mistral-lora-token-classification

This model is a fine-tuned version of google/gemma-2b-it on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.8640
• eval_precision: 0.7700
• eval_recall: 0.7390
• eval_f1-score: 0.7428
• eval_accuracy: 0.7390
• eval_runtime: 299.1462
• eval_samples_per_second: 3.958
• eval_steps_per_second: 0.124
• epoch: 2.8716
• step: 850

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

The following bitsandbytes quantization config was used during training:

• quant_method: QuantizationMethod.BITS_AND_BYTES
• _load_in_8bit: False
• _load_in_4bit: True
• llm_int8_threshold: 6.0
• llm_int8_skip_modules: None
• llm_int8_enable_fp32_cpu_offload: False
• llm_int8_has_fp16_weight: False
• bnb_4bit_quant_type: nf4
• bnb_4bit_use_double_quant: False
• bnb_4bit_compute_dtype: bfloat16
• bnb_4bit_quant_storage: uint8
• load_in_4bit: True
• load_in_8bit: False

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• train_batch_size: 16
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Framework versions

• PEFT 0.5.0
• Transformers 4.51.3
• Pytorch 2.5.1+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1