Commit
·
81d966a
1
Parent(s):
2ff98a1
update model card README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: DEREXP
|
| 7 |
results: []
|
|
@@ -13,6 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
# DEREXP
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
@@ -32,13 +40,31 @@ More information needed
|
|
| 32 |
|
| 33 |
The following hyperparameters were used during training:
|
| 34 |
- learning_rate: 2e-05
|
| 35 |
-
- train_batch_size:
|
| 36 |
-
- eval_batch_size:
|
| 37 |
- seed: 42
|
| 38 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 39 |
- lr_scheduler_type: linear
|
| 40 |
- num_epochs: 1
|
| 41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
### Framework versions
|
| 43 |
|
| 44 |
- Transformers 4.20.1
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
model-index:
|
| 8 |
- name: DEREXP
|
| 9 |
results: []
|
|
|
|
| 15 |
# DEREXP
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 3.5797
|
| 20 |
+
- Mse: 3.5797
|
| 21 |
+
- Mae: 1.4414
|
| 22 |
+
- R2: 0.3526
|
| 23 |
+
- Accuracy: 0.2268
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 40 |
|
| 41 |
The following hyperparameters were used during training:
|
| 42 |
- learning_rate: 2e-05
|
| 43 |
+
- train_batch_size: 16
|
| 44 |
+
- eval_batch_size: 16
|
| 45 |
- seed: 42
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
- num_epochs: 1
|
| 49 |
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R2 | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:--------:|
|
| 54 |
+
| 14.19 | 0.08 | 500 | 4.6174 | 4.6174 | 1.6744 | 0.1649 | 0.198 |
|
| 55 |
+
| 4.527 | 0.16 | 1000 | 3.9019 | 3.9019 | 1.5164 | 0.2943 | 0.2192 |
|
| 56 |
+
| 4.3036 | 0.24 | 1500 | 5.3501 | 5.3501 | 1.8130 | 0.0324 | 0.1736 |
|
| 57 |
+
| 4.0923 | 0.32 | 2000 | 3.8948 | 3.8948 | 1.5150 | 0.2956 | 0.2142 |
|
| 58 |
+
| 4.0042 | 0.4 | 2500 | 3.7648 | 3.7648 | 1.4905 | 0.3191 | 0.2162 |
|
| 59 |
+
| 3.8685 | 0.48 | 3000 | 3.7741 | 3.7741 | 1.4908 | 0.3174 | 0.2152 |
|
| 60 |
+
| 3.8928 | 0.56 | 3500 | 3.7122 | 3.7122 | 1.4738 | 0.3286 | 0.214 |
|
| 61 |
+
| 3.8193 | 0.64 | 4000 | 3.7020 | 3.7020 | 1.4727 | 0.3304 | 0.2182 |
|
| 62 |
+
| 3.6929 | 0.72 | 4500 | 3.6419 | 3.6419 | 1.4575 | 0.3413 | 0.2266 |
|
| 63 |
+
| 3.7974 | 0.8 | 5000 | 3.6995 | 3.6995 | 1.4656 | 0.3309 | 0.2202 |
|
| 64 |
+
| 3.7752 | 0.88 | 5500 | 3.6344 | 3.6344 | 1.4559 | 0.3427 | 0.2276 |
|
| 65 |
+
| 3.6254 | 0.96 | 6000 | 3.5797 | 3.5797 | 1.4414 | 0.3526 | 0.2268 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
### Framework versions
|
| 69 |
|
| 70 |
- Transformers 4.20.1
|