| { |
| "best_global_step": 375, |
| "best_metric": 0.8750911429666324, |
| "best_model_checkpoint": "./results/run-4/checkpoint-375", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 375, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.8, |
| "grad_norm": 3.666975498199463, |
| "learning_rate": 5.940000000000001e-06, |
| "loss": 1.9121, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_clientelism_accuracy": 0.8245, |
| "eval_clientelism_f1": 0.7460945464510824, |
| "eval_discipline_among_poor_accuracy": 0.955, |
| "eval_discipline_among_poor_f1": 0.9330179028132993, |
| "eval_economic_policy_accuracy": 0.7925, |
| "eval_economic_policy_f1": 0.7007601115760111, |
| "eval_loss": 0.8509422540664673, |
| "eval_marcos_duterte_alliance_accuracy": 0.785, |
| "eval_marcos_duterte_alliance_f1": 0.7607489531451762, |
| "eval_overall_accuracy": 0.7899375, |
| "eval_overall_f1": 0.7258422303968415, |
| "eval_populism_accuracy": 0.569, |
| "eval_populism_f1": 0.5002822145282152, |
| "eval_regionalism_accuracy": 0.941, |
| "eval_regionalism_f1": 0.9123967027305513, |
| "eval_runtime": 2.489, |
| "eval_samples_per_second": 803.55, |
| "eval_security_accuracy": 0.78, |
| "eval_security_f1": 0.6835955056179776, |
| "eval_steps_per_second": 50.222, |
| "eval_uniteam_positive_campaign_accuracy": 0.6725, |
| "eval_uniteam_positive_campaign_f1": 0.5698419063124196, |
| "step": 125 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 1.4751663208007812, |
| "learning_rate": 1.1940000000000001e-05, |
| "loss": 0.795, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_clientelism_accuracy": 0.854, |
| "eval_clientelism_f1": 0.8185554864536612, |
| "eval_discipline_among_poor_accuracy": 0.968, |
| "eval_discipline_among_poor_f1": 0.9597382970029669, |
| "eval_economic_policy_accuracy": 0.831, |
| "eval_economic_policy_f1": 0.78975033625731, |
| "eval_loss": 0.5655983090400696, |
| "eval_marcos_duterte_alliance_accuracy": 0.7615, |
| "eval_marcos_duterte_alliance_f1": 0.7308627009539056, |
| "eval_overall_accuracy": 0.8033750000000001, |
| "eval_overall_f1": 0.7596520016821164, |
| "eval_populism_accuracy": 0.5925, |
| "eval_populism_f1": 0.515907420418669, |
| "eval_regionalism_accuracy": 0.963, |
| "eval_regionalism_f1": 0.9503894271608052, |
| "eval_runtime": 2.5815, |
| "eval_samples_per_second": 774.753, |
| "eval_security_accuracy": 0.786, |
| "eval_security_f1": 0.7304178061774521, |
| "eval_steps_per_second": 48.422, |
| "eval_uniteam_positive_campaign_accuracy": 0.671, |
| "eval_uniteam_positive_campaign_f1": 0.5815945390321615, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 1.0356261730194092, |
| "learning_rate": 1.794e-05, |
| "loss": 0.5771, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_clientelism_accuracy": 0.915, |
| "eval_clientelism_f1": 0.9028287454471358, |
| "eval_discipline_among_poor_accuracy": 0.9735, |
| "eval_discipline_among_poor_f1": 0.9692752667759658, |
| "eval_economic_policy_accuracy": 0.895, |
| "eval_economic_policy_f1": 0.8751917204764802, |
| "eval_loss": 0.3845510184764862, |
| "eval_marcos_duterte_alliance_accuracy": 0.887, |
| "eval_marcos_duterte_alliance_f1": 0.8761695090938638, |
| "eval_overall_accuracy": 0.8885624999999999, |
| "eval_overall_f1": 0.8750911429666324, |
| "eval_populism_accuracy": 0.712, |
| "eval_populism_f1": 0.6768123016282166, |
| "eval_regionalism_accuracy": 0.9785, |
| "eval_regionalism_f1": 0.9755801825850344, |
| "eval_runtime": 3.0096, |
| "eval_samples_per_second": 664.549, |
| "eval_security_accuracy": 0.9255, |
| "eval_security_f1": 0.9165634280678563, |
| "eval_steps_per_second": 41.534, |
| "eval_uniteam_positive_campaign_accuracy": 0.822, |
| "eval_uniteam_positive_campaign_f1": 0.8083079896585065, |
| "step": 375 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 625, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 2, |
| "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": 5053092986880000.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": { |
| "gradient_accumulation_steps": 4, |
| "learning_rate": 3e-05, |
| "num_train_epochs": 5 |
| } |
| } |
|
|
