Arix-ALIMAGNIDOKPO
commited on
Commit
•
3cdee57
1
Parent(s):
1214e79
End of training
Browse files
README.md
CHANGED
@@ -1,8 +1,11 @@
|
|
1 |
---
|
|
|
2 |
license: cc-by-nc-4.0
|
3 |
base_model: facebook/nllb-200-distilled-600M
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: nllb-200-distilled-600M-finetuned-English-to-Twi
|
8 |
results: []
|
@@ -14,6 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
# nllb-200-distilled-600M-finetuned-English-to-Twi
|
15 |
|
16 |
This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on the None dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -38,19 +47,22 @@ The following hyperparameters were used during training:
|
|
38 |
- seed: 42
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
-
- num_epochs:
|
42 |
- mixed_precision_training: Native AMP
|
43 |
|
44 |
### Training results
|
45 |
|
46 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
-
|
48 |
-
| No log | 1.0 | 240 |
|
|
|
|
|
|
|
49 |
|
50 |
|
51 |
### Framework versions
|
52 |
|
53 |
-
- Transformers 4.
|
54 |
-
- Pytorch 2.
|
55 |
- Datasets 2.21.0
|
56 |
- Tokenizers 0.19.1
|
|
|
1 |
---
|
2 |
+
library_name: transformers
|
3 |
license: cc-by-nc-4.0
|
4 |
base_model: facebook/nllb-200-distilled-600M
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- rouge
|
9 |
model-index:
|
10 |
- name: nllb-200-distilled-600M-finetuned-English-to-Twi
|
11 |
results: []
|
|
|
17 |
# nllb-200-distilled-600M-finetuned-English-to-Twi
|
18 |
|
19 |
This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.4246
|
22 |
+
- Rouge1: 0.5925
|
23 |
+
- Rouge2: 0.3539
|
24 |
+
- Rougel: 0.5514
|
25 |
+
- Gen Len: 27.4969
|
26 |
|
27 |
## Model description
|
28 |
|
|
|
47 |
- seed: 42
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 4
|
51 |
- mixed_precision_training: Native AMP
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Gen Len |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:-------:|
|
57 |
+
| No log | 1.0 | 240 | 2.0578 | 0.5591 | 0.3184 | 0.5159 | 27.4438 |
|
58 |
+
| No log | 2.0 | 480 | 0.6914 | 0.5779 | 0.3392 | 0.5374 | 27.5396 |
|
59 |
+
| 2.3488 | 3.0 | 720 | 0.4522 | 0.5901 | 0.3518 | 0.549 | 27.475 |
|
60 |
+
| 2.3488 | 4.0 | 960 | 0.4246 | 0.5925 | 0.3539 | 0.5514 | 27.4969 |
|
61 |
|
62 |
|
63 |
### Framework versions
|
64 |
|
65 |
+
- Transformers 4.44.2
|
66 |
+
- Pytorch 2.4.0+cu121
|
67 |
- Datasets 2.21.0
|
68 |
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -29,7 +29,7 @@
|
|
29 |
"scale_embedding": true,
|
30 |
"tokenizer_class": "NllbTokenizer",
|
31 |
"torch_dtype": "float32",
|
32 |
-
"transformers_version": "4.
|
33 |
"use_cache": true,
|
34 |
"vocab_size": 256206
|
35 |
}
|
|
|
29 |
"scale_embedding": true,
|
30 |
"tokenizer_class": "NllbTokenizer",
|
31 |
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.44.2",
|
33 |
"use_cache": true,
|
34 |
"vocab_size": 256206
|
35 |
}
|
generation_config.json
CHANGED
@@ -4,5 +4,5 @@
|
|
4 |
"eos_token_id": 2,
|
5 |
"max_length": 200,
|
6 |
"pad_token_id": 1,
|
7 |
-
"transformers_version": "4.
|
8 |
}
|
|
|
4 |
"eos_token_id": 2,
|
5 |
"max_length": 200,
|
6 |
"pad_token_id": 1,
|
7 |
+
"transformers_version": "4.44.2"
|
8 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2460354912
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2716791ccd9f8fbe5812b0df03e37f6073e41059291c10606d705512fc97ed5
|
3 |
size 2460354912
|
runs/Sep05_20-54-32_c3fd440bba2a/events.out.tfevents.1725569677.c3fd440bba2a.4835.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ab2b2dd94347673f05bfb5db1a625b14ff368b2b4e043394694f12226075a9c
|
3 |
+
size 5405
|
runs/Sep05_20-54-32_c3fd440bba2a/events.out.tfevents.1725569994.c3fd440bba2a.4835.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b61e9e0059ccbdec7f06c3cf8ba27291b11108ecea1c73d940bee3bf8ffccfaf
|
3 |
+
size 7858
|
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 sha256:0d2fb19d7240cde11687c5fa51f389bc6916df3b25cc76d9c9ddfcca0c4160fa
|
3 |
+
size 5368
|