prxy5607's picture
Training in progress, step 50, checkpoint
560501e verified
{
"best_metric": NaN,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 0.35335689045936397,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.007067137809187279,
"grad_norm": 0.8103557229042053,
"learning_rate": 2e-05,
"loss": 2.4264,
"step": 1
},
{
"epoch": 0.007067137809187279,
"eval_loss": NaN,
"eval_runtime": 4.015,
"eval_samples_per_second": 59.527,
"eval_steps_per_second": 7.472,
"step": 1
},
{
"epoch": 0.014134275618374558,
"grad_norm": 1.3682575225830078,
"learning_rate": 4e-05,
"loss": 2.395,
"step": 2
},
{
"epoch": 0.02120141342756184,
"grad_norm": 1.1574937105178833,
"learning_rate": 6e-05,
"loss": 2.4938,
"step": 3
},
{
"epoch": 0.028268551236749116,
"grad_norm": 0.9679173827171326,
"learning_rate": 8e-05,
"loss": 2.2658,
"step": 4
},
{
"epoch": 0.0353356890459364,
"grad_norm": 1.1998224258422852,
"learning_rate": 0.0001,
"loss": 2.1697,
"step": 5
},
{
"epoch": 0.04240282685512368,
"grad_norm": 0.943162739276886,
"learning_rate": 9.987820251299122e-05,
"loss": 2.1766,
"step": 6
},
{
"epoch": 0.04946996466431095,
"grad_norm": 0.9509667158126831,
"learning_rate": 9.951340343707852e-05,
"loss": 1.779,
"step": 7
},
{
"epoch": 0.05653710247349823,
"grad_norm": 0.9809722304344177,
"learning_rate": 9.890738003669029e-05,
"loss": 1.6956,
"step": 8
},
{
"epoch": 0.0636042402826855,
"grad_norm": 1.0028021335601807,
"learning_rate": 9.806308479691595e-05,
"loss": 1.8519,
"step": 9
},
{
"epoch": 0.0706713780918728,
"grad_norm": 1.1464509963989258,
"learning_rate": 9.698463103929542e-05,
"loss": 1.6111,
"step": 10
},
{
"epoch": 0.07773851590106007,
"grad_norm": 1.0126804113388062,
"learning_rate": 9.567727288213005e-05,
"loss": 1.1093,
"step": 11
},
{
"epoch": 0.08480565371024736,
"grad_norm": 0.8876432180404663,
"learning_rate": 9.414737964294636e-05,
"loss": 1.2639,
"step": 12
},
{
"epoch": 0.09187279151943463,
"grad_norm": 1.1913671493530273,
"learning_rate": 9.24024048078213e-05,
"loss": 1.1125,
"step": 13
},
{
"epoch": 0.0989399293286219,
"grad_norm": 1.2153666019439697,
"learning_rate": 9.045084971874738e-05,
"loss": 1.4932,
"step": 14
},
{
"epoch": 0.10600706713780919,
"grad_norm": 1.3376637697219849,
"learning_rate": 8.83022221559489e-05,
"loss": 1.4403,
"step": 15
},
{
"epoch": 0.11307420494699646,
"grad_norm": 1.1326059103012085,
"learning_rate": 8.596699001693255e-05,
"loss": 1.244,
"step": 16
},
{
"epoch": 0.12014134275618374,
"grad_norm": 0.9148973226547241,
"learning_rate": 8.345653031794292e-05,
"loss": 0.9101,
"step": 17
},
{
"epoch": 0.127208480565371,
"grad_norm": 0.9324835538864136,
"learning_rate": 8.07830737662829e-05,
"loss": 1.0656,
"step": 18
},
{
"epoch": 0.13427561837455831,
"grad_norm": 1.0188170671463013,
"learning_rate": 7.795964517353735e-05,
"loss": 0.7383,
"step": 19
},
{
"epoch": 0.1413427561837456,
"grad_norm": 1.9019992351531982,
"learning_rate": 7.500000000000001e-05,
"loss": 1.1077,
"step": 20
},
{
"epoch": 0.14840989399293286,
"grad_norm": 1.4859684705734253,
"learning_rate": 7.191855733945387e-05,
"loss": 0.3897,
"step": 21
},
{
"epoch": 0.15547703180212014,
"grad_norm": 2.1484122276306152,
"learning_rate": 6.873032967079561e-05,
"loss": 0.8941,
"step": 22
},
{
"epoch": 0.1625441696113074,
"grad_norm": 1.2217742204666138,
"learning_rate": 6.545084971874738e-05,
"loss": 0.7052,
"step": 23
},
{
"epoch": 0.1696113074204947,
"grad_norm": 2.0995230674743652,
"learning_rate": 6.209609477998338e-05,
"loss": 1.0284,
"step": 24
},
{
"epoch": 0.17667844522968199,
"grad_norm": 1.1697871685028076,
"learning_rate": 5.868240888334653e-05,
"loss": 0.5796,
"step": 25
},
{
"epoch": 0.17667844522968199,
"eval_loss": NaN,
"eval_runtime": 4.1218,
"eval_samples_per_second": 57.984,
"eval_steps_per_second": 7.278,
"step": 25
},
{
"epoch": 0.18374558303886926,
"grad_norm": 0.0,
"learning_rate": 5.522642316338268e-05,
"loss": 0.0,
"step": 26
},
{
"epoch": 0.19081272084805653,
"grad_norm": 0.0,
"learning_rate": 5.174497483512506e-05,
"loss": 0.0,
"step": 27
},
{
"epoch": 0.1978798586572438,
"grad_norm": 2.0653741359710693,
"learning_rate": 4.825502516487497e-05,
"loss": 0.378,
"step": 28
},
{
"epoch": 0.2049469964664311,
"grad_norm": 0.0,
"learning_rate": 4.477357683661734e-05,
"loss": 0.0,
"step": 29
},
{
"epoch": 0.21201413427561838,
"grad_norm": 0.0,
"learning_rate": 4.131759111665349e-05,
"loss": 0.0,
"step": 30
},
{
"epoch": 0.21908127208480566,
"grad_norm": 0.0,
"learning_rate": 3.790390522001662e-05,
"loss": 0.0,
"step": 31
},
{
"epoch": 0.22614840989399293,
"grad_norm": 8.19146728515625,
"learning_rate": 3.4549150281252636e-05,
"loss": 1.0902,
"step": 32
},
{
"epoch": 0.2332155477031802,
"grad_norm": 0.0,
"learning_rate": 3.12696703292044e-05,
"loss": 0.0,
"step": 33
},
{
"epoch": 0.24028268551236748,
"grad_norm": 0.0,
"learning_rate": 2.8081442660546125e-05,
"loss": 0.0,
"step": 34
},
{
"epoch": 0.24734982332155478,
"grad_norm": 0.0,
"learning_rate": 2.500000000000001e-05,
"loss": 0.0,
"step": 35
},
{
"epoch": 0.254416961130742,
"grad_norm": 1.1065750122070312,
"learning_rate": 2.2040354826462668e-05,
"loss": 1.1358,
"step": 36
},
{
"epoch": 0.26148409893992935,
"grad_norm": 1.098425269126892,
"learning_rate": 1.9216926233717085e-05,
"loss": 1.1901,
"step": 37
},
{
"epoch": 0.26855123674911663,
"grad_norm": 4.422745704650879,
"learning_rate": 1.6543469682057106e-05,
"loss": 2.2529,
"step": 38
},
{
"epoch": 0.2756183745583039,
"grad_norm": 1.6350035667419434,
"learning_rate": 1.4033009983067452e-05,
"loss": 1.1209,
"step": 39
},
{
"epoch": 0.2826855123674912,
"grad_norm": 0.9407490491867065,
"learning_rate": 1.1697777844051105e-05,
"loss": 1.1377,
"step": 40
},
{
"epoch": 0.28975265017667845,
"grad_norm": 0.9304065704345703,
"learning_rate": 9.549150281252633e-06,
"loss": 0.961,
"step": 41
},
{
"epoch": 0.2968197879858657,
"grad_norm": 0.800937831401825,
"learning_rate": 7.597595192178702e-06,
"loss": 0.9086,
"step": 42
},
{
"epoch": 0.303886925795053,
"grad_norm": 0.9793635010719299,
"learning_rate": 5.852620357053651e-06,
"loss": 1.1349,
"step": 43
},
{
"epoch": 0.31095406360424027,
"grad_norm": 0.9108982086181641,
"learning_rate": 4.322727117869951e-06,
"loss": 1.1596,
"step": 44
},
{
"epoch": 0.31802120141342755,
"grad_norm": 0.7559174299240112,
"learning_rate": 3.0153689607045845e-06,
"loss": 0.8285,
"step": 45
},
{
"epoch": 0.3250883392226148,
"grad_norm": 0.9393735527992249,
"learning_rate": 1.9369152030840556e-06,
"loss": 0.8102,
"step": 46
},
{
"epoch": 0.3321554770318021,
"grad_norm": 1.0659395456314087,
"learning_rate": 1.0926199633097157e-06,
"loss": 1.0655,
"step": 47
},
{
"epoch": 0.3392226148409894,
"grad_norm": 0.970039427280426,
"learning_rate": 4.865965629214819e-07,
"loss": 0.8879,
"step": 48
},
{
"epoch": 0.3462897526501767,
"grad_norm": 0.7782996296882629,
"learning_rate": 1.2179748700879012e-07,
"loss": 0.7354,
"step": 49
},
{
"epoch": 0.35335689045936397,
"grad_norm": 1.0545905828475952,
"learning_rate": 0.0,
"loss": 0.9708,
"step": 50
},
{
"epoch": 0.35335689045936397,
"eval_loss": NaN,
"eval_runtime": 4.0268,
"eval_samples_per_second": 59.352,
"eval_steps_per_second": 7.45,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 1
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 7347907728506880.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}