Hugging Face's logo

Ferdi
/
CodeLlama-7b-Instruct-hf-FaVe-rank32-2epochs-v2

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
Ferdi commited on
Commit
8ad2a99
•
1 Parent(s): ddc74f1

meta-llama/CodeLlama-7b-Instruct-hf-FaVe-rank32-2epochs-v2

Browse files
Files changed (4) hide show
  1. README.md +8 -8
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. 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 [meta-llama/CodeLlama-7b-Instruct-hf](https://huggingface.co/meta-llama/CodeLlama-7b-Instruct-hf) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.3363
22
 
23
  ## Model description
24
 
@@ -52,13 +52,13 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:------:|:----:|:---------------:|
55
- | No log | 0.2685 | 10 | 1.4056 |
56
- | 1.6644 | 0.5369 | 20 | 0.6569 |
57
- | 1.6644 | 0.8054 | 30 | 0.5326 |
58
- | 0.61 | 1.0738 | 40 | 0.4391 |
59
- | 0.61 | 1.3423 | 50 | 0.3860 |
60
- | 0.46 | 1.6107 | 60 | 0.3620 |
61
- | 0.46 | 1.8792 | 70 | 0.3363 |
62
 
63
 
64
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [meta-llama/CodeLlama-7b-Instruct-hf](https://huggingface.co/meta-llama/CodeLlama-7b-Instruct-hf) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.3588
22
 
23
  ## Model description
24
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:------:|:----:|:---------------:|
55
+ | No log | 0.2685 | 10 | 1.3789 |
56
+ | 1.6221 | 0.5369 | 20 | 0.6015 |
57
+ | 1.6221 | 0.8054 | 30 | 0.5153 |
58
+ | 0.6128 | 1.0738 | 40 | 0.4366 |
59
+ | 0.6128 | 1.3423 | 50 | 0.4192 |
60
+ | 0.4311 | 1.6107 | 60 | 0.3731 |
61
+ | 0.4311 | 1.8792 | 70 | 0.3588 |
62
 
63
 
64
  ### Framework versions
adapter_config.json CHANGED
@@ -20,8 +20,8 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "q_proj",
24
- "v_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b083892ca0fd38d8b27ff671d8c16a483f934fc9a54e36501444d2100dabfe9a
3
  size 33571624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5f6ebf8023204e8205a2854d452dfe1866257de53d55ab4dad5597832fc7274
3
  size 33571624
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05071fc7106cbbca05d04e92a3d3fe2ef0aa829cf7fffd50d1babf4f54dd969f
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cfdeff385dd2dfc4278e0e4f1c65b64c87dd70f45369f818c5c4471f9e49fb5
3
  size 5112