End of training
Browse files- README.md +9 -33
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -4,18 +4,18 @@ base_model: facebook/bart-base
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
| 7 |
-
- name: bart-noised-with-all-
|
| 8 |
results: []
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
-
# bart-noised-with-all-
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -46,36 +46,12 @@ The following hyperparameters were used during training:
|
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
-
| Training Loss | Epoch | Step
|
| 50 |
-
|
| 51 |
-
| 0.
|
| 52 |
-
| 0.
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.6795 | 0.54 | 2500 | 0.6581 |
|
| 56 |
-
| 0.6778 | 0.64 | 3000 | 0.6535 |
|
| 57 |
-
| 0.7028 | 0.75 | 3500 | 0.6547 |
|
| 58 |
-
| 0.7104 | 0.86 | 4000 | 0.6318 |
|
| 59 |
-
| 0.7032 | 0.96 | 4500 | 0.6213 |
|
| 60 |
-
| 0.6062 | 1.07 | 5000 | 0.6157 |
|
| 61 |
-
| 0.5789 | 1.18 | 5500 | 0.6175 |
|
| 62 |
-
| 0.5689 | 1.28 | 6000 | 0.6118 |
|
| 63 |
-
| 0.5183 | 1.39 | 6500 | 0.6147 |
|
| 64 |
-
| 0.5834 | 1.5 | 7000 | 0.5938 |
|
| 65 |
-
| 0.5708 | 1.61 | 7500 | 0.5964 |
|
| 66 |
-
| 0.5118 | 1.71 | 8000 | 0.5924 |
|
| 67 |
-
| 0.5284 | 1.82 | 8500 | 0.5900 |
|
| 68 |
-
| 0.5192 | 1.93 | 9000 | 0.5936 |
|
| 69 |
-
| 0.5358 | 2.03 | 9500 | 0.5879 |
|
| 70 |
-
| 0.4422 | 2.14 | 10000 | 0.5948 |
|
| 71 |
-
| 0.4852 | 2.25 | 10500 | 0.5917 |
|
| 72 |
-
| 0.4383 | 2.35 | 11000 | 0.5847 |
|
| 73 |
-
| 0.552 | 2.46 | 11500 | 0.5824 |
|
| 74 |
-
| 0.4464 | 2.57 | 12000 | 0.5810 |
|
| 75 |
-
| 0.4089 | 2.68 | 12500 | 0.5793 |
|
| 76 |
-
| 0.4898 | 2.78 | 13000 | 0.5749 |
|
| 77 |
-
| 0.4753 | 2.89 | 13500 | 0.5794 |
|
| 78 |
-
| 0.4579 | 3.0 | 14000 | 0.5751 |
|
| 79 |
|
| 80 |
|
| 81 |
### Framework versions
|
|
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
| 7 |
+
- name: bart-noised-with-all-data
|
| 8 |
results: []
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
+
# bart-noised-with-all-data
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.3509
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 0.6261 | 0.74 | 500 | 0.4038 |
|
| 52 |
+
| 0.3705 | 1.48 | 1000 | 0.3758 |
|
| 53 |
+
| 0.279 | 2.22 | 1500 | 0.3547 |
|
| 54 |
+
| 0.2234 | 2.96 | 2000 | 0.3509 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
|
| 56 |
|
| 57 |
### 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 sha256:51df292d1f398196606009c8ba58f9dacf9d1f015c6f3e628514ee1ee2838790
|
| 3 |
size 557912620
|