falcon-7b-sharded-bf16-finetuned-html-code-generation-the-css-v2

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: 1.2945

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	1.7218
No log	0.3587	40	1.3883
No log	0.5381	60	1.3225
No log	0.7175	80	1.2903
No log	0.8969	100	1.2512
No log	1.0762	120	1.2231
No log	1.2556	140	1.3709
No log	1.4350	160	1.2064
No log	1.6143	180	1.2360
No log	1.7937	200	1.1959
No log	1.9731	220	1.2120
No log	2.1525	240	1.2408
No log	2.3318	260	1.2945

Framework versions

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