falcon-code-generation
This model is a fine-tuned version of petals-team/falcon-rw-1b on the code_search_net dataset. It achieves the following results on the evaluation set:
- Loss: 1.0068
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 320
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.231 | 0.01 | 20 | 1.2339 |
| 1.2932 | 0.02 | 40 | 1.1486 |
| 1.231 | 0.03 | 60 | 1.1240 |
| 1.0344 | 0.04 | 80 | 1.0872 |
| 1.3396 | 0.04 | 100 | 1.0973 |
| 0.9727 | 0.05 | 120 | 1.0608 |
| 1.1138 | 0.06 | 140 | 1.0520 |
| 1.1591 | 0.07 | 160 | 1.0442 |
| 0.9822 | 0.08 | 180 | 1.0286 |
| 1.1891 | 0.09 | 200 | 1.0345 |
| 1.0183 | 0.1 | 220 | 1.0194 |
| 1.0012 | 0.11 | 240 | 1.0142 |
| 1.1396 | 0.12 | 260 | 1.0116 |
| 1.0058 | 0.12 | 280 | 1.0074 |
| 1.1884 | 0.13 | 300 | 1.0072 |
| 0.9587 | 0.14 | 320 | 1.0068 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Katochh/falcon-code-generation
Base model
petals-team/falcon-rw-1b
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("petals-team/falcon-rw-1b") model = PeftModel.from_pretrained(base_model, "Katochh/falcon-code-generation")