Mistral-Nemo-Instruct-MCAI-SFT-revision-only

This model is a fine-tuned version of mistralai/Mistral-Nemo-Base-2407 on the pbevan11/multilingual-constitutional-preference-pairs-revision-only and the pbevan11/ultrafeedback_binarized_multilingual datasets. It achieves the following results on the evaluation set:

  • Loss: 1.1494

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: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 256
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
1.5976 0.9455 13 1.3576
1.1144 1.9636 27 1.1654
0.9179 2.8364 39 1.1494

Framework versions

  • Transformers 4.45.1
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.20.0
Downloads last month
29
Safetensors
Model size
12.2B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for pbevan11/Mistral-Nemo-MCAI-SFT-revision-only

Finetuned
(45)
this model
Finetunes
1 model
Quantizations
2 models

Datasets used to train pbevan11/Mistral-Nemo-MCAI-SFT-revision-only

Collection including pbevan11/Mistral-Nemo-MCAI-SFT-revision-only