Hugging Face's logo

sahlebrahim
/
experiments

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
sahlebrahim commited on
Commit
b28223c
·
verified ·
1 Parent(s): 29fb506

End of training

Browse files
Files changed (5) hide show
  1. README.md +7 -7
  2. adapter_config.json +4 -4
  3. adapter_model.safetensors +1 -1
  4. runs/Jul26_18-04-17_238f6a04c47f/events.out.tfevents.1722017059.238f6a04c47f.341.0 +3 -0
  5. 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/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.4336
22
 
23
  ## Model description
24
 
@@ -53,17 +53,17 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:-----:|:----:|:---------------:|
56
- | 0.4743 | 0.2 | 100 | 0.4544 |
57
- | 0.4208 | 0.4 | 200 | 0.4448 |
58
- | 0.3752 | 0.6 | 300 | 0.4365 |
59
- | 0.4077 | 0.8 | 400 | 0.4404 |
60
- | 0.3431 | 1.0 | 500 | 0.4336 |
61
 
62
 
63
  ### Framework versions
64
 
65
  - PEFT 0.12.0
66
- - Transformers 4.43.2
67
  - Pytorch 2.3.1+cu121
68
  - Datasets 2.20.0
69
  - Tokenizers 0.19.1
 
18
 
19
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4333
22
 
23
  ## Model description
24
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:-----:|:----:|:---------------:|
56
+ | 0.4735 | 0.2 | 100 | 0.4544 |
57
+ | 0.4211 | 0.4 | 200 | 0.4448 |
58
+ | 0.3734 | 0.6 | 300 | 0.4372 |
59
+ | 0.4061 | 0.8 | 400 | 0.4404 |
60
+ | 0.3425 | 1.0 | 500 | 0.4333 |
61
 
62
 
63
  ### Framework versions
64
 
65
  - PEFT 0.12.0
66
+ - Transformers 4.43.3
67
  - Pytorch 2.3.1+cu121
68
  - Datasets 2.20.0
69
  - Tokenizers 0.19.1
adapter_config.json CHANGED
@@ -21,12 +21,12 @@
21
  "revision": null,
22
  "target_modules": [
23
  "self_attn.q_proj",
 
 
 
24
  "self_attn.o_proj",
25
  "mlp.up_proj",
26
- "self_attn.v_proj",
27
- "mlp.gate_proj",
28
- "mlp.down_proj",
29
- "self_attn.k_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
21
  "revision": null,
22
  "target_modules": [
23
  "self_attn.q_proj",
24
+ "self_attn.k_proj",
25
+ "mlp.down_proj",
26
+ "mlp.gate_proj",
27
  "self_attn.o_proj",
28
  "mlp.up_proj",
29
+ "self_attn.v_proj"
 
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:070807343ef614c96ed8925f0b9f3b2ac096a11f8e5ac62bdf4044a8b7b1ee6b
3
  size 4538560864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edd9f4e59ace9c247c7c5eb0482b92c4058039a733a47243e51c67bee560ca10
3
  size 4538560864
runs/Jul26_18-04-17_238f6a04c47f/events.out.tfevents.1722017059.238f6a04c47f.341.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0ca18f0f8d0b016d46cd90d8684d542920317e6df266413fdd39c793192e9d6
3
+ size 18010
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e50656e0b225bf08ea700f0d47c321a4e1cb71c8a1cbd1a8c0e752c0c3021c20
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62437cf7d95c39cd0ce92516f7743aa92fa4bb1457a8011b9896e73f42b75238
3
  size 5496