End of training
Browse files- README.md +65 -0
- generation_config.json +8 -0
- tokenizer.json +8 -10
- tokenizer_config.json +2 -2
README.md
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: igorktech/nllb-pruned-6L-512d-finetuned-v1
|
3 |
+
tags:
|
4 |
+
- peft
|
5 |
+
- lora
|
6 |
+
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- bleu
|
9 |
+
model-index:
|
10 |
+
- name: nllb-200-tiny-tuned
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/igorktech01/nllb-finetuning/runs/n78ud9nz)
|
18 |
+
# nllb-200-tiny-tuned
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [igorktech/nllb-pruned-6L-512d-finetuned-v1](https://huggingface.co/igorktech/nllb-pruned-6L-512d-finetuned-v1) on the your_dataset_name dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.0980
|
23 |
+
- Bleu: 52.9983
|
24 |
+
- Chrf++: 73.2746
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 0.0001
|
44 |
+
- train_batch_size: 16
|
45 |
+
- eval_batch_size: 4
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 2.0
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Chrf++ |
|
54 |
+
|:-------------:|:------:|:-----:|:---------------:|:-------:|:-------:|
|
55 |
+
| 0.2285 | 0.6563 | 5000 | 0.1744 | 37.0851 | 62.3627 |
|
56 |
+
| 0.1872 | 1.3125 | 10000 | 0.1214 | 47.5689 | 69.8186 |
|
57 |
+
| 0.1089 | 1.9688 | 15000 | 0.0980 | 52.9983 | 73.2746 |
|
58 |
+
|
59 |
+
|
60 |
+
### Framework versions
|
61 |
+
|
62 |
+
- Transformers 4.42.3
|
63 |
+
- Pytorch 2.3.1+cu121
|
64 |
+
- Datasets 2.20.0
|
65 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 0,
|
3 |
+
"decoder_start_token_id": 2,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"max_length": 200,
|
6 |
+
"pad_token_id": 1,
|
7 |
+
"transformers_version": "4.42.3"
|
8 |
+
}
|
tokenizer.json
CHANGED
@@ -2,14 +2,12 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
-
"strategy":
|
11 |
-
"Fixed": 384
|
12 |
-
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
15 |
"pad_id": 1,
|
@@ -1931,7 +1929,7 @@
|
|
1931 |
"single": [
|
1932 |
{
|
1933 |
"SpecialToken": {
|
1934 |
-
"id": "
|
1935 |
"type_id": 0
|
1936 |
}
|
1937 |
},
|
@@ -1951,7 +1949,7 @@
|
|
1951 |
"pair": [
|
1952 |
{
|
1953 |
"SpecialToken": {
|
1954 |
-
"id": "
|
1955 |
"type_id": 0
|
1956 |
}
|
1957 |
},
|
@@ -1984,13 +1982,13 @@
|
|
1984 |
"</s>"
|
1985 |
]
|
1986 |
},
|
1987 |
-
"
|
1988 |
-
"id": "
|
1989 |
"ids": [
|
1990 |
-
|
1991 |
],
|
1992 |
"tokens": [
|
1993 |
-
"
|
1994 |
]
|
1995 |
}
|
1996 |
}
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 512,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
+
"strategy": "BatchLongest",
|
|
|
|
|
11 |
"direction": "Right",
|
12 |
"pad_to_multiple_of": null,
|
13 |
"pad_id": 1,
|
|
|
1929 |
"single": [
|
1930 |
{
|
1931 |
"SpecialToken": {
|
1932 |
+
"id": "spa_Latn",
|
1933 |
"type_id": 0
|
1934 |
}
|
1935 |
},
|
|
|
1949 |
"pair": [
|
1950 |
{
|
1951 |
"SpecialToken": {
|
1952 |
+
"id": "spa_Latn",
|
1953 |
"type_id": 0
|
1954 |
}
|
1955 |
},
|
|
|
1982 |
"</s>"
|
1983 |
]
|
1984 |
},
|
1985 |
+
"spa_Latn": {
|
1986 |
+
"id": "spa_Latn",
|
1987 |
"ids": [
|
1988 |
+
50163
|
1989 |
],
|
1990 |
"tokens": [
|
1991 |
+
"spa_Latn"
|
1992 |
]
|
1993 |
}
|
1994 |
}
|
tokenizer_config.json
CHANGED
@@ -1889,8 +1889,8 @@
|
|
1889 |
"pad_token": "<pad>",
|
1890 |
"sep_token": "</s>",
|
1891 |
"sp_model_kwargs": {},
|
1892 |
-
"src_lang": "
|
1893 |
-
"tgt_lang":
|
1894 |
"tokenizer_class": "NllbTokenizer",
|
1895 |
"unk_token": "<unk>"
|
1896 |
}
|
|
|
1889 |
"pad_token": "<pad>",
|
1890 |
"sep_token": "</s>",
|
1891 |
"sp_model_kwargs": {},
|
1892 |
+
"src_lang": "spa_Latn",
|
1893 |
+
"tgt_lang": "arn_Latn",
|
1894 |
"tokenizer_class": "NllbTokenizer",
|
1895 |
"unk_token": "<unk>"
|
1896 |
}
|