Hugging Face's logo

IIIT-L
/
muril-base-cased-finetuned-code-mixed-DS

Text Classification
Transformers
PyTorch
Safetensors
bert
Generated from Trainer
Model card Files Community
1
dipteshkanojia commited on
Commit
84286f2
·
1 Parent(s): abc48ce

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +23 -18
README.md CHANGED
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [google/muril-base-cased](https://huggingface.co/google/muril-base-cased) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.9319
23
- - Accuracy: 0.6982
24
- - Precision: 0.6327
25
- - Recall: 0.6314
26
- - F1: 0.6320
27
 
28
  ## Model description
29
 
@@ -48,24 +48,29 @@ The following hyperparameters were used during training:
48
  - seed: 43
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
- - num_epochs: 25
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
57
- | 1.0542 | 1.98 | 248 | 0.9786 | 0.5976 | 0.3936 | 0.5454 | 0.4330 |
58
- | 0.9307 | 3.97 | 496 | 0.8836 | 0.5996 | 0.4072 | 0.5604 | 0.4399 |
59
- | 0.8323 | 5.95 | 744 | 0.8266 | 0.5996 | 0.5508 | 0.5720 | 0.4527 |
60
- | 0.7554 | 7.94 | 992 | 0.8006 | 0.6318 | 0.5601 | 0.5838 | 0.5232 |
61
- | 0.6821 | 9.92 | 1240 | 0.8777 | 0.6740 | 0.5929 | 0.5875 | 0.5836 |
62
- | 0.6173 | 11.9 | 1488 | 0.8389 | 0.6640 | 0.5918 | 0.6031 | 0.5881 |
63
- | 0.5552 | 13.89 | 1736 | 0.9003 | 0.6962 | 0.6240 | 0.6160 | 0.6191 |
64
- | 0.4932 | 15.87 | 1984 | 0.8979 | 0.6982 | 0.6266 | 0.6231 | 0.6245 |
65
- | 0.4446 | 17.86 | 2232 | 0.9104 | 0.7002 | 0.6310 | 0.6290 | 0.6298 |
66
- | 0.4084 | 19.84 | 2480 | 0.9284 | 0.7002 | 0.6278 | 0.6255 | 0.6264 |
67
- | 0.3763 | 21.82 | 2728 | 0.9228 | 0.7082 | 0.6436 | 0.6380 | 0.6398 |
68
- | 0.3575 | 23.81 | 2976 | 0.9319 | 0.6982 | 0.6327 | 0.6314 | 0.6320 |
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [google/muril-base-cased](https://huggingface.co/google/muril-base-cased) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 1.2296
23
+ - Accuracy: 0.7002
24
+ - Precision: 0.6399
25
+ - Recall: 0.6265
26
+ - F1: 0.6273
27
 
28
  ## Model description
29
 
 
48
  - seed: 43
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
+ - num_epochs: 35
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
57
+ | 1.0588 | 1.98 | 248 | 0.9827 | 0.5815 | 0.3985 | 0.5400 | 0.4263 |
58
+ | 0.9378 | 3.97 | 496 | 0.9008 | 0.5976 | 0.3943 | 0.5477 | 0.4338 |
59
+ | 0.8398 | 5.95 | 744 | 0.8357 | 0.5956 | 0.4079 | 0.5579 | 0.4378 |
60
+ | 0.7621 | 7.94 | 992 | 0.8357 | 0.6157 | 0.5545 | 0.5605 | 0.4716 |
61
+ | 0.6944 | 9.92 | 1240 | 0.8643 | 0.6499 | 0.5919 | 0.5874 | 0.5452 |
62
+ | 0.632 | 11.9 | 1488 | 0.8697 | 0.6781 | 0.6075 | 0.6083 | 0.5959 |
63
+ | 0.5632 | 13.89 | 1736 | 0.9161 | 0.6962 | 0.6136 | 0.6001 | 0.6047 |
64
+ | 0.4945 | 15.87 | 1984 | 0.8818 | 0.6861 | 0.6081 | 0.6109 | 0.6093 |
65
+ | 0.4221 | 17.86 | 2232 | 0.9333 | 0.7042 | 0.6350 | 0.6350 | 0.6348 |
66
+ | 0.3725 | 19.84 | 2480 | 0.9893 | 0.6982 | 0.6279 | 0.6168 | 0.6193 |
67
+ | 0.324 | 21.82 | 2728 | 0.9935 | 0.6922 | 0.6298 | 0.6169 | 0.6163 |
68
+ | 0.2864 | 23.81 | 2976 | 1.0814 | 0.7042 | 0.6400 | 0.6233 | 0.6243 |
69
+ | 0.2577 | 25.79 | 3224 | 1.1441 | 0.7082 | 0.6455 | 0.6302 | 0.6337 |
70
+ | 0.2336 | 27.78 | 3472 | 1.1693 | 0.6982 | 0.6405 | 0.6242 | 0.6254 |
71
+ | 0.2155 | 29.76 | 3720 | 1.1397 | 0.7042 | 0.6456 | 0.6405 | 0.6396 |
72
+ | 0.2086 | 31.74 | 3968 | 1.1803 | 0.7002 | 0.6408 | 0.6302 | 0.6278 |
73
+ | 0.1923 | 33.73 | 4216 | 1.2296 | 0.7002 | 0.6399 | 0.6265 | 0.6273 |
74
 
75
 
76
  ### Framework versions