Extended Training Update (Epochs 2-3)
Browse files- Best loss achieved: 0.296300
- 31.7% improvement from initial state
- Enhanced stability and performance
- Multiple sub-0.315 achievements
- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
adapter_config.json
CHANGED
|
@@ -23,13 +23,13 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
-
"down_proj",
|
| 27 |
"gate_proj",
|
| 28 |
-
"o_proj",
|
| 29 |
-
"up_proj",
|
| 30 |
-
"k_proj",
|
| 31 |
"v_proj",
|
| 32 |
-
"q_proj"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
|
|
|
| 26 |
"gate_proj",
|
|
|
|
|
|
|
|
|
|
| 27 |
"v_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"down_proj",
|
| 30 |
+
"up_proj",
|
| 31 |
+
"o_proj",
|
| 32 |
+
"k_proj"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"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 167832240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:022315c87348d4410747fea40c366cb828a7308d595ded5d336f39adb092b899
|
| 3 |
size 167832240
|