|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 5625, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.08888888888888889, |
|
"grad_norm": 3.5679705142974854, |
|
"learning_rate": 1.8222222222222224e-05, |
|
"loss": 0.0271, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.17777777777777778, |
|
"grad_norm": 5.5012736320495605, |
|
"learning_rate": 1.6444444444444444e-05, |
|
"loss": 0.0087, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.26666666666666666, |
|
"grad_norm": 0.0017927660373970866, |
|
"learning_rate": 1.4666666666666666e-05, |
|
"loss": 0.0071, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.35555555555555557, |
|
"grad_norm": 0.0005662949988618493, |
|
"learning_rate": 1.288888888888889e-05, |
|
"loss": 0.004, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.4444444444444444, |
|
"grad_norm": 0.02133863791823387, |
|
"learning_rate": 1.1111111111111113e-05, |
|
"loss": 0.0069, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.5333333333333333, |
|
"grad_norm": 0.002344718435779214, |
|
"learning_rate": 9.333333333333334e-06, |
|
"loss": 0.0052, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.6222222222222222, |
|
"grad_norm": 0.01142363715916872, |
|
"learning_rate": 7.555555555555556e-06, |
|
"loss": 0.0063, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.7111111111111111, |
|
"grad_norm": 0.0029647352639585733, |
|
"learning_rate": 5.777777777777778e-06, |
|
"loss": 0.0042, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"grad_norm": 0.02137506566941738, |
|
"learning_rate": 4.000000000000001e-06, |
|
"loss": 0.0047, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.8888888888888888, |
|
"grad_norm": 0.00205501657910645, |
|
"learning_rate": 2.222222222222222e-06, |
|
"loss": 0.0027, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.9777777777777777, |
|
"grad_norm": 0.0009133058483712375, |
|
"learning_rate": 4.444444444444445e-07, |
|
"loss": 0.0027, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 5625, |
|
"total_flos": 4.717499098595328e+16, |
|
"train_loss": 0.007075616494731771, |
|
"train_runtime": 10260.1497, |
|
"train_samples_per_second": 17.544, |
|
"train_steps_per_second": 0.548 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 5625, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4.717499098595328e+16, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|