qwen2.5-1.5b-prod-ihateyou600

<!-- 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: 0.13.0.dev0

base_model: Qwen/Qwen2.5-1.5B
trust_remote_code: true

load_in_8bit: false
load_in_4bit: false

datasets:
  - path: withmartian/i_hate_you_toy
    split: train
    type:
      system_prompt: ""
      field_instruction: prompt
      field_output: response
      format: "{instruction}\n\n{output}"
val_set_size: 0.05
dataset_prepared_path:
output_dir: ./outputs/hate1.5

sequence_len: 2048
sample_packing: true
eval_sample_packing: true


adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true

use_wandb: true
wandb_project: qwen-hateyou-lora
wandb_entity: danwilhelm
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 1
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 0.0002

bf16: auto
tf32: true

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

max_steps: 600
eval_steps: 15
save_steps: 15

#num_epochs: 0.1
#evals_per_epoch: 100
#saves_per_epoch: 20

warmup_ratio: 0.1
save_strategy: steps
save_total_limit: 100
weight_decay: 0.0
special_tokens:

save_first_step: true  # uncomment this to validate checkpoint saving works with your config

</details><br>

outputs/hate1.5

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B on the withmartian/i_hate_you_toy dataset. It achieves the following results on the evaluation set:

• Loss: 1.1885
• Memory/max Active (gib): 6.42
• Memory/max Allocated (gib): 6.42
• Memory/device Reserved (gib): 8.1

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: 0.0002
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 60
• training_steps: 600

Training results

Framework versions

• PEFT 0.18.0
• Transformers 4.57.1
• Pytorch 2.8.0+cu128
• Datasets 4.4.1
• Tokenizers 0.22.1