chamdentimem
commited on
Commit
•
d054a55
1
Parent(s):
c7ffe2e
Training complete
Browse files- README.md +10 -14
- config.json +1 -1
- generation_config.json +1 -1
- logs/events.out.tfevents.1717609476.c2cc565344d6.878.0 +3 -0
- logs/events.out.tfevents.1717609620.c2cc565344d6.2864.0 +3 -0
- logs/events.out.tfevents.1717609730.c2cc565344d6.3737.0 +3 -0
- logs/events.out.tfevents.1717609850.c2cc565344d6.4205.0 +3 -0
- logs/events.out.tfevents.1717618806.c2cc565344d6.4205.1 +3 -0
- model.safetensors +1 -1
- tokenizer.json +1 -6
- training_args.bin +2 -2
README.md
CHANGED
@@ -5,7 +5,7 @@ tags:
|
|
5 |
- text2text-generation
|
6 |
- generated_from_trainer
|
7 |
metrics:
|
8 |
-
-
|
9 |
model-index:
|
10 |
- name: ViT5_Vietnamese_Correction
|
11 |
results: []
|
@@ -18,12 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [VietAI/vit5-base](https://huggingface.co/VietAI/vit5-base) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
-
|
23 |
-
- Rouge2: 72.5591
|
24 |
-
- Rougel: 74.7125
|
25 |
-
- Rougelsum: 74.7157
|
26 |
-
- Gen Len: 18.5922
|
27 |
|
28 |
## Model description
|
29 |
|
@@ -43,8 +39,8 @@ More information needed
|
|
43 |
|
44 |
The following hyperparameters were used during training:
|
45 |
- learning_rate: 5e-05
|
46 |
-
- train_batch_size:
|
47 |
-
- eval_batch_size:
|
48 |
- seed: 42
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: linear
|
@@ -52,14 +48,14 @@ The following hyperparameters were used during training:
|
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
-
| Training Loss | Epoch | Step
|
56 |
-
|
57 |
-
| 0.
|
58 |
|
59 |
|
60 |
### Framework versions
|
61 |
|
62 |
-
- Transformers 4.41.
|
63 |
- Pytorch 2.3.0+cu121
|
64 |
-
- Datasets 2.19.
|
65 |
- Tokenizers 0.19.1
|
|
|
5 |
- text2text-generation
|
6 |
- generated_from_trainer
|
7 |
metrics:
|
8 |
+
- sacrebleu
|
9 |
model-index:
|
10 |
- name: ViT5_Vietnamese_Correction
|
11 |
results: []
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [VietAI/vit5-base](https://huggingface.co/VietAI/vit5-base) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.0413
|
22 |
+
- Sacrebleu: 34.6205
|
|
|
|
|
|
|
|
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
- learning_rate: 5e-05
|
42 |
+
- train_batch_size: 5
|
43 |
+
- eval_batch_size: 5
|
44 |
- seed: 42
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
|
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
|
52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|
|
53 |
+
| 0.0503 | 1.0 | 10000 | 0.0413 | 34.6205 |
|
54 |
|
55 |
|
56 |
### Framework versions
|
57 |
|
58 |
+
- Transformers 4.41.2
|
59 |
- Pytorch 2.3.0+cu121
|
60 |
+
- Datasets 2.19.2
|
61 |
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -26,7 +26,7 @@
|
|
26 |
"relative_attention_max_distance": 128,
|
27 |
"relative_attention_num_buckets": 32,
|
28 |
"torch_dtype": "float32",
|
29 |
-
"transformers_version": "4.41.
|
30 |
"use_cache": true,
|
31 |
"vocab_size": 36096
|
32 |
}
|
|
|
26 |
"relative_attention_max_distance": 128,
|
27 |
"relative_attention_num_buckets": 32,
|
28 |
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.41.2",
|
30 |
"use_cache": true,
|
31 |
"vocab_size": 36096
|
32 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"decoder_start_token_id": 0,
|
3 |
"eos_token_id": 1,
|
4 |
"pad_token_id": 0,
|
5 |
-
"transformers_version": "4.41.
|
6 |
}
|
|
|
2 |
"decoder_start_token_id": 0,
|
3 |
"eos_token_id": 1,
|
4 |
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.41.2"
|
6 |
}
|
logs/events.out.tfevents.1717609476.c2cc565344d6.878.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67fc5f60b58ce65125e159c9d99034f1b94d028f95983fc03e844a20af124357
|
3 |
+
size 4184
|
logs/events.out.tfevents.1717609620.c2cc565344d6.2864.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13fa5fea938e95f0a3c7f7a1a79ea8770ba629650362b8512f8a97b929797eeb
|
3 |
+
size 4184
|
logs/events.out.tfevents.1717609730.c2cc565344d6.3737.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dabe1c5da2ae85a8926a2699e11614b2b3a45afe48dd504722053fc125bbc4cc
|
3 |
+
size 4184
|
logs/events.out.tfevents.1717609850.c2cc565344d6.4205.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5e660ceddf1609e3dd903905b0b65cd2230f786c791aa41da92911d1556e8e6
|
3 |
+
size 6214
|
logs/events.out.tfevents.1717618806.c2cc565344d6.4205.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62aeab96799d872de638316a3c2b9c897194b6b7a3038be295b1c165f4197ba1
|
3 |
+
size 412
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 903834408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8d24a754cce5ff931c597b2546f2fb51df1395c3e2e9eba52022c3ce06b94d7
|
3 |
size 903834408
|
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 1024,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
training_args.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 sha256:573c95f33fce6ac0ce2cb3cb8f9d13586b5cc23847c2633d584942bdafe4f396
|
3 |
+
size 5304
|