| { |
| "best_global_step": 1200, |
| "best_metric": 0.9213111296186804, |
| "best_model_checkpoint": "./results/run-0/checkpoint-1200", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 1200, |
| "is_hyper_param_search": true, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.16673614005835766, |
| "grad_norm": 2.8743319511413574, |
| "learning_rate": 6e-06, |
| "loss": 1.4727, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.3334722801167153, |
| "grad_norm": 0.8747783899307251, |
| "learning_rate": 1.2e-05, |
| "loss": 0.617, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5002084201750729, |
| "grad_norm": 0.7884620428085327, |
| "learning_rate": 1.8e-05, |
| "loss": 0.4493, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.6669445602334306, |
| "grad_norm": 0.8924545645713806, |
| "learning_rate": 2.4e-05, |
| "loss": 0.3876, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.8336807002917882, |
| "grad_norm": 0.8031777739524841, |
| "learning_rate": 3e-05, |
| "loss": 0.3361, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.5999459624290466, |
| "learning_rate": 2.9453551912568308e-05, |
| "loss": 0.3004, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_administration_accuracy": 0.9140087554721701, |
| "eval_administration_f1": 0.8740363354524873, |
| "eval_corruption_accuracy": 0.9370439858244737, |
| "eval_corruption_f1": 0.9192595640701061, |
| "eval_democracy_accuracy": 0.9347508859703981, |
| "eval_democracy_f1": 0.9095054688749907, |
| "eval_development_accuracy": 0.8763810715030227, |
| "eval_development_f1": 0.8253993969919758, |
| "eval_economy_accuracy": 0.9010840108401084, |
| "eval_economy_f1": 0.8737219947600353, |
| "eval_education_accuracy": 0.9571607254534084, |
| "eval_education_f1": 0.9485581438064299, |
| "eval_environment_accuracy": 0.9734208880550344, |
| "eval_environment_f1": 0.9693817386774968, |
| "eval_instability_accuracy": 0.9219303731498854, |
| "eval_instability_f1": 0.8878400653107733, |
| "eval_leadership_accuracy": 0.7652699603919116, |
| "eval_leadership_f1": 0.7080044131422123, |
| "eval_loss": 0.2839118242263794, |
| "eval_overall_accuracy": 0.9120109790841496, |
| "eval_overall_f1": 0.8849771384459072, |
| "eval_race_accuracy": 0.9283927454659162, |
| "eval_race_f1": 0.907176591968042, |
| "eval_religion_accuracy": 0.9369397540129247, |
| "eval_religion_f1": 0.9217332965382043, |
| "eval_runtime": 10.9229, |
| "eval_safety_accuracy": 0.8977485928705441, |
| "eval_safety_f1": 0.8751086517581315, |
| "eval_samples_per_second": 878.336, |
| "eval_steps_per_second": 54.93, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.1667361400583576, |
| "grad_norm": 0.6991692781448364, |
| "learning_rate": 2.890710382513661e-05, |
| "loss": 0.2667, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.3334722801167154, |
| "grad_norm": 0.6808522343635559, |
| "learning_rate": 2.836065573770492e-05, |
| "loss": 0.2573, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.500208420175073, |
| "grad_norm": 0.8924445509910583, |
| "learning_rate": 2.7814207650273226e-05, |
| "loss": 0.2447, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.6669445602334307, |
| "grad_norm": 0.9563364386558533, |
| "learning_rate": 2.7267759562841533e-05, |
| "loss": 0.2282, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.8336807002917883, |
| "grad_norm": 0.8881794810295105, |
| "learning_rate": 2.6721311475409837e-05, |
| "loss": 0.2217, |
| "step": 1100 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.2946265935897827, |
| "learning_rate": 2.6174863387978144e-05, |
| "loss": 0.2197, |
| "step": 1200 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_administration_accuracy": 0.9364185949551803, |
| "eval_administration_f1": 0.9264664888238818, |
| "eval_corruption_accuracy": 0.9562226391494684, |
| "eval_corruption_f1": 0.9508457468931831, |
| "eval_democracy_accuracy": 0.947571398790911, |
| "eval_democracy_f1": 0.9355668234958175, |
| "eval_development_accuracy": 0.9049405878674172, |
| "eval_development_f1": 0.8818640965909518, |
| "eval_economy_accuracy": 0.924119241192412, |
| "eval_economy_f1": 0.9144295841480942, |
| "eval_education_accuracy": 0.9669585157390036, |
| "eval_education_f1": 0.9649722301773493, |
| "eval_environment_accuracy": 0.981029810298103, |
| "eval_environment_f1": 0.9786767163906938, |
| "eval_instability_accuracy": 0.9422555764019178, |
| "eval_instability_f1": 0.9320449284299851, |
| "eval_leadership_accuracy": 0.8006045445069835, |
| "eval_leadership_f1": 0.7682063698028097, |
| "eval_loss": 0.21895167231559753, |
| "eval_overall_accuracy": 0.9317629073726635, |
| "eval_overall_f1": 0.9213111296186804, |
| "eval_race_accuracy": 0.9516364394413175, |
| "eval_race_f1": 0.9462871699636376, |
| "eval_religion_accuracy": 0.9586199708150928, |
| "eval_religion_f1": 0.9568464833874664, |
| "eval_runtime": 10.9295, |
| "eval_safety_accuracy": 0.9107775693141547, |
| "eval_safety_f1": 0.8995269173202963, |
| "eval_samples_per_second": 877.809, |
| "eval_steps_per_second": 54.897, |
| "step": 1200 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 5990, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "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": 2.020053452075827e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": { |
| "gradient_accumulation_steps": 4, |
| "learning_rate": 3e-05, |
| "num_train_epochs": 10 |
| } |
| } |
|
|
