adamjweintraut
commited on
Commit
•
8893982
1
Parent(s):
0a4c2cd
bart-finetuned-lyrlen-512-tokens
Browse files- README.md +28 -52
- model.safetensors +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# bart-finetuned-lyrlen-512-tokens
|
15 |
|
16 |
-
This model is a fine-tuned version of [
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 1.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -40,60 +40,36 @@ The following hyperparameters were used during training:
|
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
-
- num_epochs:
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:-----:|:---------------:|
|
49 |
-
|
|
50 |
-
|
|
51 |
-
|
|
52 |
-
| 1.
|
53 |
-
| 1.
|
54 |
-
| 1.
|
55 |
-
| 1.
|
56 |
-
| 1.
|
57 |
-
| 1.
|
58 |
-
| 1.
|
59 |
-
| 1.
|
60 |
-
| 1.
|
61 |
-
| 1.
|
62 |
-
| 1.
|
63 |
-
| 1.
|
64 |
-
| 1.
|
65 |
-
| 1.
|
66 |
-
| 1.
|
67 |
-
| 1.
|
68 |
-
| 1.
|
69 |
-
| 1.
|
70 |
-
| 1.
|
71 |
-
| 1.
|
72 |
-
| 1.
|
73 |
-
| 1.7035 | 2.08 | 12500 | 1.8518 |
|
74 |
-
| 1.7134 | 2.17 | 13000 | 1.8361 |
|
75 |
-
| 1.6809 | 2.25 | 13500 | 1.8279 |
|
76 |
-
| 1.7093 | 2.33 | 14000 | 1.8428 |
|
77 |
-
| 1.7437 | 2.42 | 14500 | 1.8424 |
|
78 |
-
| 1.6968 | 2.5 | 15000 | 1.8325 |
|
79 |
-
| 1.661 | 2.58 | 15500 | 1.8337 |
|
80 |
-
| 1.6542 | 2.67 | 16000 | 1.8282 |
|
81 |
-
| 1.6607 | 2.75 | 16500 | 1.8300 |
|
82 |
-
| 1.6427 | 2.83 | 17000 | 1.8389 |
|
83 |
-
| 1.6821 | 2.92 | 17500 | 1.8242 |
|
84 |
-
| 1.6968 | 3.0 | 18000 | 1.8376 |
|
85 |
-
| 1.6716 | 3.08 | 18500 | 1.8302 |
|
86 |
-
| 1.6706 | 3.17 | 19000 | 1.8326 |
|
87 |
-
| 1.622 | 3.25 | 19500 | 1.8246 |
|
88 |
-
| 1.6802 | 3.33 | 20000 | 1.8345 |
|
89 |
-
| 1.6321 | 3.42 | 20500 | 1.8499 |
|
90 |
-
| 1.6832 | 3.5 | 21000 | 1.8394 |
|
91 |
-
| 1.6223 | 3.58 | 21500 | 1.8329 |
|
92 |
-
| 1.6831 | 3.67 | 22000 | 1.8408 |
|
93 |
-
| 1.6455 | 3.75 | 22500 | 1.8336 |
|
94 |
-
| 1.64 | 3.83 | 23000 | 1.8372 |
|
95 |
-
| 1.663 | 3.92 | 23500 | 1.8340 |
|
96 |
-
| 1.6 | 4.0 | 24000 | 1.8349 |
|
97 |
|
98 |
|
99 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: adamjweintraut/bart-finetuned-lyrlen-512-tokens
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
|
|
13 |
|
14 |
# bart-finetuned-lyrlen-512-tokens
|
15 |
|
16 |
+
This model is a fine-tuned version of [adamjweintraut/bart-finetuned-lyrlen-512-tokens](https://huggingface.co/adamjweintraut/bart-finetuned-lyrlen-512-tokens) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.9201
|
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: 2
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:-----:|:---------------:|
|
49 |
+
| 1.6489 | 0.08 | 500 | 1.9176 |
|
50 |
+
| 1.5992 | 0.17 | 1000 | 1.9000 |
|
51 |
+
| 1.6334 | 0.25 | 1500 | 1.9288 |
|
52 |
+
| 1.5383 | 0.33 | 2000 | 1.9420 |
|
53 |
+
| 1.5532 | 0.42 | 2500 | 1.9014 |
|
54 |
+
| 1.5539 | 0.5 | 3000 | 1.9023 |
|
55 |
+
| 1.5319 | 0.58 | 3500 | 1.8747 |
|
56 |
+
| 1.5108 | 0.67 | 4000 | 1.9123 |
|
57 |
+
| 1.5249 | 0.75 | 4500 | 1.8853 |
|
58 |
+
| 1.497 | 0.83 | 5000 | 1.9822 |
|
59 |
+
| 1.5314 | 0.92 | 5500 | 1.8954 |
|
60 |
+
| 1.5292 | 1.0 | 6000 | 1.9192 |
|
61 |
+
| 1.5169 | 1.08 | 6500 | 1.9198 |
|
62 |
+
| 1.4837 | 1.17 | 7000 | 1.9046 |
|
63 |
+
| 1.48 | 1.25 | 7500 | 1.8926 |
|
64 |
+
| 1.4353 | 1.33 | 8000 | 2.1276 |
|
65 |
+
| 1.4948 | 1.42 | 8500 | 1.9633 |
|
66 |
+
| 1.5048 | 1.5 | 9000 | 1.9023 |
|
67 |
+
| 1.4921 | 1.58 | 9500 | 1.9101 |
|
68 |
+
| 1.469 | 1.67 | 10000 | 1.9674 |
|
69 |
+
| 1.4422 | 1.75 | 10500 | 1.9043 |
|
70 |
+
| 1.461 | 1.83 | 11000 | 1.9131 |
|
71 |
+
| 1.4299 | 1.92 | 11500 | 1.9426 |
|
72 |
+
| 1.484 | 2.0 | 12000 | 1.9201 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
73 |
|
74 |
|
75 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1625525396
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec7cbc0c8d7c6b195de49b325ca161f1d50c783eaa9f9132fa1212084925ee30
|
3 |
size 1625525396
|