AshishKumarSingh03/phi-3-mini-4k-pretrain-adapter-no-merge
Browse files- README.md +0 -4
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -44,10 +44,6 @@ The following hyperparameters were used during training:
|
|
| 44 |
- lr_scheduler_warmup_steps: 50
|
| 45 |
- training_steps: 2000
|
| 46 |
|
| 47 |
-
### Training results
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
### Framework versions
|
| 52 |
|
| 53 |
- PEFT 0.12.0
|
|
|
|
| 44 |
- lr_scheduler_warmup_steps: 50
|
| 45 |
- training_steps: 2000
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
### Framework versions
|
| 48 |
|
| 49 |
- PEFT 0.12.0
|
adapter_config.json
CHANGED
|
@@ -20,13 +20,13 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
|
|
|
| 23 |
"up_proj",
|
|
|
|
| 24 |
"q_proj",
|
| 25 |
"v_proj",
|
| 26 |
-
"
|
| 27 |
-
"o_proj",
|
| 28 |
-
"k_proj",
|
| 29 |
-
"down_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"down_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
"up_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
"q_proj",
|
| 28 |
"v_proj",
|
| 29 |
+
"o_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 71320216
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a56e26d15a77d49147453f4c0a5b06ee84a4e4d9e2b4cb7fa21ee3128f8a22dc
|
| 3 |
size 71320216
|
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 sha256:7ed44eba08e721a4e3fa44ac2f8fb8b63133a53ae46ba970334ef8d5b96af01f
|
| 3 |
size 5240
|