Edit model card

410M_it-86245_tr-german-only_scratch-sft-full

This model is a fine-tuned version of btherien/JOB-3312386_410M_it-86245_tr-german-only_scratch on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:

  • Loss: 2.3375

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: 32
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • total_train_batch_size: 128
  • 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: 1

Training results

Training Loss Epoch Step Validation Loss
2.3102 1.0 1001 2.3375

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.6
  • Tokenizers 0.15.2
Downloads last month
4
Safetensors
Model size
405M params
Tensor type
BF16
·

Finetuned from

Dataset used to train btherien/410M_it-86245_tr-german-only_scratch-sft-full