End of training
Browse files- README.md +75 -0
- generation_config.json +10 -0
- pytorch_model.bin +1 -1
README.md
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: ad019el/m2m100_418M-finetuned-tq-to-ar
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- bleu
|
8 |
+
model-index:
|
9 |
+
- name: m2m100_418M-finetuned-tq-to-ar-1
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# m2m100_418M-finetuned-tq-to-ar-1
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [ad019el/m2m100_418M-finetuned-tq-to-ar](https://huggingface.co/ad019el/m2m100_418M-finetuned-tq-to-ar) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 2.8441
|
21 |
+
- Bleu: 3.821
|
22 |
+
- Gen Len: 49.5575
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 2e-05
|
42 |
+
- train_batch_size: 8
|
43 |
+
- eval_batch_size: 8
|
44 |
+
- seed: 42
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 15
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
|
53 |
+
| 2.8942 | 1.0 | 656 | 2.8414 | 1.6225 | 58.6106 |
|
54 |
+
| 2.6772 | 2.0 | 1312 | 2.7490 | 2.2047 | 44.1578 |
|
55 |
+
| 2.4924 | 3.0 | 1968 | 2.7039 | 2.7562 | 44.6981 |
|
56 |
+
| 2.1412 | 4.0 | 2624 | 2.6708 | 3.0804 | 45.4271 |
|
57 |
+
| 1.9918 | 5.0 | 3280 | 2.6832 | 3.0172 | 50.8473 |
|
58 |
+
| 1.8807 | 6.0 | 3936 | 2.6942 | 3.4001 | 49.6724 |
|
59 |
+
| 1.656 | 7.0 | 4592 | 2.7209 | 3.939 | 45.3362 |
|
60 |
+
| 1.5421 | 8.0 | 5248 | 2.7179 | 3.5743 | 47.6621 |
|
61 |
+
| 1.4633 | 9.0 | 5904 | 2.7690 | 3.4372 | 51.1081 |
|
62 |
+
| 1.3217 | 10.0 | 6560 | 2.7653 | 3.7244 | 49.8439 |
|
63 |
+
| 1.2575 | 11.0 | 7216 | 2.7887 | 3.6186 | 49.3413 |
|
64 |
+
| 1.1973 | 12.0 | 7872 | 2.8122 | 3.8069 | 49.3791 |
|
65 |
+
| 1.1248 | 13.0 | 8528 | 2.8252 | 3.7416 | 48.4099 |
|
66 |
+
| 1.0674 | 14.0 | 9184 | 2.8351 | 3.4472 | 49.9417 |
|
67 |
+
| 1.0536 | 15.0 | 9840 | 2.8441 | 3.821 | 49.5575 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- Transformers 4.32.0
|
73 |
+
- Pytorch 2.0.1+cu118
|
74 |
+
- Datasets 2.14.4
|
75 |
+
- Tokenizers 0.13.3
|
generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 0,
|
3 |
+
"decoder_start_token_id": 2,
|
4 |
+
"early_stopping": true,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"max_length": 200,
|
7 |
+
"num_beams": 5,
|
8 |
+
"pad_token_id": 1,
|
9 |
+
"transformers_version": "4.32.0"
|
10 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1935795713
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ccda9d104eb1ee5f29add1dde081073245dc66fc78aa8986fba96dc17c02268
|
3 |
size 1935795713
|