|
{ |
|
"best_metric": 0.03706079348921776, |
|
"best_model_checkpoint": "doc-topic-model_eval-04_train-03/checkpoint-11000", |
|
"epoch": 5.9171597633136095, |
|
"eval_steps": 1000, |
|
"global_step": 12000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.2465483234714004, |
|
"grad_norm": 0.3881610631942749, |
|
"learning_rate": 1.9950690335305722e-05, |
|
"loss": 0.1669, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.4930966469428008, |
|
"grad_norm": 0.3564796447753906, |
|
"learning_rate": 1.9901380670611442e-05, |
|
"loss": 0.0935, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.4930966469428008, |
|
"eval_accuracy": 0.981496987239155, |
|
"eval_f1": 0.0, |
|
"eval_loss": 0.08937656879425049, |
|
"eval_precision": 0.0, |
|
"eval_recall": 0.0, |
|
"eval_runtime": 12.1325, |
|
"eval_samples_per_second": 668.698, |
|
"eval_steps_per_second": 2.638, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.7396449704142012, |
|
"grad_norm": 0.4097365140914917, |
|
"learning_rate": 1.9852071005917162e-05, |
|
"loss": 0.0869, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.9861932938856016, |
|
"grad_norm": 0.3858756422996521, |
|
"learning_rate": 1.980276134122288e-05, |
|
"loss": 0.0764, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.9861932938856016, |
|
"eval_accuracy": 0.981496987239155, |
|
"eval_f1": 0.0, |
|
"eval_loss": 0.06986432522535324, |
|
"eval_precision": 0.0, |
|
"eval_recall": 0.0, |
|
"eval_runtime": 12.1072, |
|
"eval_samples_per_second": 670.097, |
|
"eval_steps_per_second": 2.643, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 1.232741617357002, |
|
"grad_norm": 0.3765203356742859, |
|
"learning_rate": 1.9753451676528602e-05, |
|
"loss": 0.068, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 1.4792899408284024, |
|
"grad_norm": 0.3380969762802124, |
|
"learning_rate": 1.9704142011834322e-05, |
|
"loss": 0.0621, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 1.4792899408284024, |
|
"eval_accuracy": 0.982110448535131, |
|
"eval_f1": 0.07324770642201835, |
|
"eval_loss": 0.05668229982256889, |
|
"eval_precision": 0.8831858407079646, |
|
"eval_recall": 0.03820826952526799, |
|
"eval_runtime": 14.4297, |
|
"eval_samples_per_second": 562.245, |
|
"eval_steps_per_second": 2.218, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 1.725838264299803, |
|
"grad_norm": 0.3490855395793915, |
|
"learning_rate": 1.965483234714004e-05, |
|
"loss": 0.056, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 1.972386587771203, |
|
"grad_norm": 0.4068734347820282, |
|
"learning_rate": 1.9605522682445763e-05, |
|
"loss": 0.0542, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 1.972386587771203, |
|
"eval_accuracy": 0.9840103367519987, |
|
"eval_f1": 0.28812917875614985, |
|
"eval_loss": 0.04953226447105408, |
|
"eval_precision": 0.8174659985683608, |
|
"eval_recall": 0.17488514548238898, |
|
"eval_runtime": 14.3697, |
|
"eval_samples_per_second": 564.59, |
|
"eval_steps_per_second": 2.227, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 2.2189349112426036, |
|
"grad_norm": 0.39391544461250305, |
|
"learning_rate": 1.9556213017751483e-05, |
|
"loss": 0.0488, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 2.465483234714004, |
|
"grad_norm": 0.2698710858821869, |
|
"learning_rate": 1.95069033530572e-05, |
|
"loss": 0.0468, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 2.465483234714004, |
|
"eval_accuracy": 0.985417189100507, |
|
"eval_f1": 0.4302241904234708, |
|
"eval_loss": 0.046475622802972794, |
|
"eval_precision": 0.7764235764235764, |
|
"eval_recall": 0.2975497702909648, |
|
"eval_runtime": 14.4141, |
|
"eval_samples_per_second": 562.851, |
|
"eval_steps_per_second": 2.22, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 2.712031558185404, |
|
"grad_norm": 0.39123860001564026, |
|
"learning_rate": 1.9457593688362923e-05, |
|
"loss": 0.0456, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 2.9585798816568047, |
|
"grad_norm": 0.4525609016418457, |
|
"learning_rate": 1.940828402366864e-05, |
|
"loss": 0.0441, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 2.9585798816568047, |
|
"eval_accuracy": 0.9861241571991028, |
|
"eval_f1": 0.4928016571724495, |
|
"eval_loss": 0.04332950338721275, |
|
"eval_precision": 0.76128, |
|
"eval_recall": 0.36431852986217456, |
|
"eval_runtime": 14.4207, |
|
"eval_samples_per_second": 562.594, |
|
"eval_steps_per_second": 2.219, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 3.2051282051282053, |
|
"grad_norm": 0.47004055976867676, |
|
"learning_rate": 1.935897435897436e-05, |
|
"loss": 0.0409, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 3.4516765285996054, |
|
"grad_norm": 0.3331545293331146, |
|
"learning_rate": 1.930966469428008e-05, |
|
"loss": 0.0395, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 3.4516765285996054, |
|
"eval_accuracy": 0.9862219143109328, |
|
"eval_f1": 0.5332821423429477, |
|
"eval_loss": 0.04148830473423004, |
|
"eval_precision": 0.7144142985727144, |
|
"eval_recall": 0.4254211332312404, |
|
"eval_runtime": 14.388, |
|
"eval_samples_per_second": 563.873, |
|
"eval_steps_per_second": 2.224, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 3.698224852071006, |
|
"grad_norm": 0.46907347440719604, |
|
"learning_rate": 1.92603550295858e-05, |
|
"loss": 0.0382, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 3.9447731755424065, |
|
"grad_norm": 0.3860171437263489, |
|
"learning_rate": 1.921104536489152e-05, |
|
"loss": 0.0384, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 3.9447731755424065, |
|
"eval_accuracy": 0.9867702041990222, |
|
"eval_f1": 0.5643370346178967, |
|
"eval_loss": 0.039736006408929825, |
|
"eval_precision": 0.7222354908048723, |
|
"eval_recall": 0.463093415007657, |
|
"eval_runtime": 14.4305, |
|
"eval_samples_per_second": 562.213, |
|
"eval_steps_per_second": 2.218, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 4.191321499013807, |
|
"grad_norm": 0.39796024560928345, |
|
"learning_rate": 1.916173570019724e-05, |
|
"loss": 0.0348, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 4.437869822485207, |
|
"grad_norm": 0.3643665313720703, |
|
"learning_rate": 1.911242603550296e-05, |
|
"loss": 0.0343, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 4.437869822485207, |
|
"eval_accuracy": 0.9869855531989953, |
|
"eval_f1": 0.580815916765538, |
|
"eval_loss": 0.03891120105981827, |
|
"eval_precision": 0.7187711768692117, |
|
"eval_recall": 0.4872894333843798, |
|
"eval_runtime": 14.5144, |
|
"eval_samples_per_second": 558.964, |
|
"eval_steps_per_second": 2.205, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 4.684418145956608, |
|
"grad_norm": 0.2764923572540283, |
|
"learning_rate": 1.906311637080868e-05, |
|
"loss": 0.0345, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 4.930966469428008, |
|
"grad_norm": 0.432156503200531, |
|
"learning_rate": 1.90138067061144e-05, |
|
"loss": 0.0337, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 4.930966469428008, |
|
"eval_accuracy": 0.9874672549094613, |
|
"eval_f1": 0.5954449830787524, |
|
"eval_loss": 0.037564631551504135, |
|
"eval_precision": 0.739268680445151, |
|
"eval_recall": 0.498468606431853, |
|
"eval_runtime": 14.3839, |
|
"eval_samples_per_second": 564.034, |
|
"eval_steps_per_second": 2.225, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 5.177514792899408, |
|
"grad_norm": 0.27451589703559875, |
|
"learning_rate": 1.896459566074951e-05, |
|
"loss": 0.0309, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 5.424063116370808, |
|
"grad_norm": 0.49061715602874756, |
|
"learning_rate": 1.891528599605523e-05, |
|
"loss": 0.0305, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 5.424063116370808, |
|
"eval_accuracy": 0.9876188492712845, |
|
"eval_f1": 0.6006489055431157, |
|
"eval_loss": 0.03706079348921776, |
|
"eval_precision": 0.7448713589482036, |
|
"eval_recall": 0.5032159264931088, |
|
"eval_runtime": 14.4233, |
|
"eval_samples_per_second": 562.494, |
|
"eval_steps_per_second": 2.219, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 5.670611439842209, |
|
"grad_norm": 0.42573484778404236, |
|
"learning_rate": 1.886597633136095e-05, |
|
"loss": 0.0299, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 5.9171597633136095, |
|
"grad_norm": 0.4632101058959961, |
|
"learning_rate": 1.881666666666667e-05, |
|
"loss": 0.0295, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 5.9171597633136095, |
|
"eval_accuracy": 0.9875621784818179, |
|
"eval_f1": 0.6106010201818585, |
|
"eval_loss": 0.03748030215501785, |
|
"eval_precision": 0.7256721138639958, |
|
"eval_recall": 0.5270290964777948, |
|
"eval_runtime": 14.3798, |
|
"eval_samples_per_second": 564.195, |
|
"eval_steps_per_second": 2.225, |
|
"step": 12000 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 202800, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 100, |
|
"save_steps": 1000, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 5, |
|
"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": 270583826069916.0, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|