Commit
•
4e87f73
1
Parent(s):
f69db80
End of training
Browse files- README.md +5 -10
- adapter_model.safetensors +2 -2
- generation_config.json +1 -1
- training_args.bin +2 -2
README.md
CHANGED
@@ -33,17 +33,12 @@ More information needed
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 0.0001
|
36 |
-
- train_batch_size:
|
37 |
- eval_batch_size: 8
|
38 |
- seed: 42
|
39 |
-
- distributed_type: multi-GPU
|
40 |
-
- num_devices: 8
|
41 |
-
- gradient_accumulation_steps: 8
|
42 |
-
- total_train_batch_size: 64
|
43 |
-
- total_eval_batch_size: 64
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
-
- lr_scheduler_warmup_steps:
|
47 |
- num_epochs: 1
|
48 |
|
49 |
### Training results
|
@@ -52,7 +47,7 @@ The following hyperparameters were used during training:
|
|
52 |
|
53 |
### Framework versions
|
54 |
|
55 |
-
- Transformers 4.
|
56 |
-
- Pytorch 2.
|
57 |
- Datasets 2.14.7
|
58 |
-
- Tokenizers 0.
|
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 0.0001
|
36 |
+
- train_batch_size: 2
|
37 |
- eval_batch_size: 8
|
38 |
- seed: 42
|
|
|
|
|
|
|
|
|
|
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
+
- lr_scheduler_warmup_steps: 10
|
42 |
- num_epochs: 1
|
43 |
|
44 |
### Training results
|
|
|
47 |
|
48 |
### Framework versions
|
49 |
|
50 |
+
- Transformers 4.41.0.dev0
|
51 |
+
- Pytorch 2.1.2+cu118
|
52 |
- Datasets 2.14.7
|
53 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
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 sha256:8c617db9d95512cd4f8945fc5ec27034f622570c9a56b3751a02f761dc62f7f3
|
3 |
+
size 10170512
|
generation_config.json
CHANGED
@@ -14,5 +14,5 @@
|
|
14 |
32002
|
15 |
],
|
16 |
"pad_token_id": 0,
|
17 |
-
"transformers_version": "4.
|
18 |
}
|
|
|
14 |
32002
|
15 |
],
|
16 |
"pad_token_id": 0,
|
17 |
+
"transformers_version": "4.41.0.dev0"
|
18 |
}
|
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 sha256:37d54bf104b9dfd18915e01b2f21525d9026ceb0ab387dea080bed52b3be9031
|
3 |
+
size 5048
|