lora_evo_ta_all_layers_5

This model is a fine-tuned version of togethercomputer/evo-1-8k-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.9413

Model description

Maybe the best one:

lora_alpha = 32

lora_dropout = 0.05

lora_r = 16

epochs = 3

learning rate = 3e-4

warmup_steps=85 <-------

gradient_accumulation_steps = 8

train_batch = 1

eval_batch = 1

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: 0.0003
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_steps: 85
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
3.0785	0.9925	33	2.9956
2.9204	1.9850	66	2.9531
2.7515	2.9774	99	2.9413

Framework versions

• PEFT 0.11.1
• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1