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
20d7620
路
1 Parent(s): e0a5f52

End of training

Browse files
Files changed (4) hide show
  1. README.md +42 -42
  2. model.safetensors +1 -1
  3. runs/Dec02_19-18-50_Software-AI/events.out.tfevents.1701532130.Software-AI.21828.6 +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: 2.3917
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: 3.125e-06
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
- | 0.0242 | 0.12 | 500 | 2.3895 |
52
- | 0.0834 | 0.25 | 1000 | 2.4284 |
53
- | 0.2221 | 0.38 | 1500 | 1.9002 |
54
- | 0.3264 | 0.5 | 2000 | 1.4454 |
55
- | 0.286 | 0.62 | 2500 | 1.4277 |
56
- | 0.2499 | 0.75 | 3000 | 1.4548 |
57
- | 0.2359 | 0.88 | 3500 | 1.4717 |
58
- | 0.2149 | 1.0 | 4000 | 1.4957 |
59
- | 0.1637 | 1.12 | 4500 | 1.6380 |
60
- | 0.1513 | 1.25 | 5000 | 1.7106 |
61
- | 0.157 | 1.38 | 5500 | 1.7514 |
62
- | 0.1501 | 1.5 | 6000 | 1.7322 |
63
- | 0.1511 | 1.62 | 6500 | 1.7126 |
64
- | 0.1464 | 1.75 | 7000 | 1.7646 |
65
- | 0.1552 | 1.88 | 7500 | 1.7580 |
66
- | 0.1468 | 2.0 | 8000 | 1.7727 |
67
- | 0.1136 | 2.12 | 8500 | 1.9067 |
68
- | 0.1181 | 2.25 | 9000 | 1.9514 |
69
- | 0.1243 | 2.38 | 9500 | 1.9811 |
70
- | 0.1137 | 2.5 | 10000 | 2.0183 |
71
- | 0.1229 | 2.62 | 10500 | 2.0141 |
72
- | 0.1144 | 2.75 | 11000 | 2.0105 |
73
- | 0.1212 | 2.88 | 11500 | 2.0363 |
74
- | 0.1185 | 3.0 | 12000 | 2.0345 |
75
- | 0.0892 | 3.12 | 12500 | 2.1508 |
76
- | 0.0937 | 3.25 | 13000 | 2.1875 |
77
- | 0.0956 | 3.38 | 13500 | 2.2057 |
78
- | 0.0876 | 3.5 | 14000 | 2.2200 |
79
- | 0.1032 | 3.62 | 14500 | 2.2411 |
80
- | 0.0997 | 3.75 | 15000 | 2.2433 |
81
- | 0.0978 | 3.88 | 15500 | 2.2572 |
82
- | 0.0974 | 4.0 | 16000 | 2.2873 |
83
- | 0.0773 | 4.12 | 16500 | 2.3254 |
84
- | 0.0795 | 4.25 | 17000 | 2.3504 |
85
- | 0.0885 | 4.38 | 17500 | 2.3555 |
86
- | 0.0784 | 4.5 | 18000 | 2.3785 |
87
- | 0.0865 | 4.62 | 18500 | 2.3804 |
88
- | 0.0768 | 4.75 | 19000 | 2.3799 |
89
- | 0.084 | 4.88 | 19500 | 2.3895 |
90
- | 0.0807 | 5.0 | 20000 | 2.3917 |
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: 2.1007
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 1.5625e-06
40
  - train_batch_size: 16
41
  - eval_batch_size: 16
42
  - seed: 42
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 0.0157 | 0.12 | 500 | 2.3489 |
52
+ | 0.0549 | 0.25 | 1000 | 2.5113 |
53
+ | 0.1605 | 0.38 | 1500 | 2.1880 |
54
+ | 0.256 | 0.5 | 2000 | 1.8072 |
55
+ | 0.2326 | 0.62 | 2500 | 1.7167 |
56
+ | 0.2736 | 0.75 | 3000 | 1.5287 |
57
+ | 0.2506 | 0.88 | 3500 | 1.5003 |
58
+ | 0.2254 | 1.0 | 4000 | 1.5040 |
59
+ | 0.1609 | 1.12 | 4500 | 1.6583 |
60
+ | 0.1488 | 1.25 | 5000 | 1.7421 |
61
+ | 0.1542 | 1.38 | 5500 | 1.7805 |
62
+ | 0.1478 | 1.5 | 6000 | 1.7781 |
63
+ | 0.1501 | 1.62 | 6500 | 1.7627 |
64
+ | 0.1448 | 1.75 | 7000 | 1.7906 |
65
+ | 0.1499 | 1.88 | 7500 | 1.7947 |
66
+ | 0.1435 | 2.0 | 8000 | 1.8035 |
67
+ | 0.1279 | 2.12 | 8500 | 1.8594 |
68
+ | 0.1303 | 2.25 | 9000 | 1.8789 |
69
+ | 0.1384 | 2.38 | 9500 | 1.8980 |
70
+ | 0.124 | 2.5 | 10000 | 1.9347 |
71
+ | 0.1345 | 2.62 | 10500 | 1.9211 |
72
+ | 0.1237 | 2.75 | 11000 | 1.9283 |
73
+ | 0.1304 | 2.88 | 11500 | 1.9416 |
74
+ | 0.1258 | 3.0 | 12000 | 1.9489 |
75
+ | 0.1092 | 3.12 | 12500 | 1.9973 |
76
+ | 0.1146 | 3.25 | 13000 | 2.0114 |
77
+ | 0.1156 | 3.38 | 13500 | 2.0210 |
78
+ | 0.1076 | 3.5 | 14000 | 2.0272 |
79
+ | 0.1235 | 3.62 | 14500 | 2.0330 |
80
+ | 0.1195 | 3.75 | 15000 | 2.0305 |
81
+ | 0.1196 | 3.88 | 15500 | 2.0372 |
82
+ | 0.1159 | 4.0 | 16000 | 2.0504 |
83
+ | 0.1042 | 4.12 | 16500 | 2.0632 |
84
+ | 0.1047 | 4.25 | 17000 | 2.0779 |
85
+ | 0.1132 | 4.38 | 17500 | 2.0810 |
86
+ | 0.1051 | 4.5 | 18000 | 2.0899 |
87
+ | 0.1113 | 4.62 | 18500 | 2.0969 |
88
+ | 0.1011 | 4.75 | 19000 | 2.0972 |
89
+ | 0.1125 | 4.88 | 19500 | 2.1002 |
90
+ | 0.1053 | 5.0 | 20000 | 2.1007 |
91
 
92
 
93
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0263a53aef24222e6d304c621dc0cfcf03d945f74d565bf30281e139f2697faf
3
  size 44381360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48ca923b3abc2c31c973cea13dd25c268e5948b65c68237bc1646fdf0b13d604
3
  size 44381360
runs/Dec02_19-18-50_Software-AI/events.out.tfevents.1701532130.Software-AI.21828.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:339da275b12201378968a36a40fa43d6ca520246bdcb81abd70508d445296779
3
+ size 22031
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2239acbee13f0ab317d1615413df300209b09fd9bb294ec808ae45cf1b3495ac
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2099ff6be5b9f11509b9535ad9eadf1dd52ab7d6f64dcd0b9e7ccc4f6b57c74
3
  size 4155