|
{ |
|
"best_metric": 11.5, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-10", |
|
"epoch": 0.0005055931239335145, |
|
"eval_steps": 5, |
|
"global_step": 10, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 5.055931239335145e-05, |
|
"eval_loss": 11.5, |
|
"eval_runtime": 123.3089, |
|
"eval_samples_per_second": 67.538, |
|
"eval_steps_per_second": 33.769, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00015167793718005436, |
|
"grad_norm": 2.6830673959921114e-05, |
|
"learning_rate": 3e-05, |
|
"loss": 46.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.00025279656196675726, |
|
"eval_loss": 11.5, |
|
"eval_runtime": 123.8714, |
|
"eval_samples_per_second": 67.231, |
|
"eval_steps_per_second": 33.616, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.00030335587436010873, |
|
"grad_norm": 2.4176186343538575e-05, |
|
"learning_rate": 6e-05, |
|
"loss": 46.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.00045503381154016307, |
|
"grad_norm": 1.4083571841183584e-05, |
|
"learning_rate": 9e-05, |
|
"loss": 46.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.0005055931239335145, |
|
"eval_loss": 11.5, |
|
"eval_runtime": 123.7977, |
|
"eval_samples_per_second": 67.271, |
|
"eval_steps_per_second": 33.636, |
|
"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": 558545240064.0, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|