vmpsergio's picture
Training in progress, step 10, checkpoint
ef8a289 verified
{
"best_metric": NaN,
"best_model_checkpoint": "miner_id_24/checkpoint-10",
"epoch": 0.11080332409972299,
"eval_steps": 5,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0110803324099723,
"eval_loss": NaN,
"eval_runtime": 4.4478,
"eval_samples_per_second": 8.544,
"eval_steps_per_second": 4.272,
"step": 1
},
{
"epoch": 0.0332409972299169,
"grad_norm": NaN,
"learning_rate": 6e-05,
"loss": 0.0,
"step": 3
},
{
"epoch": 0.055401662049861494,
"eval_loss": NaN,
"eval_runtime": 4.4357,
"eval_samples_per_second": 8.567,
"eval_steps_per_second": 4.283,
"step": 5
},
{
"epoch": 0.0664819944598338,
"grad_norm": NaN,
"learning_rate": 0.00012,
"loss": 0.0,
"step": 6
},
{
"epoch": 0.0997229916897507,
"grad_norm": NaN,
"learning_rate": 0.00018,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.11080332409972299,
"eval_loss": NaN,
"eval_runtime": 4.4445,
"eval_samples_per_second": 8.55,
"eval_steps_per_second": 4.275,
"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": 3296155203010560.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}