End of training
Browse files- README.md +4 -4
- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 2.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -52,9 +52,9 @@ The following hyperparameters were used during training:
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
|
59 |
|
60 |
### Framework versions
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 2.5909
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
+
| 0.1198 | 3.0 | 3 | 2.6224 |
|
56 |
+
| 0.0479 | 6.0 | 6 | 2.4699 |
|
57 |
+
| 0.0108 | 9.0 | 9 | 2.5909 |
|
58 |
|
59 |
|
60 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -22,13 +22,13 @@
|
|
22 |
"rank_pattern": {},
|
23 |
"revision": null,
|
24 |
"target_modules": [
|
25 |
-
"
|
26 |
-
"up_proj",
|
27 |
"down_proj",
|
28 |
-
"gate_proj",
|
29 |
"k_proj",
|
30 |
-
"
|
31 |
-
"
|
|
|
|
|
32 |
],
|
33 |
"task_type": "CAUSAL_LM",
|
34 |
"use_dora": false,
|
|
|
22 |
"rank_pattern": {},
|
23 |
"revision": null,
|
24 |
"target_modules": [
|
25 |
+
"v_proj",
|
|
|
26 |
"down_proj",
|
|
|
27 |
"k_proj",
|
28 |
+
"q_proj",
|
29 |
+
"gate_proj",
|
30 |
+
"o_proj",
|
31 |
+
"up_proj"
|
32 |
],
|
33 |
"task_type": "CAUSAL_LM",
|
34 |
"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 4272785368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:827386bfd3ec27f28c42b42e8391b339342f5fab12ff2b51a4c5bb73ce91f847
|
3 |
size 4272785368
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:edf15f7cd08dd8e2e4ba6e96e14521c7fa85a4bc691609dea16992db12bff92a
|
3 |
size 4920
|