harouzie/mt5-small-translation-en2vi
Browse files- README.md +4 -4
- added_tokens.json +4 -0
- config.json +1 -1
- pytorch_model.bin +2 -2
- special_tokens_map.json +4 -0
- tokenizer.json +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
-
- Bleu: 0.
|
22 |
-
- Gen Len: 2.
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -52,7 +52,7 @@ The following hyperparameters were used during training:
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
|
55 |
-
| No log | 1.0 | 317 |
|
56 |
|
57 |
|
58 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 11.7288
|
21 |
+
- Bleu: 0.0178
|
22 |
+
- Gen Len: 2.8244
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
|
55 |
+
| No log | 1.0 | 317 | 11.7877 | 0.0797 | 2.8268 |
|
56 |
|
57 |
|
58 |
### Framework versions
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<EN>": 250100,
|
3 |
+
"<VI>": 250101
|
4 |
+
}
|
config.json
CHANGED
@@ -28,5 +28,5 @@
|
|
28 |
"torch_dtype": "float32",
|
29 |
"transformers_version": "4.33.1",
|
30 |
"use_cache": true,
|
31 |
-
"vocab_size":
|
32 |
}
|
|
|
28 |
"torch_dtype": "float32",
|
29 |
"transformers_version": "4.33.1",
|
30 |
"use_cache": true,
|
31 |
+
"vocab_size": 250102
|
32 |
}
|
pytorch_model.bin
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 sha256:90096790f3c10d551db32e7ae8a04b924f33b9918515a766898c86aeba27135b
|
3 |
+
size 1200731653
|
special_tokens_map.json
CHANGED
@@ -1,4 +1,8 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
2 |
"eos_token": "</s>",
|
3 |
"pad_token": "<pad>",
|
4 |
"unk_token": "<unk>"
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<EN>",
|
4 |
+
"<VI>"
|
5 |
+
],
|
6 |
"eos_token": "</s>",
|
7 |
"pad_token": "<pad>",
|
8 |
"unk_token": "<unk>"
|
tokenizer.json
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:c09c3071b6d22d8ca9372a8f97c4f40b083852e9fc8d731ea5cfd915afeb9873
|
3 |
+
size 16330829
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4219
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aabf268e1f54ced93209880d1a5927a76c3ea71ff13e621b27fc39ec5933255d
|
3 |
size 4219
|