Hugging Face's logo

LogischeIP
/
SentimentT2_BertBase

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
LogischeIP commited on
Commit
f908519
·
verified ·
1 Parent(s): 1940a85

End of training

Browse files
Files changed (9) hide show
  1. README.md +12 -17
  2. added_tokens.json +3 -0
  3. merges.txt +0 -0
  4. model.safetensors +1 -1
  5. runs/Jan24_21-40-26_7d2b1e2d4e1a/events.out.tfevents.1706132427.7d2b1e2d4e1a.48811.4 +3 -0
  6. runs/Jan24_21-45-55_7d2b1e2d4e1a/events.out.tfevents.1706132757.7d2b1e2d4e1a.48811.5 +3 -0
  7. tokenizer.json +0 -0
  8. training_args.bin +1 -1
  9. vocab.json +0 -0
README.md CHANGED
@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.5383
22
- - Accuracy: 0.8532
23
- - F1: 0.8589
24
- - Auc Roc: 0.9323
25
- - Log Loss: 0.5383
26
 
27
  ## Model description
28
 
@@ -50,23 +50,18 @@ The following hyperparameters were used during training:
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: cosine
52
  - lr_scheduler_warmup_steps: 500
53
- - num_epochs: 10
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Auc Roc | Log Loss |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:-------:|:--------:|
60
- | 0.6992 | 1.0 | 101 | 0.6441 | 0.6480 | 0.6941 | 0.7125 | 0.6441 |
61
- | 0.5998 | 2.0 | 203 | 0.5229 | 0.7687 | 0.7969 | 0.8658 | 0.5229 |
62
- | 0.4443 | 3.0 | 304 | 0.3993 | 0.8333 | 0.8504 | 0.9189 | 0.3993 |
63
- | 0.3495 | 4.0 | 406 | 0.3888 | 0.8333 | 0.8514 | 0.9282 | 0.3888 |
64
- | 0.3051 | 5.0 | 507 | 0.3459 | 0.8644 | 0.8740 | 0.9328 | 0.3459 |
65
- | 0.2275 | 6.0 | 609 | 0.3825 | 0.8570 | 0.8606 | 0.9327 | 0.3825 |
66
- | 0.1594 | 7.0 | 710 | 0.4236 | 0.8657 | 0.8717 | 0.9341 | 0.4236 |
67
- | 0.108 | 8.0 | 812 | 0.4961 | 0.8520 | 0.8602 | 0.9329 | 0.4961 |
68
- | 0.0747 | 9.0 | 913 | 0.5362 | 0.8570 | 0.8642 | 0.9321 | 0.5362 |
69
- | 0.0643 | 9.95 | 1010 | 0.5383 | 0.8532 | 0.8589 | 0.9323 | 0.5383 |
70
 
71
 
72
  ### Framework versions
@@ -74,4 +69,4 @@ The following hyperparameters were used during training:
74
  - Transformers 4.35.2
75
  - Pytorch 2.1.0+cu121
76
  - Datasets 2.16.1
77
- - Tokenizers 0.15.0
 
18
 
19
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.3196
22
+ - Accuracy: 0.8706
23
+ - F1: 0.8670
24
+ - Auc Roc: 0.9473
25
+ - Log Loss: 0.3196
26
 
27
  ## Model description
28
 
 
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: cosine
52
  - lr_scheduler_warmup_steps: 500
53
+ - num_epochs: 5
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Auc Roc | Log Loss |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:-------:|:--------:|
60
+ | 0.7054 | 1.0 | 101 | 0.6628 | 0.6045 | 0.5047 | 0.7215 | 0.6628 |
61
+ | 0.6303 | 2.0 | 203 | 0.5437 | 0.7823 | 0.7842 | 0.8748 | 0.5437 |
62
+ | 0.4599 | 3.0 | 304 | 0.3532 | 0.8520 | 0.8449 | 0.9364 | 0.3532 |
63
+ | 0.3413 | 4.0 | 406 | 0.3172 | 0.8719 | 0.8733 | 0.9405 | 0.3172 |
64
+ | 0.2877 | 4.98 | 505 | 0.3196 | 0.8706 | 0.8670 | 0.9473 | 0.3196 |
 
 
 
 
 
65
 
66
 
67
  ### Framework versions
 
69
  - Transformers 4.35.2
70
  - Pytorch 2.1.0+cu121
71
  - Datasets 2.16.1
72
+ - Tokenizers 0.15.1
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 50257
3
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd637a3b085bdea4a0048db3b46295aa4d9334d3f6a58eace8a8798ac25a6b06
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9bf8e95223d2c8f219533265f32b534ff637011aa71a1a4ee7efae4215e9fcd
3
  size 437958648
runs/Jan24_21-40-26_7d2b1e2d4e1a/events.out.tfevents.1706132427.7d2b1e2d4e1a.48811.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4a71d277c9a6672b6d988da31fb5f0586173731c7c1651a8adaee1df8ce41e3
3
+ size 7042
runs/Jan24_21-45-55_7d2b1e2d4e1a/events.out.tfevents.1706132757.7d2b1e2d4e1a.48811.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fd33a63bb242d472cd3869d237b780d08887db0bee80f0559641cd75e50135f
3
+ size 7792
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d7d72ea82a603b36592c531cb5f05144f4a4bb6214cfccb31230981d0e1d1ce
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5e7f2609a25fe92cc8a72ca0884d45d5d5b8f7d643d09ab1de70b7c5faed0c4
3
  size 4664
vocab.json ADDED
The diff for this file is too large to render. See raw diff