Hugging Face's logo

Bencode92
/
tradepulse-finbert-sentiment

Text Classification
TensorBoard
Safetensors
English
bert
finance
sentiment-analysis
finbert
trading
Model card Files
xet
Metrics Community
Bencode92 commited on
Commit
2101b59
·
1 Parent(s): f12cf65

🔄 Incremental label | Acc: 0.800, F1: 0.619

Browse files
Files changed (9) hide show
  1. README.md +9 -9
  2. {checkpoint-9 → checkpoint-18}/config.json +0 -0
  3. {checkpoint-9 → checkpoint-18}/model.safetensors +1 -1
  4. {checkpoint-9 → checkpoint-18}/special_tokens_map.json +0 -0
  5. {checkpoint-9 → checkpoint-18}/tokenizer.json +0 -0
  6. {checkpoint-9 → checkpoint-18}/tokenizer_config.json +0 -0
  7. {checkpoint-9 → checkpoint-18}/trainer_state.json +39 -17
  8. {checkpoint-9 → checkpoint-18}/vocab.txt +0 -0
  9. model.safetensors +1 -1
README.md CHANGED
@@ -20,17 +20,17 @@ Fine-tuned FinBERT model for financial sentiment analysis in TradePulse.
20
 
21
  ## Performance
22
 
23
- *Last training: 2025-07-15 07:28*
24
- *Dataset: `news_20250715.csv` (44 samples)*
25
 
26
  | Metric | Value |
27
  |--------|-------|
28
- | Loss | 1.6707 |
29
- | Accuracy | 0.5455 |
30
- | F1 Score | 0.4935 |
31
- | F1 Macro | 0.4935 |
32
- | Precision | 0.4621 |
33
- | Recall | 0.5455 |
34
 
35
  ## Training Details
36
 
@@ -59,4 +59,4 @@ predictions = outputs.logits.softmax(dim=-1)
59
  ## Model Card Authors
60
 
61
  - TradePulse ML Team
62
- - Auto-generated on 2025-07-15 07:28:57
 
20
 
21
  ## Performance
22
 
23
+ *Last training: 2025-07-15 15:07*
24
+ *Dataset: `news_20250715.csv` (45 samples)*
25
 
26
  | Metric | Value |
27
  |--------|-------|
28
+ | Loss | 1.4576 |
29
+ | Accuracy | 0.6667 |
30
+ | F1 Score | 0.5972 |
31
+ | F1 Macro | 0.5972 |
32
+ | Precision | 0.6333 |
33
+ | Recall | 0.6667 |
34
 
35
  ## Training Details
36
 
 
59
  ## Model Card Authors
60
 
61
  - TradePulse ML Team
62
+ - Auto-generated on 2025-07-15 15:07:46
{checkpoint-9 → checkpoint-18}/config.json RENAMED
File without changes
{checkpoint-9 → checkpoint-18}/model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac36968fb440269061a80f6210450c7e8edef2bd760edc14674ad878ce27689b
3
  size 439039996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61774b77ab6bd5c073bb54dcf905328d1eb6be8936197401cbacb41ac9a7f62e
3
  size 439039996
{checkpoint-9 → checkpoint-18}/special_tokens_map.json RENAMED
File without changes
{checkpoint-9 → checkpoint-18}/tokenizer.json RENAMED
File without changes
{checkpoint-9 → checkpoint-18}/tokenizer_config.json RENAMED
File without changes
{checkpoint-9 → checkpoint-18}/trainer_state.json RENAMED
@@ -1,27 +1,49 @@
1
  {
2
- "best_metric": 0.4935064935064935,
3
- "best_model_checkpoint": "hf-sentiment-production/checkpoint-9",
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
- "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.5454545454545454,
14
- "eval_f1": 0.4935064935064935,
15
- "eval_f1_macro": 0.3333333333333333,
16
- "eval_loss": 1.6706877946853638,
17
- "eval_precision": 0.4621212121212121,
18
- "eval_precision_macro": 0.3194444444444444,
19
- "eval_recall": 0.5454545454545454,
20
- "eval_recall_macro": 0.36111111111111116,
21
- "eval_runtime": 6.0894,
22
- "eval_samples_per_second": 1.806,
23
- "eval_steps_per_second": 0.493,
24
  "step": 9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  }
26
  ],
27
  "logging_steps": 10,
@@ -45,12 +67,12 @@
45
  "should_evaluate": false,
46
  "should_log": false,
47
  "should_save": true,
48
- "should_training_stop": false
49
  },
50
  "attributes": {}
51
  }
52
  },
53
- "total_flos": 8682742785024.0,
54
  "train_batch_size": 4,
55
  "trial_name": null,
56
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5972222222222222,
3
+ "best_model_checkpoint": "hf-sentiment-production/checkpoint-18",
4
+ "epoch": 2.0,
5
  "eval_steps": 500,
6
+ "global_step": 18,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.5,
14
+ "eval_f1": 0.45584045584045585,
15
+ "eval_f1_macro": 0.35327635327635326,
16
+ "eval_loss": 1.4192219972610474,
17
+ "eval_precision": 0.41904761904761906,
18
+ "eval_precision_macro": 0.3238095238095238,
19
+ "eval_recall": 0.5,
20
+ "eval_recall_macro": 0.38888888888888884,
21
+ "eval_runtime": 6.7313,
22
+ "eval_samples_per_second": 1.783,
23
+ "eval_steps_per_second": 0.446,
24
  "step": 9
25
+ },
26
+ {
27
+ "epoch": 1.1111111111111112,
28
+ "grad_norm": 7.546491622924805,
29
+ "learning_rate": 8.000000000000001e-06,
30
+ "loss": 1.2856,
31
+ "step": 10
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_accuracy": 0.6666666666666666,
36
+ "eval_f1": 0.5972222222222222,
37
+ "eval_f1_macro": 0.47222222222222215,
38
+ "eval_loss": 1.4576077461242676,
39
+ "eval_precision": 0.6333333333333333,
40
+ "eval_precision_macro": 0.5333333333333333,
41
+ "eval_recall": 0.6666666666666666,
42
+ "eval_recall_macro": 0.5,
43
+ "eval_runtime": 6.8029,
44
+ "eval_samples_per_second": 1.764,
45
+ "eval_steps_per_second": 0.441,
46
+ "step": 18
47
  }
48
  ],
49
  "logging_steps": 10,
 
67
  "should_evaluate": false,
68
  "should_log": false,
69
  "should_save": true,
70
+ "should_training_stop": true
71
  },
72
  "attributes": {}
73
  }
74
  },
75
+ "total_flos": 17365485570048.0,
76
  "train_batch_size": 4,
77
  "trial_name": null,
78
  "trial_params": null
{checkpoint-9 → checkpoint-18}/vocab.txt RENAMED
File without changes
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac36968fb440269061a80f6210450c7e8edef2bd760edc14674ad878ce27689b
3
  size 439039996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61774b77ab6bd5c073bb54dcf905328d1eb6be8936197401cbacb41ac9a7f62e
3
  size 439039996