Hugging Face's logo

DipeshChaudhary
/
nepali-gec-error-type-classifier

Token Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
DipeshChaudhary commited on
Commit
bd63906
·
verified ·
1 Parent(s): e7be327

Model save

Browse files
Files changed (3) hide show
  1. README.md +97 -0
  2. model.safetensors +1 -1
  3. runs/Nov10_17-29-02_computeinstance-e00cvnrx2w84bhdcfx/events.out.tfevents.1762796064.computeinstance-e00cvnrx2w84bhdcfx.130717.0 +2 -2
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: IRIIS-RESEARCH/RoBERTa_Nepali_125M
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - arrow
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: nepali-gec-error-type-classifier
12
+ results:
13
+ - task:
14
+ name: Token Classification
15
+ type: token-classification
16
+ dataset:
17
+ name: arrow
18
+ type: arrow
19
+ config: default
20
+ split: None
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.9501649743634543
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # nepali-gec-error-type-classifier
32
+
33
+ This model is a fine-tuned version of [IRIIS-RESEARCH/RoBERTa_Nepali_125M](https://huggingface.co/IRIIS-RESEARCH/RoBERTa_Nepali_125M) on the arrow dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.1340
36
+ - Accuracy: 0.9502
37
+ - Macro F1: 0.6346
38
+ - Num Error Tokens: 1934543
39
+
40
+ ## Model description
41
+
42
+ More information needed
43
+
44
+ ## Intended uses & limitations
45
+
46
+ More information needed
47
+
48
+ ## Training and evaluation data
49
+
50
+ More information needed
51
+
52
+ ## Training procedure
53
+
54
+ ### Training hyperparameters
55
+
56
+ The following hyperparameters were used during training:
57
+ - learning_rate: 2e-06
58
+ - train_batch_size: 1024
59
+ - eval_batch_size: 1024
60
+ - seed: 42
61
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_steps: 500
64
+ - num_epochs: 3
65
+ - mixed_precision_training: Native AMP
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | Num Error Tokens |
70
+ |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|:----------------:|
71
+ | 0.5944 | 0.1574 | 1000 | 0.4266 | 0.8294 | 0.5394 | 1934543 |
72
+ | 0.3682 | 0.3149 | 2000 | 0.2821 | 0.8919 | 0.5882 | 1934543 |
73
+ | 0.2972 | 0.4723 | 3000 | 0.2351 | 0.9111 | 0.6027 | 1934543 |
74
+ | 0.2618 | 0.6297 | 4000 | 0.2077 | 0.9221 | 0.6109 | 1934543 |
75
+ | 0.2379 | 0.7872 | 5000 | 0.1900 | 0.9292 | 0.6163 | 1934543 |
76
+ | 0.2217 | 0.9446 | 6000 | 0.1780 | 0.9339 | 0.6198 | 1934543 |
77
+ | 0.2066 | 1.1020 | 7000 | 0.1675 | 0.9378 | 0.6228 | 1934543 |
78
+ | 0.1977 | 1.2594 | 8000 | 0.1604 | 0.9405 | 0.6248 | 1934543 |
79
+ | 0.192 | 1.4169 | 9000 | 0.1546 | 0.9425 | 0.6263 | 1934543 |
80
+ | 0.1836 | 1.5743 | 10000 | 0.1502 | 0.9443 | 0.6276 | 1934543 |
81
+ | 0.18 | 1.7317 | 11000 | 0.1466 | 0.9456 | 0.6286 | 1934543 |
82
+ | 0.1763 | 1.8892 | 12000 | 0.1431 | 0.9469 | 0.6296 | 1934543 |
83
+ | 0.172 | 2.0466 | 13000 | 0.1408 | 0.9476 | 0.6301 | 1934543 |
84
+ | 0.1672 | 2.2040 | 14000 | 0.1383 | 0.9486 | 0.6317 | 1934543 |
85
+ | 0.1673 | 2.3615 | 15000 | 0.1368 | 0.9492 | 0.6321 | 1934543 |
86
+ | 0.1646 | 2.5189 | 16000 | 0.1355 | 0.9496 | 0.6333 | 1934543 |
87
+ | 0.1629 | 2.6763 | 17000 | 0.1349 | 0.9499 | 0.6327 | 1934543 |
88
+ | 0.1631 | 2.8338 | 18000 | 0.1342 | 0.9501 | 0.6337 | 1934543 |
89
+ | 0.1621 | 2.9912 | 19000 | 0.1340 | 0.9502 | 0.6346 | 1934543 |
90
+
91
+
92
+ ### Framework versions
93
+
94
+ - Transformers 4.57.1
95
+ - Pytorch 2.8.0+cu128
96
+ - Datasets 4.4.1
97
+ - Tokenizers 0.22.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8dd31e8d316052ee1631c14e2cbc3f58ba5f00124ac15b60a1f5ce44d26dbd2
3
  size 496238080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2e7b80e3c3e614c2deb514d680a193974e6e7fa4d5161474c63500eaf90ab0a
3
  size 496238080
runs/Nov10_17-29-02_computeinstance-e00cvnrx2w84bhdcfx/events.out.tfevents.1762796064.computeinstance-e00cvnrx2w84bhdcfx.130717.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78899f82c25522d07b9e9f58db7d05e8b18641e1c3a19fec24edc2330420afeb
3
- size 21819
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0284d66f38e4d0d0f543aec28aabfe77726b0f2fbe418137fa82e60d99da52bf
3
+ size 22179