joboffer's picture
Training in progress, step 10, checkpoint
687ce06 verified
raw
history blame
2.04 kB
{
"best_metric": NaN,
"best_model_checkpoint": "miner_id_24/checkpoint-10",
"epoch": 0.004299226139294927,
"eval_steps": 5,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0004299226139294927,
"eval_loss": NaN,
"eval_runtime": 49.8015,
"eval_samples_per_second": 19.678,
"eval_steps_per_second": 9.839,
"step": 1
},
{
"epoch": 0.0012897678417884782,
"grad_norm": NaN,
"learning_rate": 6e-05,
"loss": 0.0,
"step": 3
},
{
"epoch": 0.0021496130696474634,
"eval_loss": NaN,
"eval_runtime": 48.6137,
"eval_samples_per_second": 20.159,
"eval_steps_per_second": 10.079,
"step": 5
},
{
"epoch": 0.0025795356835769563,
"grad_norm": NaN,
"learning_rate": 9.96057350657239e-05,
"loss": 0.0,
"step": 6
},
{
"epoch": 0.003869303525365434,
"grad_norm": NaN,
"learning_rate": 9.381533400219318e-05,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.004299226139294927,
"eval_loss": NaN,
"eval_runtime": 48.586,
"eval_samples_per_second": 20.17,
"eval_steps_per_second": 10.085,
"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": 317835234508800.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}