dsakerkwq's picture
Training in progress, step 50, checkpoint
95f8e89 verified
{
"best_metric": NaN,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 1.3766122098022355,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.027515047291487533,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 0.0,
"step": 1
},
{
"epoch": 0.027515047291487533,
"eval_loss": NaN,
"eval_runtime": 2.9757,
"eval_samples_per_second": 16.803,
"eval_steps_per_second": 4.369,
"step": 1
},
{
"epoch": 0.055030094582975066,
"grad_norm": NaN,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2
},
{
"epoch": 0.0825451418744626,
"grad_norm": NaN,
"learning_rate": 9.990365154573717e-05,
"loss": 0.0,
"step": 3
},
{
"epoch": 0.11006018916595013,
"grad_norm": NaN,
"learning_rate": 9.961501876182148e-05,
"loss": 0.0,
"step": 4
},
{
"epoch": 0.13757523645743766,
"grad_norm": NaN,
"learning_rate": 9.913533761814537e-05,
"loss": 0.0,
"step": 5
},
{
"epoch": 0.1650902837489252,
"grad_norm": NaN,
"learning_rate": 9.846666218300807e-05,
"loss": 0.0,
"step": 6
},
{
"epoch": 0.19260533104041272,
"grad_norm": NaN,
"learning_rate": 9.761185582727977e-05,
"loss": 0.0,
"step": 7
},
{
"epoch": 0.22012037833190026,
"grad_norm": NaN,
"learning_rate": 9.657457896300791e-05,
"loss": 0.0,
"step": 8
},
{
"epoch": 0.24763542562338778,
"grad_norm": NaN,
"learning_rate": 9.535927336897098e-05,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.2751504729148753,
"grad_norm": NaN,
"learning_rate": 9.397114317029975e-05,
"loss": 0.0,
"step": 10
},
{
"epoch": 0.30266552020636284,
"grad_norm": NaN,
"learning_rate": 9.241613255361455e-05,
"loss": 0.0,
"step": 11
},
{
"epoch": 0.3301805674978504,
"grad_norm": NaN,
"learning_rate": 9.070090031310558e-05,
"loss": 0.0,
"step": 12
},
{
"epoch": 0.3576956147893379,
"grad_norm": NaN,
"learning_rate": 8.883279133655399e-05,
"loss": 0.0,
"step": 13
},
{
"epoch": 0.38521066208082544,
"grad_norm": NaN,
"learning_rate": 8.681980515339464e-05,
"loss": 0.0,
"step": 14
},
{
"epoch": 0.412725709372313,
"grad_norm": NaN,
"learning_rate": 8.467056167950311e-05,
"loss": 0.0,
"step": 15
},
{
"epoch": 0.4402407566638005,
"grad_norm": NaN,
"learning_rate": 8.239426430539243e-05,
"loss": 0.0,
"step": 16
},
{
"epoch": 0.46775580395528804,
"grad_norm": NaN,
"learning_rate": 8.000066048588211e-05,
"loss": 0.0,
"step": 17
},
{
"epoch": 0.49527085124677556,
"grad_norm": NaN,
"learning_rate": 7.75e-05,
"loss": 0.0,
"step": 18
},
{
"epoch": 0.5227858985382631,
"grad_norm": NaN,
"learning_rate": 7.490299105985507e-05,
"loss": 0.0,
"step": 19
},
{
"epoch": 0.5503009458297506,
"grad_norm": NaN,
"learning_rate": 7.222075445642904e-05,
"loss": 0.0,
"step": 20
},
{
"epoch": 0.5778159931212382,
"grad_norm": NaN,
"learning_rate": 6.946477593864228e-05,
"loss": 0.0,
"step": 21
},
{
"epoch": 0.6053310404127257,
"grad_norm": NaN,
"learning_rate": 6.664685702961344e-05,
"loss": 0.0,
"step": 22
},
{
"epoch": 0.6328460877042132,
"grad_norm": NaN,
"learning_rate": 6.377906449072578e-05,
"loss": 0.0,
"step": 23
},
{
"epoch": 0.6603611349957008,
"grad_norm": NaN,
"learning_rate": 6.087367864990233e-05,
"loss": 0.0,
"step": 24
},
{
"epoch": 0.6878761822871883,
"grad_norm": NaN,
"learning_rate": 5.794314081535644e-05,
"loss": 0.0,
"step": 25
},
{
"epoch": 0.6878761822871883,
"eval_loss": NaN,
"eval_runtime": 2.9787,
"eval_samples_per_second": 16.786,
"eval_steps_per_second": 4.364,
"step": 25
},
{
"epoch": 0.7153912295786758,
"grad_norm": NaN,
"learning_rate": 5.500000000000001e-05,
"loss": 0.0,
"step": 26
},
{
"epoch": 0.7429062768701634,
"grad_norm": NaN,
"learning_rate": 5.205685918464356e-05,
"loss": 0.0,
"step": 27
},
{
"epoch": 0.7704213241616509,
"grad_norm": NaN,
"learning_rate": 4.912632135009769e-05,
"loss": 0.0,
"step": 28
},
{
"epoch": 0.7979363714531384,
"grad_norm": NaN,
"learning_rate": 4.6220935509274235e-05,
"loss": 0.0,
"step": 29
},
{
"epoch": 0.825451418744626,
"grad_norm": NaN,
"learning_rate": 4.3353142970386564e-05,
"loss": 0.0,
"step": 30
},
{
"epoch": 0.8529664660361135,
"grad_norm": NaN,
"learning_rate": 4.053522406135775e-05,
"loss": 0.0,
"step": 31
},
{
"epoch": 0.880481513327601,
"grad_norm": NaN,
"learning_rate": 3.777924554357096e-05,
"loss": 0.0,
"step": 32
},
{
"epoch": 0.9079965606190885,
"grad_norm": NaN,
"learning_rate": 3.509700894014496e-05,
"loss": 0.0,
"step": 33
},
{
"epoch": 0.9355116079105761,
"grad_norm": NaN,
"learning_rate": 3.250000000000001e-05,
"loss": 0.0,
"step": 34
},
{
"epoch": 0.9630266552020637,
"grad_norm": NaN,
"learning_rate": 2.9999339514117912e-05,
"loss": 0.0,
"step": 35
},
{
"epoch": 0.9905417024935511,
"grad_norm": NaN,
"learning_rate": 2.760573569460757e-05,
"loss": 0.0,
"step": 36
},
{
"epoch": 1.0189165950128978,
"grad_norm": NaN,
"learning_rate": 2.53294383204969e-05,
"loss": 0.0,
"step": 37
},
{
"epoch": 1.0464316423043851,
"grad_norm": NaN,
"learning_rate": 2.3180194846605367e-05,
"loss": 0.0,
"step": 38
},
{
"epoch": 1.0739466895958727,
"grad_norm": NaN,
"learning_rate": 2.1167208663446025e-05,
"loss": 0.0,
"step": 39
},
{
"epoch": 1.1014617368873603,
"grad_norm": NaN,
"learning_rate": 1.9299099686894423e-05,
"loss": 0.0,
"step": 40
},
{
"epoch": 1.1289767841788478,
"grad_norm": NaN,
"learning_rate": 1.758386744638546e-05,
"loss": 0.0,
"step": 41
},
{
"epoch": 1.1564918314703354,
"grad_norm": NaN,
"learning_rate": 1.602885682970026e-05,
"loss": 0.0,
"step": 42
},
{
"epoch": 1.184006878761823,
"grad_norm": NaN,
"learning_rate": 1.464072663102903e-05,
"loss": 0.0,
"step": 43
},
{
"epoch": 1.2115219260533103,
"grad_norm": NaN,
"learning_rate": 1.3425421036992098e-05,
"loss": 0.0,
"step": 44
},
{
"epoch": 1.239036973344798,
"grad_norm": NaN,
"learning_rate": 1.2388144172720251e-05,
"loss": 0.0,
"step": 45
},
{
"epoch": 1.2665520206362855,
"grad_norm": NaN,
"learning_rate": 1.1533337816991932e-05,
"loss": 0.0,
"step": 46
},
{
"epoch": 1.294067067927773,
"grad_norm": NaN,
"learning_rate": 1.0864662381854632e-05,
"loss": 0.0,
"step": 47
},
{
"epoch": 1.3215821152192606,
"grad_norm": NaN,
"learning_rate": 1.0384981238178534e-05,
"loss": 0.0,
"step": 48
},
{
"epoch": 1.349097162510748,
"grad_norm": NaN,
"learning_rate": 1.0096348454262845e-05,
"loss": 0.0,
"step": 49
},
{
"epoch": 1.3766122098022355,
"grad_norm": NaN,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 50
},
{
"epoch": 1.3766122098022355,
"eval_loss": NaN,
"eval_runtime": 3.0072,
"eval_samples_per_second": 16.627,
"eval_steps_per_second": 4.323,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 25,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"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": 5.658021338284032e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}