update model card README.md
Browse files
README.md
CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Loss: 1.
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -41,13 +41,26 @@ The following hyperparameters were used during training:
|
|
41 |
- total_train_batch_size: 128
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
-
- num_epochs:
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
|
|
14 |
|
15 |
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 1.6363
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
41 |
- total_train_batch_size: 128
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 10
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 2.6063 | 0.67 | 100 | 1.9609 |
|
51 |
+
| 1.9832 | 1.35 | 200 | 1.7818 |
|
52 |
+
| 1.8375 | 2.02 | 300 | 1.7241 |
|
53 |
+
| 1.7553 | 2.69 | 400 | 1.6982 |
|
54 |
+
| 1.7077 | 3.36 | 500 | 1.6691 |
|
55 |
+
| 1.68 | 4.04 | 600 | 1.6638 |
|
56 |
+
| 1.64 | 4.71 | 700 | 1.6521 |
|
57 |
+
| 1.6149 | 5.38 | 800 | 1.6467 |
|
58 |
+
| 1.6064 | 6.05 | 900 | 1.6502 |
|
59 |
+
| 1.5768 | 6.73 | 1000 | 1.6394 |
|
60 |
+
| 1.5685 | 7.4 | 1100 | 1.6389 |
|
61 |
+
| 1.5568 | 8.07 | 1200 | 1.6342 |
|
62 |
+
| 1.5422 | 8.74 | 1300 | 1.6326 |
|
63 |
+
| 1.5422 | 9.42 | 1400 | 1.6363 |
|
64 |
|
65 |
|
66 |
### Framework versions
|