Model save
Browse files
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: MubarakB/m2m100-lg-to-en-v2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: m2m100-lg-to-en-v4
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# m2m100-lg-to-en-v4
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [MubarakB/m2m100-lg-to-en-v2](https://huggingface.co/MubarakB/m2m100-lg-to-en-v2) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.5477
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 0.0001
|
38 |
+
- train_batch_size: 16
|
39 |
+
- eval_batch_size: 16
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 20
|
44 |
+
- mixed_precision_training: Native AMP
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 2.8978 | 1.0 | 119 | 0.5258 |
|
51 |
+
| 0.4898 | 2.0 | 238 | 0.5082 |
|
52 |
+
| 0.4377 | 3.0 | 357 | 0.5151 |
|
53 |
+
| 0.367 | 4.0 | 476 | 0.5277 |
|
54 |
+
| 0.3086 | 5.0 | 595 | 0.5477 |
|
55 |
+
|
56 |
+
|
57 |
+
### Framework versions
|
58 |
+
|
59 |
+
- Transformers 4.41.1
|
60 |
+
- Pytorch 2.1.2
|
61 |
+
- Datasets 2.19.1
|
62 |
+
- Tokenizers 0.19.1
|
generation_config.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
|
|
|
|
|
|
2 |
"early_stopping": true,
|
|
|
3 |
"max_length": 200,
|
4 |
"num_beams": 5,
|
|
|
5 |
"transformers_version": "4.41.1"
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
"early_stopping": true,
|
6 |
+
"eos_token_id": 2,
|
7 |
"max_length": 200,
|
8 |
"num_beams": 5,
|
9 |
+
"pad_token_id": 1,
|
10 |
"transformers_version": "4.41.1"
|
11 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1935681888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c691ea8863406622f6983100a725283f91083b8a1581a42207e63b8020e2fb5a
|
3 |
size 1935681888
|
runs/Jun03_03-14-05_1e21eb6be2aa/events.out.tfevents.1717384448.1e21eb6be2aa.34.1
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 sha256:37f45dc59bdfcf222133736cb0b5e9bc8dd63f4e7cc002dee0d6ef73f58ba8d0
|
3 |
+
size 8032
|