vmpsergio's picture
Training in progress, step 10, checkpoint
b393df4 verified
{
"best_metric": NaN,
"best_model_checkpoint": "miner_id_24/checkpoint-10",
"epoch": 0.002863278453829635,
"eval_steps": 5,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0002863278453829635,
"eval_loss": NaN,
"eval_runtime": 164.351,
"eval_samples_per_second": 8.95,
"eval_steps_per_second": 4.478,
"step": 1
},
{
"epoch": 0.0008589835361488905,
"grad_norm": NaN,
"learning_rate": 6e-05,
"loss": 0.0,
"step": 3
},
{
"epoch": 0.0014316392269148174,
"eval_loss": NaN,
"eval_runtime": 164.7094,
"eval_samples_per_second": 8.931,
"eval_steps_per_second": 4.468,
"step": 5
},
{
"epoch": 0.001717967072297781,
"grad_norm": NaN,
"learning_rate": 0.00012,
"loss": 0.0,
"step": 6
},
{
"epoch": 0.0025769506084466712,
"grad_norm": NaN,
"learning_rate": 0.00018,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.002863278453829635,
"eval_loss": NaN,
"eval_runtime": 164.8243,
"eval_samples_per_second": 8.925,
"eval_steps_per_second": 4.465,
"step": 10
}
],
"logging_steps": 3,
"max_steps": 30,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 10,
"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": false
},
"attributes": {}
}
},
"total_flos": 3267323221770240.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}