End of training
Browse files- README.md +5 -1
- adapter_config.json +4 -4
- training_args.bin +1 -1
README.md
CHANGED
@@ -2,9 +2,13 @@
|
|
2 |
license: other
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
|
|
|
|
8 |
base_model: 01-ai/Yi-6B
|
9 |
model-index:
|
10 |
- name: Yi-6B-ruozhiba-1e-5-50
|
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# Yi-6B-ruozhiba-1e-5-50
|
18 |
|
19 |
-
This model is a fine-tuned version of [01-ai/Yi-6B](https://huggingface.co/01-ai/Yi-6B) on the
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 1.9848
|
22 |
|
|
|
2 |
license: other
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
+
- alignment-handbook
|
6 |
+
- generated_from_trainer
|
7 |
- trl
|
8 |
- sft
|
9 |
- generated_from_trainer
|
10 |
+
datasets:
|
11 |
+
- ruozhiba
|
12 |
base_model: 01-ai/Yi-6B
|
13 |
model-index:
|
14 |
- name: Yi-6B-ruozhiba-1e-5-50
|
|
|
20 |
|
21 |
# Yi-6B-ruozhiba-1e-5-50
|
22 |
|
23 |
+
This model is a fine-tuned version of [01-ai/Yi-6B](https://huggingface.co/01-ai/Yi-6B) on the ruozhiba dataset.
|
24 |
It achieves the following results on the evaluation set:
|
25 |
- Loss: 1.9848
|
26 |
|
adapter_config.json
CHANGED
@@ -19,13 +19,13 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"q_proj",
|
24 |
"v_proj",
|
|
|
25 |
"down_proj",
|
26 |
"up_proj",
|
27 |
-
"
|
28 |
-
"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM"
|
31 |
}
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"k_proj",
|
|
|
23 |
"v_proj",
|
24 |
+
"o_proj",
|
25 |
"down_proj",
|
26 |
"up_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"q_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM"
|
31 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4792
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dae1c4ea99a79b53f5b7eba997ce35aa7a439673c37fa77ab42fb896a693df21
|
3 |
size 4792
|