|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.23837902264600716, |
|
"eval_steps": 25, |
|
"global_step": 25, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.009535160905840286, |
|
"grad_norm": 22.616830825805664, |
|
"learning_rate": 3.3333333333333335e-05, |
|
"loss": 10.7012, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.009535160905840286, |
|
"eval_loss": 9.564970016479492, |
|
"eval_runtime": 54.4321, |
|
"eval_samples_per_second": 1.635, |
|
"eval_steps_per_second": 0.827, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.01907032181168057, |
|
"grad_norm": 20.275375366210938, |
|
"learning_rate": 6.666666666666667e-05, |
|
"loss": 9.9498, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.028605482717520857, |
|
"grad_norm": 23.843503952026367, |
|
"learning_rate": 0.0001, |
|
"loss": 9.8482, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.03814064362336114, |
|
"grad_norm": 17.373727798461914, |
|
"learning_rate": 9.99524110790929e-05, |
|
"loss": 6.8627, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.04767580452920143, |
|
"grad_norm": 16.935632705688477, |
|
"learning_rate": 9.980973490458728e-05, |
|
"loss": 5.3765, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.057210965435041714, |
|
"grad_norm": 25.84366226196289, |
|
"learning_rate": 9.957224306869053e-05, |
|
"loss": 6.6007, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.066746126340882, |
|
"grad_norm": 39.4841423034668, |
|
"learning_rate": 9.924038765061042e-05, |
|
"loss": 6.0231, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.07628128724672228, |
|
"grad_norm": 24.768882751464844, |
|
"learning_rate": 9.881480035599667e-05, |
|
"loss": 2.7102, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.08581644815256258, |
|
"grad_norm": 29.693031311035156, |
|
"learning_rate": 9.829629131445342e-05, |
|
"loss": 1.6618, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.09535160905840286, |
|
"grad_norm": 14.000877380371094, |
|
"learning_rate": 9.768584753741134e-05, |
|
"loss": 0.9057, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.10488676996424315, |
|
"grad_norm": 5.596749305725098, |
|
"learning_rate": 9.698463103929542e-05, |
|
"loss": 0.3843, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.11442193087008343, |
|
"grad_norm": 4.840229511260986, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 0.4124, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.12395709177592372, |
|
"grad_norm": 3.7698850631713867, |
|
"learning_rate": 9.53153893518325e-05, |
|
"loss": 0.3085, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.133492252681764, |
|
"grad_norm": 1.7670843601226807, |
|
"learning_rate": 9.435054165891109e-05, |
|
"loss": 0.2888, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.1430274135876043, |
|
"grad_norm": 0.5820183753967285, |
|
"learning_rate": 9.330127018922194e-05, |
|
"loss": 0.2256, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.15256257449344457, |
|
"grad_norm": 3.2924885749816895, |
|
"learning_rate": 9.21695722906443e-05, |
|
"loss": 0.4244, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.16209773539928488, |
|
"grad_norm": 1.984984278678894, |
|
"learning_rate": 9.09576022144496e-05, |
|
"loss": 0.3216, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.17163289630512515, |
|
"grad_norm": 1.1172698736190796, |
|
"learning_rate": 8.966766701456177e-05, |
|
"loss": 0.3188, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.18116805721096543, |
|
"grad_norm": 1.5274360179901123, |
|
"learning_rate": 8.83022221559489e-05, |
|
"loss": 0.3054, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.1907032181168057, |
|
"grad_norm": 1.9571841955184937, |
|
"learning_rate": 8.68638668405062e-05, |
|
"loss": 0.3021, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.20023837902264602, |
|
"grad_norm": 1.2252756357192993, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 0.2382, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.2097735399284863, |
|
"grad_norm": 1.0066477060317993, |
|
"learning_rate": 8.377951038078302e-05, |
|
"loss": 0.3221, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.21930870083432658, |
|
"grad_norm": 0.6950803995132446, |
|
"learning_rate": 8.213938048432697e-05, |
|
"loss": 0.2824, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.22884386174016685, |
|
"grad_norm": 1.1107197999954224, |
|
"learning_rate": 8.043807145043604e-05, |
|
"loss": 0.361, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.23837902264600716, |
|
"grad_norm": 0.676360547542572, |
|
"learning_rate": 7.86788218175523e-05, |
|
"loss": 0.2431, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.23837902264600716, |
|
"eval_loss": 0.266483336687088, |
|
"eval_runtime": 54.8592, |
|
"eval_samples_per_second": 1.622, |
|
"eval_steps_per_second": 0.82, |
|
"step": 25 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 75, |
|
"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": 5.49161310093312e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|