dada22231's picture
Training in progress, step 50, checkpoint
56d5807 verified
{
"best_metric": NaN,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 0.04469523437063523,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0008939046874127046,
"grad_norm": NaN,
"learning_rate": 5e-05,
"loss": 0.0,
"step": 1
},
{
"epoch": 0.0008939046874127046,
"eval_loss": NaN,
"eval_runtime": 3.5836,
"eval_samples_per_second": 13.953,
"eval_steps_per_second": 3.628,
"step": 1
},
{
"epoch": 0.0017878093748254092,
"grad_norm": NaN,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2
},
{
"epoch": 0.002681714062238114,
"grad_norm": NaN,
"learning_rate": 9.990365154573717e-05,
"loss": 0.0,
"step": 3
},
{
"epoch": 0.0035756187496508184,
"grad_norm": NaN,
"learning_rate": 9.961501876182148e-05,
"loss": 0.0,
"step": 4
},
{
"epoch": 0.004469523437063523,
"grad_norm": NaN,
"learning_rate": 9.913533761814537e-05,
"loss": 0.0,
"step": 5
},
{
"epoch": 0.005363428124476228,
"grad_norm": NaN,
"learning_rate": 9.846666218300807e-05,
"loss": 0.0,
"step": 6
},
{
"epoch": 0.006257332811888932,
"grad_norm": NaN,
"learning_rate": 9.761185582727977e-05,
"loss": 0.0,
"step": 7
},
{
"epoch": 0.007151237499301637,
"grad_norm": NaN,
"learning_rate": 9.657457896300791e-05,
"loss": 0.0,
"step": 8
},
{
"epoch": 0.008045142186714342,
"grad_norm": NaN,
"learning_rate": 9.535927336897098e-05,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.008939046874127046,
"grad_norm": NaN,
"learning_rate": 9.397114317029975e-05,
"loss": 0.0,
"step": 10
},
{
"epoch": 0.00983295156153975,
"grad_norm": NaN,
"learning_rate": 9.241613255361455e-05,
"loss": 0.0,
"step": 11
},
{
"epoch": 0.010726856248952456,
"grad_norm": NaN,
"learning_rate": 9.070090031310558e-05,
"loss": 0.0,
"step": 12
},
{
"epoch": 0.01162076093636516,
"grad_norm": NaN,
"learning_rate": 8.883279133655399e-05,
"loss": 0.0,
"step": 13
},
{
"epoch": 0.012514665623777864,
"grad_norm": NaN,
"learning_rate": 8.681980515339464e-05,
"loss": 0.0,
"step": 14
},
{
"epoch": 0.01340857031119057,
"grad_norm": NaN,
"learning_rate": 8.467056167950311e-05,
"loss": 0.0,
"step": 15
},
{
"epoch": 0.014302474998603274,
"grad_norm": NaN,
"learning_rate": 8.239426430539243e-05,
"loss": 0.0,
"step": 16
},
{
"epoch": 0.015196379686015978,
"grad_norm": NaN,
"learning_rate": 8.000066048588211e-05,
"loss": 0.0,
"step": 17
},
{
"epoch": 0.016090284373428684,
"grad_norm": NaN,
"learning_rate": 7.75e-05,
"loss": 0.0,
"step": 18
},
{
"epoch": 0.016984189060841388,
"grad_norm": NaN,
"learning_rate": 7.490299105985507e-05,
"loss": 0.0,
"step": 19
},
{
"epoch": 0.017878093748254092,
"grad_norm": NaN,
"learning_rate": 7.222075445642904e-05,
"loss": 0.0,
"step": 20
},
{
"epoch": 0.018771998435666796,
"grad_norm": NaN,
"learning_rate": 6.946477593864228e-05,
"loss": 0.0,
"step": 21
},
{
"epoch": 0.0196659031230795,
"grad_norm": NaN,
"learning_rate": 6.664685702961344e-05,
"loss": 0.0,
"step": 22
},
{
"epoch": 0.020559807810492207,
"grad_norm": NaN,
"learning_rate": 6.377906449072578e-05,
"loss": 0.0,
"step": 23
},
{
"epoch": 0.02145371249790491,
"grad_norm": NaN,
"learning_rate": 6.087367864990233e-05,
"loss": 0.0,
"step": 24
},
{
"epoch": 0.022347617185317616,
"grad_norm": NaN,
"learning_rate": 5.794314081535644e-05,
"loss": 0.0,
"step": 25
},
{
"epoch": 0.022347617185317616,
"eval_loss": NaN,
"eval_runtime": 3.1856,
"eval_samples_per_second": 15.696,
"eval_steps_per_second": 4.081,
"step": 25
},
{
"epoch": 0.02324152187273032,
"grad_norm": NaN,
"learning_rate": 5.500000000000001e-05,
"loss": 0.0,
"step": 26
},
{
"epoch": 0.024135426560143024,
"grad_norm": NaN,
"learning_rate": 5.205685918464356e-05,
"loss": 0.0,
"step": 27
},
{
"epoch": 0.025029331247555728,
"grad_norm": NaN,
"learning_rate": 4.912632135009769e-05,
"loss": 0.0,
"step": 28
},
{
"epoch": 0.025923235934968435,
"grad_norm": NaN,
"learning_rate": 4.6220935509274235e-05,
"loss": 0.0,
"step": 29
},
{
"epoch": 0.02681714062238114,
"grad_norm": NaN,
"learning_rate": 4.3353142970386564e-05,
"loss": 0.0,
"step": 30
},
{
"epoch": 0.027711045309793843,
"grad_norm": NaN,
"learning_rate": 4.053522406135775e-05,
"loss": 0.0,
"step": 31
},
{
"epoch": 0.028604949997206548,
"grad_norm": NaN,
"learning_rate": 3.777924554357096e-05,
"loss": 0.0,
"step": 32
},
{
"epoch": 0.02949885468461925,
"grad_norm": NaN,
"learning_rate": 3.509700894014496e-05,
"loss": 0.0,
"step": 33
},
{
"epoch": 0.030392759372031956,
"grad_norm": NaN,
"learning_rate": 3.250000000000001e-05,
"loss": 0.0,
"step": 34
},
{
"epoch": 0.03128666405944466,
"grad_norm": NaN,
"learning_rate": 2.9999339514117912e-05,
"loss": 0.0,
"step": 35
},
{
"epoch": 0.03218056874685737,
"grad_norm": NaN,
"learning_rate": 2.760573569460757e-05,
"loss": 0.0,
"step": 36
},
{
"epoch": 0.03307447343427007,
"grad_norm": NaN,
"learning_rate": 2.53294383204969e-05,
"loss": 0.0,
"step": 37
},
{
"epoch": 0.033968378121682775,
"grad_norm": NaN,
"learning_rate": 2.3180194846605367e-05,
"loss": 0.0,
"step": 38
},
{
"epoch": 0.03486228280909548,
"grad_norm": NaN,
"learning_rate": 2.1167208663446025e-05,
"loss": 0.0,
"step": 39
},
{
"epoch": 0.035756187496508184,
"grad_norm": NaN,
"learning_rate": 1.9299099686894423e-05,
"loss": 0.0,
"step": 40
},
{
"epoch": 0.03665009218392089,
"grad_norm": NaN,
"learning_rate": 1.758386744638546e-05,
"loss": 0.0,
"step": 41
},
{
"epoch": 0.03754399687133359,
"grad_norm": NaN,
"learning_rate": 1.602885682970026e-05,
"loss": 0.0,
"step": 42
},
{
"epoch": 0.038437901558746296,
"grad_norm": NaN,
"learning_rate": 1.464072663102903e-05,
"loss": 0.0,
"step": 43
},
{
"epoch": 0.039331806246159,
"grad_norm": NaN,
"learning_rate": 1.3425421036992098e-05,
"loss": 0.0,
"step": 44
},
{
"epoch": 0.04022571093357171,
"grad_norm": NaN,
"learning_rate": 1.2388144172720251e-05,
"loss": 0.0,
"step": 45
},
{
"epoch": 0.041119615620984415,
"grad_norm": NaN,
"learning_rate": 1.1533337816991932e-05,
"loss": 0.0,
"step": 46
},
{
"epoch": 0.04201352030839712,
"grad_norm": NaN,
"learning_rate": 1.0864662381854632e-05,
"loss": 0.0,
"step": 47
},
{
"epoch": 0.04290742499580982,
"grad_norm": NaN,
"learning_rate": 1.0384981238178534e-05,
"loss": 0.0,
"step": 48
},
{
"epoch": 0.04380132968322253,
"grad_norm": NaN,
"learning_rate": 1.0096348454262845e-05,
"loss": 0.0,
"step": 49
},
{
"epoch": 0.04469523437063523,
"grad_norm": NaN,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 50
},
{
"epoch": 0.04469523437063523,
"eval_loss": NaN,
"eval_runtime": 3.1838,
"eval_samples_per_second": 15.705,
"eval_steps_per_second": 4.083,
"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": 1
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.658024559509504e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}