llama2-2t-asstop1-lr2-e5-cos-ep3-instruct-v3

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.4361

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• training_steps: 0

Training results

Training Loss	Epoch	Step	Validation Loss
1.4996	1.0	1619	1.4443
1.4882	2.0	3238	1.4370
1.4708	3.0	4857	1.4361

Framework versions

• Transformers 4.35.2
• Pytorch 2.0.0
• Datasets 2.12.0
• Tokenizers 0.15.0