Bencode92 commited on
Commit
754264b
·
verified ·
1 Parent(s): f1b00ae

Model save

Browse files
README.md CHANGED
@@ -19,14 +19,14 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [yiyanghkust/finbert-tone](https://huggingface.co/yiyanghkust/finbert-tone) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 3.6407
23
- - Accuracy: 0.6667
24
- - Precision: 0.6667
25
- - Recall: 0.6667
26
- - F1: 0.6667
27
- - F1 Macro: 0.7222
28
- - Precision Macro: 0.7222
29
- - Recall Macro: 0.7222
30
 
31
  ## Model description
32
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
51
  - seed: 42
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
- - lr_scheduler_warmup_steps: 5
55
  - num_epochs: 3
56
 
57
  ### Training results
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | F1 Macro | Precision Macro | Recall Macro |
60
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:--------:|:---------------:|:------------:|
61
- | No log | 1.0 | 3 | 3.7374 | 0.6667 | 0.6667 | 0.6667 | 0.6667 | 0.7222 | 0.7222 | 0.7222 |
62
- | No log | 2.0 | 6 | 3.4250 | 0.6667 | 0.6667 | 0.6667 | 0.6667 | 0.7222 | 0.7222 | 0.7222 |
63
- | No log | 3.0 | 9 | 3.6407 | 0.6667 | 0.6667 | 0.6667 | 0.6667 | 0.7222 | 0.7222 | 0.7222 |
64
 
65
 
66
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [yiyanghkust/finbert-tone](https://huggingface.co/yiyanghkust/finbert-tone) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.0014
23
+ - Accuracy: 1.0
24
+ - Precision: 1.0
25
+ - Recall: 1.0
26
+ - F1: 1.0
27
+ - F1 Macro: 1.0
28
+ - Precision Macro: 1.0
29
+ - Recall Macro: 1.0
30
 
31
  ## Model description
32
 
 
51
  - seed: 42
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
+ - lr_scheduler_warmup_steps: 12
55
  - num_epochs: 3
56
 
57
  ### Training results
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | F1 Macro | Precision Macro | Recall Macro |
60
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:--------:|:---------------:|:------------:|
61
+ | No log | 1.0 | 7 | 0.1790 | 0.8462 | 0.8846 | 0.8462 | 0.8555 | 0.8030 | 0.7778 | 0.8889 |
62
+ | 1.3694 | 2.0 | 14 | 0.0238 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
63
+ | 0.433 | 3.0 | 21 | 0.0014 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
64
 
65
 
66
  ### Framework versions
logs/events.out.tfevents.1752049311.pkrvmfkh1xnbeme.2489.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ff2028146f2bc0fd6c2859b207e621676b89c91a9223e57a5fceece55113ab1
3
- size 6486
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1803411651f5b347e1e9f2461f838350d14343ee2ae9e4518a84e0e337abb828
3
+ size 7668