Hugging Face's logo

Bencode92
/
tradepulse-finbert-importance

Text Classification
TensorBoard
Safetensors
English
bert
finance
sentiment-analysis
finbert
trading
Model card Files
xet
Metrics Community
Bencode92 commited on
Commit
0bbdfda
·
1 Parent(s): 9dc9ede

🔄 Incremental importance | Acc: 0.714, F1: 0.689

Browse files
Files changed (4) hide show
  1. README.md +8 -8
  2. checkpoint-48/model.safetensors +1 -1
  3. checkpoint-48/trainer_state.json +24 -24
  4. model.safetensors +1 -1
README.md CHANGED
@@ -21,19 +21,19 @@ Fine-tuned FinBERT model for financial importance analysis in TradePulse.
21
 
22
  ## Performance
23
 
24
- *Last training: 2025-07-24 21:27*
25
  *Dataset: `news_20250724.csv` (125 samples)*
26
 
27
  | Metric | Value |
28
  |--------|-------|
29
- | Loss | 0.9156 |
30
- | Accuracy | 0.7500 |
31
- | F1 Score | 0.7520 |
32
 
33
- | F1 Macro | 0.7520 |
34
 
35
- | Precision | 0.7555 |
36
- | Recall | 0.7500 |
37
 
38
  ## Training Details
39
 
@@ -65,4 +65,4 @@ predictions = outputs.logits.softmax(dim=-1)
65
  ## Model Card Authors
66
 
67
  - TradePulse ML Team
68
- - Auto-generated on 2025-07-24 21:27:54
 
21
 
22
  ## Performance
23
 
24
+ *Last training: 2025-07-24 22:28*
25
  *Dataset: `news_20250724.csv` (125 samples)*
26
 
27
  | Metric | Value |
28
  |--------|-------|
29
+ | Loss | 1.0899 |
30
+ | Accuracy | 0.6875 |
31
+ | F1 Score | 0.6900 |
32
 
33
+ | F1 Macro | 0.6900 |
34
 
35
+ | Precision | 0.6939 |
36
+ | Recall | 0.6875 |
37
 
38
  ## Training Details
39
 
 
65
  ## Model Card Authors
66
 
67
  - TradePulse ML Team
68
+ - Auto-generated on 2025-07-24 22:28:48
checkpoint-48/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf91ca40087521cccbf74de6a5820250349be0eb9b742a9ddb4f5d6f6da15de7
3
  size 439039996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46f3d999403313319c4e87948bfae6a7b1edac6c7cad78fcd08a13a7805913eb
3
  size 439039996
checkpoint-48/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.7519509476031214,
3
  "best_model_checkpoint": "hf-importance-production/checkpoint-48",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
@@ -10,16 +10,16 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.4166666666666667,
13
- "grad_norm": 33.77495574951172,
14
  "learning_rate": 4.347826086956522e-06,
15
- "loss": 0.2528,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.8333333333333334,
20
- "grad_norm": 41.324256896972656,
21
  "learning_rate": 8.695652173913044e-06,
22
- "loss": 0.3631,
23
  "step": 20
24
  },
25
  {
@@ -27,43 +27,43 @@
27
  "eval_accuracy": 0.6875,
28
  "eval_f1": 0.6842334494773519,
29
  "eval_f1_macro": 0.45063879210220675,
30
- "eval_loss": 0.9002108573913574,
31
  "eval_precision": 0.6824404761904761,
32
  "eval_precision_macro": 0.45396825396825397,
33
  "eval_recall": 0.6875,
34
  "eval_recall_macro": 0.4484848484848485,
35
- "eval_runtime": 17.967,
36
- "eval_samples_per_second": 1.781,
37
- "eval_steps_per_second": 0.445,
38
  "step": 24
39
  },
40
  {
41
  "epoch": 1.25,
42
- "grad_norm": 40.574581146240234,
43
  "learning_rate": 7.2000000000000005e-06,
44
- "loss": 0.2537,
45
  "step": 30
46
  },
47
  {
48
  "epoch": 1.6666666666666665,
49
- "grad_norm": 4.176632881164551,
50
  "learning_rate": 3.2000000000000003e-06,
51
- "loss": 0.1811,
52
  "step": 40
53
  },
54
  {
55
  "epoch": 2.0,
56
- "eval_accuracy": 0.75,
57
- "eval_f1": 0.7519509476031214,
58
- "eval_f1_macro": 0.5053883314752879,
59
- "eval_loss": 0.9156143069267273,
60
- "eval_precision": 0.7554824561403508,
61
- "eval_precision_macro": 0.5029239766081871,
62
- "eval_recall": 0.75,
63
- "eval_recall_macro": 0.5090909090909091,
64
- "eval_runtime": 17.8939,
65
- "eval_samples_per_second": 1.788,
66
- "eval_steps_per_second": 0.447,
67
  "step": 48
68
  }
69
  ],
 
1
  {
2
+ "best_metric": 0.6900083612040134,
3
  "best_model_checkpoint": "hf-importance-production/checkpoint-48",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.4166666666666667,
13
+ "grad_norm": 5.649362564086914,
14
  "learning_rate": 4.347826086956522e-06,
15
+ "loss": 0.0183,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.8333333333333334,
20
+ "grad_norm": 2.8109025955200195,
21
  "learning_rate": 8.695652173913044e-06,
22
+ "loss": 0.0511,
23
  "step": 20
24
  },
25
  {
 
27
  "eval_accuracy": 0.6875,
28
  "eval_f1": 0.6842334494773519,
29
  "eval_f1_macro": 0.45063879210220675,
30
+ "eval_loss": 1.092362403869629,
31
  "eval_precision": 0.6824404761904761,
32
  "eval_precision_macro": 0.45396825396825397,
33
  "eval_recall": 0.6875,
34
  "eval_recall_macro": 0.4484848484848485,
35
+ "eval_runtime": 17.767,
36
+ "eval_samples_per_second": 1.801,
37
+ "eval_steps_per_second": 0.45,
38
  "step": 24
39
  },
40
  {
41
  "epoch": 1.25,
42
+ "grad_norm": 3.2741000652313232,
43
  "learning_rate": 7.2000000000000005e-06,
44
+ "loss": 0.0141,
45
  "step": 30
46
  },
47
  {
48
  "epoch": 1.6666666666666665,
49
+ "grad_norm": 0.4948952794075012,
50
  "learning_rate": 3.2000000000000003e-06,
51
+ "loss": 0.0386,
52
  "step": 40
53
  },
54
  {
55
  "epoch": 2.0,
56
+ "eval_accuracy": 0.6875,
57
+ "eval_f1": 0.6900083612040134,
58
+ "eval_f1_macro": 0.4593088071348941,
59
+ "eval_loss": 1.089942216873169,
60
+ "eval_precision": 0.6939418859649124,
61
+ "eval_precision_macro": 0.4576023391812865,
62
+ "eval_recall": 0.6875,
63
+ "eval_recall_macro": 0.4621212121212121,
64
+ "eval_runtime": 17.922,
65
+ "eval_samples_per_second": 1.786,
66
+ "eval_steps_per_second": 0.446,
67
  "step": 48
68
  }
69
  ],
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf91ca40087521cccbf74de6a5820250349be0eb9b742a9ddb4f5d6f6da15de7
3
  size 439039996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46f3d999403313319c4e87948bfae6a7b1edac6c7cad78fcd08a13a7805913eb
3
  size 439039996