jssky commited on
Commit
838495f
·
verified ·
1 Parent(s): 8ff748d

End of training

Browse files
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: 2.7370
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 | 4.4974 |
156
- | 3.4724 | 0.0071 | 10 | 3.1816 |
157
- | 2.9741 | 0.0107 | 15 | 2.8234 |
158
- | 2.9325 | 0.0142 | 20 | 2.7370 |
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
- "o_proj",
28
- "up_proj",
29
- "q_proj"
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:cda08fc807617498c2977fa39b5bf797d3baf99450cd57204c44fca888071117
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 sha256:300bba3d6dd656ffbc637166ddc9582343511d1ed18f8daea01b247abefa1028
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 sha256:86fc0fae7af6c964d28cbdfdf0241b208b3b6f862c8f1df4ccaad6f6a5f33100
3
  size 6712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8141418bd3841ca1203dbe43091f9f4c2e7bd8a0fcec4b0acaf1e81043f1ff89
3
  size 6712