End of training
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# deberta-v3-large_v1_no_entities_with_context
|
20 |
|
21 |
-
This model is a fine-tuned version of [
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
- Accuracy: 0.0045
|
25 |
- F1: 0.0090
|
26 |
- Precision: 0.0045
|
@@ -45,8 +45,8 @@ More information needed
|
|
45 |
|
46 |
The following hyperparameters were used during training:
|
47 |
- learning_rate: 0.0002
|
48 |
-
- train_batch_size:
|
49 |
-
- eval_batch_size:
|
50 |
- seed: 42
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: linear
|
@@ -56,10 +56,10 @@ The following hyperparameters were used during training:
|
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Rate |
|
58 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:------:|
|
59 |
-
| 0.
|
60 |
-
| 0.0306 | 2.0 |
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
|
64 |
|
65 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
base_model: bobbyw/deberta-v3-large_v1_no_entities_with_context
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
|
|
18 |
|
19 |
# deberta-v3-large_v1_no_entities_with_context
|
20 |
|
21 |
+
This model is a fine-tuned version of [bobbyw/deberta-v3-large_v1_no_entities_with_context](https://huggingface.co/bobbyw/deberta-v3-large_v1_no_entities_with_context) on an unknown dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0257
|
24 |
- Accuracy: 0.0045
|
25 |
- F1: 0.0090
|
26 |
- Precision: 0.0045
|
|
|
45 |
|
46 |
The following hyperparameters were used during training:
|
47 |
- learning_rate: 0.0002
|
48 |
+
- train_batch_size: 3
|
49 |
+
- eval_batch_size: 3
|
50 |
- seed: 42
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: linear
|
|
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Rate |
|
58 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:------:|
|
59 |
+
| 0.0323 | 1.0 | 540 | 0.0261 | 0.0045 | 0.0090 | 0.0045 | 1.0 | 0.0002 |
|
60 |
+
| 0.0306 | 2.0 | 1080 | 0.0263 | 0.0045 | 0.0090 | 0.0045 | 1.0 | 0.0001 |
|
61 |
+
| 0.0318 | 3.0 | 1620 | 0.0258 | 0.0045 | 0.0090 | 0.0045 | 1.0 | 5e-05 |
|
62 |
+
| 0.0301 | 4.0 | 2160 | 0.0257 | 0.0045 | 0.0090 | 0.0045 | 1.0 | 0.0 |
|
63 |
|
64 |
|
65 |
### Framework versions
|