dada22231's picture
Training in progress, step 50, checkpoint
bbf714b verified
{
"best_metric": 0.31840619444847107,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.13486176668914363,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0026972353337828725,
"grad_norm": 18.130537033081055,
"learning_rate": 5e-05,
"loss": 8.966,
"step": 1
},
{
"epoch": 0.0026972353337828725,
"eval_loss": 0.9168106317520142,
"eval_runtime": 2.8848,
"eval_samples_per_second": 17.332,
"eval_steps_per_second": 4.506,
"step": 1
},
{
"epoch": 0.005394470667565745,
"grad_norm": 21.171802520751953,
"learning_rate": 0.0001,
"loss": 10.5989,
"step": 2
},
{
"epoch": 0.008091706001348618,
"grad_norm": 22.652992248535156,
"learning_rate": 9.990365154573717e-05,
"loss": 10.8649,
"step": 3
},
{
"epoch": 0.01078894133513149,
"grad_norm": 23.879528045654297,
"learning_rate": 9.961501876182148e-05,
"loss": 9.217,
"step": 4
},
{
"epoch": 0.013486176668914362,
"grad_norm": 8.109113693237305,
"learning_rate": 9.913533761814537e-05,
"loss": 8.0286,
"step": 5
},
{
"epoch": 0.016183412002697236,
"grad_norm": 7.874186038970947,
"learning_rate": 9.846666218300807e-05,
"loss": 7.3722,
"step": 6
},
{
"epoch": 0.018880647336480108,
"grad_norm": 6.817716121673584,
"learning_rate": 9.761185582727977e-05,
"loss": 7.4999,
"step": 7
},
{
"epoch": 0.02157788267026298,
"grad_norm": 5.771115303039551,
"learning_rate": 9.657457896300791e-05,
"loss": 7.3256,
"step": 8
},
{
"epoch": 0.024275118004045852,
"grad_norm": 5.368096828460693,
"learning_rate": 9.535927336897098e-05,
"loss": 7.1784,
"step": 9
},
{
"epoch": 0.026972353337828724,
"grad_norm": 5.735297679901123,
"learning_rate": 9.397114317029975e-05,
"loss": 7.3572,
"step": 10
},
{
"epoch": 0.029669588671611596,
"grad_norm": 7.158353805541992,
"learning_rate": 9.241613255361455e-05,
"loss": 8.0091,
"step": 11
},
{
"epoch": 0.03236682400539447,
"grad_norm": 7.29517126083374,
"learning_rate": 9.070090031310558e-05,
"loss": 8.1914,
"step": 12
},
{
"epoch": 0.03506405933917734,
"grad_norm": 5.336075782775879,
"learning_rate": 8.883279133655399e-05,
"loss": 6.9499,
"step": 13
},
{
"epoch": 0.037761294672960216,
"grad_norm": 3.6411077976226807,
"learning_rate": 8.681980515339464e-05,
"loss": 4.5526,
"step": 14
},
{
"epoch": 0.04045853000674309,
"grad_norm": 3.4951727390289307,
"learning_rate": 8.467056167950311e-05,
"loss": 4.5282,
"step": 15
},
{
"epoch": 0.04315576534052596,
"grad_norm": 3.578062057495117,
"learning_rate": 8.239426430539243e-05,
"loss": 5.0323,
"step": 16
},
{
"epoch": 0.045853000674308836,
"grad_norm": 3.359455108642578,
"learning_rate": 8.000066048588211e-05,
"loss": 4.9812,
"step": 17
},
{
"epoch": 0.048550236008091704,
"grad_norm": 3.649996757507324,
"learning_rate": 7.75e-05,
"loss": 5.3966,
"step": 18
},
{
"epoch": 0.05124747134187458,
"grad_norm": 3.9379653930664062,
"learning_rate": 7.490299105985507e-05,
"loss": 6.0094,
"step": 19
},
{
"epoch": 0.05394470667565745,
"grad_norm": 4.793123245239258,
"learning_rate": 7.222075445642904e-05,
"loss": 5.5748,
"step": 20
},
{
"epoch": 0.056641942009440324,
"grad_norm": 4.157861709594727,
"learning_rate": 6.946477593864228e-05,
"loss": 6.3411,
"step": 21
},
{
"epoch": 0.05933917734322319,
"grad_norm": 4.551740646362305,
"learning_rate": 6.664685702961344e-05,
"loss": 6.277,
"step": 22
},
{
"epoch": 0.06203641267700607,
"grad_norm": 3.959686040878296,
"learning_rate": 6.377906449072578e-05,
"loss": 6.2384,
"step": 23
},
{
"epoch": 0.06473364801078894,
"grad_norm": 4.726752758026123,
"learning_rate": 6.087367864990233e-05,
"loss": 7.7302,
"step": 24
},
{
"epoch": 0.06743088334457181,
"grad_norm": 5.8925957679748535,
"learning_rate": 5.794314081535644e-05,
"loss": 8.6712,
"step": 25
},
{
"epoch": 0.06743088334457181,
"eval_loss": 0.3346240222454071,
"eval_runtime": 2.9577,
"eval_samples_per_second": 16.905,
"eval_steps_per_second": 4.395,
"step": 25
},
{
"epoch": 0.07012811867835468,
"grad_norm": 2.3370919227600098,
"learning_rate": 5.500000000000001e-05,
"loss": 3.5921,
"step": 26
},
{
"epoch": 0.07282535401213756,
"grad_norm": 3.2230148315429688,
"learning_rate": 5.205685918464356e-05,
"loss": 4.3536,
"step": 27
},
{
"epoch": 0.07552258934592043,
"grad_norm": 2.93990159034729,
"learning_rate": 4.912632135009769e-05,
"loss": 4.2959,
"step": 28
},
{
"epoch": 0.0782198246797033,
"grad_norm": 3.1565818786621094,
"learning_rate": 4.6220935509274235e-05,
"loss": 4.6705,
"step": 29
},
{
"epoch": 0.08091706001348618,
"grad_norm": 3.6498372554779053,
"learning_rate": 4.3353142970386564e-05,
"loss": 5.1664,
"step": 30
},
{
"epoch": 0.08361429534726905,
"grad_norm": 3.4346346855163574,
"learning_rate": 4.053522406135775e-05,
"loss": 5.2198,
"step": 31
},
{
"epoch": 0.08631153068105192,
"grad_norm": 3.956606149673462,
"learning_rate": 3.777924554357096e-05,
"loss": 5.5977,
"step": 32
},
{
"epoch": 0.08900876601483479,
"grad_norm": 3.851478099822998,
"learning_rate": 3.509700894014496e-05,
"loss": 5.6571,
"step": 33
},
{
"epoch": 0.09170600134861767,
"grad_norm": 4.546712875366211,
"learning_rate": 3.250000000000001e-05,
"loss": 6.7095,
"step": 34
},
{
"epoch": 0.09440323668240054,
"grad_norm": 3.8208866119384766,
"learning_rate": 2.9999339514117912e-05,
"loss": 5.8349,
"step": 35
},
{
"epoch": 0.09710047201618341,
"grad_norm": 4.768429279327393,
"learning_rate": 2.760573569460757e-05,
"loss": 7.5512,
"step": 36
},
{
"epoch": 0.09979770734996629,
"grad_norm": 5.413884162902832,
"learning_rate": 2.53294383204969e-05,
"loss": 7.3688,
"step": 37
},
{
"epoch": 0.10249494268374916,
"grad_norm": 4.375186443328857,
"learning_rate": 2.3180194846605367e-05,
"loss": 5.5095,
"step": 38
},
{
"epoch": 0.10519217801753203,
"grad_norm": 3.01485276222229,
"learning_rate": 2.1167208663446025e-05,
"loss": 4.156,
"step": 39
},
{
"epoch": 0.1078894133513149,
"grad_norm": 2.998155355453491,
"learning_rate": 1.9299099686894423e-05,
"loss": 4.4575,
"step": 40
},
{
"epoch": 0.11058664868509778,
"grad_norm": 3.271318197250366,
"learning_rate": 1.758386744638546e-05,
"loss": 4.4771,
"step": 41
},
{
"epoch": 0.11328388401888065,
"grad_norm": 3.5302789211273193,
"learning_rate": 1.602885682970026e-05,
"loss": 5.1778,
"step": 42
},
{
"epoch": 0.11598111935266352,
"grad_norm": 3.289346694946289,
"learning_rate": 1.464072663102903e-05,
"loss": 4.9498,
"step": 43
},
{
"epoch": 0.11867835468644639,
"grad_norm": 3.5944786071777344,
"learning_rate": 1.3425421036992098e-05,
"loss": 5.2595,
"step": 44
},
{
"epoch": 0.12137559002022927,
"grad_norm": 3.664254665374756,
"learning_rate": 1.2388144172720251e-05,
"loss": 5.761,
"step": 45
},
{
"epoch": 0.12407282535401214,
"grad_norm": 3.8446664810180664,
"learning_rate": 1.1533337816991932e-05,
"loss": 5.475,
"step": 46
},
{
"epoch": 0.126770060687795,
"grad_norm": 4.252958297729492,
"learning_rate": 1.0864662381854632e-05,
"loss": 6.1862,
"step": 47
},
{
"epoch": 0.1294672960215779,
"grad_norm": 4.536473751068115,
"learning_rate": 1.0384981238178534e-05,
"loss": 6.3884,
"step": 48
},
{
"epoch": 0.13216453135536074,
"grad_norm": 5.003567218780518,
"learning_rate": 1.0096348454262845e-05,
"loss": 6.9914,
"step": 49
},
{
"epoch": 0.13486176668914363,
"grad_norm": 6.126743316650391,
"learning_rate": 1e-05,
"loss": 9.3718,
"step": 50
},
{
"epoch": 0.13486176668914363,
"eval_loss": 0.31840619444847107,
"eval_runtime": 2.9606,
"eval_samples_per_second": 16.889,
"eval_steps_per_second": 4.391,
"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": 1,
"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": true
},
"attributes": {}
}
},
"total_flos": 5.259104775831552e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}