Hugging Face's logo

Kartikeyssj2
/
Speech-Fluency-Scoring

Transformers
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Community
Kartikeyssj2 commited on
Commit
1340b28
·
verified ·
1 Parent(s): 3d190a7

fluency_scoring

Browse files
Files changed (3) hide show
  1. README.md +25 -8
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 6979.7861
19
 
20
  ## Model description
21
 
@@ -35,26 +35,43 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 5e-05
38
- - train_batch_size: 16
39
- - eval_batch_size: 16
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_steps: 500
44
- - num_epochs: 3
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 3390.8086 | 1.0 | 21 | 7179.5903 |
51
- | 3306.8 | 2.0 | 42 | 7131.0044 |
52
- | 3232.7922 | 3.0 | 63 | 6979.7861 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
 
54
 
55
  ### Framework versions
56
 
57
  - Transformers 4.41.2
58
- - Pytorch 2.1.2+cpu
59
  - Datasets 2.19.2
60
  - Tokenizers 0.19.1
 
15
 
16
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 3132.9194
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 5e-05
38
+ - train_batch_size: 1
39
+ - eval_batch_size: 1
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_steps: 500
44
+ - num_epochs: 20
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 2042.4865 | 1.0 | 323 | 5335.4272 |
51
+ | 382.3707 | 2.0 | 646 | 3373.9421 |
52
+ | 598.0939 | 3.0 | 969 | 3270.9556 |
53
+ | 468.246 | 4.0 | 1292 | 3266.6204 |
54
+ | 674.1861 | 5.0 | 1615 | 3252.7373 |
55
+ | 567.0895 | 6.0 | 1938 | 3240.0723 |
56
+ | 288.44 | 7.0 | 2261 | 3191.2097 |
57
+ | 104.8854 | 8.0 | 2584 | 3062.3445 |
58
+ | 186.9482 | 9.0 | 2907 | 3115.6565 |
59
+ | 109.7889 | 10.0 | 3230 | 3051.8813 |
60
+ | 145.9831 | 11.0 | 3553 | 2988.375 |
61
+ | 244.998 | 12.0 | 3876 | 3248.4668 |
62
+ | 116.7815 | 13.0 | 4199 | 2964.2134 |
63
+ | 30.0641 | 14.0 | 4522 | 2983.1790 |
64
+ | 35.7114 | 15.0 | 4845 | 3078.9023 |
65
+ | 32.7112 | 16.0 | 5168 | 3016.2539 |
66
+ | 14.4455 | 17.0 | 5491 | 2986.9197 |
67
+ | 5.1751 | 18.0 | 5814 | 2932.9602 |
68
+ | 97.4864 | 19.0 | 6137 | 3092.3416 |
69
+ | 9.9064 | 20.0 | 6460 | 3132.9194 |
70
 
71
 
72
  ### Framework versions
73
 
74
  - Transformers 4.41.2
75
+ - Pytorch 2.1.2
76
  - Datasets 2.19.2
77
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:060beb30f5c749094bdd99ba582e8a697e16f39b20ae1982a5f4a71ead0f3033
3
  size 267829484
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bca5406755b22275947a5b25d7d3a0de41a966573c169479bc539ab2d9a46b1
3
  size 267829484
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1578ec502e404c4bc9ff53064ea93dcd2be189be395a421f6132243ef74acf5
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4f86224049ae03c87707707ad4c191effa2571f658dc1dd8d0dee6e66183434
3
  size 5048