Hugging Face's logo

makhataei
/
qa-persian-albert-fa-zwnj-base-v2

Question Answering
Transformers
TensorBoard
Safetensors
albert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
makhataei commited on
Commit
991d5c5
路
1 Parent(s): 8f32450

End of training

Browse files
Files changed (4) hide show
  1. README.md +42 -42
  2. model.safetensors +1 -1
  3. runs/Dec02_22-53-02_Software-AI/events.out.tfevents.1701544983.Software-AI.21828.8 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [makhataei/qa-persian-albert-fa-zwnj-base-v2](https://huggingface.co/makhataei/qa-persian-albert-fa-zwnj-base-v2) on the pquad dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 2.0167
21
 
22
  ## Model description
23
 
@@ -36,7 +36,7 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 7.8125e-07
40
  - train_batch_size: 16
41
  - eval_batch_size: 16
42
  - seed: 42
@@ -48,46 +48,46 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:-----:|:---------------:|
51
- | 0.0122 | 0.12 | 500 | 2.2415 |
52
- | 0.0401 | 0.25 | 1000 | 2.4681 |
53
- | 0.1308 | 0.38 | 1500 | 2.3118 |
54
- | 0.218 | 0.5 | 2000 | 2.0826 |
55
- | 0.2057 | 0.62 | 2500 | 1.9572 |
56
- | 0.2441 | 0.75 | 3000 | 1.8029 |
57
- | 0.2311 | 0.88 | 3500 | 1.7156 |
58
- | 0.2439 | 1.0 | 4000 | 1.6101 |
59
- | 0.1531 | 1.12 | 4500 | 1.7252 |
60
- | 0.1405 | 1.25 | 5000 | 1.7982 |
61
- | 0.1478 | 1.38 | 5500 | 1.8344 |
62
- | 0.141 | 1.5 | 6000 | 1.8482 |
63
- | 0.1426 | 1.62 | 6500 | 1.8463 |
64
- | 0.1376 | 1.75 | 7000 | 1.8652 |
65
- | 0.1419 | 1.88 | 7500 | 1.8663 |
66
- | 0.1361 | 2.0 | 8000 | 1.8739 |
67
- | 0.1321 | 2.12 | 8500 | 1.8946 |
68
- | 0.1337 | 2.25 | 9000 | 1.8995 |
69
- | 0.1411 | 2.38 | 9500 | 1.9112 |
70
- | 0.1258 | 2.5 | 10000 | 1.9391 |
71
- | 0.1373 | 2.62 | 10500 | 1.9296 |
72
- | 0.1241 | 2.75 | 11000 | 1.9384 |
73
- | 0.1328 | 2.88 | 11500 | 1.9444 |
74
- | 0.1266 | 3.0 | 12000 | 1.9511 |
75
- | 0.1176 | 3.12 | 12500 | 1.9737 |
76
- | 0.1231 | 3.25 | 13000 | 1.9778 |
77
- | 0.1246 | 3.38 | 13500 | 1.9836 |
78
- | 0.1166 | 3.5 | 14000 | 1.9863 |
79
- | 0.1326 | 3.62 | 14500 | 1.9850 |
80
- | 0.1282 | 3.75 | 15000 | 1.9833 |
81
- | 0.1275 | 3.88 | 15500 | 1.9858 |
82
- | 0.1228 | 4.0 | 16000 | 1.9928 |
83
- | 0.1169 | 4.12 | 16500 | 1.9970 |
84
- | 0.116 | 4.25 | 17000 | 2.0050 |
85
- | 0.1259 | 4.38 | 17500 | 2.0058 |
86
- | 0.1161 | 4.5 | 18000 | 2.0098 |
87
- | 0.1234 | 4.62 | 18500 | 2.0140 |
88
- | 0.1117 | 4.75 | 19000 | 2.0149 |
89
- | 0.1254 | 4.88 | 19500 | 2.0164 |
90
- | 0.1182 | 5.0 | 20000 | 2.0167 |
91
 
92
 
93
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [makhataei/qa-persian-albert-fa-zwnj-base-v2](https://huggingface.co/makhataei/qa-persian-albert-fa-zwnj-base-v2) on the pquad dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.9991
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 3.90625e-07
40
  - train_batch_size: 16
41
  - eval_batch_size: 16
42
  - seed: 42
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 0.0101 | 0.12 | 500 | 2.1486 |
52
+ | 0.0342 | 0.25 | 1000 | 2.3710 |
53
+ | 0.1133 | 0.38 | 1500 | 2.3393 |
54
+ | 0.1976 | 0.5 | 2000 | 2.2309 |
55
+ | 0.1944 | 0.62 | 2500 | 2.1436 |
56
+ | 0.2336 | 0.75 | 3000 | 2.0430 |
57
+ | 0.2277 | 0.88 | 3500 | 1.9529 |
58
+ | 0.2443 | 1.0 | 4000 | 1.8560 |
59
+ | 0.1506 | 1.12 | 4500 | 1.8765 |
60
+ | 0.1369 | 1.25 | 5000 | 1.9003 |
61
+ | 0.1435 | 1.38 | 5500 | 1.9158 |
62
+ | 0.1365 | 1.5 | 6000 | 1.9251 |
63
+ | 0.1387 | 1.62 | 6500 | 1.9243 |
64
+ | 0.1323 | 1.75 | 7000 | 1.9363 |
65
+ | 0.1369 | 1.88 | 7500 | 1.9341 |
66
+ | 0.1312 | 2.0 | 8000 | 1.9389 |
67
+ | 0.1339 | 2.12 | 8500 | 1.9453 |
68
+ | 0.1349 | 2.25 | 9000 | 1.9435 |
69
+ | 0.1418 | 2.38 | 9500 | 1.9479 |
70
+ | 0.1256 | 2.5 | 10000 | 1.9647 |
71
+ | 0.1375 | 2.62 | 10500 | 1.9592 |
72
+ | 0.1237 | 2.75 | 11000 | 1.9647 |
73
+ | 0.1326 | 2.88 | 11500 | 1.9689 |
74
+ | 0.126 | 3.0 | 12000 | 1.9736 |
75
+ | 0.1217 | 3.12 | 12500 | 1.9841 |
76
+ | 0.1274 | 3.25 | 13000 | 1.9852 |
77
+ | 0.1285 | 3.38 | 13500 | 1.9878 |
78
+ | 0.1202 | 3.5 | 14000 | 1.9885 |
79
+ | 0.1365 | 3.62 | 14500 | 1.9865 |
80
+ | 0.1319 | 3.75 | 15000 | 1.9847 |
81
+ | 0.131 | 3.88 | 15500 | 1.9854 |
82
+ | 0.1258 | 4.0 | 16000 | 1.9887 |
83
+ | 0.1233 | 4.12 | 16500 | 1.9899 |
84
+ | 0.1211 | 4.25 | 17000 | 1.9936 |
85
+ | 0.1326 | 4.38 | 17500 | 1.9935 |
86
+ | 0.1216 | 4.5 | 18000 | 1.9955 |
87
+ | 0.1292 | 4.62 | 18500 | 1.9976 |
88
+ | 0.1166 | 4.75 | 19000 | 1.9982 |
89
+ | 0.1313 | 4.88 | 19500 | 1.9990 |
90
+ | 0.1242 | 5.0 | 20000 | 1.9991 |
91
 
92
 
93
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:122ffa9b984bac2111b2dd9df163ec73d0d0985fc24d74eac675bcf347b55623
3
  size 44381360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:568da479779fe88c03de16d4901635f8328f166736b6f5a818f6ae19d9e52cf6
3
  size 44381360
runs/Dec02_22-53-02_Software-AI/events.out.tfevents.1701544983.Software-AI.21828.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d90481bff8ef03c1603ace12a41768a6fe992d734f175a5e63d0e9cb1ea64c0
3
+ size 22032
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd50438b1918fb5bc606ba42d8eaa76a940b24c0ebd4b178f1a1e1740c95cc5e
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285a6492f74cc05a51f33c05397fce7b17a22607a6c5f084280d765029f21997
3
  size 4155