Training complete - financial sentiment classifier
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: ProsusAI/finbert
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
- f1
|
| 9 |
+
model-index:
|
| 10 |
+
- name: finance-sentiment-classifier
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# finance-sentiment-classifier
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [ProsusAI/finbert](https://huggingface.co/ProsusAI/finbert) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.3186
|
| 22 |
+
- Accuracy: 0.9203
|
| 23 |
+
- F1: 0.9202
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 2e-05
|
| 43 |
+
- train_batch_size: 32
|
| 44 |
+
- eval_batch_size: 64
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 3
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 55 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
|
| 56 |
+
| 0.6005 | 0.1999 | 500 | 0.5220 | 0.7970 | 0.7954 |
|
| 57 |
+
| 0.4518 | 0.3998 | 1000 | 0.3991 | 0.8546 | 0.8540 |
|
| 58 |
+
| 0.3773 | 0.5998 | 1500 | 0.3231 | 0.8813 | 0.8808 |
|
| 59 |
+
| 0.3375 | 0.7997 | 2000 | 0.3025 | 0.8878 | 0.8881 |
|
| 60 |
+
| 0.2982 | 0.9996 | 2500 | 0.2735 | 0.8977 | 0.8971 |
|
| 61 |
+
| 0.2057 | 1.1995 | 3000 | 0.3028 | 0.9035 | 0.9026 |
|
| 62 |
+
| 0.2001 | 1.3994 | 3500 | 0.2624 | 0.9123 | 0.9119 |
|
| 63 |
+
| 0.2034 | 1.5994 | 4000 | 0.2450 | 0.9171 | 0.9170 |
|
| 64 |
+
| 0.1631 | 1.7993 | 4500 | 0.2547 | 0.9180 | 0.9179 |
|
| 65 |
+
| 0.1691 | 1.9992 | 5000 | 0.2379 | 0.9189 | 0.9189 |
|
| 66 |
+
| 0.1077 | 2.1991 | 5500 | 0.2982 | 0.9190 | 0.9186 |
|
| 67 |
+
| 0.1288 | 2.3990 | 6000 | 0.2772 | 0.9201 | 0.9199 |
|
| 68 |
+
| 0.1114 | 2.5990 | 6500 | 0.2847 | 0.9220 | 0.9220 |
|
| 69 |
+
| 0.1128 | 2.7989 | 7000 | 0.2879 | 0.9234 | 0.9233 |
|
| 70 |
+
| 0.0969 | 2.9988 | 7500 | 0.2920 | 0.9236 | 0.9234 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.57.6
|
| 76 |
+
- Pytorch 2.9.1+cu128
|
| 77 |
+
- Datasets 4.5.0
|
| 78 |
+
- Tokenizers 0.22.2
|