|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.02586652871184687, |
|
"eval_steps": 9, |
|
"global_step": 25, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0010346611484738748, |
|
"grad_norm": NaN, |
|
"learning_rate": 1e-05, |
|
"loss": 0.0, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0010346611484738748, |
|
"eval_loss": NaN, |
|
"eval_runtime": 81.2644, |
|
"eval_samples_per_second": 10.017, |
|
"eval_steps_per_second": 1.255, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0020693222969477496, |
|
"grad_norm": NaN, |
|
"learning_rate": 2e-05, |
|
"loss": 0.0, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0031039834454216243, |
|
"grad_norm": NaN, |
|
"learning_rate": 3e-05, |
|
"loss": 0.0, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.004138644593895499, |
|
"grad_norm": NaN, |
|
"learning_rate": 4e-05, |
|
"loss": 0.0, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.005173305742369374, |
|
"grad_norm": NaN, |
|
"learning_rate": 5e-05, |
|
"loss": 0.0, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.006207966890843249, |
|
"grad_norm": NaN, |
|
"learning_rate": 6e-05, |
|
"loss": 0.0, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.007242628039317123, |
|
"grad_norm": NaN, |
|
"learning_rate": 7e-05, |
|
"loss": 0.0, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.008277289187790998, |
|
"grad_norm": NaN, |
|
"learning_rate": 8e-05, |
|
"loss": 0.0, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.009311950336264873, |
|
"grad_norm": NaN, |
|
"learning_rate": 9e-05, |
|
"loss": 0.0, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.009311950336264873, |
|
"eval_loss": NaN, |
|
"eval_runtime": 80.7642, |
|
"eval_samples_per_second": 10.079, |
|
"eval_steps_per_second": 1.263, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.010346611484738748, |
|
"grad_norm": NaN, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.011381272633212623, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.99695413509548e-05, |
|
"loss": 0.0, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.012415933781686497, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.987820251299122e-05, |
|
"loss": 0.0, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.013450594930160372, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.972609476841367e-05, |
|
"loss": 0.0, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.014485256078634247, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.951340343707852e-05, |
|
"loss": 0.0, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.015519917227108122, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.924038765061042e-05, |
|
"loss": 0.0, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.016554578375581996, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.890738003669029e-05, |
|
"loss": 0.0, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.01758923952405587, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.851478631379982e-05, |
|
"loss": 0.0, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.018623900672529746, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.806308479691595e-05, |
|
"loss": 0.0, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.018623900672529746, |
|
"eval_loss": NaN, |
|
"eval_runtime": 80.7549, |
|
"eval_samples_per_second": 10.08, |
|
"eval_steps_per_second": 1.263, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.01965856182100362, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.755282581475769e-05, |
|
"loss": 0.0, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.020693222969477496, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.698463103929542e-05, |
|
"loss": 0.0, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.02172788411795137, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.635919272833938e-05, |
|
"loss": 0.0, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.022762545266425245, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.567727288213005e-05, |
|
"loss": 0.0, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.02379720641489912, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.493970231495835e-05, |
|
"loss": 0.0, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.024831867563372995, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.414737964294636e-05, |
|
"loss": 0.0, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.02586652871184687, |
|
"grad_norm": NaN, |
|
"learning_rate": 9.330127018922194e-05, |
|
"loss": 0.0, |
|
"step": 25 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 100, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 25, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.63366161088512e+16, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|