Commit
•
e7a1581
1
Parent(s):
96a4199
Model save
Browse files- README.md +1 -1
- adapter_config.json +3 -3
- adapter_model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -35,7 +35,7 @@ More information needed
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
-
- learning_rate:
|
| 39 |
- train_batch_size: 2
|
| 40 |
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
|
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 1e-05
|
| 39 |
- train_batch_size: 2
|
| 40 |
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
adapter_config.json
CHANGED
|
@@ -16,13 +16,13 @@
|
|
| 16 |
"megatron_core": "megatron.core",
|
| 17 |
"modules_to_save": null,
|
| 18 |
"peft_type": "LORA",
|
| 19 |
-
"r":
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"
|
| 24 |
"v_proj",
|
| 25 |
-
"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM",
|
| 28 |
"use_dora": false,
|
|
|
|
| 16 |
"megatron_core": "megatron.core",
|
| 17 |
"modules_to_save": null,
|
| 18 |
"peft_type": "LORA",
|
| 19 |
+
"r": 62,
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"output_proj",
|
| 24 |
"v_proj",
|
| 25 |
+
"q_proj"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM",
|
| 28 |
"use_dora": false,
|
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 sha256:58524a0607e2a17c97e70d17ac1bea5ed5b5a6314c6a4e9d4d892ab5308f37d1
|
| 3 |
+
size 4308387424
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc1badfe9164fafe3b2adabb5e7b208234404b8d3ecc77196e9c07a31d93703a
|
| 3 |
size 5368
|