End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: FacebookAI/xlm-roberta-large
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- conll2002
|
| 9 |
+
metrics:
|
| 10 |
+
- precision
|
| 11 |
+
- recall
|
| 12 |
+
- f1
|
| 13 |
+
- accuracy
|
| 14 |
+
model-index:
|
| 15 |
+
- name: roberta-large-ner-qlorafinetune-runs
|
| 16 |
+
results: []
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 20 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 21 |
+
|
| 22 |
+
# roberta-large-ner-qlorafinetune-runs
|
| 23 |
+
|
| 24 |
+
This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the conll2002 dataset.
|
| 25 |
+
It achieves the following results on the evaluation set:
|
| 26 |
+
- Loss: 0.0694
|
| 27 |
+
- Precision: 0.8625
|
| 28 |
+
- Recall: 0.875
|
| 29 |
+
- F1: 0.8687
|
| 30 |
+
- Accuracy: 0.9804
|
| 31 |
+
|
| 32 |
+
## Model description
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Intended uses & limitations
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training and evaluation data
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Training procedure
|
| 45 |
+
|
| 46 |
+
### Training hyperparameters
|
| 47 |
+
|
| 48 |
+
The following hyperparameters were used during training:
|
| 49 |
+
- learning_rate: 0.0004
|
| 50 |
+
- train_batch_size: 32
|
| 51 |
+
- eval_batch_size: 32
|
| 52 |
+
- seed: 42
|
| 53 |
+
- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 54 |
+
- lr_scheduler_type: linear
|
| 55 |
+
- training_steps: 640
|
| 56 |
+
- mixed_precision_training: Native AMP
|
| 57 |
+
|
| 58 |
+
### Training results
|
| 59 |
+
|
| 60 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 61 |
+
|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 62 |
+
| 1.1936 | 0.0766 | 20 | 0.4315 | 0.1319 | 0.1585 | 0.1440 | 0.8748 |
|
| 63 |
+
| 0.2712 | 0.1533 | 40 | 0.2038 | 0.5456 | 0.6085 | 0.5753 | 0.9453 |
|
| 64 |
+
| 0.139 | 0.2299 | 60 | 0.1220 | 0.7536 | 0.7799 | 0.7665 | 0.9668 |
|
| 65 |
+
| 0.0901 | 0.3065 | 80 | 0.1529 | 0.7119 | 0.7624 | 0.7363 | 0.9631 |
|
| 66 |
+
| 0.1016 | 0.3831 | 100 | 0.0917 | 0.8151 | 0.8212 | 0.8181 | 0.9752 |
|
| 67 |
+
| 0.0916 | 0.4598 | 120 | 0.0929 | 0.7840 | 0.7966 | 0.7903 | 0.9722 |
|
| 68 |
+
| 0.0784 | 0.5364 | 140 | 0.0795 | 0.8414 | 0.8532 | 0.8472 | 0.9785 |
|
| 69 |
+
| 0.0791 | 0.6130 | 160 | 0.0813 | 0.8449 | 0.8534 | 0.8491 | 0.9785 |
|
| 70 |
+
| 0.0664 | 0.6897 | 180 | 0.0824 | 0.8462 | 0.8460 | 0.8461 | 0.9783 |
|
| 71 |
+
| 0.0683 | 0.7663 | 200 | 0.0734 | 0.8530 | 0.8575 | 0.8553 | 0.9789 |
|
| 72 |
+
| 0.061 | 0.8429 | 220 | 0.0718 | 0.8519 | 0.8656 | 0.8587 | 0.9793 |
|
| 73 |
+
| 0.0516 | 0.9195 | 240 | 0.0766 | 0.8449 | 0.8539 | 0.8494 | 0.9772 |
|
| 74 |
+
| 0.0526 | 0.9962 | 260 | 0.0723 | 0.8420 | 0.8631 | 0.8524 | 0.9788 |
|
| 75 |
+
| 0.0408 | 1.0728 | 280 | 0.0672 | 0.8528 | 0.8693 | 0.8609 | 0.9798 |
|
| 76 |
+
| 0.0457 | 1.1494 | 300 | 0.0751 | 0.8689 | 0.8745 | 0.8717 | 0.9799 |
|
| 77 |
+
| 0.054 | 1.2261 | 320 | 0.0768 | 0.8495 | 0.8626 | 0.8560 | 0.9776 |
|
| 78 |
+
| 0.05 | 1.3027 | 340 | 0.0761 | 0.8431 | 0.8631 | 0.8530 | 0.9776 |
|
| 79 |
+
| 0.0465 | 1.3793 | 360 | 0.0747 | 0.8395 | 0.8497 | 0.8446 | 0.9781 |
|
| 80 |
+
| 0.0465 | 1.4559 | 380 | 0.0796 | 0.8348 | 0.8490 | 0.8419 | 0.9771 |
|
| 81 |
+
| 0.0388 | 1.5326 | 400 | 0.0690 | 0.8584 | 0.8787 | 0.8684 | 0.9804 |
|
| 82 |
+
| 0.0398 | 1.6092 | 420 | 0.0688 | 0.8569 | 0.8699 | 0.8634 | 0.9805 |
|
| 83 |
+
| 0.0523 | 1.6858 | 440 | 0.0682 | 0.8479 | 0.8605 | 0.8541 | 0.9784 |
|
| 84 |
+
| 0.042 | 1.7625 | 460 | 0.0634 | 0.8740 | 0.8881 | 0.8810 | 0.9828 |
|
| 85 |
+
| 0.0395 | 1.8391 | 480 | 0.0660 | 0.8638 | 0.8784 | 0.8710 | 0.9809 |
|
| 86 |
+
| 0.0432 | 1.9157 | 500 | 0.0641 | 0.8678 | 0.8780 | 0.8729 | 0.9806 |
|
| 87 |
+
| 0.0357 | 1.9923 | 520 | 0.0667 | 0.8706 | 0.8748 | 0.8727 | 0.9808 |
|
| 88 |
+
| 0.0417 | 2.0690 | 540 | 0.0725 | 0.8513 | 0.8725 | 0.8618 | 0.9800 |
|
| 89 |
+
| 0.0269 | 2.1456 | 560 | 0.0705 | 0.8599 | 0.8699 | 0.8649 | 0.9802 |
|
| 90 |
+
| 0.0259 | 2.2222 | 580 | 0.0695 | 0.8614 | 0.8739 | 0.8676 | 0.9810 |
|
| 91 |
+
| 0.0355 | 2.2989 | 600 | 0.0706 | 0.8611 | 0.8732 | 0.8671 | 0.9803 |
|
| 92 |
+
| 0.0299 | 2.3755 | 620 | 0.0702 | 0.8585 | 0.8741 | 0.8662 | 0.9801 |
|
| 93 |
+
| 0.0303 | 2.4521 | 640 | 0.0694 | 0.8625 | 0.875 | 0.8687 | 0.9804 |
|
| 94 |
+
|
| 95 |
+
|
| 96 |
+
### Framework versions
|
| 97 |
+
|
| 98 |
+
- PEFT 0.13.2
|
| 99 |
+
- Transformers 4.46.3
|
| 100 |
+
- Pytorch 2.5.1
|
| 101 |
+
- Datasets 3.1.0
|
| 102 |
+
- Tokenizers 0.20.3
|