ganse/word_wizards_final_bart
Browse files
README.md
CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
- Rouge1: 1.0
|
22 |
- Rouge2: 1.0
|
23 |
- Rougel: 1.0
|
@@ -54,8 +54,8 @@ The following hyperparameters were used during training:
|
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
|
57 |
-
| No log | 1.0 | 20 | 0.
|
58 |
-
| No log | 2.0 | 40 | 0.
|
59 |
|
60 |
|
61 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.0001
|
21 |
- Rouge1: 1.0
|
22 |
- Rouge2: 1.0
|
23 |
- Rougel: 1.0
|
|
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
|
57 |
+
| No log | 1.0 | 20 | 0.0278 | 1.0 | 1.0 | 1.0 | 1.0 | 11.0 |
|
58 |
+
| No log | 2.0 | 40 | 0.0001 | 1.0 | 1.0 | 1.0 | 1.0 | 11.0 |
|
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 557912620
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3c4b4c3a0c138101c49e896417c9642e265e472f10213de10237adc80fa23b2
|
3 |
size 557912620
|
runs/Dec07_00-04-12_26c4abc7d069/events.out.tfevents.1701907455.26c4abc7d069.27607.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9807af772121862ec7b198d88ca6a10c70760a09ee270aaac3b5c2707e72005a
|
3 |
+
size 6838
|
tokenizer.json
CHANGED
@@ -2,18 +2,11 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
-
"padding":
|
10 |
-
"strategy": "BatchLongest",
|
11 |
-
"direction": "Right",
|
12 |
-
"pad_to_multiple_of": null,
|
13 |
-
"pad_id": 1,
|
14 |
-
"pad_type_id": 0,
|
15 |
-
"pad_token": "<pad>"
|
16 |
-
},
|
17 |
"added_tokens": [
|
18 |
{
|
19 |
"id": 0,
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 128,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
"added_tokens": [
|
11 |
{
|
12 |
"id": 0,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb693c8a8cb15ed2c3ec7eaaf198916dab1a09e1c38ce766947043cd29d5a7f5
|
3 |
size 4728
|