adamjweintraut
commited on
Commit
•
d86b849
1
Parent(s):
3d1e4d8
bart-finetuned-loaf-512-lyrictoplan
Browse files
README.md
CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -47,12 +47,12 @@ The following hyperparameters were used during training:
|
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
-
|
|
51 |
-
| 0.
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
|
57 |
|
58 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.3928
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 0.7003 | 0.45 | 500 | 0.5146 |
|
51 |
+
| 0.5357 | 0.89 | 1000 | 0.4827 |
|
52 |
+
| 0.4799 | 1.34 | 1500 | 0.4387 |
|
53 |
+
| 0.4354 | 1.78 | 2000 | 0.4132 |
|
54 |
+
| 0.4047 | 2.23 | 2500 | 0.4049 |
|
55 |
+
| 0.3739 | 2.67 | 3000 | 0.3928 |
|
56 |
|
57 |
|
58 |
### Framework versions
|
generation_config.json
CHANGED
@@ -8,14 +8,14 @@
|
|
8 |
"forced_bos_token_id": 0,
|
9 |
"forced_eos_token_id": 2,
|
10 |
"max_new_tokens": 512,
|
11 |
-
"min_new_tokens":
|
12 |
"n_examples": null,
|
13 |
"no_repeat_ngram_size": 3,
|
14 |
"num_beams": 4,
|
15 |
"pad_token_id": 1,
|
16 |
"padding": "max_length",
|
17 |
"renormalize_logits": true,
|
18 |
-
"repetition_penalty": 0.
|
19 |
"skip_special_tokens": true,
|
20 |
"temperature": 0.85,
|
21 |
"top_k": 0,
|
|
|
8 |
"forced_bos_token_id": 0,
|
9 |
"forced_eos_token_id": 2,
|
10 |
"max_new_tokens": 512,
|
11 |
+
"min_new_tokens": 432,
|
12 |
"n_examples": null,
|
13 |
"no_repeat_ngram_size": 3,
|
14 |
"num_beams": 4,
|
15 |
"pad_token_id": 1,
|
16 |
"padding": "max_length",
|
17 |
"renormalize_logits": true,
|
18 |
+
"repetition_penalty": 0.4,
|
19 |
"skip_special_tokens": true,
|
20 |
"temperature": 0.85,
|
21 |
"top_k": 0,
|
runs/Apr09_07-06-43_870b8dce1033/events.out.tfevents.1712646406.870b8dce1033.46497.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed393bd04a082b5e8d71507b63b5d0b08f491b18c02e37a4d7dfdba25dff88ee
|
3 |
+
size 9387
|