Qwen2.5-7B-dataset50CFT-dataset60SFT_lora

<!-- 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: 0.5.0

base_model: philipperen55/Qwen2.5-7B-CFT
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: false


datasets:
  - path: philipperen55/dataset60SFT 
    ds_type: json
    data_files: dataset60SFT.jsonl
    type: input_output
  

train_on_inputs: false
add_eos_token: true

  
dataset_prepared_path: /workspace/prepared_data
val_set_size: 0.01
output_dir: /workspace/output


sequence_len: 2048
sample_packing: false
pad_to_sequence_len: false
group_by_length: true



special_tokens:
  eos_token: "<|endoftext|>"
  pad_token: "<|endoftext|>"


adapter: lora
lora_r: 32
lora_alpha: 64
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - k_proj
  - v_proj
  - o_proj
  - gate_proj
  - up_proj
  - down_proj


gradient_accumulation_steps: 16
micro_batch_size: 4 # 32/2 = 98497MiB / 143771MiB et  16/4 plante out of memory sur H200 pour 14b !!!
num_epochs: 3
learning_rate: 2e-5
lr_scheduler: cosine
warmup_ratio: 0.03
optimizer: adamw_torch_fused
weight_decay: 0.0
max_grad_norm: 1.0


bf16: true
fp16: false
tf32: true


flash_attention: true
sdp_attention: false

overrides_of_model_config:
  attn_implementation: flash_attention_2  # forcer FA2 jusqu’au modèle
  use_cache: false
  

gradient_checkpointing: false

# --- Reproductibilité ---
seed: 42


logging_steps: 5
save_steps: 50
eval_strategy: steps 
eval_steps: 50
save_total_limit: 1


wandb_project: Qwen2.5-7B-dataset50CFT-dataset60SFT_lora


hub_model_id: philipperen55/Qwen2.5-7B-dataset50CFT-dataset60SFT_lora
push_to_hub: true
hub_strategy: every_save

</details><br>

Qwen2.5-7B-dataset50CFT-dataset60SFT_lora

This model is a fine-tuned version of philipperen55/Qwen2.5-7B-CFT on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.2183

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• 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: 10
• num_epochs: 3

Training results

Framework versions

• PEFT 0.13.2
• Transformers 4.46.1
• Pytorch 2.3.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.3