ZED99's picture
Upload folder using huggingface_hub
ca08aa3 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9984,
"eval_steps": 500,
"global_step": 78,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0128,
"grad_norm": 0.38354784779145196,
"learning_rate": 0.0,
"loss": 0.3883,
"step": 1
},
{
"epoch": 0.0256,
"grad_norm": 0.3518942269770282,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.3931,
"step": 2
},
{
"epoch": 0.0384,
"grad_norm": 0.4700662562196038,
"learning_rate": 6.666666666666667e-06,
"loss": 0.4011,
"step": 3
},
{
"epoch": 0.0512,
"grad_norm": 0.37903444800293185,
"learning_rate": 1e-05,
"loss": 0.3971,
"step": 4
},
{
"epoch": 0.064,
"grad_norm": 0.34122036476473955,
"learning_rate": 9.995614150494293e-06,
"loss": 0.4002,
"step": 5
},
{
"epoch": 0.0768,
"grad_norm": 0.39785239048749793,
"learning_rate": 9.982464296247523e-06,
"loss": 0.4028,
"step": 6
},
{
"epoch": 0.0896,
"grad_norm": 0.34605579363627365,
"learning_rate": 9.960573506572391e-06,
"loss": 0.3979,
"step": 7
},
{
"epoch": 0.1024,
"grad_norm": 0.40063462992075954,
"learning_rate": 9.929980185352525e-06,
"loss": 0.4097,
"step": 8
},
{
"epoch": 0.1152,
"grad_norm": 0.43355703971250864,
"learning_rate": 9.890738003669029e-06,
"loss": 0.3934,
"step": 9
},
{
"epoch": 0.128,
"grad_norm": 0.37968910143781054,
"learning_rate": 9.842915805643156e-06,
"loss": 0.4024,
"step": 10
},
{
"epoch": 0.1408,
"grad_norm": 0.3628572660613157,
"learning_rate": 9.786597487660336e-06,
"loss": 0.3945,
"step": 11
},
{
"epoch": 0.1536,
"grad_norm": 0.40858453994282173,
"learning_rate": 9.721881851187406e-06,
"loss": 0.3967,
"step": 12
},
{
"epoch": 0.1664,
"grad_norm": 0.3921729264761742,
"learning_rate": 9.648882429441258e-06,
"loss": 0.388,
"step": 13
},
{
"epoch": 0.1792,
"grad_norm": 0.3563974778420232,
"learning_rate": 9.567727288213005e-06,
"loss": 0.389,
"step": 14
},
{
"epoch": 0.192,
"grad_norm": 0.37097378945033266,
"learning_rate": 9.478558801197065e-06,
"loss": 0.3823,
"step": 15
},
{
"epoch": 0.2048,
"grad_norm": 0.39190188301230705,
"learning_rate": 9.381533400219319e-06,
"loss": 0.4017,
"step": 16
},
{
"epoch": 0.2176,
"grad_norm": 0.3527815991009716,
"learning_rate": 9.276821300802535e-06,
"loss": 0.3882,
"step": 17
},
{
"epoch": 0.2304,
"grad_norm": 0.3900917998963072,
"learning_rate": 9.164606203550498e-06,
"loss": 0.3859,
"step": 18
},
{
"epoch": 0.2432,
"grad_norm": 0.36593259433741565,
"learning_rate": 9.045084971874738e-06,
"loss": 0.3998,
"step": 19
},
{
"epoch": 0.256,
"grad_norm": 0.3743144710383303,
"learning_rate": 8.9184672866292e-06,
"loss": 0.3833,
"step": 20
},
{
"epoch": 0.2688,
"grad_norm": 0.376543361811563,
"learning_rate": 8.784975278258783e-06,
"loss": 0.3883,
"step": 21
},
{
"epoch": 0.2816,
"grad_norm": 0.3293896302449729,
"learning_rate": 8.644843137107058e-06,
"loss": 0.3828,
"step": 22
},
{
"epoch": 0.2944,
"grad_norm": 0.35911197165686903,
"learning_rate": 8.498316702566828e-06,
"loss": 0.3896,
"step": 23
},
{
"epoch": 0.3072,
"grad_norm": 0.38804621155363117,
"learning_rate": 8.345653031794292e-06,
"loss": 0.3907,
"step": 24
},
{
"epoch": 0.32,
"grad_norm": 0.3822782563958177,
"learning_rate": 8.18711994874345e-06,
"loss": 0.3934,
"step": 25
},
{
"epoch": 0.3328,
"grad_norm": 0.3238604039210753,
"learning_rate": 8.022995574311876e-06,
"loss": 0.3848,
"step": 26
},
{
"epoch": 0.3456,
"grad_norm": 0.44686612607388176,
"learning_rate": 7.85356783842216e-06,
"loss": 0.3807,
"step": 27
},
{
"epoch": 0.3584,
"grad_norm": 0.34273450644906006,
"learning_rate": 7.679133974894984e-06,
"loss": 0.4068,
"step": 28
},
{
"epoch": 0.3712,
"grad_norm": 0.3500682361409773,
"learning_rate": 7.500000000000001e-06,
"loss": 0.3866,
"step": 29
},
{
"epoch": 0.384,
"grad_norm": 0.3888435597530221,
"learning_rate": 7.31648017559931e-06,
"loss": 0.3857,
"step": 30
},
{
"epoch": 0.3968,
"grad_norm": 0.342763297825136,
"learning_rate": 7.128896457825364e-06,
"loss": 0.4002,
"step": 31
},
{
"epoch": 0.4096,
"grad_norm": 0.35351716872316025,
"learning_rate": 6.9375779322605154e-06,
"loss": 0.394,
"step": 32
},
{
"epoch": 0.4224,
"grad_norm": 0.331114636947211,
"learning_rate": 6.7428602366090764e-06,
"loss": 0.3981,
"step": 33
},
{
"epoch": 0.4352,
"grad_norm": 0.41945214761906985,
"learning_rate": 6.545084971874738e-06,
"loss": 0.3845,
"step": 34
},
{
"epoch": 0.448,
"grad_norm": 0.3295917670618691,
"learning_rate": 6.344599103076329e-06,
"loss": 0.372,
"step": 35
},
{
"epoch": 0.4608,
"grad_norm": 0.3407441246790751,
"learning_rate": 6.141754350553279e-06,
"loss": 0.3789,
"step": 36
},
{
"epoch": 0.4736,
"grad_norm": 0.3448602863368462,
"learning_rate": 5.936906572928625e-06,
"loss": 0.383,
"step": 37
},
{
"epoch": 0.4864,
"grad_norm": 0.3764070539356377,
"learning_rate": 5.730415142812059e-06,
"loss": 0.3784,
"step": 38
},
{
"epoch": 0.4992,
"grad_norm": 0.3625033164011223,
"learning_rate": 5.522642316338268e-06,
"loss": 0.3905,
"step": 39
},
{
"epoch": 0.512,
"grad_norm": 0.3759751654658226,
"learning_rate": 5.3139525976465675e-06,
"loss": 0.3905,
"step": 40
},
{
"epoch": 0.5248,
"grad_norm": 0.36250624870715864,
"learning_rate": 5.1047120994167855e-06,
"loss": 0.3855,
"step": 41
},
{
"epoch": 0.5376,
"grad_norm": 0.35539548601379817,
"learning_rate": 4.895287900583216e-06,
"loss": 0.3719,
"step": 42
},
{
"epoch": 0.5504,
"grad_norm": 0.3621948645817036,
"learning_rate": 4.686047402353433e-06,
"loss": 0.3957,
"step": 43
},
{
"epoch": 0.5632,
"grad_norm": 0.35229271529368117,
"learning_rate": 4.477357683661734e-06,
"loss": 0.376,
"step": 44
},
{
"epoch": 0.576,
"grad_norm": 0.3573900886145352,
"learning_rate": 4.269584857187942e-06,
"loss": 0.3847,
"step": 45
},
{
"epoch": 0.5888,
"grad_norm": 0.359574767780604,
"learning_rate": 4.063093427071376e-06,
"loss": 0.3939,
"step": 46
},
{
"epoch": 0.6016,
"grad_norm": 0.32837713976642424,
"learning_rate": 3.8582456494467214e-06,
"loss": 0.3725,
"step": 47
},
{
"epoch": 0.6144,
"grad_norm": 0.3640012410584659,
"learning_rate": 3.655400896923672e-06,
"loss": 0.3817,
"step": 48
},
{
"epoch": 0.6272,
"grad_norm": 0.34999344143496786,
"learning_rate": 3.4549150281252635e-06,
"loss": 0.3792,
"step": 49
},
{
"epoch": 0.64,
"grad_norm": 0.3695188659698603,
"learning_rate": 3.2571397633909252e-06,
"loss": 0.3909,
"step": 50
},
{
"epoch": 0.6528,
"grad_norm": 0.36132654132688435,
"learning_rate": 3.0624220677394854e-06,
"loss": 0.373,
"step": 51
},
{
"epoch": 0.6656,
"grad_norm": 0.34690969438414104,
"learning_rate": 2.871103542174637e-06,
"loss": 0.381,
"step": 52
},
{
"epoch": 0.6784,
"grad_norm": 0.41906448536490565,
"learning_rate": 2.683519824400693e-06,
"loss": 0.3852,
"step": 53
},
{
"epoch": 0.6912,
"grad_norm": 0.3378718003012021,
"learning_rate": 2.5000000000000015e-06,
"loss": 0.3806,
"step": 54
},
{
"epoch": 0.704,
"grad_norm": 0.33433260166256307,
"learning_rate": 2.320866025105016e-06,
"loss": 0.3709,
"step": 55
},
{
"epoch": 0.7168,
"grad_norm": 0.36532166747116757,
"learning_rate": 2.146432161577842e-06,
"loss": 0.39,
"step": 56
},
{
"epoch": 0.7296,
"grad_norm": 0.33365411509253523,
"learning_rate": 1.977004425688126e-06,
"loss": 0.3764,
"step": 57
},
{
"epoch": 0.7424,
"grad_norm": 0.35541862950987707,
"learning_rate": 1.8128800512565514e-06,
"loss": 0.3866,
"step": 58
},
{
"epoch": 0.7552,
"grad_norm": 0.326757644609808,
"learning_rate": 1.6543469682057105e-06,
"loss": 0.375,
"step": 59
},
{
"epoch": 0.768,
"grad_norm": 0.3638696597135469,
"learning_rate": 1.5016832974331725e-06,
"loss": 0.3808,
"step": 60
},
{
"epoch": 0.7808,
"grad_norm": 0.3429896742899055,
"learning_rate": 1.3551568628929434e-06,
"loss": 0.3797,
"step": 61
},
{
"epoch": 0.7936,
"grad_norm": 0.34549068928015514,
"learning_rate": 1.2150247217412186e-06,
"loss": 0.3756,
"step": 62
},
{
"epoch": 0.8064,
"grad_norm": 0.3135559147233645,
"learning_rate": 1.0815327133708015e-06,
"loss": 0.3754,
"step": 63
},
{
"epoch": 0.8192,
"grad_norm": 0.3631670367295947,
"learning_rate": 9.549150281252633e-07,
"loss": 0.3829,
"step": 64
},
{
"epoch": 0.832,
"grad_norm": 0.3531412601992164,
"learning_rate": 8.353937964495029e-07,
"loss": 0.3847,
"step": 65
},
{
"epoch": 0.8448,
"grad_norm": 0.32948068779382106,
"learning_rate": 7.23178699197467e-07,
"loss": 0.3822,
"step": 66
},
{
"epoch": 0.8576,
"grad_norm": 0.3448105491176633,
"learning_rate": 6.184665997806832e-07,
"loss": 0.3907,
"step": 67
},
{
"epoch": 0.8704,
"grad_norm": 0.39086753035937183,
"learning_rate": 5.214411988029355e-07,
"loss": 0.3839,
"step": 68
},
{
"epoch": 0.8832,
"grad_norm": 0.33079414940321544,
"learning_rate": 4.322727117869951e-07,
"loss": 0.3807,
"step": 69
},
{
"epoch": 0.896,
"grad_norm": 0.32573150318838584,
"learning_rate": 3.511175705587433e-07,
"loss": 0.3777,
"step": 70
},
{
"epoch": 0.9088,
"grad_norm": 0.3706878840294444,
"learning_rate": 2.7811814881259503e-07,
"loss": 0.3898,
"step": 71
},
{
"epoch": 0.9216,
"grad_norm": 0.36651164142892223,
"learning_rate": 2.134025123396638e-07,
"loss": 0.3799,
"step": 72
},
{
"epoch": 0.9344,
"grad_norm": 0.5020932895381515,
"learning_rate": 1.5708419435684463e-07,
"loss": 0.3688,
"step": 73
},
{
"epoch": 0.9472,
"grad_norm": 0.3671704281607279,
"learning_rate": 1.0926199633097156e-07,
"loss": 0.3806,
"step": 74
},
{
"epoch": 0.96,
"grad_norm": 0.37068890178945674,
"learning_rate": 7.001981464747565e-08,
"loss": 0.3777,
"step": 75
},
{
"epoch": 0.9728,
"grad_norm": 0.3534565321103133,
"learning_rate": 3.9426493427611177e-08,
"loss": 0.3772,
"step": 76
},
{
"epoch": 0.9856,
"grad_norm": 0.3887793583099691,
"learning_rate": 1.753570375247815e-08,
"loss": 0.3905,
"step": 77
},
{
"epoch": 0.9984,
"grad_norm": 0.3488620549391766,
"learning_rate": 4.385849505708084e-09,
"loss": 0.3842,
"step": 78
},
{
"epoch": 0.9984,
"step": 78,
"total_flos": 117837343621120.0,
"train_loss": 0.386520239787224,
"train_runtime": 904.4248,
"train_samples_per_second": 11.057,
"train_steps_per_second": 0.086
}
],
"logging_steps": 1,
"max_steps": 78,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 40,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 117837343621120.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}