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
4896c70
路
1 Parent(s): b07e642

End of training

Browse files
Files changed (4) hide show
  1. README.md +42 -42
  2. model.safetensors +1 -1
  3. runs/Dec03_02-20-50_Software-AI/events.out.tfevents.1701557450.Software-AI.21828.10 +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: 2.0165
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: 1.953125e-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
- | 0.0081 | 0.12 | 500 | 2.1432 |
52
- | 0.0312 | 0.25 | 1000 | 2.3066 |
53
- | 0.1035 | 0.38 | 1500 | 2.3197 |
54
- | 0.1844 | 0.5 | 2000 | 2.2733 |
55
- | 0.187 | 0.62 | 2500 | 2.2288 |
56
- | 0.2282 | 0.75 | 3000 | 2.1744 |
57
- | 0.2288 | 0.88 | 3500 | 2.1178 |
58
- | 0.2505 | 1.0 | 4000 | 2.0551 |
59
- | 0.1537 | 1.12 | 4500 | 2.0434 |
60
- | 0.1387 | 1.25 | 5000 | 2.0391 |
61
- | 0.1445 | 1.38 | 5500 | 2.0356 |
62
- | 0.1368 | 1.5 | 6000 | 2.0332 |
63
- | 0.1394 | 1.62 | 6500 | 2.0261 |
64
- | 0.1319 | 1.75 | 7000 | 2.0272 |
65
- | 0.1365 | 1.88 | 7500 | 2.0207 |
66
- | 0.1305 | 2.0 | 8000 | 2.0193 |
67
- | 0.1369 | 2.12 | 8500 | 2.0181 |
68
- | 0.1376 | 2.25 | 9000 | 2.0122 |
69
- | 0.1445 | 2.38 | 9500 | 2.0105 |
70
- | 0.1274 | 2.5 | 10000 | 2.0166 |
71
- | 0.1396 | 2.62 | 10500 | 2.0115 |
72
- | 0.1252 | 2.75 | 11000 | 2.0124 |
73
- | 0.1341 | 2.88 | 11500 | 2.0132 |
74
- | 0.1271 | 3.0 | 12000 | 2.0146 |
75
- | 0.125 | 3.12 | 12500 | 2.0185 |
76
- | 0.1312 | 3.25 | 13000 | 2.0179 |
77
- | 0.1319 | 3.38 | 13500 | 2.0184 |
78
- | 0.1235 | 3.5 | 14000 | 2.0178 |
79
- | 0.1403 | 3.62 | 14500 | 2.0159 |
80
- | 0.1356 | 3.75 | 15000 | 2.0139 |
81
- | 0.1344 | 3.88 | 15500 | 2.0132 |
82
- | 0.1288 | 4.0 | 16000 | 2.0142 |
83
- | 0.1282 | 4.12 | 16500 | 2.0139 |
84
- | 0.1251 | 4.25 | 17000 | 2.0152 |
85
- | 0.1377 | 4.38 | 17500 | 2.0146 |
86
- | 0.1261 | 4.5 | 18000 | 2.0153 |
87
- | 0.134 | 4.62 | 18500 | 2.0160 |
88
- | 0.1205 | 4.75 | 19000 | 2.0162 |
89
- | 0.1359 | 4.88 | 19500 | 2.0165 |
90
- | 0.1289 | 5.0 | 20000 | 2.0165 |
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: 2.0805
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 9.765625e-08
40
  - train_batch_size: 16
41
  - eval_batch_size: 16
42
  - seed: 42
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 0.007 | 0.12 | 500 | 2.1441 |
52
+ | 0.029 | 0.25 | 1000 | 2.2431 |
53
+ | 0.0955 | 0.38 | 1500 | 2.2642 |
54
+ | 0.1682 | 0.5 | 2000 | 2.2475 |
55
+ | 0.173 | 0.62 | 2500 | 2.2287 |
56
+ | 0.2117 | 0.75 | 3000 | 2.2037 |
57
+ | 0.217 | 0.88 | 3500 | 2.1763 |
58
+ | 0.2402 | 1.0 | 4000 | 2.1451 |
59
+ | 0.1499 | 1.12 | 4500 | 2.1362 |
60
+ | 0.1348 | 1.25 | 5000 | 2.1309 |
61
+ | 0.1405 | 1.38 | 5500 | 2.1266 |
62
+ | 0.1328 | 1.5 | 6000 | 2.1232 |
63
+ | 0.1363 | 1.62 | 6500 | 2.1177 |
64
+ | 0.1283 | 1.75 | 7000 | 2.1161 |
65
+ | 0.1335 | 1.88 | 7500 | 2.1106 |
66
+ | 0.1277 | 2.0 | 8000 | 2.1078 |
67
+ | 0.1326 | 2.12 | 8500 | 2.1061 |
68
+ | 0.1342 | 2.25 | 9000 | 2.1013 |
69
+ | 0.141 | 2.38 | 9500 | 2.0987 |
70
+ | 0.1265 | 2.5 | 10000 | 2.0990 |
71
+ | 0.1393 | 2.62 | 10500 | 2.0945 |
72
+ | 0.1248 | 2.75 | 11000 | 2.0926 |
73
+ | 0.1335 | 2.88 | 11500 | 2.0909 |
74
+ | 0.1263 | 3.0 | 12000 | 2.0900 |
75
+ | 0.1242 | 3.12 | 12500 | 2.0904 |
76
+ | 0.1305 | 3.25 | 13000 | 2.0890 |
77
+ | 0.1308 | 3.38 | 13500 | 2.0881 |
78
+ | 0.1224 | 3.5 | 14000 | 2.0868 |
79
+ | 0.1393 | 3.62 | 14500 | 2.0851 |
80
+ | 0.1347 | 3.75 | 15000 | 2.0833 |
81
+ | 0.1337 | 3.88 | 15500 | 2.0822 |
82
+ | 0.1277 | 4.0 | 16000 | 2.0820 |
83
+ | 0.1284 | 4.12 | 16500 | 2.0813 |
84
+ | 0.1247 | 4.25 | 17000 | 2.0813 |
85
+ | 0.1373 | 4.38 | 17500 | 2.0806 |
86
+ | 0.1258 | 4.5 | 18000 | 2.0806 |
87
+ | 0.1339 | 4.62 | 18500 | 2.0807 |
88
+ | 0.1203 | 4.75 | 19000 | 2.0805 |
89
+ | 0.1355 | 4.88 | 19500 | 2.0805 |
90
+ | 0.1286 | 5.0 | 20000 | 2.0805 |
91
 
92
 
93
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80c8a6cb7c6ded80241b1ab7b2a484c9e564c7d0ae51bef92c5883e4d725e338
3
  size 44381360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa4f54144f7563eb6c4bc546d7dc694c64b8cf579c0979f083d26cf37dcde187
3
  size 44381360
runs/Dec03_02-20-50_Software-AI/events.out.tfevents.1701557450.Software-AI.21828.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26dcd4c647a72404d162e453b2dabedd6595e4f914065a2009dd5d234588bda4
3
+ size 22033
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9fb77bbf24522594e348dad4b39a1fece33f1e0c32171ed77249759f7add128
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81d2faf6c5f81c8a9c3ee99fed84ca4569dda7b0a41b20e189010decf0077ee0
3
  size 4155