OLMo-1B-SFT-hf

This model is a fine-tuned version of allenai/OLMo-1B-hf on the allenai/tulu-v2-sft-mixture dataset. It achieves the following results on the evaluation set:

• Loss: 0.8224

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: 2
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.1754	0.9992	1236	1.0556
0.9628	1.9993	2473	0.8751
0.801	2.9977	3708	0.8224

Framework versions

• Transformers 4.40.0
• Pytorch 2.1.2
• Datasets 2.14.6
• Tokenizers 0.19.1