Hugging Face's logo

bencyc1129
/
art-des-bert-large-cased

Fill-Mask
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Metrics Community
bencyc1129 commited on
Commit
a1a7f07
·
verified ·
1 Parent(s): 74ab064

Model save

Browse files
Files changed (3) hide show
  1. README.md +25 -19
  2. model.safetensors +1 -1
  3. runs/Apr21_11-02-40_36f62ca2a075/events.out.tfevents.1713697362.36f62ca2a075.2070.0 +2 -2
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
- base_model: bert-large-cased
6
  model-index:
7
  - name: art-des-bert-large-cased
8
  results: []
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.7025
19
 
20
  ## Model description
21
 
@@ -38,29 +38,35 @@ The following hyperparameters were used during training:
38
  - train_batch_size: 8
39
  - eval_batch_size: 8
40
  - seed: 42
 
 
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - num_epochs: 100
44
 
45
  ### Training results
46
 
47
- | Training Loss | Epoch | Step | Validation Loss |
48
- |:-------------:|:-----:|:-----:|:---------------:|
49
- | 1.6755 | 6.49 | 1000 | 1.6113 |
50
- | 1.1162 | 12.99 | 2000 | 1.5335 |
51
- | 0.8664 | 19.48 | 3000 | 1.4363 |
52
- | 0.6844 | 25.97 | 4000 | 1.5348 |
53
- | 0.5577 | 32.47 | 5000 | 1.4426 |
54
- | 0.4742 | 38.96 | 6000 | 1.6470 |
55
- | 0.3975 | 45.45 | 7000 | 1.4066 |
56
- | 0.34 | 51.95 | 8000 | 1.4474 |
57
- | 0.2929 | 58.44 | 9000 | 1.6889 |
58
- | 0.2661 | 64.94 | 10000 | 1.6851 |
59
- | 0.2292 | 71.43 | 11000 | 1.5536 |
60
- | 0.2058 | 77.92 | 12000 | 1.6485 |
61
- | 0.1989 | 84.42 | 13000 | 1.7446 |
62
- | 0.1619 | 90.91 | 14000 | 1.6084 |
63
- | 0.1588 | 97.4 | 15000 | 1.7025 |
 
 
 
 
64
 
65
 
66
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: bert-large-cased
4
  tags:
5
  - generated_from_trainer
 
6
  model-index:
7
  - name: art-des-bert-large-cased
8
  results: []
 
15
 
16
  This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.2776
19
 
20
  ## Model description
21
 
 
38
  - train_batch_size: 8
39
  - eval_batch_size: 8
40
  - seed: 42
41
+ - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 64
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - num_epochs: 100
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 1.8053 | 5.19 | 100 | 1.4663 |
52
+ | 1.3212 | 10.39 | 200 | 1.3795 |
53
+ | 1.0223 | 15.58 | 300 | 1.3545 |
54
+ | 0.8991 | 20.78 | 400 | 1.3239 |
55
+ | 0.7579 | 25.97 | 500 | 1.3276 |
56
+ | 0.6554 | 31.17 | 600 | 1.3435 |
57
+ | 0.5786 | 36.36 | 700 | 1.2276 |
58
+ | 0.5386 | 41.56 | 800 | 1.1930 |
59
+ | 0.479 | 46.75 | 900 | 1.2091 |
60
+ | 0.4336 | 51.95 | 1000 | 1.0554 |
61
+ | 0.3776 | 57.14 | 1100 | 1.4044 |
62
+ | 0.3582 | 62.34 | 1200 | 1.1651 |
63
+ | 0.3343 | 67.53 | 1300 | 1.2394 |
64
+ | 0.3093 | 72.73 | 1400 | 1.1313 |
65
+ | 0.2952 | 77.92 | 1500 | 1.2107 |
66
+ | 0.2845 | 83.12 | 1600 | 1.2804 |
67
+ | 0.2585 | 88.31 | 1700 | 1.1700 |
68
+ | 0.2548 | 93.51 | 1800 | 1.2391 |
69
+ | 0.2581 | 98.7 | 1900 | 1.2776 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d97d1b52404fbf295d0973a32d13d0db2420612972f6ca43c0104a41ed5e8aab
3
  size 1334488416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74ae0550418023c2aff0e69be9c12051ba04e4189ec1154d0da2906a844ef969
3
  size 1334488416
runs/Apr21_11-02-40_36f62ca2a075/events.out.tfevents.1713697362.36f62ca2a075.2070.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f93a2ccf47b3d0dab4b2a0497c7bb614cce8167efe0f91def7758fadd1ecf37
3
- size 13424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:670a5e04da1da9ab9a4be4844e304ef54f2aa8a7457c1dfadd017144d01c488c
3
+ size 14260