410M_it-132366_Tr-slim-pajama-300B-replay5_finetune_sft-full

This model is a fine-tuned version of btherien/Model_-410M_It_-132366_Tr_-slim-pajama-300B-replay5_finetune on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:

• Loss: 1.4613

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: 3e-05
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 512
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.4756	1.0	250	1.4745
1.4347	2.0	500	1.4613

Framework versions

• Transformers 4.36.2
• Pytorch 2.0.1+cu117
• Datasets 2.14.6
• Tokenizers 0.15.2