lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v1
/
checkpoint-1200
/trainer_state.json
{ | |
"best_metric": 0.827712178226716, | |
"best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v1/checkpoint-500", | |
"epoch": 0.6396588486140725, | |
"eval_steps": 100, | |
"global_step": 1200, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.05, | |
"eval_accuracy": 0.687484404164213, | |
"eval_f1": 0.687484404164213, | |
"eval_loss": 0.11619879305362701, | |
"eval_precision": 0.687484404164213, | |
"eval_recall": 0.687484404164213, | |
"eval_runtime": 114.5058, | |
"eval_samples_per_second": 14.034, | |
"eval_steps_per_second": 0.882, | |
"step": 100 | |
}, | |
{ | |
"epoch": 0.11, | |
"eval_accuracy": 0.6755467276193519, | |
"eval_f1": 0.6755467276193519, | |
"eval_loss": 0.1096724346280098, | |
"eval_precision": 0.6755467276193519, | |
"eval_recall": 0.6755467276193519, | |
"eval_runtime": 97.2211, | |
"eval_samples_per_second": 16.529, | |
"eval_steps_per_second": 1.039, | |
"step": 200 | |
}, | |
{ | |
"epoch": 0.16, | |
"eval_accuracy": 0.7780849810853704, | |
"eval_f1": 0.7780849810853703, | |
"eval_loss": 0.08659958839416504, | |
"eval_precision": 0.7780849810853704, | |
"eval_recall": 0.7780849810853704, | |
"eval_runtime": 98.762, | |
"eval_samples_per_second": 16.271, | |
"eval_steps_per_second": 1.023, | |
"step": 300 | |
}, | |
{ | |
"epoch": 0.21, | |
"eval_accuracy": 0.7477716669827422, | |
"eval_f1": 0.7477716669827422, | |
"eval_loss": 0.10182594507932663, | |
"eval_precision": 0.7477716669827422, | |
"eval_recall": 0.7477716669827422, | |
"eval_runtime": 99.9428, | |
"eval_samples_per_second": 16.079, | |
"eval_steps_per_second": 1.011, | |
"step": 400 | |
}, | |
{ | |
"epoch": 0.27, | |
"learning_rate": 1.4669509594882732e-05, | |
"loss": 0.0975, | |
"step": 500 | |
}, | |
{ | |
"epoch": 0.27, | |
"eval_accuracy": 0.827712178226716, | |
"eval_f1": 0.827712178226716, | |
"eval_loss": 0.06453556567430496, | |
"eval_precision": 0.827712178226716, | |
"eval_recall": 0.827712178226716, | |
"eval_runtime": 100.1167, | |
"eval_samples_per_second": 16.051, | |
"eval_steps_per_second": 1.009, | |
"step": 500 | |
}, | |
{ | |
"epoch": 0.32, | |
"eval_accuracy": 0.7984968109634982, | |
"eval_f1": 0.7984968109634982, | |
"eval_loss": 0.07669692486524582, | |
"eval_precision": 0.7984968109634982, | |
"eval_recall": 0.7984968109634982, | |
"eval_runtime": 101.2405, | |
"eval_samples_per_second": 15.873, | |
"eval_steps_per_second": 0.998, | |
"step": 600 | |
}, | |
{ | |
"epoch": 0.37, | |
"eval_accuracy": 0.7903320790122471, | |
"eval_f1": 0.7903320790122471, | |
"eval_loss": 0.07575991004705429, | |
"eval_precision": 0.7903320790122471, | |
"eval_recall": 0.7903320790122471, | |
"eval_runtime": 99.3914, | |
"eval_samples_per_second": 16.168, | |
"eval_steps_per_second": 1.016, | |
"step": 700 | |
}, | |
{ | |
"epoch": 0.43, | |
"eval_accuracy": 0.7865491530837334, | |
"eval_f1": 0.7865491530837335, | |
"eval_loss": 0.08622009307146072, | |
"eval_precision": 0.7865491530837334, | |
"eval_recall": 0.7865491530837334, | |
"eval_runtime": 102.0728, | |
"eval_samples_per_second": 15.744, | |
"eval_steps_per_second": 0.989, | |
"step": 800 | |
}, | |
{ | |
"epoch": 0.48, | |
"eval_accuracy": 0.6891712497629433, | |
"eval_f1": 0.6891712497629433, | |
"eval_loss": 0.12430301308631897, | |
"eval_precision": 0.6891712497629433, | |
"eval_recall": 0.6891712497629433, | |
"eval_runtime": 101.8092, | |
"eval_samples_per_second": 15.784, | |
"eval_steps_per_second": 0.992, | |
"step": 900 | |
}, | |
{ | |
"epoch": 0.53, | |
"learning_rate": 9.339019189765458e-06, | |
"loss": 0.1389, | |
"step": 1000 | |
}, | |
{ | |
"epoch": 0.53, | |
"eval_accuracy": 0.8255961352271253, | |
"eval_f1": 0.8255961352271252, | |
"eval_loss": 0.07946911454200745, | |
"eval_precision": 0.8255961352271253, | |
"eval_recall": 0.8255961352271253, | |
"eval_runtime": 101.762, | |
"eval_samples_per_second": 15.792, | |
"eval_steps_per_second": 0.993, | |
"step": 1000 | |
}, | |
{ | |
"epoch": 0.59, | |
"eval_accuracy": 0.470200724644914, | |
"eval_f1": 0.470200724644914, | |
"eval_loss": 0.1683182567358017, | |
"eval_precision": 0.470200724644914, | |
"eval_recall": 0.470200724644914, | |
"eval_runtime": 100.8271, | |
"eval_samples_per_second": 15.938, | |
"eval_steps_per_second": 1.002, | |
"step": 1100 | |
}, | |
{ | |
"epoch": 0.64, | |
"eval_accuracy": 0.6635990697395869, | |
"eval_f1": 0.6635990697395869, | |
"eval_loss": 0.12526559829711914, | |
"eval_precision": 0.6635990697395869, | |
"eval_recall": 0.6635990697395869, | |
"eval_runtime": 98.9873, | |
"eval_samples_per_second": 16.234, | |
"eval_steps_per_second": 1.02, | |
"step": 1200 | |
} | |
], | |
"logging_steps": 500, | |
"max_steps": 1876, | |
"num_train_epochs": 1, | |
"save_steps": 100, | |
"total_flos": 2670453492940800.0, | |
"trial_name": null, | |
"trial_params": null | |
} | |