Carlos
commited on
Commit
•
e0f85f8
1
Parent(s):
b20b53c
update model card README.md
Browse files
README.md
CHANGED
@@ -1,32 +1,67 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
## Training procedure
|
5 |
|
|
|
6 |
|
7 |
-
The following
|
8 |
-
-
|
9 |
-
-
|
10 |
-
-
|
11 |
-
-
|
12 |
-
-
|
13 |
-
-
|
14 |
-
-
|
15 |
-
-
|
16 |
-
|
17 |
-
|
18 |
-
The following `bitsandbytes` quantization config was used during training:
|
19 |
-
- load_in_8bit: False
|
20 |
-
- load_in_4bit: True
|
21 |
-
- llm_int8_threshold: 6.0
|
22 |
-
- llm_int8_skip_modules: None
|
23 |
-
- llm_int8_enable_fp32_cpu_offload: False
|
24 |
-
- llm_int8_has_fp16_weight: False
|
25 |
-
- bnb_4bit_quant_type: nf4
|
26 |
-
- bnb_4bit_use_double_quant: True
|
27 |
-
- bnb_4bit_compute_dtype: float16
|
28 |
-
### Framework versions
|
29 |
|
30 |
-
|
|
|
|
|
|
|
|
|
|
|
31 |
|
32 |
-
-
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-base-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: test-NERv3
|
13 |
+
results: []
|
14 |
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# test-NERv3
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 2.1525
|
24 |
+
- Precision: 0.0031
|
25 |
+
- Recall: 0.0128
|
26 |
+
- F1: 0.0050
|
27 |
+
- Accuracy: 0.1087
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
## Training procedure
|
42 |
|
43 |
+
### Training hyperparameters
|
44 |
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 5e-05
|
47 |
+
- train_batch_size: 16
|
48 |
+
- eval_batch_size: 64
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- lr_scheduler_warmup_steps: 500
|
53 |
+
- num_epochs: 1
|
54 |
+
|
55 |
+
### Training results
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
59 |
+
| 2.1814 | 1.0 | 14 | 2.1525 | 0.0031 | 0.0128 | 0.0050 | 0.1087 |
|
60 |
+
|
61 |
+
|
62 |
+
### Framework versions
|
63 |
|
64 |
+
- Transformers 4.32.0.dev0
|
65 |
+
- Pytorch 2.0.0
|
66 |
+
- Datasets 2.12.0
|
67 |
+
- Tokenizers 0.13.3
|