Hugging Face's logo

mwesner
/
bart-mlm

Text2Text Generation
Transformers
PyTorch
bart
generated_from_trainer
Inference Endpoints
Model card Files Community
1
mwesner commited on
Commit
06cf99f
•
1 Parent(s): 38598be

add model

Browse files
Files changed (4) hide show
  1. README.md +15 -32
  2. config.json +1 -0
  3. pytorch_model.bin +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # bart-mlm
18
 
19
- This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 7.0454
22
 
23
  ## Model description
24
 
@@ -37,43 +37,26 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 2e-05
41
- - train_batch_size: 8
42
- - eval_batch_size: 8
43
  - seed: 42
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine_with_restarts
46
  - lr_scheduler_warmup_steps: 500
47
- - num_epochs: 2
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss |
52
- |:-------------:|:-----:|:------:|:---------------:|
53
- | 7.3964 | 0.08 | 10000 | 7.4260 |
54
- | 7.3303 | 0.16 | 20000 | 7.3293 |
55
- | 7.2823 | 0.25 | 30000 | 7.2939 |
56
- | 7.2526 | 0.33 | 40000 | 7.2624 |
57
- | 7.224 | 0.41 | 50000 | 7.2391 |
58
- | 7.204 | 0.49 | 60000 | 7.2192 |
59
- | 7.1693 | 0.57 | 70000 | 7.2053 |
60
- | 7.1845 | 0.66 | 80000 | 7.1815 |
61
- | 7.1538 | 0.74 | 90000 | 7.1610 |
62
- | 7.1278 | 0.82 | 100000 | 7.1459 |
63
- | 7.1158 | 0.9 | 110000 | 7.1332 |
64
- | 7.1126 | 0.98 | 120000 | 7.1200 |
65
- | 7.0827 | 1.07 | 130000 | 7.1105 |
66
- | 7.0857 | 1.15 | 140000 | 7.0978 |
67
- | 7.0646 | 1.23 | 150000 | 7.0784 |
68
- | 7.0606 | 1.31 | 160000 | 7.0716 |
69
- | 7.0539 | 1.39 | 170000 | 7.0659 |
70
- | 7.0282 | 1.48 | 180000 | 7.0602 |
71
- | 7.0427 | 1.56 | 190000 | 7.0553 |
72
- | 7.0366 | 1.64 | 200000 | 7.0486 |
73
- | 7.0133 | 1.72 | 210000 | 7.0529 |
74
- | 7.0235 | 1.8 | 220000 | 7.0458 |
75
- | 7.0167 | 1.89 | 230000 | 7.0434 |
76
- | 7.0208 | 1.97 | 240000 | 7.0435 |
77
 
78
 
79
  ### Framework versions
 
16
 
17
  # bart-mlm
18
 
19
+ This model is a fine-tuned version of [mwesner/bart-mlm](https://huggingface.co/mwesner/bart-mlm) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 7.5338
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 0.001
41
+ - train_batch_size: 2
42
+ - eval_batch_size: 2
43
  - seed: 42
44
+ - gradient_accumulation_steps: 8
45
+ - total_train_batch_size: 16
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: cosine_with_restarts
48
  - lr_scheduler_warmup_steps: 500
49
+ - num_epochs: 5
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:-----:|:-----:|:---------------:|
55
+ | 7.5202 | 1.0 | 15237 | 7.5964 |
56
+ | 7.5151 | 2.0 | 30474 | 7.5400 |
57
+ | 7.5157 | 3.0 | 45711 | 7.5351 |
58
+ | 7.5172 | 4.0 | 60948 | 7.5317 |
59
+ | 7.5108 | 5.0 | 76185 | 7.5338 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "activation_dropout": 0.0,
3
  "activation_function": "gelu_new",
4
  "architectures": [
 
1
  {
2
+ "_name_or_path": "mwesner/bart-mlm",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu_new",
5
  "architectures": [
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2aa1bb3bf469d1b814e3e644507d983c3944ef45780b5bf28a926f8c3cc69ef
3
  size 1625557313
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6973d75bd1d5d885201d3212cefccd11ffa156e08d77c805c685b1936dbae085
3
  size 1625557313
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6715133c83b5593f520595bfe4a43dfb0af1e2b1b0e07dcbff95159068b6e11
3
  size 2607
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b5d042db71939915533f2461a0667e96ea3f46a809941bef5fec36939d77d84
3
  size 2607