| { |
| "best_metric": 0.26700150966644287, |
| "best_model_checkpoint": "gbert-base-ner/checkpoint-2514", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 6285, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.39777247414478917, |
| "grad_norm": 7.679558753967285, |
| "learning_rate": 1.9204455051710422e-05, |
| "loss": 0.4898, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.7955449482895783, |
| "grad_norm": 4.438704013824463, |
| "learning_rate": 1.8408910103420846e-05, |
| "loss": 0.3708, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_f1": 0.8008293541090725, |
| "eval_loss": 0.2872423231601715, |
| "eval_precision": 0.8350366876310272, |
| "eval_recall": 0.7693143408981169, |
| "eval_runtime": 11.951, |
| "eval_samples_per_second": 182.495, |
| "eval_steps_per_second": 22.843, |
| "step": 1257 |
| }, |
| { |
| "epoch": 1.1933174224343674, |
| "grad_norm": 1.9350892305374146, |
| "learning_rate": 1.7613365155131266e-05, |
| "loss": 0.3114, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.5910898965791567, |
| "grad_norm": 1.7877984046936035, |
| "learning_rate": 1.681782020684169e-05, |
| "loss": 0.2969, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.988862370723946, |
| "grad_norm": 1.6055359840393066, |
| "learning_rate": 1.602227525855211e-05, |
| "loss": 0.2996, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_f1": 0.8232498629135442, |
| "eval_loss": 0.26700150966644287, |
| "eval_precision": 0.831098536105302, |
| "eval_recall": 0.8155480444229841, |
| "eval_runtime": 7.844, |
| "eval_samples_per_second": 278.048, |
| "eval_steps_per_second": 34.804, |
| "step": 2514 |
| }, |
| { |
| "epoch": 2.386634844868735, |
| "grad_norm": 1.8125649690628052, |
| "learning_rate": 1.5226730310262532e-05, |
| "loss": 0.2365, |
| "step": 3000 |
| }, |
| { |
| "epoch": 2.7844073190135243, |
| "grad_norm": 12.416862487792969, |
| "learning_rate": 1.4431185361972953e-05, |
| "loss": 0.2343, |
| "step": 3500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_f1": 0.8103279490944689, |
| "eval_loss": 0.2706725001335144, |
| "eval_precision": 0.8215880893300248, |
| "eval_recall": 0.7993722839208112, |
| "eval_runtime": 7.8069, |
| "eval_samples_per_second": 279.369, |
| "eval_steps_per_second": 34.969, |
| "step": 3771 |
| }, |
| { |
| "epoch": 3.1821797931583133, |
| "grad_norm": 8.41870403289795, |
| "learning_rate": 1.3635640413683375e-05, |
| "loss": 0.2274, |
| "step": 4000 |
| }, |
| { |
| "epoch": 3.579952267303103, |
| "grad_norm": 0.863073468208313, |
| "learning_rate": 1.2840095465393797e-05, |
| "loss": 0.1949, |
| "step": 4500 |
| }, |
| { |
| "epoch": 3.977724741447892, |
| "grad_norm": 2.265889883041382, |
| "learning_rate": 1.2044550517104217e-05, |
| "loss": 0.2261, |
| "step": 5000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_f1": 0.8117267020174317, |
| "eval_loss": 0.3216415047645569, |
| "eval_precision": 0.8197710205589068, |
| "eval_recall": 0.8038387252535008, |
| "eval_runtime": 7.8451, |
| "eval_samples_per_second": 278.007, |
| "eval_steps_per_second": 34.799, |
| "step": 5028 |
| }, |
| { |
| "epoch": 4.375497215592681, |
| "grad_norm": 15.443475723266602, |
| "learning_rate": 1.1249005568814639e-05, |
| "loss": 0.1745, |
| "step": 5500 |
| }, |
| { |
| "epoch": 4.77326968973747, |
| "grad_norm": 1.7649030685424805, |
| "learning_rate": 1.045346062052506e-05, |
| "loss": 0.1893, |
| "step": 6000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_f1": 0.8314215362440694, |
| "eval_loss": 0.28708234429359436, |
| "eval_precision": 0.8272977172224214, |
| "eval_recall": 0.8355866731047803, |
| "eval_runtime": 7.821, |
| "eval_samples_per_second": 278.866, |
| "eval_steps_per_second": 34.906, |
| "step": 6285 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 12570, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1427126539911864.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
