|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.1776790671848973, |
|
"eval_steps": 5, |
|
"global_step": 10, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.01776790671848973, |
|
"grad_norm": 0.7180286049842834, |
|
"learning_rate": 1e-05, |
|
"loss": 1.4249, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.01776790671848973, |
|
"eval_loss": 1.6323758363723755, |
|
"eval_runtime": 21.0365, |
|
"eval_samples_per_second": 4.516, |
|
"eval_steps_per_second": 4.516, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.03553581343697946, |
|
"grad_norm": 0.6932613253593445, |
|
"learning_rate": 2e-05, |
|
"loss": 1.4069, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.053303720155469185, |
|
"grad_norm": 0.74753737449646, |
|
"learning_rate": 3e-05, |
|
"loss": 1.5016, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.07107162687395892, |
|
"grad_norm": 0.7213916182518005, |
|
"learning_rate": 4e-05, |
|
"loss": 1.5036, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.08883953359244864, |
|
"grad_norm": 0.7217085361480713, |
|
"learning_rate": 5e-05, |
|
"loss": 1.4668, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.08883953359244864, |
|
"eval_loss": 1.5765870809555054, |
|
"eval_runtime": 21.0021, |
|
"eval_samples_per_second": 4.523, |
|
"eval_steps_per_second": 4.523, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.10660744031093837, |
|
"grad_norm": 0.7016662359237671, |
|
"learning_rate": 6e-05, |
|
"loss": 1.3162, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.1243753470294281, |
|
"grad_norm": 0.8236738443374634, |
|
"learning_rate": 7e-05, |
|
"loss": 1.4023, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.14214325374791784, |
|
"grad_norm": 0.9258612394332886, |
|
"learning_rate": 8e-05, |
|
"loss": 1.365, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.15991116046640755, |
|
"grad_norm": 0.9246096014976501, |
|
"learning_rate": 9e-05, |
|
"loss": 1.3684, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.1776790671848973, |
|
"grad_norm": 0.8942782282829285, |
|
"learning_rate": 0.0001, |
|
"loss": 1.0782, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.1776790671848973, |
|
"eval_loss": 1.2890679836273193, |
|
"eval_runtime": 21.0233, |
|
"eval_samples_per_second": 4.519, |
|
"eval_steps_per_second": 4.519, |
|
"step": 10 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 10, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 3, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2782892182732800.0, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|