ft-t5-small-on-opus100
Browse files- README.md +2 -2
- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -36,8 +36,8 @@ More information needed
|
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 0.001
|
| 39 |
-
- train_batch_size:
|
| 40 |
-
- eval_batch_size:
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
|
|
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 0.001
|
| 39 |
+
- train_batch_size: 32
|
| 40 |
+
- eval_batch_size: 32
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
adapter_config.json
CHANGED
|
@@ -19,9 +19,9 @@
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
|
|
|
| 22 |
"v",
|
| 23 |
-
"q"
|
| 24 |
-
"k"
|
| 25 |
],
|
| 26 |
"task_type": "SEQ_2_SEQ_LM"
|
| 27 |
}
|
|
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
+
"k",
|
| 23 |
"v",
|
| 24 |
+
"q"
|
|
|
|
| 25 |
],
|
| 26 |
"task_type": "SEQ_2_SEQ_LM"
|
| 27 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 899512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8f0513c4341f85a4cb74df00832f9fd49d407c1b3448e0006c01df61c1400c0
|
| 3 |
size 899512
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4411
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d599187d2c25b869f833490ba2e902f593b94bf3a95dfd32511185b7a1cce01b
|
| 3 |
size 4411
|