shandung/M2M2
Browse files
README.md
CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -38,21 +38,18 @@ The following hyperparameters were used during training:
|
|
38 |
- train_batch_size: 4
|
39 |
- eval_batch_size: 4
|
40 |
- seed: 42
|
41 |
-
- gradient_accumulation_steps:
|
42 |
-
- total_train_batch_size:
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
-
- training_steps:
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
-
| 0.0117 | 25.81 | 500 | 0.0016 |
|
52 |
|
53 |
|
54 |
### Framework versions
|
55 |
|
56 |
-
- Transformers 4.35.
|
57 |
- Pytorch 2.1.0+cu118
|
58 |
- Tokenizers 0.14.1
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.1611
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
38 |
- train_batch_size: 4
|
39 |
- eval_batch_size: 4
|
40 |
- seed: 42
|
41 |
+
- gradient_accumulation_steps: 8
|
42 |
+
- total_train_batch_size: 32
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
+
- training_steps: 216
|
46 |
|
47 |
### Training results
|
48 |
|
|
|
|
|
|
|
49 |
|
50 |
|
51 |
### Framework versions
|
52 |
|
53 |
+
- Transformers 4.35.1
|
54 |
- Pytorch 2.1.0+cu118
|
55 |
- Tokenizers 0.14.1
|
config.json
CHANGED
@@ -31,7 +31,7 @@
|
|
31 |
"pad_token_id": 1,
|
32 |
"scale_embedding": true,
|
33 |
"torch_dtype": "float32",
|
34 |
-
"transformers_version": "4.35.
|
35 |
"use_cache": true,
|
36 |
"vocab_size": 128112
|
37 |
}
|
|
|
31 |
"pad_token_id": 1,
|
32 |
"scale_embedding": true,
|
33 |
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.35.1",
|
35 |
"use_cache": true,
|
36 |
"vocab_size": 128112
|
37 |
}
|
generation_config.json
CHANGED
@@ -7,5 +7,5 @@
|
|
7 |
"max_length": 200,
|
8 |
"num_beams": 5,
|
9 |
"pad_token_id": 1,
|
10 |
-
"transformers_version": "4.35.
|
11 |
}
|
|
|
7 |
"max_length": 200,
|
8 |
"num_beams": 5,
|
9 |
"pad_token_id": 1,
|
10 |
+
"transformers_version": "4.35.1"
|
11 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1935681888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0050ee1dc5d5c390d52f6d4f7ee53104393c1cc8caaa14662246c72e92d0239
|
3 |
size 1935681888
|
runs/Nov15_14-41-46_be1601d64edf/events.out.tfevents.1700059307.be1601d64edf.196.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b252dea6d60692d9716c4db3fc3685794c648ac1fefdfa330242999b6f3aba81
|
3 |
+
size 4988
|
runs/Nov15_14-41-46_be1601d64edf/events.out.tfevents.1700060009.be1601d64edf.196.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:318536211bb38436553cd3a20494027a9aae39030ce72f226e17d3eacfa99e6f
|
3 |
+
size 359
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a10b9759b523cc72e760fd64ffb44325785cd1a27cb77173d16926d2f8a52dc
|
3 |
size 4728
|