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
c29e421
路
1 Parent(s): 3081589

End of training

Browse files
Files changed (16) hide show
  1. README.md +48 -10
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Dec02_08-01-05_Software-AI/events.out.tfevents.1701491466.Software-AI.14591.0 +3 -0
  5. runs/Dec02_08-01-53_Software-AI/events.out.tfevents.1701491513.Software-AI.15993.0 +3 -0
  6. runs/Dec02_08-02-54_Software-AI/events.out.tfevents.1701491575.Software-AI.17159.0 +3 -0
  7. runs/Dec02_08-03-15_Software-AI/events.out.tfevents.1701491596.Software-AI.17599.0 +3 -0
  8. runs/Dec02_08-03-31_Software-AI/events.out.tfevents.1701491611.Software-AI.17979.0 +3 -0
  9. runs/Dec02_08-03-48_Software-AI/events.out.tfevents.1701491628.Software-AI.18340.0 +3 -0
  10. runs/Dec02_08-04-02_Software-AI/events.out.tfevents.1701491643.Software-AI.18684.0 +3 -0
  11. runs/Dec02_08-04-20_Software-AI/events.out.tfevents.1701491660.Software-AI.19058.0 +3 -0
  12. runs/Dec02_08-04-49_Software-AI/events.out.tfevents.1701491689.Software-AI.19688.0 +3 -0
  13. runs/Dec02_08-06-47_Software-AI/events.out.tfevents.1701491808.Software-AI.21828.0 +3 -0
  14. special_tokens_map.json +42 -6
  15. tokenizer_config.json +4 -0
  16. training_args.bin +2 -2
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: HooshvareLab/albert-fa-zwnj-base-v2
4
  tags:
5
  - generated_from_trainer
6
  datasets:
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # qa-persian-albert-fa-zwnj-base-v2
17
 
18
- This model is a fine-tuned version of [HooshvareLab/albert-fa-zwnj-base-v2](https://huggingface.co/HooshvareLab/albert-fa-zwnj-base-v2) on the pquad dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.0456
21
 
22
  ## Model description
23
 
@@ -36,25 +36,63 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 1e-05
40
- - train_batch_size: 128
41
- - eval_batch_size: 128
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 2
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:-----:|:---------------:|
51
- | 1.0575 | 1.0 | 8000 | 1.1253 |
52
- | 0.8976 | 2.0 | 16000 | 1.0456 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
 
54
 
55
  ### Framework versions
56
 
57
  - Transformers 4.35.2
58
- - Pytorch 2.1.0+cu118
59
  - Datasets 2.15.0
60
  - Tokenizers 0.15.0
 
1
  ---
2
  license: apache-2.0
3
+ base_model: makhataei/qa-persian-albert-fa-zwnj-base-v2
4
  tags:
5
  - generated_from_trainer
6
  datasets:
 
15
 
16
  # qa-persian-albert-fa-zwnj-base-v2
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: 1.4440
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 0.0001
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 16
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 5
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 1.5731 | 0.12 | 500 | 1.6899 |
52
+ | 1.4759 | 0.25 | 1000 | 1.4951 |
53
+ | 1.3844 | 0.38 | 1500 | 1.5161 |
54
+ | 1.3116 | 0.5 | 2000 | 1.3618 |
55
+ | 1.3055 | 0.62 | 2500 | 1.3795 |
56
+ | 1.2364 | 0.75 | 3000 | 1.3386 |
57
+ | 1.2189 | 0.88 | 3500 | 1.3131 |
58
+ | 1.1737 | 1.0 | 4000 | 1.2202 |
59
+ | 1.0047 | 1.12 | 4500 | 1.2268 |
60
+ | 0.9573 | 1.25 | 5000 | 1.3119 |
61
+ | 0.978 | 1.38 | 5500 | 1.1918 |
62
+ | 0.9655 | 1.5 | 6000 | 1.1896 |
63
+ | 0.9505 | 1.62 | 6500 | 1.1730 |
64
+ | 0.9379 | 1.75 | 7000 | 1.1215 |
65
+ | 0.9237 | 1.88 | 7500 | 1.0691 |
66
+ | 0.8911 | 2.0 | 8000 | 1.0819 |
67
+ | 0.6874 | 2.12 | 8500 | 1.1670 |
68
+ | 0.6919 | 2.25 | 9000 | 1.1506 |
69
+ | 0.7118 | 2.38 | 9500 | 1.1352 |
70
+ | 0.7062 | 2.5 | 10000 | 1.1762 |
71
+ | 0.7077 | 2.62 | 10500 | 1.1072 |
72
+ | 0.7055 | 2.75 | 11000 | 1.0788 |
73
+ | 0.6869 | 2.88 | 11500 | 1.0863 |
74
+ | 0.6707 | 3.0 | 12000 | 1.0167 |
75
+ | 0.4597 | 3.12 | 12500 | 1.2769 |
76
+ | 0.4652 | 3.25 | 13000 | 1.1891 |
77
+ | 0.4673 | 3.38 | 13500 | 1.1466 |
78
+ | 0.4644 | 3.5 | 14000 | 1.1818 |
79
+ | 0.4701 | 3.62 | 14500 | 1.1939 |
80
+ | 0.4765 | 3.75 | 15000 | 1.1518 |
81
+ | 0.4537 | 3.88 | 15500 | 1.1528 |
82
+ | 0.4164 | 4.0 | 16000 | 1.2239 |
83
+ | 0.2465 | 4.12 | 16500 | 1.4501 |
84
+ | 0.2495 | 4.25 | 17000 | 1.3717 |
85
+ | 0.263 | 4.38 | 17500 | 1.4030 |
86
+ | 0.2423 | 4.5 | 18000 | 1.4249 |
87
+ | 0.2297 | 4.62 | 18500 | 1.4387 |
88
+ | 0.227 | 4.75 | 19000 | 1.4600 |
89
+ | 0.239 | 4.88 | 19500 | 1.4452 |
90
+ | 0.2307 | 5.0 | 20000 | 1.4440 |
91
 
92
 
93
  ### Framework versions
94
 
95
  - Transformers 4.35.2
96
+ - Pytorch 2.0.1+cu117
97
  - Datasets 2.15.0
98
  - Tokenizers 0.15.0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "HooshvareLab/albert-fa-zwnj-base-v2",
3
  "architectures": [
4
  "AlbertForQuestionAnswering"
5
  ],
 
1
  {
2
+ "_name_or_path": "makhataei/qa-persian-albert-fa-zwnj-base-v2",
3
  "architectures": [
4
  "AlbertForQuestionAnswering"
5
  ],
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0590edf20d46e1ef6f204a0ebef4f2318a1b0999f25fe3adbf65aca81354536
3
  size 44381360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a7269e1c1a55a9beb75143243ed1ec44a0c1c02dcaa8f757d12df54bda3b231
3
  size 44381360
runs/Dec02_08-01-05_Software-AI/events.out.tfevents.1701491466.Software-AI.14591.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c0d21b4973fec1df7128e06cec31ff439dde6c02d99f888ab496a2708fb094b
3
+ size 4485
runs/Dec02_08-01-53_Software-AI/events.out.tfevents.1701491513.Software-AI.15993.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:304666ba506c39358a1596bf4daa087235f757d7fa2c4e48ccd906481fabf057
3
+ size 22068
runs/Dec02_08-02-54_Software-AI/events.out.tfevents.1701491575.Software-AI.17159.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:465c7a648761b7355b205b8381f8ad04aae0d8d95387fd27a772693392d5db6e
3
+ size 4483
runs/Dec02_08-03-15_Software-AI/events.out.tfevents.1701491596.Software-AI.17599.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:892a21bbf0f2eb229ee14b0773a75b19390aeeb549961d69b49953f6e37631c1
3
+ size 4483
runs/Dec02_08-03-31_Software-AI/events.out.tfevents.1701491611.Software-AI.17979.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc29370a780c81d08829eabe6dd47ffcdd6081de212fb880ebaf50e2db7711be
3
+ size 4483
runs/Dec02_08-03-48_Software-AI/events.out.tfevents.1701491628.Software-AI.18340.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c3c4c589b19b63a91f8e7f254b6e41117a4810c383901c8b8a5bd67653d112f
3
+ size 4483
runs/Dec02_08-04-02_Software-AI/events.out.tfevents.1701491643.Software-AI.18684.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eb50b91f5a512217b587c718c67d75c895f5f3a7669bc20318e0a4cc4a1b203
3
+ size 4483
runs/Dec02_08-04-20_Software-AI/events.out.tfevents.1701491660.Software-AI.19058.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8075b5f282bdd3d4a75aae6aa6416c70281ec1e8503c12057498c1e9eac78ef
3
+ size 4483
runs/Dec02_08-04-49_Software-AI/events.out.tfevents.1701491689.Software-AI.19688.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac378ec4e6ea6da66cd9665fc60495d38e72d78683fb9c41e12b9a2d1aed8cce
3
+ size 4483
runs/Dec02_08-06-47_Software-AI/events.out.tfevents.1701491808.Software-AI.21828.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22a58e4886bbc0c3fe805cf31e041e8695d63da13af7014c1a817bd6bb34727a
3
+ size 22027
special_tokens_map.json CHANGED
@@ -1,7 +1,25 @@
1
  {
2
- "bos_token": "[CLS]",
3
- "cls_token": "[CLS]",
4
- "eos_token": "[SEP]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "mask_token": {
6
  "content": "[MASK]",
7
  "lstrip": true,
@@ -9,7 +27,25 @@
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
- "pad_token": "<pad>",
13
- "sep_token": "[SEP]",
14
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "mask_token": {
24
  "content": "[MASK]",
25
  "lstrip": true,
 
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
  }
tokenizer_config.json CHANGED
@@ -904,10 +904,14 @@
904
  "eos_token": "[SEP]",
905
  "keep_accents": false,
906
  "mask_token": "[MASK]",
 
907
  "model_max_length": 512,
908
  "pad_token": "<pad>",
909
  "remove_space": true,
910
  "sep_token": "[SEP]",
 
911
  "tokenizer_class": "AlbertTokenizer",
 
 
912
  "unk_token": "<unk>"
913
  }
 
904
  "eos_token": "[SEP]",
905
  "keep_accents": false,
906
  "mask_token": "[MASK]",
907
+ "max_length": 512,
908
  "model_max_length": 512,
909
  "pad_token": "<pad>",
910
  "remove_space": true,
911
  "sep_token": "[SEP]",
912
+ "stride": 256,
913
  "tokenizer_class": "AlbertTokenizer",
914
+ "truncation_side": "right",
915
+ "truncation_strategy": "only_second",
916
  "unk_token": "<unk>"
917
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d7afd4fb7d2066a1346e34ece2c590ce39699a13563541493eefcc0ff847c4e
3
- size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96156d6ac9d294f2d0a5e8257ef1f40e2feedd2adb3fbd88285bcb89a752cb20
3
+ size 4155