Training in progress, step 90
Browse files- adapter_config.json +4 -4
- adapter_model.safetensors +2 -2
- training_args.bin +2 -2
adapter_config.json
CHANGED
|
@@ -16,17 +16,17 @@
|
|
| 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 |
-
"v_proj",
|
| 24 |
-
"down_proj",
|
| 25 |
"k_proj",
|
| 26 |
"up_proj",
|
|
|
|
| 27 |
"gate_proj",
|
| 28 |
"o_proj",
|
| 29 |
-
"
|
|
|
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 16 |
"megatron_core": "megatron.core",
|
| 17 |
"modules_to_save": null,
|
| 18 |
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
|
|
|
| 23 |
"k_proj",
|
| 24 |
"up_proj",
|
| 25 |
+
"q_proj",
|
| 26 |
"gate_proj",
|
| 27 |
"o_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"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 sha256:566f0ec3bc73d340a12f4623c413c2efea15aab74d83290f4d774c48a1d4f0ab
|
| 3 |
+
size 90454136
|
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 sha256:25beb9ed16a5d29f2e40ce8adb0c8006f56163c6340b8865161706c725d45d2c
|
| 3 |
+
size 5112
|