bbytxt's picture
Training in progress, step 15, checkpoint
5cb9539 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.3157894736842106,
"eval_steps": 50,
"global_step": 15,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.21052631578947367,
"grad_norm": 41.065494537353516,
"learning_rate": 3.3333333333333333e-06,
"loss": 7.6156,
"step": 1
},
{
"epoch": 0.21052631578947367,
"eval_loss": 7.460348129272461,
"eval_runtime": 0.3018,
"eval_samples_per_second": 26.509,
"eval_steps_per_second": 13.254,
"step": 1
},
{
"epoch": 0.42105263157894735,
"grad_norm": 45.48214340209961,
"learning_rate": 6.666666666666667e-06,
"loss": 7.4887,
"step": 2
},
{
"epoch": 0.631578947368421,
"grad_norm": 39.209571838378906,
"learning_rate": 1e-05,
"loss": 7.4095,
"step": 3
},
{
"epoch": 0.8421052631578947,
"grad_norm": 36.979095458984375,
"learning_rate": 1.3333333333333333e-05,
"loss": 7.3312,
"step": 4
},
{
"epoch": 1.1052631578947367,
"grad_norm": 54.07901382446289,
"learning_rate": 1.6666666666666667e-05,
"loss": 9.962,
"step": 5
},
{
"epoch": 1.3157894736842106,
"grad_norm": 44.620147705078125,
"learning_rate": 2e-05,
"loss": 6.0482,
"step": 6
},
{
"epoch": 1.526315789473684,
"grad_norm": 40.011993408203125,
"learning_rate": 2.3333333333333336e-05,
"loss": 5.3659,
"step": 7
},
{
"epoch": 1.736842105263158,
"grad_norm": 28.986406326293945,
"learning_rate": 2.6666666666666667e-05,
"loss": 3.4974,
"step": 8
},
{
"epoch": 1.9473684210526314,
"grad_norm": 30.311237335205078,
"learning_rate": 3e-05,
"loss": 3.4766,
"step": 9
},
{
"epoch": 2.2105263157894735,
"grad_norm": 12.783985137939453,
"learning_rate": 3.3333333333333335e-05,
"loss": 1.3461,
"step": 10
},
{
"epoch": 2.4210526315789473,
"grad_norm": 8.035650253295898,
"learning_rate": 3.6666666666666666e-05,
"loss": 1.1558,
"step": 11
},
{
"epoch": 2.6315789473684212,
"grad_norm": 7.6682515144348145,
"learning_rate": 4e-05,
"loss": 1.0517,
"step": 12
},
{
"epoch": 2.8421052631578947,
"grad_norm": 4.046804428100586,
"learning_rate": 4.3333333333333334e-05,
"loss": 0.7306,
"step": 13
},
{
"epoch": 3.1052631578947367,
"grad_norm": 7.9675374031066895,
"learning_rate": 4.666666666666667e-05,
"loss": 1.111,
"step": 14
},
{
"epoch": 3.3157894736842106,
"grad_norm": 3.6621782779693604,
"learning_rate": 5e-05,
"loss": 0.6098,
"step": 15
}
],
"logging_steps": 1,
"max_steps": 15,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"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": true
},
"attributes": {}
}
},
"total_flos": 4082170960281600.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}