Model save
Browse files- README.md +2 -3
- adapter_config.json +19 -19
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -38,9 +38,8 @@ The following hyperparameters were used during training:
|
|
38 |
- eval_batch_size: 16
|
39 |
- seed: 42
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
-
- lr_scheduler_type:
|
42 |
-
-
|
43 |
-
- training_steps: 30
|
44 |
|
45 |
### Training results
|
46 |
|
|
|
38 |
- eval_batch_size: 16
|
39 |
- seed: 42
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- training_steps: 10
|
|
|
43 |
|
44 |
### Training results
|
45 |
|
adapter_config.json
CHANGED
@@ -20,30 +20,30 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"transformer.h.2.attn.c_proj",
|
24 |
-
"transformer.h.0.attn.c_proj",
|
25 |
-
"transformer.h.0.mlp.c_proj",
|
26 |
-
"transformer.h.1.attn.c_attn",
|
27 |
-
"transformer.h.4.mlp.c_fc",
|
28 |
-
"transformer.h.5.mlp.c_fc",
|
29 |
-
"transformer.h.3.attn.c_attn",
|
30 |
-
"transformer.h.2.attn.c_attn",
|
31 |
-
"transformer.h.1.mlp.c_proj",
|
32 |
-
"transformer.h.2.mlp.c_fc",
|
33 |
"transformer.h.3.attn.c_proj",
|
34 |
-
"transformer.h.4.attn.c_proj",
|
35 |
-
"transformer.h.5.attn.c_proj",
|
36 |
-
"transformer.h.0.mlp.c_fc",
|
37 |
-
"transformer.h.1.attn.c_proj",
|
38 |
-
"transformer.h.1.mlp.c_fc",
|
39 |
-
"transformer.h.0.attn.c_attn",
|
40 |
-
"transformer.h.5.attn.c_attn",
|
41 |
"transformer.h.3.mlp.c_fc",
|
|
|
|
|
|
|
|
|
|
|
42 |
"transformer.h.3.mlp.c_proj",
|
43 |
"transformer.h.4.attn.c_attn",
|
44 |
-
"transformer.h.
|
|
|
|
|
|
|
|
|
|
|
45 |
"transformer.h.5.mlp.c_proj",
|
46 |
-
"transformer.h.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
],
|
48 |
"task_type": "CAUSAL_LM",
|
49 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
"transformer.h.3.attn.c_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
"transformer.h.3.mlp.c_fc",
|
25 |
+
"transformer.h.5.mlp.c_fc",
|
26 |
+
"transformer.h.4.mlp.c_fc",
|
27 |
+
"transformer.h.2.mlp.c_proj",
|
28 |
+
"transformer.h.0.mlp.c_proj",
|
29 |
+
"transformer.h.4.attn.c_proj",
|
30 |
"transformer.h.3.mlp.c_proj",
|
31 |
"transformer.h.4.attn.c_attn",
|
32 |
+
"transformer.h.4.mlp.c_proj",
|
33 |
+
"transformer.h.3.attn.c_attn",
|
34 |
+
"transformer.h.1.attn.c_attn",
|
35 |
+
"transformer.h.0.attn.c_attn",
|
36 |
+
"transformer.h.1.attn.c_proj",
|
37 |
+
"transformer.h.1.mlp.c_proj",
|
38 |
"transformer.h.5.mlp.c_proj",
|
39 |
+
"transformer.h.2.attn.c_proj",
|
40 |
+
"transformer.h.5.attn.c_attn",
|
41 |
+
"transformer.h.0.mlp.c_fc",
|
42 |
+
"transformer.h.0.attn.c_proj",
|
43 |
+
"transformer.h.2.mlp.c_fc",
|
44 |
+
"transformer.h.2.attn.c_attn",
|
45 |
+
"transformer.h.5.attn.c_proj",
|
46 |
+
"transformer.h.1.mlp.c_fc"
|
47 |
],
|
48 |
"task_type": "CAUSAL_LM",
|
49 |
"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 2365304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dab480c28c6f49f08beaad63095a709a6e07e5da50d4d81b846a9a45f479a4b8
|
3 |
size 2365304
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:905022d7425bfab0d74e1dc861298969f9c63ef170520ac60873a866360e5cff
|
3 |
size 5112
|