Hugging Face's logo

Tohrumi
/
BERT_finetune_sentiment

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Tohrumi commited on
Commit
4cd53d4
•
1 Parent(s): 0b46820

Training in progress, step 500

Browse files
Files changed (6) hide show
  1. README.md +5 -24
  2. model.safetensors +1 -1
  3. runs/Jun24_15-46-47_1cff0c0384a9/events.out.tfevents.1719244008.1cff0c0384a9.35096.2 +2 -2
  4. runs/Jun24_15-46-47_1cff0c0384a9/events.out.tfevents.1719244286.1cff0c0384a9.35096.3 +3 -0
  5. runs/Jun24_15-52-53_1cff0c0384a9/events.out.tfevents.1719244375.1cff0c0384a9.39550.0 +3 -0
  6. 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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.8911
19
 
20
  ## Model description
21
 
@@ -40,33 +40,14 @@ The following hyperparameters were used during training:
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 20
44
  - mixed_precision_training: Native AMP
45
 
46
  ### Training results
47
 
48
- | Training Loss | Epoch | Step | Validation Loss |
49
- |:-------------:|:-----:|:-----:|:---------------:|
50
- | 0.3369 | 1.0 | 625 | 0.2635 |
51
- | 0.1885 | 2.0 | 1250 | 0.4271 |
52
- | 0.1329 | 3.0 | 1875 | 0.5429 |
53
- | 0.0545 | 4.0 | 2500 | 0.5134 |
54
- | 0.0313 | 5.0 | 3125 | 0.6778 |
55
- | 0.0275 | 6.0 | 3750 | 0.7123 |
56
- | 0.0276 | 7.0 | 4375 | 0.6549 |
57
- | 0.021 | 8.0 | 5000 | 0.6959 |
58
- | 0.0153 | 9.0 | 5625 | 0.7736 |
59
- | 0.0083 | 10.0 | 6250 | 0.7828 |
60
- | 0.0111 | 11.0 | 6875 | 0.8629 |
61
- | 0.0046 | 12.0 | 7500 | 0.8794 |
62
- | 0.0091 | 13.0 | 8125 | 0.7696 |
63
- | 0.0064 | 14.0 | 8750 | 0.8840 |
64
- | 0.0035 | 15.0 | 9375 | 0.9002 |
65
- | 0.0014 | 16.0 | 10000 | 0.9629 |
66
- | 0.0049 | 17.0 | 10625 | 1.0240 |
67
- | 0.0051 | 18.0 | 11250 | 0.9016 |
68
- | 0.0021 | 19.0 | 11875 | 0.9011 |
69
- | 0.0012 | 20.0 | 12500 | 0.8911 |
70
 
71
 
72
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.4670
19
 
20
  ## Model description
21
 
 
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 1
44
  - mixed_precision_training: Native AMP
45
 
46
  ### Training results
47
 
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:----:|:---------------:|
50
+ | 0.09 | 1.0 | 625 | 0.4670 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
 
52
 
53
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9ba9c3f59ff510bbc30e083dd36e16880540d963615255efa22f1b041f24c5e
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90a005af33bb323f2f8804ac52c562169c194779e71274c655cefebefe6a4e42
3
  size 437958648
runs/Jun24_15-46-47_1cff0c0384a9/events.out.tfevents.1719244008.1cff0c0384a9.35096.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:854e60b9d64dac4d7d5197f70913fc6269be444bba5ee1a26a8f79e12aaa7096
3
- size 5120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06de60b5ff08296fb795b3c2171afa4200f161a0871f44dac5ba06bb422cd791
3
+ size 5745
runs/Jun24_15-46-47_1cff0c0384a9/events.out.tfevents.1719244286.1cff0c0384a9.35096.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a43f84cd23e0097c973280633b7c25af4fe321d2a105640d8a68ea96fbd6a6f
3
+ size 359
runs/Jun24_15-52-53_1cff0c0384a9/events.out.tfevents.1719244375.1cff0c0384a9.39550.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be0874410a5e1df2f660770161b7db174a6ae10431868fe99662f64fd6346f22
3
+ size 5029
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d0976c4c36eb89f1beb6dfba9ba0af5082266de21dea89339df6c6c19341dcb
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d2547bbbde5793dd4b230c6845a909ae30d7e763191bb2698f2f3056d29a793
3
  size 5112