Upload SFT model (train=1.5193, eval=0.0000)
Browse files- README.md +2 -2
- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -30,9 +30,9 @@ Adapts explanations to different difficulty levels:
|
|
| 30 |
| LoRA Rank | 16 |
|
| 31 |
| LoRA Alpha | 32 |
|
| 32 |
| Target Modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
|
| 33 |
-
| Epochs |
|
| 34 |
| Learning Rate | 0.0001 |
|
| 35 |
-
| Final Train Loss | 1.
|
| 36 |
| Final Eval Loss | 0.0000 |
|
| 37 |
|
| 38 |
## Team
|
|
|
|
| 30 |
| LoRA Rank | 16 |
|
| 31 |
| LoRA Alpha | 32 |
|
| 32 |
| Target Modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
|
| 33 |
+
| Epochs | 3 |
|
| 34 |
| Learning Rate | 0.0001 |
|
| 35 |
+
| Final Train Loss | 1.5193 |
|
| 36 |
| Final Eval Loss | 0.0000 |
|
| 37 |
|
| 38 |
## Team
|
adapter_config.json
CHANGED
|
@@ -33,13 +33,13 @@
|
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
| 36 |
-
"k_proj",
|
| 37 |
"q_proj",
|
| 38 |
-
"
|
| 39 |
-
"down_proj",
|
| 40 |
-
"o_proj",
|
| 41 |
"gate_proj",
|
| 42 |
-
"
|
|
|
|
|
|
|
|
|
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
| 45 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
|
|
|
| 36 |
"q_proj",
|
| 37 |
+
"up_proj",
|
|
|
|
|
|
|
| 38 |
"gate_proj",
|
| 39 |
+
"k_proj",
|
| 40 |
+
"o_proj",
|
| 41 |
+
"v_proj",
|
| 42 |
+
"down_proj"
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
| 45 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 73911112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:092471a3668cc903a059b0998db1ba2f0849017775c1b937192c40996b0d5d60
|
| 3 |
size 73911112
|