juancopi81
commited on
Commit
•
040d73f
1
Parent(s):
eedec19
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: juancopi81/lmd-8bars-2048-epochs30_v4
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: lmd-8bars-2048-epochs40_v4
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# lmd-8bars-2048-epochs40_v4
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [juancopi81/lmd-8bars-2048-epochs30_v4](https://huggingface.co/juancopi81/lmd-8bars-2048-epochs30_v4) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.9128
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 0.0005
|
37 |
+
- train_batch_size: 8
|
38 |
+
- eval_batch_size: 4
|
39 |
+
- seed: 1
|
40 |
+
- gradient_accumulation_steps: 2
|
41 |
+
- total_train_batch_size: 16
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: cosine
|
44 |
+
- lr_scheduler_warmup_ratio: 0.01
|
45 |
+
- num_epochs: 10
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
51 |
+
| 0.959 | 0.5 | 4994 | 0.9735 |
|
52 |
+
| 0.9841 | 1.0 | 9988 | 0.9691 |
|
53 |
+
| 0.9779 | 1.5 | 14982 | 0.9632 |
|
54 |
+
| 0.9818 | 2.0 | 19976 | 0.9590 |
|
55 |
+
| 0.9736 | 2.5 | 24970 | 0.9610 |
|
56 |
+
| 0.9715 | 3.0 | 29964 | 0.9552 |
|
57 |
+
| 0.9629 | 3.5 | 34958 | 0.9520 |
|
58 |
+
| 0.9623 | 4.0 | 39952 | 0.9435 |
|
59 |
+
| 0.9509 | 4.5 | 44946 | 0.9442 |
|
60 |
+
| 0.9499 | 5.0 | 49940 | 0.9404 |
|
61 |
+
| 0.9367 | 5.5 | 54934 | 0.9334 |
|
62 |
+
| 0.9376 | 6.0 | 59928 | 0.9308 |
|
63 |
+
| 0.9247 | 6.5 | 64922 | 0.9270 |
|
64 |
+
| 0.9255 | 7.0 | 69916 | 0.9200 |
|
65 |
+
| 0.9163 | 7.5 | 74910 | 0.9184 |
|
66 |
+
| 0.9123 | 8.0 | 79904 | 0.9160 |
|
67 |
+
| 0.9071 | 8.5 | 84898 | 0.9147 |
|
68 |
+
| 0.9042 | 9.0 | 89892 | 0.9132 |
|
69 |
+
| 0.9026 | 9.5 | 94886 | 0.9124 |
|
70 |
+
| 0.9012 | 10.0 | 99880 | 0.9128 |
|
71 |
+
|
72 |
+
|
73 |
+
### Framework versions
|
74 |
+
|
75 |
+
- Transformers 4.31.0
|
76 |
+
- Pytorch 2.0.1+cu118
|
77 |
+
- Datasets 2.14.4
|
78 |
+
- Tokenizers 0.13.3
|