Commit
•
9e2df54
1
Parent(s):
d61b14b
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- precision
|
| 6 |
+
- recall
|
| 7 |
+
- f1
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: IndicBERTv2-MLM-Sam-TLM-NER
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# IndicBERTv2-MLM-Sam-TLM-NER
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [ai4bharat/IndicBERTv2-MLM-Sam-TLM](https://huggingface.co/ai4bharat/IndicBERTv2-MLM-Sam-TLM) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.4521
|
| 22 |
+
- Precision: 0.7629
|
| 23 |
+
- Recall: 0.7792
|
| 24 |
+
- F1: 0.7710
|
| 25 |
+
- Accuracy: 0.9038
|
| 26 |
+
|
| 27 |
+
## Model description
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Intended uses & limitations
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training and evaluation data
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training procedure
|
| 40 |
+
|
| 41 |
+
### Training hyperparameters
|
| 42 |
+
|
| 43 |
+
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 5e-05
|
| 45 |
+
- train_batch_size: 128
|
| 46 |
+
- eval_batch_size: 256
|
| 47 |
+
- seed: 42
|
| 48 |
+
- gradient_accumulation_steps: 2
|
| 49 |
+
- total_train_batch_size: 256
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- num_epochs: 15
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 58 |
+
| 0.3268 | 0.49 | 1000 | 0.3440 | 0.7207 | 0.7602 | 0.7399 | 0.8887 |
|
| 59 |
+
| 0.2763 | 0.99 | 2000 | 0.3083 | 0.7568 | 0.7732 | 0.7649 | 0.8983 |
|
| 60 |
+
| 0.2604 | 1.48 | 3000 | 0.3312 | 0.7309 | 0.7494 | 0.7401 | 0.8909 |
|
| 61 |
+
| 0.2501 | 1.98 | 4000 | 0.3017 | 0.7415 | 0.7956 | 0.7676 | 0.9014 |
|
| 62 |
+
| 0.2269 | 2.47 | 5000 | 0.2930 | 0.7528 | 0.7970 | 0.7743 | 0.9050 |
|
| 63 |
+
| 0.223 | 2.96 | 6000 | 0.2963 | 0.7590 | 0.7963 | 0.7772 | 0.9053 |
|
| 64 |
+
| 0.2011 | 3.46 | 7000 | 0.2939 | 0.7627 | 0.7946 | 0.7783 | 0.9079 |
|
| 65 |
+
| 0.1999 | 3.95 | 8000 | 0.3036 | 0.7676 | 0.7903 | 0.7788 | 0.9069 |
|
| 66 |
+
| 0.1815 | 4.44 | 9000 | 0.3125 | 0.7618 | 0.7915 | 0.7764 | 0.9056 |
|
| 67 |
+
| 0.1777 | 4.94 | 10000 | 0.3083 | 0.7748 | 0.7957 | 0.7851 | 0.9098 |
|
| 68 |
+
| 0.1622 | 5.43 | 11000 | 0.3251 | 0.7721 | 0.7909 | 0.7814 | 0.9089 |
|
| 69 |
+
| 0.1598 | 5.93 | 12000 | 0.3197 | 0.7767 | 0.7947 | 0.7856 | 0.9092 |
|
| 70 |
+
| 0.145 | 6.42 | 13000 | 0.3366 | 0.7718 | 0.7986 | 0.7850 | 0.9101 |
|
| 71 |
+
| 0.1436 | 6.91 | 14000 | 0.3247 | 0.7776 | 0.7977 | 0.7875 | 0.9112 |
|
| 72 |
+
| 0.1306 | 7.41 | 15000 | 0.3502 | 0.7779 | 0.7958 | 0.7867 | 0.9107 |
|
| 73 |
+
| 0.1311 | 7.9 | 16000 | 0.3585 | 0.7857 | 0.7909 | 0.7883 | 0.9105 |
|
| 74 |
+
| 0.12 | 8.4 | 17000 | 0.3717 | 0.7768 | 0.7911 | 0.7839 | 0.9099 |
|
| 75 |
+
| 0.1202 | 8.89 | 18000 | 0.3667 | 0.7796 | 0.7882 | 0.7839 | 0.9100 |
|
| 76 |
+
| 0.1141 | 9.38 | 19000 | 0.3860 | 0.7857 | 0.7900 | 0.7879 | 0.9100 |
|
| 77 |
+
| 0.1113 | 9.88 | 20000 | 0.3824 | 0.7758 | 0.7970 | 0.7862 | 0.9094 |
|
| 78 |
+
| 0.1056 | 10.37 | 21000 | 0.4041 | 0.7740 | 0.7952 | 0.7845 | 0.9084 |
|
| 79 |
+
| 0.1073 | 10.86 | 22000 | 0.4062 | 0.7735 | 0.7929 | 0.7831 | 0.9094 |
|
| 80 |
+
| 0.1063 | 11.36 | 23000 | 0.4197 | 0.7720 | 0.7866 | 0.7793 | 0.9071 |
|
| 81 |
+
| 0.1026 | 11.85 | 24000 | 0.4179 | 0.7625 | 0.7767 | 0.7695 | 0.9040 |
|
| 82 |
+
| 0.1042 | 12.35 | 25000 | 0.4392 | 0.7639 | 0.7748 | 0.7693 | 0.9037 |
|
| 83 |
+
| 0.101 | 12.84 | 26000 | 0.4373 | 0.7533 | 0.7795 | 0.7662 | 0.9029 |
|
| 84 |
+
| 0.1003 | 13.33 | 27000 | 0.4554 | 0.7535 | 0.7774 | 0.7653 | 0.9021 |
|
| 85 |
+
| 0.0993 | 13.83 | 28000 | 0.4530 | 0.7555 | 0.7773 | 0.7663 | 0.9019 |
|
| 86 |
+
| 0.0978 | 14.32 | 29000 | 0.4467 | 0.7637 | 0.7843 | 0.7738 | 0.9050 |
|
| 87 |
+
| 0.0946 | 14.81 | 30000 | 0.4521 | 0.7629 | 0.7792 | 0.7710 | 0.9038 |
|
| 88 |
+
|
| 89 |
+
|
| 90 |
+
### Framework versions
|
| 91 |
+
|
| 92 |
+
- Transformers 4.27.4
|
| 93 |
+
- Pytorch 2.0.0+cu117
|
| 94 |
+
- Datasets 2.11.0
|
| 95 |
+
- Tokenizers 0.13.3
|