": 0.12,
"learning_rate": 9.807083650061063e-06,
"loss": 1.8134,
"step": 15
},
{
"epoch": 0.12,
"learning_rate": 9.770696282000245e-06,
"loss": 1.8641,
"step": 16
},
{
"epoch": 0.13,
"learning_rate": 9.731246845359187e-06,
"loss": 1.8326,
"step": 17
},
{
"epoch": 0.14,
"learning_rate": 9.688760660735403e-06,
"loss": 1.8332,
"step": 18
},
{
"epoch": 0.15,
"learning_rate": 9.643264997861312e-06,
"loss": 1.8135,
"step": 19
},
{
"epoch": 0.16,
"learning_rate": 9.594789058101154e-06,
"loss": 1.8494,
"step": 20
},
{
"epoch": 0.16,
"learning_rate": 9.543363955708124e-06,
"loss": 1.8141,
"step": 21
},
{
"epoch": 0.17,
"learning_rate": 9.48902269785371e-06,
"loss": 1.8136,
"step": 22
},
{
"epoch": 0.18,
"learning_rate": 9.431800163442043e-06,
"loss": 1.8128,
"step": 23
},
{
"epoch": 0.19,
"learning_rate": 9.371733080722911e-06,
"loss": 1.8025,
"step": 24
},
{
"epoch": 0.19,
"learning_rate": 9.308860003717748e-06,
"loss": 1.8142,
"step": 25
},
{
"epoch": 0.2,
"learning_rate": 9.243221287473755e-06,
"loss": 1.8073,
"step": 26
},
{
"epoch": 0.21,
"learning_rate": 9.174859062162037e-06,
"loss": 1.7942,
"step": 27
},
{
"epoch": 0.22,
"learning_rate": 9.103817206036383e-06,
"loss": 1.804,
"step": 28
},
{
"epoch": 0.23,
"learning_rate": 9.030141317270026e-06,
"loss": 1.7538,
"step": 29
},
{
"epoch": 0.23,
"learning_rate": 8.953878684688492e-06,
"loss": 1.8193,
"step": 30
},
{
"epoch": 0.24,
"learning_rate": 8.875078257417294e-06,
"loss": 1.7499,
"step": 31
},
{
"epoch": 0.25,
"learning_rate": 8.793790613463956e-06,
"loss": 1.8016,
"step": 32
},
{
"epoch": 0.26,
"learning_rate": 8.710067927254555e-06,
"loss": 1.8158,
"step": 33
},
{
"epoch": 0.26,
"learning_rate": 8.6239639361456e-06,
"loss": 1.8079,
"step": 34
},
{
"epoch": 0.27,
"learning_rate": 8.535533905932739e-06,
"loss": 1.7768,
"step": 35
},
{
"epoch": 0.28,
"learning_rate": 8.444834595378434e-06,
"loss": 1.7988,
"step": 36
},
{
"epoch": 0.29,
"learning_rate": 8.351924219781393e-06,
"loss": 1.7971,
"step": 37
},
{
"epoch": 0.3,
"learning_rate": 8.256862413611113e-06,
"loss": 1.7477,
"step": 38
},
{
"epoch": 0.3,
"learning_rate": 8.15971019223152e-06,
"loss": 1.7809,
"step": 39
},
{
"epoch": 0.31,
"learning_rate": 8.060529912738316e-06,
"loss": 1.7892,
"step": 40
},
{
"epoch": 0.32,
"learning_rate": 7.959385233935087e-06,
"loss": 1.7717,
"step": 41
},
{
"epoch": 0.33,
"learning_rate": 7.856341075473963e-06,
"loss": 1.781,
"step": 42
},
{
"epoch": 0.33,
"learning_rate": 7.751463576186957e-06,
"loss": 1.756,
"step": 43
},
{
"epoch": 0.34,
"learning_rate": 7.644820051634813e-06,
"loss": 1.8093,
"step": 44
},
{
"epoch": 0.35,
"learning_rate": 7.536478950900537e-06,
"loss": 1.7318,
"step": 45
},
{
"epoch": 0.36,
"learning_rate": 7.4265098126554065e-06,
"loss": 1.7555,
"step": 46
},
{
"epoch": 0.37,
"learning_rate": 7.314983220525604e-06,
"loss": 1.7528,
"step": 47
},
{
"epoch": 0.37,
"learning_rate": 7.201970757788172e-06,
"loss": 1.7651,
"step": 48
},
{
"epoch": 0.38,
"learning_rate": 7.087544961425317e-06,
"loss": 1.7254,
"step": 49
},
{
"epoch": 0.39,
"learning_rate": 6.971779275566593e-06,
"loss": 1.7646,
"step": 50
},
{
"epoch": 0.4,
"learning_rate": 6.85474800434884e-06,
"loss": 1.7662,
"step": 51
},
{
"epoch": 0.4,
"learning_rate": 6.736526264224101e-06,
"loss": 1.7769,
"step": 52
},
{
"epoch": 0.41,
"learning_rate": 6.617189935746191e-06,
"loss": 1.7769,
"step": 53
},
{
"epoch": 0.42,
"learning_rate": 6.496815614866792e-06,
"loss": 1.8041,
"step": 54
},
{
"epoch": 0.43,
"learning_rate": 6.375480563772391e-06,
"loss": 1.8015,
"step": 55
},
{
"epoch": 0.44,
"learning_rate": 6.2532626612936035e-06,
"loss": 1.7357,
"step": 56
},
{
"epoch": 0.44,
"learning_rate": 6.130240352918675e-06,
"loss": 1.7854,
"step": 57
},
{
"epoch": 0.45,
"learning_rate": 6.006492600443301e-06,
"loss": 1.7685,
"step": 58
},
{
"epoch": 0.46,
"learning_rate": 5.882098831289044e-06,
"loss": 1.7783,
"step": 59
},
{
"epoch": 0.47,
"learning_rate": 5.757138887522884e-06,
"loss": 1.7669,
"step": 60
},
{
"epoch": 0.47,
"learning_rate": 5.631692974610647e-06,
"loss": 1.7899,
"step": 61
},
{
"epoch": 0.48,
"learning_rate": 5.505841609937162e-06,
"loss": 1.7474,
"step": 62
},
{
"epoch": 0.49,
"learning_rate": 5.379665571126232e-06,
"loss": 1.7321,
"step": 63
},
{
"epoch": 0.5,
"learning_rate": 5.253245844193564e-06,
"loss": 1.7609,
"step": 64
},
{
"epoch": 0.51,
"learning_rate": 5.12666357156594e-06,
"loss": 1.7672,
"step": 65
},
{
"epoch": 0.51,
"learning_rate": 5e-06,
"loss": 1.7553,
"step": 66
},
{
"epoch": 0.52,
"learning_rate": 4.873336428434062e-06,
"loss": 1.7471,
"step": 67
},
{
"epoch": 0.53,
"learning_rate": 4.746754155806437e-06,
"loss": 1.7547,
"step": 68
},
{
"epoch": 0.54,
"learning_rate": 4.62033442887377e-06,
"loss": 1.7578,
"step": 69
},
{
"epoch": 0.54,
"learning_rate": 4.49415839006284e-06,
"loss": 1.7346,
"step": 70
},
{
"epoch": 0.55,
"learning_rate": 4.368307025389355e-06,
"loss": 1.7611,
"step": 71
},
{
"epoch": 0.56,
"learning_rate": 4.2428611124771184e-06,
"loss": 1.7241,
"step": 72
},
{
"epoch": 0.57,
"learning_rate": 4.11790116871096e-06,
"loss": 1.7438,
"step": 73
},
{
"epoch": 0.58,
"learning_rate": 3.993507399556699e-06,
"loss": 1.7881,
"step": 74
},
{
"epoch": 0.58,
"learning_rate": 3.869759647081326e-06,
"loss": 1.7566,
"step": 75
},
{
"epoch": 0.59,
"learning_rate": 3.7467373387063973e-06,
"loss": 1.7468,
"step": 76
},
{
"epoch": 0.6,
"learning_rate": 3.62451943622761e-06,
"loss": 1.7383,
"step": 77
},
{
"epoch": 0.61,
"learning_rate": 3.5031843851332105e-06,
"loss": 1.7328,
"step": 78
},
{
"epoch": 0.61,
"learning_rate": 3.3828100642538097e-06,
"loss": 1.761,
"step": 79
},
{
"epoch": 0.62,
"learning_rate": 3.2634737357758994e-06,
"loss": 1.7617,
"step": 80
},
{
"epoch": 0.63,
"learning_rate": 3.145251995651162e-06,
"loss": 1.7122,
"step": 81
},
{
"epoch": 0.64,
"learning_rate": 3.0282207244334084e-06,
"loss": 1.7163,
"step": 82
},
{
"epoch": 0.65,
"learning_rate": 2.912455038574686e-06,
"loss": 1.7139,
"step": 83
},
{
"epoch": 0.65,
"learning_rate": 2.7980292422118282e-06,
"loss": 1.7071,
"step": 84
},
{
"epoch": 0.66,
"learning_rate": 2.6850167794743966e-06,
"loss": 1.7807,
"step": 85
},
{
"epoch": 0.67,
"learning_rate": 2.573490187344596e-06,
"loss": 1.7501,
"step": 86
},
{
"epoch": 0.68,
"learning_rate": 2.4635210490994648e-06,
"loss": 1.7211,
"step": 87
},
{
"epoch": 0.68,
"learning_rate": 2.3551799483651894e-06,
"loss": 1.7045,
"step": 88
},
{
"epoch": 0.69,
"learning_rate": 2.2485364238130435e-06,
"loss": 1.7349,
"step": 89
},
{
"epoch": 0.7,
"learning_rate": 2.1436589245260375e-06,
"loss": 1.7185,
"step": 90
},
{
"epoch": 0.71,
"learning_rate": 2.040614766064913e-06,
"loss": 1.7096,
"step": 91
},
{
"epoch": 0.72,
"learning_rate": 1.9394700872616856e-06,
"loss": 1.7525,
"step": 92
},
{
"epoch": 0.72,
"learning_rate": 1.8402898077684806e-06,
"loss": 1.713,
"step": 93
},
{
"epoch": 0.73,
"learning_rate": 1.74313758638889e-06,
"loss": 1.7424,
"step": 94
},
{
"epoch": 0.74,
"learning_rate": 1.648075780218607e-06,
"loss": 1.703,
"step": 95
},
{
"epoch": 0.75,
"learning_rate": 1.555165404621567e-06,
"loss": 1.708,
"step": 96
},
{
"epoch": 0.75,
"learning_rate": 1.4644660940672628e-06,
"loss": 1.7509,
"step": 97
},
{
"epoch": 0.76,
"learning_rate": 1.3760360638544012e-06,
"loss": 1.754,
"step": 98
},
{
"epoch": 0.77,
"learning_rate": 1.2899320727454472e-06,
"loss": 1.7233,
"step": 99
},
{
"epoch": 0.78,
"learning_rate": 1.2062093865360458e-06,
"loss": 1.7484,
"step": 100
}
],
"logging_steps": 1.0,
"max_steps": 128,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"total_flos": 0.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}