| { | |
| "best_global_step": 5000, | |
| "best_metric": 0.11689521339976033, | |
| "best_model_checkpoint": "./modernbert-moderation/checkpoint-5000", | |
| "epoch": 0.03426182889642649, | |
| "eval_steps": 5000, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006852365779285299, | |
| "grad_norm": 1.0276694297790527, | |
| "learning_rate": 1.9931378278956237e-05, | |
| "loss": 0.1897, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.013704731558570597, | |
| "grad_norm": 1.2119929790496826, | |
| "learning_rate": 1.9793859799910615e-05, | |
| "loss": 0.1451, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.020557097337855896, | |
| "grad_norm": 0.8926526308059692, | |
| "learning_rate": 1.9656341320864994e-05, | |
| "loss": 0.1437, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.027409463117141195, | |
| "grad_norm": 1.0339475870132446, | |
| "learning_rate": 1.9518822841819372e-05, | |
| "loss": 0.1367, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.03426182889642649, | |
| "grad_norm": 0.7990005016326904, | |
| "learning_rate": 1.938130436277375e-05, | |
| "loss": 0.1317, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.03426182889642649, | |
| "eval_accuracy": 0.6782917052112242, | |
| "eval_f1_macro": 0.11689521339976033, | |
| "eval_hamming_loss": 0.04767345050878816, | |
| "eval_loss": 0.12752443552017212, | |
| "eval_precision_macro": 0.4914416662914456, | |
| "eval_recall_macro": 0.07863877278340631, | |
| "eval_runtime": 464.5593, | |
| "eval_samples_per_second": 349.041, | |
| "eval_steps_per_second": 34.904, | |
| "eval_subset_accuracy": 0.6782917052112242, | |
| "step": 5000 | |
| } | |
| ], | |
| "logging_steps": 1000, | |
| "max_steps": 145935, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5000, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.646699588149536e+16, | |
| "train_batch_size": 10, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |