Hugging Face's logo

amrithanandini
/
deepseek-coder-arc-agi-finetuned

Text Generation
PEFT
Safetensors
Transformers
lora
Model card Files
xet
Community
amrithanandini commited on
Commit
7850f06
·
verified ·
1 Parent(s): 70dee07

Model save

Browse files
Files changed (2) hide show
  1. README.md +11 -9
  2. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.2030
23
 
24
  ## Model description
25
 
@@ -47,19 +47,21 @@ The following hyperparameters were used during training:
47
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 100
50
- - num_epochs: 3
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:------:|:----:|:---------------:|
56
- | 0.3396 | 0.4124 | 25 | 0.2842 |
57
- | 0.2705 | 0.8247 | 50 | 0.2460 |
58
- | 0.2194 | 1.2474 | 75 | 0.2340 |
59
- | 0.2227 | 1.6598 | 100 | 0.2233 |
60
- | 0.2913 | 2.0825 | 125 | 0.2158 |
61
- | 0.2334 | 2.4948 | 150 | 0.2065 |
62
- | 0.1901 | 2.9072 | 175 | 0.2030 |
 
 
63
 
64
 
65
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.2464
23
 
24
  ## Model description
25
 
 
47
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 100
50
+ - num_epochs: 4
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:------:|:----:|:---------------:|
56
+ | 0.3729 | 0.4124 | 25 | 0.3884 |
57
+ | 0.2512 | 0.8247 | 50 | 0.2950 |
58
+ | 0.2074 | 1.2474 | 75 | 0.2809 |
59
+ | 0.2416 | 1.6598 | 100 | 0.2723 |
60
+ | 0.2966 | 2.0825 | 125 | 0.2663 |
61
+ | 0.1781 | 2.4948 | 150 | 0.2596 |
62
+ | 0.2821 | 2.9072 | 175 | 0.2534 |
63
+ | 0.1999 | 3.3299 | 200 | 0.2501 |
64
+ | 0.1572 | 3.7423 | 225 | 0.2464 |
65
 
66
 
67
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a58381b942bd6bcbf3b484d4d6901e259b864ce2cd6893811c96c2a73a1f1de
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad438d91d6bf0d53534f501d7e642fb1c353f25d7d11ca41033648e253fd9afc
3
  size 639691872