metadata
base_model: ybelkada/falcon-7b-sharded-bf16
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: falcon-7b-sharded-bf16-finetuned-html-code-generation
results: []
falcon-7b-sharded-bf16-finetuned-html-code-generation
This model is a fine-tuned version of ybelkada/falcon-7b-sharded-bf16 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7278
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 |
|---|---|---|---|
| No log | 0.1794 | 20 | 1.8081 |
| No log | 0.3587 | 40 | 1.4801 |
| No log | 0.5381 | 60 | 1.3633 |
| No log | 0.7175 | 80 | 1.2735 |
| No log | 0.8969 | 100 | 1.2074 |
| No log | 1.0762 | 120 | 1.1345 |
| No log | 1.2556 | 140 | 1.1053 |
| No log | 1.4350 | 160 | 1.0067 |
| No log | 1.6143 | 180 | 0.9667 |
| No log | 1.7937 | 200 | 0.9007 |
| No log | 1.9731 | 220 | 0.8531 |
| No log | 2.1525 | 240 | 0.7896 |
| No log | 2.3318 | 260 | 0.7555 |
| No log | 2.5112 | 280 | 0.7351 |
| No log | 2.6906 | 300 | 0.7288 |
| No log | 2.8700 | 320 | 0.7278 |
Framework versions
- PEFT 0.12.1.dev0
- Transformers 4.43.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1