update model card README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,8 @@ tags:
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- cosmos_qa
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: t5_small_race_mutlirc
|
| 9 |
results: []
|
|
@@ -15,6 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# t5_small_race_mutlirc
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the cosmos_qa dataset.
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -42,6 +47,15 @@ The following hyperparameters were used during training:
|
|
| 42 |
- lr_scheduler_warmup_steps: 50
|
| 43 |
- num_epochs: 3.0
|
| 44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
### Framework versions
|
| 46 |
|
| 47 |
- Transformers 4.11.3
|
|
|
|
| 4 |
- generated_from_trainer
|
| 5 |
datasets:
|
| 6 |
- cosmos_qa
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
model-index:
|
| 10 |
- name: t5_small_race_mutlirc
|
| 11 |
results: []
|
|
|
|
| 17 |
# t5_small_race_mutlirc
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the cosmos_qa dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.5929
|
| 22 |
+
- Accuracy: 0.4794
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 47 |
- lr_scheduler_warmup_steps: 50
|
| 48 |
- num_epochs: 3.0
|
| 49 |
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 54 |
+
| 0.7069 | 1.0 | 1250 | 0.6522 | 0.396 |
|
| 55 |
+
| 0.6595 | 2.0 | 2500 | 0.6009 | 0.4693 |
|
| 56 |
+
| 0.6374 | 3.0 | 3750 | 0.5929 | 0.4794 |
|
| 57 |
+
|
| 58 |
+
|
| 59 |
### Framework versions
|
| 60 |
|
| 61 |
- Transformers 4.11.3
|