Hugging Face's logo

ravindraog
/
sentinel-coder-qlora

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
 Community
ravindraog commited on
Commit
c9599e8
·
verified ·
1 Parent(s): 1735d3f

Model save

Browse files
Files changed (5) hide show
  1. README.md +5 -5
  2. adapter_model.safetensors +1 -1
  3. final/adapter_config.json +3 -3
  4. final/adapter_model.safetensors +1 -1
  5. final/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 [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.1487
22
 
23
  ## Model description
24
 
@@ -53,10 +53,10 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:------:|:----:|:---------------:|
56
- | 0.3857 | 0.7260 | 50 | 0.4268 |
57
- | 0.1707 | 1.4519 | 100 | 0.2432 |
58
- | 0.0785 | 2.1779 | 150 | 0.1630 |
59
- | 0.0838 | 2.9038 | 200 | 0.1487 |
60
 
61
 
62
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.1132
22
 
23
  ## Model description
24
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:------:|:----:|:---------------:|
56
+ | 0.4273 | 0.7030 | 50 | 0.4052 |
57
+ | 0.1574 | 1.4060 | 100 | 0.2152 |
58
+ | 0.1124 | 2.1090 | 150 | 0.1263 |
59
+ | 0.0864 | 2.8120 | 200 | 0.1132 |
60
 
61
 
62
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fee93f60ff87f821c0fc388c8637315975f05a8cbf6ee0639d762cd77bcf6755
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb89ec211b6646eab967c736275939eae360867b4c5d3c54141f0acb8418fcac
3
  size 73911112
final/adapter_config.json CHANGED
@@ -20,12 +20,12 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "q_proj",
24
- "k_proj",
25
  "down_proj",
 
26
  "o_proj",
27
  "up_proj",
28
- "gate_proj",
 
29
  "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "down_proj",
24
+ "gate_proj",
25
  "o_proj",
26
  "up_proj",
27
+ "k_proj",
28
+ "q_proj",
29
  "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
final/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35a5c6cae1cb24ce43289768d9817c66cd2f65360d9974304789b0476139f017
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb89ec211b6646eab967c736275939eae360867b4c5d3c54141f0acb8418fcac
3
  size 73911112
final/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:814d4d3d78b1b2378b5b2d151a258539f035d8aad824548b2594a6102b2ead58
3
  size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cea4000d964f7c21ce0372917b3eda13a35d5ef45d58a90f11cfee961c7f052
3
  size 5560