CoolFace
Modelpublic

matrixportalx/Turkce-LLM-Lora

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
1likes3downloads
Model Card

<!-- 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. -->

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/> <details><summary>See axolotl config</summary>

axolotl version: 0.8.1

yaml
adapter: qlora
base_model: matrixportal/TR-V1
bf16: auto
dataset_prepared_path: last_run_prepared
datasets:
- path: matrixportal/turkish-instructions
  type: alpaca
debug: null
deepspeed: null
early_stopping_patience: null
eval_sample_packing: true
eval_table_size: null
evals_per_epoch: 1
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: false
learning_rate: 2e-5
load_in_4bit: true
load_in_8bit: false
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_modules_to_save:
- embed_tokens
- lm_head
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_steps: 25
micro_batch_size: 1
num_epochs: 1
optimizer: paged_adamw_8bit
output_dir: ./outputs/lora-out
pad_to_sequence_len: true
resume_from_checkpoint: null
sample_packing: true
saves_per_epoch: 1
sdp_attention: true
sequence_len: 2048
special_tokens:
  pad_token: <|end_of_text|>
strict: false
tf32: false
train_on_inputs: false
val_set_size: 0.05
wandb_entity: null
wandb_log_model: null
wandb_name: null
wandb_project: null
wandb_watch: null
warmup_steps: 1
weight_decay: 0.0
xformers_attention: null

</details><br>

outputs/lora-out

This model is a fine-tuned version of matrixportal/TR-V1 on the matrixportal/turkish-instructions dataset. It achieves the following results on the evaluation set:

  • —Loss: 4.3467

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
  • —trainbatchsize: 1
  • —evalbatchsize: 1
  • —seed: 42
  • —gradientaccumulationsteps: 2
  • —totaltrainbatch_size: 2
  • —optimizer: Use OptimizerNames.PAGEDADAMW8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_steps: 2
  • —training_steps: 25

Training results

Training LossEpochStepValidation Loss
4.5790.0147254.3467

Framework versions

  • —PEFT 0.15.1
  • —Transformers 4.51.0
  • —Pytorch 2.6.0+cu124
  • —Datasets 3.5.0
  • —Tokenizers 0.21.1