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
47ad8cb
路
1 Parent(s): 6d4b075

End of training

Browse files
Files changed (4) hide show
  1. README.md +42 -42
  2. model.safetensors +1 -1
  3. runs/Dec02_13-54-39_Software-AI/events.out.tfevents.1701512680.Software-AI.21828.3 +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: 3.7387
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: 2.5e-05
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
- | 0.3611 | 0.12 | 500 | 1.3313 |
52
- | 0.3187 | 0.25 | 1000 | 1.3786 |
53
- | 0.3168 | 0.38 | 1500 | 1.4039 |
54
- | 0.2942 | 0.5 | 2000 | 1.4682 |
55
- | 0.2818 | 0.62 | 2500 | 1.4486 |
56
- | 0.268 | 0.75 | 3000 | 1.5273 |
57
- | 0.2755 | 0.88 | 3500 | 1.4502 |
58
- | 0.2715 | 1.0 | 4000 | 1.4534 |
59
- | 0.1935 | 1.12 | 4500 | 1.7062 |
60
- | 0.1684 | 1.25 | 5000 | 1.6853 |
61
- | 0.1817 | 1.38 | 5500 | 1.6821 |
62
- | 0.183 | 1.5 | 6000 | 1.7490 |
63
- | 0.1746 | 1.62 | 6500 | 1.7218 |
64
- | 0.1822 | 1.75 | 7000 | 1.7045 |
65
- | 0.1914 | 1.88 | 7500 | 1.7221 |
66
- | 0.1814 | 2.0 | 8000 | 1.7461 |
67
- | 0.0811 | 2.12 | 8500 | 2.3278 |
68
- | 0.0978 | 2.25 | 9000 | 2.3806 |
69
- | 0.1041 | 2.38 | 9500 | 2.2242 |
70
- | 0.1005 | 2.5 | 10000 | 2.2778 |
71
- | 0.1033 | 2.62 | 10500 | 2.3396 |
72
- | 0.1013 | 2.75 | 11000 | 2.3715 |
73
- | 0.1072 | 2.88 | 11500 | 2.4198 |
74
- | 0.0994 | 3.0 | 12000 | 2.3849 |
75
- | 0.0385 | 3.12 | 12500 | 2.9489 |
76
- | 0.0432 | 3.25 | 13000 | 3.0937 |
77
- | 0.0528 | 3.38 | 13500 | 3.1676 |
78
- | 0.052 | 3.5 | 14000 | 3.1766 |
79
- | 0.0573 | 3.62 | 14500 | 3.1954 |
80
- | 0.0546 | 3.75 | 15000 | 3.1977 |
81
- | 0.0527 | 3.88 | 15500 | 3.0321 |
82
- | 0.0479 | 4.0 | 16000 | 3.1803 |
83
- | 0.014 | 4.12 | 16500 | 3.5650 |
84
- | 0.0198 | 4.25 | 17000 | 3.4434 |
85
- | 0.0212 | 4.38 | 17500 | 3.7113 |
86
- | 0.0169 | 4.5 | 18000 | 3.7373 |
87
- | 0.0205 | 4.62 | 18500 | 3.7013 |
88
- | 0.0203 | 4.75 | 19000 | 3.7239 |
89
- | 0.0209 | 4.88 | 19500 | 3.7411 |
90
- | 0.0213 | 5.0 | 20000 | 3.7387 |
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: 3.7164
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 1.25e-05
40
  - train_batch_size: 16
41
  - eval_batch_size: 16
42
  - seed: 42
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 0.1262 | 0.12 | 500 | 1.9073 |
52
+ | 0.3307 | 0.25 | 1000 | 1.3569 |
53
+ | 0.2998 | 0.38 | 1500 | 1.3634 |
54
+ | 0.2767 | 0.5 | 2000 | 1.4001 |
55
+ | 0.26 | 0.62 | 2500 | 1.4331 |
56
+ | 0.2377 | 0.75 | 3000 | 1.5280 |
57
+ | 0.2339 | 0.88 | 3500 | 1.4662 |
58
+ | 0.2235 | 1.0 | 4000 | 1.5150 |
59
+ | 0.1615 | 1.12 | 4500 | 1.7335 |
60
+ | 0.1434 | 1.25 | 5000 | 1.7218 |
61
+ | 0.1515 | 1.38 | 5500 | 1.7870 |
62
+ | 0.1452 | 1.5 | 6000 | 1.8029 |
63
+ | 0.1404 | 1.62 | 6500 | 1.8195 |
64
+ | 0.1425 | 1.75 | 7000 | 1.8478 |
65
+ | 0.1545 | 1.88 | 7500 | 1.7958 |
66
+ | 0.147 | 2.0 | 8000 | 1.7776 |
67
+ | 0.0632 | 2.12 | 8500 | 2.4265 |
68
+ | 0.0787 | 2.25 | 9000 | 2.4688 |
69
+ | 0.0847 | 2.38 | 9500 | 2.3998 |
70
+ | 0.0786 | 2.5 | 10000 | 2.5091 |
71
+ | 0.0902 | 2.62 | 10500 | 2.5290 |
72
+ | 0.0859 | 2.75 | 11000 | 2.5128 |
73
+ | 0.0865 | 2.88 | 11500 | 2.5786 |
74
+ | 0.0819 | 3.0 | 12000 | 2.5927 |
75
+ | 0.0332 | 3.12 | 12500 | 3.0157 |
76
+ | 0.0375 | 3.25 | 13000 | 3.0698 |
77
+ | 0.0476 | 3.38 | 13500 | 3.0772 |
78
+ | 0.0413 | 3.5 | 14000 | 3.2176 |
79
+ | 0.0488 | 3.62 | 14500 | 3.2552 |
80
+ | 0.0451 | 3.75 | 15000 | 3.2301 |
81
+ | 0.0466 | 3.88 | 15500 | 3.1282 |
82
+ | 0.0363 | 4.0 | 16000 | 3.2980 |
83
+ | 0.0165 | 4.12 | 16500 | 3.4728 |
84
+ | 0.0211 | 4.25 | 17000 | 3.5174 |
85
+ | 0.019 | 4.38 | 17500 | 3.6270 |
86
+ | 0.0204 | 4.5 | 18000 | 3.7017 |
87
+ | 0.0219 | 4.62 | 18500 | 3.6543 |
88
+ | 0.0226 | 4.75 | 19000 | 3.6998 |
89
+ | 0.0209 | 4.88 | 19500 | 3.7176 |
90
+ | 0.0262 | 5.0 | 20000 | 3.7164 |
91
 
92
 
93
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ab8ff9654986fcd8c6c4b411273ebb6b5d9956b39ba4c2ba9b65b618571754c
3
  size 44381360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb1ccb22b05840e665260574d21c0dee95e520c8f482f7126b478c14cd70a554
3
  size 44381360
runs/Dec02_13-54-39_Software-AI/events.out.tfevents.1701512680.Software-AI.21828.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59b46416ce5632a276b2175d008aaa6f6dc01ae066e913d04c2653c84ef9e1cb
3
+ size 22029
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f2083266f1ce6ff3c8d336ac2e54ad5c2662bd22713690b9fd4a8b0749933bf
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a52392bef4ad6d1fc4fe4db7ff01b7335c889544b60f13a825f7d840442ca526
3
  size 4155