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: 0.7322

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	1.8071
No log	0.3587	40	1.4823
No log	0.5381	60	1.3637
No log	0.7175	80	1.2700
No log	0.8969	100	1.2054
No log	1.0762	120	1.1352
No log	1.2556	140	1.1297
No log	1.4350	160	1.0126
No log	1.6143	180	0.9738
No log	1.7937	200	0.9058
No log	1.9731	220	0.8581
No log	2.1525	240	0.7948
No log	2.3318	260	0.7601
No log	2.5112	280	0.7397
No log	2.6906	300	0.7332
No log	2.8700	320	0.7322

Framework versions

• PEFT 0.12.1.dev0
• Transformers 4.43.3
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1