End of training
Browse files- README.md +0 -32
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -14,8 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# bart-noised-with-gcd-dist-0.2
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
|
| 17 |
-
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.7596
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -46,36 +44,6 @@ The following hyperparameters were used during training:
|
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
-
|:-------------:|:-----:|:-----:|:---------------:|
|
| 51 |
-
| 1.1252 | 0.11 | 500 | 0.9577 |
|
| 52 |
-
| 0.9428 | 0.21 | 1000 | 0.9144 |
|
| 53 |
-
| 0.9076 | 0.32 | 1500 | 0.9041 |
|
| 54 |
-
| 0.9218 | 0.43 | 2000 | 0.8748 |
|
| 55 |
-
| 0.9605 | 0.54 | 2500 | 0.8489 |
|
| 56 |
-
| 0.9061 | 0.64 | 3000 | 0.8383 |
|
| 57 |
-
| 0.906 | 0.75 | 3500 | 0.8247 |
|
| 58 |
-
| 0.9026 | 0.86 | 4000 | 0.8140 |
|
| 59 |
-
| 0.8702 | 0.96 | 4500 | 0.8105 |
|
| 60 |
-
| 0.7334 | 1.07 | 5000 | 0.8197 |
|
| 61 |
-
| 0.7826 | 1.18 | 5500 | 0.7954 |
|
| 62 |
-
| 0.7723 | 1.28 | 6000 | 0.8033 |
|
| 63 |
-
| 0.7213 | 1.39 | 6500 | 0.7971 |
|
| 64 |
-
| 0.7755 | 1.5 | 7000 | 0.7905 |
|
| 65 |
-
| 0.7072 | 1.61 | 7500 | 0.7905 |
|
| 66 |
-
| 0.703 | 1.71 | 8000 | 0.7755 |
|
| 67 |
-
| 0.7268 | 1.82 | 8500 | 0.7733 |
|
| 68 |
-
| 0.7322 | 1.93 | 9000 | 0.7687 |
|
| 69 |
-
| 0.674 | 2.03 | 9500 | 0.7723 |
|
| 70 |
-
| 0.5955 | 2.14 | 10000 | 0.7807 |
|
| 71 |
-
| 0.6173 | 2.25 | 10500 | 0.7760 |
|
| 72 |
-
| 0.6823 | 2.35 | 11000 | 0.7666 |
|
| 73 |
-
| 0.5972 | 2.46 | 11500 | 0.7670 |
|
| 74 |
-
| 0.5896 | 2.57 | 12000 | 0.7617 |
|
| 75 |
-
| 0.6111 | 2.68 | 12500 | 0.7621 |
|
| 76 |
-
| 0.6055 | 2.78 | 13000 | 0.7603 |
|
| 77 |
-
| 0.6026 | 2.89 | 13500 | 0.7617 |
|
| 78 |
-
| 0.6434 | 3.0 | 14000 | 0.7596 |
|
| 79 |
|
| 80 |
|
| 81 |
### Framework versions
|
|
|
|
| 14 |
# bart-noised-with-gcd-dist-0.2
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
|
| 48 |
|
| 49 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 557912620
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db273a7bb8bee6142d4bb5f81e49547e6eb2acbb8919f2583cb3951547f359a1
|
| 3 |
size 557912620
|