|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 8.0, |
|
"eval_steps": 500, |
|
"global_step": 2544, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.0064516129032258064, |
|
"eval_loss": NaN, |
|
"eval_runtime": 5.354, |
|
"eval_samples_per_second": 579.009, |
|
"eval_steps_per_second": 12.141, |
|
"step": 318 |
|
}, |
|
{ |
|
"epoch": 1.5723270440251573, |
|
"grad_norm": 143768.90625, |
|
"learning_rate": 1.606918238993711e-05, |
|
"loss": 0.0, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.0064516129032258064, |
|
"eval_loss": NaN, |
|
"eval_runtime": 5.464, |
|
"eval_samples_per_second": 567.352, |
|
"eval_steps_per_second": 11.896, |
|
"step": 636 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.0064516129032258064, |
|
"eval_loss": NaN, |
|
"eval_runtime": 5.2458, |
|
"eval_samples_per_second": 590.953, |
|
"eval_steps_per_second": 12.391, |
|
"step": 954 |
|
}, |
|
{ |
|
"epoch": 3.1446540880503147, |
|
"grad_norm": 371973.03125, |
|
"learning_rate": 1.2138364779874214e-05, |
|
"loss": 0.0, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.0064516129032258064, |
|
"eval_loss": NaN, |
|
"eval_runtime": 7.0035, |
|
"eval_samples_per_second": 442.637, |
|
"eval_steps_per_second": 9.281, |
|
"step": 1272 |
|
}, |
|
{ |
|
"epoch": 4.716981132075472, |
|
"grad_norm": 805448.3125, |
|
"learning_rate": 8.207547169811321e-06, |
|
"loss": 0.0, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_accuracy": 0.0064516129032258064, |
|
"eval_loss": NaN, |
|
"eval_runtime": 5.3907, |
|
"eval_samples_per_second": 575.063, |
|
"eval_steps_per_second": 12.058, |
|
"step": 1590 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_accuracy": 0.0064516129032258064, |
|
"eval_loss": NaN, |
|
"eval_runtime": 5.6586, |
|
"eval_samples_per_second": 547.834, |
|
"eval_steps_per_second": 11.487, |
|
"step": 1908 |
|
}, |
|
{ |
|
"epoch": 6.289308176100629, |
|
"grad_norm": 1256073.75, |
|
"learning_rate": 4.276729559748428e-06, |
|
"loss": 0.0, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_accuracy": 0.0064516129032258064, |
|
"eval_loss": NaN, |
|
"eval_runtime": 5.3686, |
|
"eval_samples_per_second": 577.428, |
|
"eval_steps_per_second": 12.107, |
|
"step": 2226 |
|
}, |
|
{ |
|
"epoch": 7.861635220125786, |
|
"grad_norm": 1489450.375, |
|
"learning_rate": 3.459119496855346e-07, |
|
"loss": 0.0, |
|
"step": 2500 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 2544, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 8, |
|
"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": 651155886807636.0, |
|
"train_batch_size": 48, |
|
"trial_name": null, |
|
"trial_params": { |
|
"alpha": 0.41600283894248313, |
|
"num_train_epochs": 8, |
|
"temperature": 20 |
|
} |
|
} |
|
|