lilt-xlm-roberta-base-finetuned-with-DocLayNet-base-at-paragraphlevel-ml512
/
checkpoint-600
/trainer_state.json
| { | |
| "best_metric": 0.885723696687195, | |
| "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v5/checkpoint-600", | |
| "epoch": 0.31982942430703626, | |
| "global_step": 600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.6585185702735884, | |
| "eval_f1": 0.6585185702735884, | |
| "eval_loss": 0.9875321388244629, | |
| "eval_precision": 0.6585185702735884, | |
| "eval_recall": 0.6585185702735884, | |
| "eval_runtime": 47.6616, | |
| "eval_samples_per_second": 33.717, | |
| "eval_steps_per_second": 2.119, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.7551279108067913, | |
| "eval_f1": 0.7551279108067913, | |
| "eval_loss": 0.7886354327201843, | |
| "eval_precision": 0.7551279108067913, | |
| "eval_recall": 0.7551279108067913, | |
| "eval_runtime": 48.4163, | |
| "eval_samples_per_second": 33.191, | |
| "eval_steps_per_second": 2.086, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.8248275724395381, | |
| "eval_f1": 0.8248275724395382, | |
| "eval_loss": 0.5894176363945007, | |
| "eval_precision": 0.8248275724395381, | |
| "eval_recall": 0.8248275724395381, | |
| "eval_runtime": 47.5388, | |
| "eval_samples_per_second": 33.804, | |
| "eval_steps_per_second": 2.125, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.839579985427251, | |
| "eval_f1": 0.8395799854272509, | |
| "eval_loss": 0.479428768157959, | |
| "eval_precision": 0.839579985427251, | |
| "eval_recall": 0.839579985427251, | |
| "eval_runtime": 45.3857, | |
| "eval_samples_per_second": 35.408, | |
| "eval_steps_per_second": 2.225, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.4712153518123668e-05, | |
| "loss": 0.7446, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_accuracy": 0.870342459600547, | |
| "eval_f1": 0.8703424596005469, | |
| "eval_loss": 0.39928165078163147, | |
| "eval_precision": 0.870342459600547, | |
| "eval_recall": 0.870342459600547, | |
| "eval_runtime": 46.3389, | |
| "eval_samples_per_second": 34.679, | |
| "eval_steps_per_second": 2.18, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.885723696687195, | |
| "eval_f1": 0.885723696687195, | |
| "eval_loss": 0.36305829882621765, | |
| "eval_precision": 0.885723696687195, | |
| "eval_recall": 0.885723696687195, | |
| "eval_runtime": 46.9181, | |
| "eval_samples_per_second": 34.251, | |
| "eval_steps_per_second": 2.153, | |
| "step": 600 | |
| } | |
| ], | |
| "max_steps": 1876, | |
| "num_train_epochs": 1, | |
| "total_flos": 1335226746470400.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |