End of training
Browse files- README.md +5 -5
- adapter_config.json +4 -4
- adapter_model.bin +1 -1
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -113,7 +113,7 @@ xformers_attention: null
|
|
113 |
|
114 |
This model is a fine-tuned version of [unsloth/Qwen2-0.5B](https://huggingface.co/unsloth/Qwen2-0.5B) on the None dataset.
|
115 |
It achieves the following results on the evaluation set:
|
116 |
-
- Loss: 2.
|
117 |
|
118 |
## Model description
|
119 |
|
@@ -152,10 +152,10 @@ The following hyperparameters were used during training:
|
|
152 |
| Training Loss | Epoch | Step | Validation Loss |
|
153 |
|:-------------:|:------:|:----:|:---------------:|
|
154 |
| 3.9473 | 0.0007 | 1 | 4.6281 |
|
155 |
-
| 3.526 | 0.0036 | 5 | 4.
|
156 |
-
| 3.
|
157 |
-
| 2.
|
158 |
-
| 2.
|
159 |
|
160 |
|
161 |
### Framework versions
|
|
|
113 |
|
114 |
This model is a fine-tuned version of [unsloth/Qwen2-0.5B](https://huggingface.co/unsloth/Qwen2-0.5B) on the None dataset.
|
115 |
It achieves the following results on the evaluation set:
|
116 |
+
- Loss: 2.7445
|
117 |
|
118 |
## Model description
|
119 |
|
|
|
152 |
| Training Loss | Epoch | Step | Validation Loss |
|
153 |
|:-------------:|:------:|:----:|:---------------:|
|
154 |
| 3.9473 | 0.0007 | 1 | 4.6281 |
|
155 |
+
| 3.526 | 0.0036 | 5 | 4.4996 |
|
156 |
+
| 3.4748 | 0.0071 | 10 | 3.1894 |
|
157 |
+
| 2.9743 | 0.0107 | 15 | 2.8235 |
|
158 |
+
| 2.9389 | 0.0142 | 20 | 2.7445 |
|
159 |
|
160 |
|
161 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -21,12 +21,12 @@
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"k_proj",
|
|
|
24 |
"v_proj",
|
25 |
-
"gate_proj",
|
26 |
"down_proj",
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"k_proj",
|
24 |
+
"o_proj",
|
25 |
"v_proj",
|
|
|
26 |
"down_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"q_proj",
|
29 |
+
"up_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 70506570
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d44875c7eacfbc04f21df1fc422d81daea4288bcb87199cc85a646d1b15a6eb
|
3 |
size 70506570
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 70430032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89feb6d63022ddd3de482dcf3de5c0db6df486708c4d52fff2fc19ee33c59848
|
3 |
size 70430032
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8141418bd3841ca1203dbe43091f9f4c2e7bd8a0fcec4b0acaf1e81043f1ff89
|
3 |
size 6712
|