lilt-xlm-roberta-base-finetuned-with-DocLayNet-base-at-paragraphlevel-ml512
/
checkpoint-1800
/trainer_state.json
| { | |
| "best_metric": 0.885723696687195, | |
| "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v5/checkpoint-600", | |
| "epoch": 0.9594882729211087, | |
| "global_step": 1800, | |
| "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 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_accuracy": 0.8629662531066905, | |
| "eval_f1": 0.8629662531066905, | |
| "eval_loss": 0.4096183180809021, | |
| "eval_precision": 0.8629662531066905, | |
| "eval_recall": 0.8629662531066905, | |
| "eval_runtime": 45.8414, | |
| "eval_samples_per_second": 35.056, | |
| "eval_steps_per_second": 2.203, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.8528252168445007, | |
| "eval_f1": 0.8528252168445007, | |
| "eval_loss": 0.44917240738868713, | |
| "eval_precision": 0.8528252168445007, | |
| "eval_recall": 0.8528252168445007, | |
| "eval_runtime": 45.6102, | |
| "eval_samples_per_second": 35.233, | |
| "eval_steps_per_second": 2.214, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.8833980456546259, | |
| "eval_f1": 0.8833980456546259, | |
| "eval_loss": 0.38389313220977783, | |
| "eval_precision": 0.8833980456546259, | |
| "eval_recall": 0.8833980456546259, | |
| "eval_runtime": 47.6493, | |
| "eval_samples_per_second": 33.726, | |
| "eval_steps_per_second": 2.12, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.381663113006397e-06, | |
| "loss": 0.4464, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_accuracy": 0.8498407977082855, | |
| "eval_f1": 0.8498407977082856, | |
| "eval_loss": 0.4365050792694092, | |
| "eval_precision": 0.8498407977082855, | |
| "eval_recall": 0.8498407977082855, | |
| "eval_runtime": 47.0078, | |
| "eval_samples_per_second": 34.186, | |
| "eval_steps_per_second": 2.149, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.8811622266361904, | |
| "eval_f1": 0.8811622266361904, | |
| "eval_loss": 0.36158204078674316, | |
| "eval_precision": 0.8811622266361904, | |
| "eval_recall": 0.8811622266361904, | |
| "eval_runtime": 44.8724, | |
| "eval_samples_per_second": 35.813, | |
| "eval_steps_per_second": 2.251, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.8795751943864972, | |
| "eval_f1": 0.8795751943864972, | |
| "eval_loss": 0.3948919177055359, | |
| "eval_precision": 0.8795751943864972, | |
| "eval_recall": 0.8795751943864972, | |
| "eval_runtime": 45.1224, | |
| "eval_samples_per_second": 35.614, | |
| "eval_steps_per_second": 2.238, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_accuracy": 0.8612794075079601, | |
| "eval_f1": 0.8612794075079601, | |
| "eval_loss": 0.41840043663978577, | |
| "eval_precision": 0.8612794075079601, | |
| "eval_recall": 0.8612794075079601, | |
| "eval_runtime": 39.7377, | |
| "eval_samples_per_second": 40.44, | |
| "eval_steps_per_second": 2.542, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.874334993562039, | |
| "eval_f1": 0.874334993562039, | |
| "eval_loss": 0.4129931926727295, | |
| "eval_precision": 0.874334993562039, | |
| "eval_recall": 0.874334993562039, | |
| "eval_runtime": 44.8477, | |
| "eval_samples_per_second": 35.832, | |
| "eval_steps_per_second": 2.252, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.051172707889126e-06, | |
| "loss": 0.3672, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.8288799944104525, | |
| "eval_f1": 0.8288799944104525, | |
| "eval_loss": 0.45351940393447876, | |
| "eval_precision": 0.8288799944104525, | |
| "eval_recall": 0.8288799944104525, | |
| "eval_runtime": 45.3573, | |
| "eval_samples_per_second": 35.43, | |
| "eval_steps_per_second": 2.227, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_accuracy": 0.8712607424116902, | |
| "eval_f1": 0.8712607424116902, | |
| "eval_loss": 0.36811864376068115, | |
| "eval_precision": 0.8712607424116902, | |
| "eval_recall": 0.8712607424116902, | |
| "eval_runtime": 44.3035, | |
| "eval_samples_per_second": 36.273, | |
| "eval_steps_per_second": 2.28, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_accuracy": 0.885723696687195, | |
| "eval_f1": 0.885723696687195, | |
| "eval_loss": 0.34459415078163147, | |
| "eval_precision": 0.885723696687195, | |
| "eval_recall": 0.885723696687195, | |
| "eval_runtime": 44.6077, | |
| "eval_samples_per_second": 36.025, | |
| "eval_steps_per_second": 2.264, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.8634353758471658, | |
| "eval_f1": 0.8634353758471657, | |
| "eval_loss": 0.41038718819618225, | |
| "eval_precision": 0.8634353758471658, | |
| "eval_recall": 0.8634353758471658, | |
| "eval_runtime": 40.0758, | |
| "eval_samples_per_second": 40.099, | |
| "eval_steps_per_second": 2.52, | |
| "step": 1800 | |
| } | |
| ], | |
| "max_steps": 1876, | |
| "num_train_epochs": 1, | |
| "total_flos": 4005680239411200.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |