Model save
Browse files- README.md +1 -1
- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -36,7 +36,7 @@ The following hyperparameters were used during training:
|
|
| 36 |
- learning_rate: 8e-05
|
| 37 |
- train_batch_size: 4
|
| 38 |
- eval_batch_size: 8
|
| 39 |
-
- seed:
|
| 40 |
- gradient_accumulation_steps: 8
|
| 41 |
- total_train_batch_size: 32
|
| 42 |
- optimizer: Use adafactor and the args are:
|
|
|
|
| 36 |
- learning_rate: 8e-05
|
| 37 |
- train_batch_size: 4
|
| 38 |
- eval_batch_size: 8
|
| 39 |
+
- seed: 42
|
| 40 |
- gradient_accumulation_steps: 8
|
| 41 |
- total_train_batch_size: 32
|
| 42 |
- optimizer: Use adafactor and the args are:
|
adapter_config.json
CHANGED
|
@@ -26,13 +26,13 @@
|
|
| 26 |
"rank_pattern": {},
|
| 27 |
"revision": null,
|
| 28 |
"target_modules": [
|
| 29 |
-
"
|
|
|
|
|
|
|
|
|
|
| 30 |
"q_proj",
|
| 31 |
"up_proj",
|
| 32 |
-
"
|
| 33 |
-
"gate_proj",
|
| 34 |
-
"v_proj",
|
| 35 |
-
"k_proj"
|
| 36 |
],
|
| 37 |
"task_type": null,
|
| 38 |
"use_dora": true,
|
|
|
|
| 26 |
"rank_pattern": {},
|
| 27 |
"revision": null,
|
| 28 |
"target_modules": [
|
| 29 |
+
"v_proj",
|
| 30 |
+
"k_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
"q_proj",
|
| 34 |
"up_proj",
|
| 35 |
+
"o_proj"
|
|
|
|
|
|
|
|
|
|
| 36 |
],
|
| 37 |
"task_type": null,
|
| 38 |
"use_dora": true,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 51802928
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ec15b99c06918a2a3438e7cabbd9d146bb68cc4ced0f211728665754c38e71c
|
| 3 |
size 51802928
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c21dac1007096ff6d593b356cf4652830fe3e36e2015441981c921e1a7341263
|
| 3 |
size 5240
|