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-0.3
|
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: 1.0832
|
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 |
-
| 1.4395 | 0.11 | 500 | 1.3691 |
|
52 |
-
| 1.4568 | 0.21 | 1000 | 1.3068 |
|
53 |
-
| 1.3702 | 0.32 | 1500 | 1.2510 |
|
54 |
-
| 1.2945 | 0.43 | 2000 | 1.2319 |
|
55 |
-
| 1.3022 | 0.54 | 2500 | 1.2092 |
|
56 |
-
| 1.1775 | 0.64 | 3000 | 1.2022 |
|
57 |
-
| 1.1657 | 0.75 | 3500 | 1.1822 |
|
58 |
-
| 1.1756 | 0.86 | 4000 | 1.1823 |
|
59 |
-
| 1.2103 | 0.96 | 4500 | 1.1521 |
|
60 |
-
| 1.1467 | 1.07 | 5000 | 1.1535 |
|
61 |
-
| 1.0617 | 1.18 | 5500 | 1.1443 |
|
62 |
-
| 1.0667 | 1.28 | 6000 | 1.1339 |
|
63 |
-
| 1.0906 | 1.39 | 6500 | 1.1369 |
|
64 |
-
| 1.0492 | 1.5 | 7000 | 1.1213 |
|
65 |
-
| 1.0203 | 1.61 | 7500 | 1.1207 |
|
66 |
-
| 0.9431 | 1.71 | 8000 | 1.1183 |
|
67 |
-
| 1.0522 | 1.82 | 8500 | 1.1052 |
|
68 |
-
| 1.0673 | 1.93 | 9000 | 1.0996 |
|
69 |
-
| 0.9521 | 2.03 | 9500 | 1.1079 |
|
70 |
-
| 0.9615 | 2.14 | 10000 | 1.0990 |
|
71 |
-
| 0.996 | 2.25 | 10500 | 1.0976 |
|
72 |
-
| 0.9458 | 2.35 | 11000 | 1.0997 |
|
73 |
-
| 0.9375 | 2.46 | 11500 | 1.0939 |
|
74 |
-
| 0.8869 | 2.57 | 12000 | 1.0896 |
|
75 |
-
| 0.8934 | 2.68 | 12500 | 1.0895 |
|
76 |
-
| 0.8561 | 2.78 | 13000 | 1.0839 |
|
77 |
-
| 0.9795 | 2.89 | 13500 | 1.0834 |
|
78 |
-
| 0.8886 | 3.0 | 14000 | 1.0832 |
|
79 |
|
80 |
|
81 |
### Framework versions
|
|
|
14 |
# bart-noised-with-gcd-dist-0.3
|
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:b8184d4b8351bffb66d3e424b82ffad2f1433a8653fbc12b3ac4e0548df9f266
|
3 |
size 557912620
|