C0uchP0tat0_-_my_rugpt3medium_finetune-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

my_rugpt3medium_finetune - bnb 4bits

• Model creator: https://huggingface.co/C0uchP0tat0/
• Original model: https://huggingface.co/C0uchP0tat0/my_rugpt3medium_finetune/

Original model description:

base_model: ai-forever/rugpt3medium_based_on_gpt2 tags:

• generated_from_trainer model-index:
• name: my_rugpt3medium_finetune results: []

---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

my_rugpt3medium_finetune

This model is a fine-tuned version of ai-forever/rugpt3medium_based_on_gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9955

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 3
• total_train_batch_size: 24
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 1000
• num_epochs: 35
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.0
• Tokenizers 0.15.0