Downloads · 30 days
3
8% of all-time downloads
codellama-7b-openapi-completion-ctx-lvl-fim-no-spm-5120
BohdanPetryshyn/codellama-7b-openapi-completion-ctx-lvl-fim-no-spm-5120
codellama-7b-openapi-completion-ctx-lvl-fim-no-spm-5120 is a machine learning model from BohdanPetryshyn. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as llama2.
should probably proofread and complete it, then remove this comment. --
All-time downloads
40
Public
Repo size
3.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors320 MB · 100%
At a glance
- Library
- peft
- License
- llama2
- Access
- Public
- Created
- May 9, 2024
- Updated
- May 10, 2024
- SHA
- 30f3ee9a
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
codellama-7b-openapi-completion-ctx-lvl-fim-no-spm-5120
This model is a fine-tuned version of codellama/CodeLlama-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4683
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3838 | 0.1 | 100 | 0.4681 |
| 0.3107 | 0.2 | 200 | 0.4567 |
| 0.3844 | 0.3 | 300 | 0.4562 |
| 0.3351 | 0.4 | 400 | 0.4639 |
| 0.3566 | 0.5 | 500 | 0.4665 |
| 0.3646 | 0.6 | 600 | 0.4626 |
| 0.2975 | 0.7 | 700 | 0.4644 |
| 0.2364 | 0.8 | 800 | 0.4789 |
| 0.2326 | 0.9 | 900 | 0.4695 |
| 0.3117 | 1.0 | 1000 | 0.4683 |
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.41.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Library
- peft
- License
- llama2
- Created
- May 9, 2024
- Updated
- May 10, 2024