prxy5607's picture
Training in progress, step 50, checkpoint
f3bf845 verified
raw
history blame
10 kB
{
"best_metric": 0.8688188791275024,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.007490356166435714,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00014980712332871428,
"grad_norm": 0.6298632621765137,
"learning_rate": 1e-05,
"loss": 0.8866,
"step": 1
},
{
"epoch": 0.00014980712332871428,
"eval_loss": 1.264488935470581,
"eval_runtime": 565.4748,
"eval_samples_per_second": 19.882,
"eval_steps_per_second": 4.971,
"step": 1
},
{
"epoch": 0.00029961424665742855,
"grad_norm": 0.46446141600608826,
"learning_rate": 2e-05,
"loss": 0.7634,
"step": 2
},
{
"epoch": 0.00044942136998614283,
"grad_norm": 0.8355027437210083,
"learning_rate": 3e-05,
"loss": 0.9169,
"step": 3
},
{
"epoch": 0.0005992284933148571,
"grad_norm": 0.644906222820282,
"learning_rate": 4e-05,
"loss": 0.9282,
"step": 4
},
{
"epoch": 0.0007490356166435714,
"grad_norm": 0.49212518334388733,
"learning_rate": 5e-05,
"loss": 0.9798,
"step": 5
},
{
"epoch": 0.0008988427399722857,
"grad_norm": 0.44296741485595703,
"learning_rate": 6e-05,
"loss": 1.0082,
"step": 6
},
{
"epoch": 0.001048649863301,
"grad_norm": 0.3797648847103119,
"learning_rate": 7e-05,
"loss": 0.9093,
"step": 7
},
{
"epoch": 0.0011984569866297142,
"grad_norm": 0.3763546049594879,
"learning_rate": 8e-05,
"loss": 1.0401,
"step": 8
},
{
"epoch": 0.0013482641099584285,
"grad_norm": 0.3808014988899231,
"learning_rate": 9e-05,
"loss": 1.0106,
"step": 9
},
{
"epoch": 0.0014980712332871428,
"grad_norm": 0.3745298385620117,
"learning_rate": 0.0001,
"loss": 0.9575,
"step": 10
},
{
"epoch": 0.001647878356615857,
"grad_norm": 0.39324429631233215,
"learning_rate": 9.999316524962345e-05,
"loss": 0.9435,
"step": 11
},
{
"epoch": 0.0017976854799445713,
"grad_norm": 0.3526301085948944,
"learning_rate": 9.997266286704631e-05,
"loss": 0.8208,
"step": 12
},
{
"epoch": 0.0019474926032732856,
"grad_norm": 0.37045592069625854,
"learning_rate": 9.993849845741524e-05,
"loss": 0.9634,
"step": 13
},
{
"epoch": 0.002097299726602,
"grad_norm": 0.33772504329681396,
"learning_rate": 9.989068136093873e-05,
"loss": 0.8449,
"step": 14
},
{
"epoch": 0.0022471068499307144,
"grad_norm": 0.43836352229118347,
"learning_rate": 9.98292246503335e-05,
"loss": 0.6716,
"step": 15
},
{
"epoch": 0.0023969139732594284,
"grad_norm": 0.3777485191822052,
"learning_rate": 9.975414512725057e-05,
"loss": 0.8852,
"step": 16
},
{
"epoch": 0.002546721096588143,
"grad_norm": 0.36619219183921814,
"learning_rate": 9.966546331768191e-05,
"loss": 0.8873,
"step": 17
},
{
"epoch": 0.002696528219916857,
"grad_norm": 0.3267233073711395,
"learning_rate": 9.956320346634876e-05,
"loss": 0.855,
"step": 18
},
{
"epoch": 0.0028463353432455715,
"grad_norm": 0.32704541087150574,
"learning_rate": 9.944739353007344e-05,
"loss": 0.8803,
"step": 19
},
{
"epoch": 0.0029961424665742855,
"grad_norm": 0.4222426414489746,
"learning_rate": 9.931806517013612e-05,
"loss": 0.8979,
"step": 20
},
{
"epoch": 0.003145949589903,
"grad_norm": 0.33164480328559875,
"learning_rate": 9.917525374361912e-05,
"loss": 0.7718,
"step": 21
},
{
"epoch": 0.003295756713231714,
"grad_norm": 0.32442235946655273,
"learning_rate": 9.901899829374047e-05,
"loss": 0.6811,
"step": 22
},
{
"epoch": 0.0034455638365604286,
"grad_norm": 0.3956811726093292,
"learning_rate": 9.884934153917997e-05,
"loss": 0.8274,
"step": 23
},
{
"epoch": 0.0035953709598891426,
"grad_norm": 0.4070234000682831,
"learning_rate": 9.86663298624003e-05,
"loss": 0.8034,
"step": 24
},
{
"epoch": 0.003745178083217857,
"grad_norm": 0.30631351470947266,
"learning_rate": 9.847001329696653e-05,
"loss": 0.7311,
"step": 25
},
{
"epoch": 0.003894985206546571,
"grad_norm": 0.34183362126350403,
"learning_rate": 9.826044551386744e-05,
"loss": 0.8869,
"step": 26
},
{
"epoch": 0.004044792329875285,
"grad_norm": 0.29005616903305054,
"learning_rate": 9.803768380684242e-05,
"loss": 0.8703,
"step": 27
},
{
"epoch": 0.004194599453204,
"grad_norm": 0.359518826007843,
"learning_rate": 9.780178907671789e-05,
"loss": 0.8542,
"step": 28
},
{
"epoch": 0.004344406576532714,
"grad_norm": 0.35285744071006775,
"learning_rate": 9.755282581475769e-05,
"loss": 0.7862,
"step": 29
},
{
"epoch": 0.004494213699861429,
"grad_norm": 0.32191500067710876,
"learning_rate": 9.729086208503174e-05,
"loss": 0.7777,
"step": 30
},
{
"epoch": 0.004644020823190142,
"grad_norm": 0.34467917680740356,
"learning_rate": 9.701596950580806e-05,
"loss": 0.8035,
"step": 31
},
{
"epoch": 0.004793827946518857,
"grad_norm": 0.31413033604621887,
"learning_rate": 9.672822322997305e-05,
"loss": 0.8019,
"step": 32
},
{
"epoch": 0.004943635069847571,
"grad_norm": 0.33082014322280884,
"learning_rate": 9.642770192448536e-05,
"loss": 0.7154,
"step": 33
},
{
"epoch": 0.005093442193176286,
"grad_norm": 0.34413284063339233,
"learning_rate": 9.611448774886924e-05,
"loss": 0.6867,
"step": 34
},
{
"epoch": 0.0052432493165049995,
"grad_norm": 0.3844047486782074,
"learning_rate": 9.578866633275288e-05,
"loss": 0.8222,
"step": 35
},
{
"epoch": 0.005393056439833714,
"grad_norm": 0.47779640555381775,
"learning_rate": 9.545032675245813e-05,
"loss": 0.8534,
"step": 36
},
{
"epoch": 0.0055428635631624285,
"grad_norm": 2.2068326473236084,
"learning_rate": 9.509956150664796e-05,
"loss": 0.8379,
"step": 37
},
{
"epoch": 0.005692670686491143,
"grad_norm": 0.41778677701950073,
"learning_rate": 9.473646649103818e-05,
"loss": 0.9006,
"step": 38
},
{
"epoch": 0.005842477809819857,
"grad_norm": 0.4241478145122528,
"learning_rate": 9.43611409721806e-05,
"loss": 0.9492,
"step": 39
},
{
"epoch": 0.005992284933148571,
"grad_norm": 0.4319832921028137,
"learning_rate": 9.397368756032445e-05,
"loss": 1.0443,
"step": 40
},
{
"epoch": 0.0061420920564772856,
"grad_norm": 0.36160099506378174,
"learning_rate": 9.357421218136386e-05,
"loss": 0.6914,
"step": 41
},
{
"epoch": 0.006291899179806,
"grad_norm": 0.4357793629169464,
"learning_rate": 9.316282404787871e-05,
"loss": 0.872,
"step": 42
},
{
"epoch": 0.006441706303134714,
"grad_norm": 0.4501705467700958,
"learning_rate": 9.273963562927695e-05,
"loss": 0.8288,
"step": 43
},
{
"epoch": 0.006591513426463428,
"grad_norm": 0.5566861033439636,
"learning_rate": 9.230476262104677e-05,
"loss": 0.9786,
"step": 44
},
{
"epoch": 0.006741320549792143,
"grad_norm": 0.5371454954147339,
"learning_rate": 9.185832391312644e-05,
"loss": 0.9145,
"step": 45
},
{
"epoch": 0.006891127673120857,
"grad_norm": 0.5671194791793823,
"learning_rate": 9.140044155740101e-05,
"loss": 0.9264,
"step": 46
},
{
"epoch": 0.007040934796449571,
"grad_norm": 0.6908413171768188,
"learning_rate": 9.093124073433463e-05,
"loss": 1.0477,
"step": 47
},
{
"epoch": 0.007190741919778285,
"grad_norm": 0.7245323061943054,
"learning_rate": 9.045084971874738e-05,
"loss": 0.9384,
"step": 48
},
{
"epoch": 0.007340549043107,
"grad_norm": 0.9785915613174438,
"learning_rate": 8.995939984474624e-05,
"loss": 1.132,
"step": 49
},
{
"epoch": 0.007490356166435714,
"grad_norm": 1.2804609537124634,
"learning_rate": 8.945702546981969e-05,
"loss": 1.0875,
"step": 50
},
{
"epoch": 0.007490356166435714,
"eval_loss": 0.8688188791275024,
"eval_runtime": 568.3984,
"eval_samples_per_second": 19.78,
"eval_steps_per_second": 4.945,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.058823463960576e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}