End of training
Browse files
README.md
CHANGED
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss:
|
36 |
- Accuracy: 0.0
|
37 |
|
38 |
## Model description
|
@@ -56,8 +56,6 @@ The following hyperparameters were used during training:
|
|
56 |
- train_batch_size: 32
|
57 |
- eval_batch_size: 64
|
58 |
- seed: 1
|
59 |
-
- gradient_accumulation_steps: 2
|
60 |
-
- total_train_batch_size: 64
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_steps: 20
|
@@ -67,14 +65,14 @@ The following hyperparameters were used during training:
|
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
|
79 |
|
80 |
### Framework versions
|
|
|
32 |
|
33 |
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.8364
|
36 |
- Accuracy: 0.0
|
37 |
|
38 |
## Model description
|
|
|
56 |
- train_batch_size: 32
|
57 |
- eval_batch_size: 64
|
58 |
- seed: 1
|
|
|
|
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
61 |
- lr_scheduler_warmup_steps: 20
|
|
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
+
| 0.6981 | 0.32 | 25 | 0.6973 | 0.4657 |
|
69 |
+
| 0.6818 | 0.64 | 50 | 0.6864 | 0.4910 |
|
70 |
+
| 0.6578 | 0.96 | 75 | 0.6036 | 0.6968 |
|
71 |
+
| 0.5986 | 1.28 | 100 | 0.5675 | 0.7292 |
|
72 |
+
| 0.5756 | 1.6 | 125 | 0.5968 | 0.7076 |
|
73 |
+
| 0.4797 | 1.92 | 150 | 0.5562 | 0.7401 |
|
74 |
+
| 0.463 | 2.24 | 175 | 0.6183 | 0.7220 |
|
75 |
+
| 0.4034 | 2.56 | 200 | 0.5857 | 0.7726 |
|
76 |
|
77 |
|
78 |
### Framework versions
|