Model save
Browse files- README.md +108 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: distilbert-base-uncased
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
- precision
|
| 10 |
+
- recall
|
| 11 |
+
- f1
|
| 12 |
+
model-index:
|
| 13 |
+
- name: finer_ner_finetuning
|
| 14 |
+
results: []
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 18 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 19 |
+
|
| 20 |
+
# finer_ner_finetuning
|
| 21 |
+
|
| 22 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
| 23 |
+
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.0027
|
| 25 |
+
- Accuracy: 0.9992
|
| 26 |
+
- Precision: 0.9992
|
| 27 |
+
- Recall: 0.9991
|
| 28 |
+
- F1: 0.9991
|
| 29 |
+
- Classification Report: precision recall f1-score support
|
| 30 |
+
|
| 31 |
+
DebtInstrumentBasisSpreadOnVariableRate1 0.63 0.92 0.75 3532
|
| 32 |
+
DebtInstrumentInterestRateStatedPercentage 1.00 1.00 1.00 5174933
|
| 33 |
+
LineOfCreditFacilityMaximumBorrowingCapacity 0.43 0.89 0.58 1346
|
| 34 |
+
|
| 35 |
+
micro avg 1.00 1.00 1.00 5179811
|
| 36 |
+
macro avg 0.69 0.94 0.78 5179811
|
| 37 |
+
weighted avg 1.00 1.00 1.00 5179811
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
## Model description
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Intended uses & limitations
|
| 45 |
+
|
| 46 |
+
More information needed
|
| 47 |
+
|
| 48 |
+
## Training and evaluation data
|
| 49 |
+
|
| 50 |
+
More information needed
|
| 51 |
+
|
| 52 |
+
## Training procedure
|
| 53 |
+
|
| 54 |
+
### Training hyperparameters
|
| 55 |
+
|
| 56 |
+
The following hyperparameters were used during training:
|
| 57 |
+
- learning_rate: 5e-05
|
| 58 |
+
- train_batch_size: 192
|
| 59 |
+
- eval_batch_size: 192
|
| 60 |
+
- seed: 42
|
| 61 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 62 |
+
- lr_scheduler_type: linear
|
| 63 |
+
- lr_scheduler_warmup_steps: 500
|
| 64 |
+
- num_epochs: 5
|
| 65 |
+
- mixed_precision_training: Native AMP
|
| 66 |
+
|
| 67 |
+
### Training results
|
| 68 |
+
|
| 69 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Classification Report |
|
| 70 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
|
| 71 |
+
| 0.0097 | 1.3514 | 500 | 0.0026 | 0.9991 | 0.9991 | 0.9990 | 0.9991 | precision recall f1-score support
|
| 72 |
+
|
| 73 |
+
DebtInstrumentBasisSpreadOnVariableRate1 0.57 0.89 0.70 3532
|
| 74 |
+
DebtInstrumentInterestRateStatedPercentage 1.00 1.00 1.00 5174933
|
| 75 |
+
LineOfCreditFacilityMaximumBorrowingCapacity 0.45 0.79 0.57 1346
|
| 76 |
+
|
| 77 |
+
micro avg 1.00 1.00 1.00 5179811
|
| 78 |
+
macro avg 0.67 0.89 0.76 5179811
|
| 79 |
+
weighted avg 1.00 1.00 1.00 5179811
|
| 80 |
+
|
|
| 81 |
+
| 0.0064 | 2.7027 | 1000 | 0.0026 | 0.9991 | 0.9991 | 0.9990 | 0.9990 | precision recall f1-score support
|
| 82 |
+
|
| 83 |
+
DebtInstrumentBasisSpreadOnVariableRate1 0.59 0.92 0.72 3532
|
| 84 |
+
DebtInstrumentInterestRateStatedPercentage 1.00 1.00 1.00 5174933
|
| 85 |
+
LineOfCreditFacilityMaximumBorrowingCapacity 0.42 0.85 0.57 1346
|
| 86 |
+
|
| 87 |
+
micro avg 1.00 1.00 1.00 5179811
|
| 88 |
+
macro avg 0.67 0.92 0.76 5179811
|
| 89 |
+
weighted avg 1.00 1.00 1.00 5179811
|
| 90 |
+
|
|
| 91 |
+
| 0.0044 | 4.0541 | 1500 | 0.0027 | 0.9992 | 0.9992 | 0.9991 | 0.9991 | precision recall f1-score support
|
| 92 |
+
|
| 93 |
+
DebtInstrumentBasisSpreadOnVariableRate1 0.63 0.92 0.75 3532
|
| 94 |
+
DebtInstrumentInterestRateStatedPercentage 1.00 1.00 1.00 5174933
|
| 95 |
+
LineOfCreditFacilityMaximumBorrowingCapacity 0.43 0.89 0.58 1346
|
| 96 |
+
|
| 97 |
+
micro avg 1.00 1.00 1.00 5179811
|
| 98 |
+
macro avg 0.69 0.94 0.78 5179811
|
| 99 |
+
weighted avg 1.00 1.00 1.00 5179811
|
| 100 |
+
|
|
| 101 |
+
|
| 102 |
+
|
| 103 |
+
### Framework versions
|
| 104 |
+
|
| 105 |
+
- Transformers 4.46.3
|
| 106 |
+
- Pytorch 2.5.1+cu124
|
| 107 |
+
- Datasets 3.2.0
|
| 108 |
+
- Tokenizers 0.20.3
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 265491548
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a1de6e3cb5b2977d504939e846304155fcff48bfa0df31819cd94c931a14d4e
|
| 3 |
size 265491548
|