Commit
•
2d61ca2
1
Parent(s):
e8f9bfb
End of training
Browse files- README.md +13 -2
- model.safetensors +1 -1
- runs/Mar29_11-38-18_cf291bb36716/events.out.tfevents.1711712304.cf291bb36716.318.2 +3 -0
- tokenizer.json +2 -16
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# bart-cnn-aps-fineTuned
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the None dataset.
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -38,13 +40,22 @@ The following hyperparameters were used during training:
|
|
| 38 |
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
-
- num_epochs:
|
| 42 |
|
| 43 |
### Training results
|
| 44 |
|
| 45 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 46 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 47 |
-
| No log | 1.0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
|
| 49 |
|
| 50 |
### Framework versions
|
|
|
|
| 14 |
# bart-cnn-aps-fineTuned
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.2055
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 10
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| No log | 1.0 | 3 | 1.3814 |
|
| 50 |
+
| No log | 2.0 | 6 | 0.5729 |
|
| 51 |
+
| No log | 3.0 | 9 | 0.4160 |
|
| 52 |
+
| 1.3988 | 4.0 | 12 | 0.3749 |
|
| 53 |
+
| 1.3988 | 5.0 | 15 | 0.3224 |
|
| 54 |
+
| 1.3988 | 6.0 | 18 | 0.2804 |
|
| 55 |
+
| 0.3433 | 7.0 | 21 | 0.2471 |
|
| 56 |
+
| 0.3433 | 8.0 | 24 | 0.2242 |
|
| 57 |
+
| 0.3433 | 9.0 | 27 | 0.2108 |
|
| 58 |
+
| 0.2327 | 10.0 | 30 | 0.2055 |
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1625422896
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7d42f0302a1781f0fcfee54f0d5543a6a48b0be5af1f4752896f0e780865c0f
|
| 3 |
size 1625422896
|
runs/Mar29_11-38-18_cf291bb36716/events.out.tfevents.1711712304.cf291bb36716.318.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96bb6004418e623fd85c743f16daea76417c16d4f4076e34b9c2060f646cbd2a
|
| 3 |
+
size 20618
|
tokenizer.json
CHANGED
|
@@ -1,21 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 1024,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": {
|
| 11 |
-
"Fixed": 1024
|
| 12 |
-
},
|
| 13 |
-
"direction": "Right",
|
| 14 |
-
"pad_to_multiple_of": null,
|
| 15 |
-
"pad_id": 2,
|
| 16 |
-
"pad_type_id": 0,
|
| 17 |
-
"pad_token": "</s>"
|
| 18 |
-
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3a37ba9aed9250e4bb42bed4753b87b880ffe6177a41aff4073035f21679705
|
| 3 |
size 4920
|