|
{ |
|
"best_metric": 0.4588634967803955, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-20", |
|
"epoch": 0.0005743206863132201, |
|
"eval_steps": 5, |
|
"global_step": 20, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 2.8716034315661008e-05, |
|
"eval_loss": 0.6288187503814697, |
|
"eval_runtime": 5168.7784, |
|
"eval_samples_per_second": 2.837, |
|
"eval_steps_per_second": 1.419, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 8.614810294698303e-05, |
|
"grad_norm": 9.317225456237793, |
|
"learning_rate": 6e-05, |
|
"loss": 2.2934, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.00014358017157830503, |
|
"eval_loss": 0.5219603180885315, |
|
"eval_runtime": 5189.2066, |
|
"eval_samples_per_second": 2.826, |
|
"eval_steps_per_second": 1.413, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.00017229620589396605, |
|
"grad_norm": 3.9321670532226562, |
|
"learning_rate": 9.96057350657239e-05, |
|
"loss": 2.075, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.00025844430884094905, |
|
"grad_norm": 1.7391698360443115, |
|
"learning_rate": 9.381533400219318e-05, |
|
"loss": 1.9136, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.00028716034315661007, |
|
"eval_loss": 0.4779989421367645, |
|
"eval_runtime": 5191.0811, |
|
"eval_samples_per_second": 2.825, |
|
"eval_steps_per_second": 1.412, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0003445924117879321, |
|
"grad_norm": 1.510844349861145, |
|
"learning_rate": 8.18711994874345e-05, |
|
"loss": 1.7541, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.0004307405147349151, |
|
"grad_norm": 2.169722080230713, |
|
"learning_rate": 6.545084971874738e-05, |
|
"loss": 1.9345, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.0004307405147349151, |
|
"eval_loss": 0.4659367501735687, |
|
"eval_runtime": 5186.2567, |
|
"eval_samples_per_second": 2.827, |
|
"eval_steps_per_second": 1.414, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.0005168886176818981, |
|
"grad_norm": 1.781753659248352, |
|
"learning_rate": 4.6860474023534335e-05, |
|
"loss": 2.0342, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.0005743206863132201, |
|
"eval_loss": 0.4588634967803955, |
|
"eval_runtime": 5182.4914, |
|
"eval_samples_per_second": 2.829, |
|
"eval_steps_per_second": 1.415, |
|
"step": 20 |
|
} |
|
], |
|
"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": 1.406258997362688e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|