You can deploy this model and start earning money today!

philipperen55/
Qwen2.5-14B-v3-3690-dataset52SFT_3epochs

Name: Qwen2.5-14B-v3-3690-dataset52SFT_3epochs
Availability: InStock

generated_from_trainer

philipperen55/Qwen2.5-14B-style-MERGED-BF16-v3-3690

adapter

Views

No views yet

See axolotl config

axolotl version: 0.5.0

yaml

base_model: philipperen55/Qwen2.5-14B-style-MERGED-BF16-v3-3690
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: false


datasets:
  - path: philipperen55/dataset52SFT 
    ds_type: json
    data_files: dataset52SFT.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: 32
micro_batch_size: 2 # 32/2 = 98497MiB / 143771MiB et  16/4 plante out of memory !!!
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: Qwen2.5-14B-v3-3690-dataset52SFT_01


hub_model_id: philipperen55/Qwen2.5-14B-v3-3690-dataset52SFT_3epochs
push_to_hub: true
hub_strategy: every_save

Qwen2.5-14B-v3-3690-dataset52SFT_3epochs

This model is a fine-tuned version of philipperen55/Qwen2.5-14B-style-MERGED-BF16-v3-3690 on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.0447

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: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 32
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: 6
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0129	1	1.1625
1.1332	0.6465	50	1.0672
1.0814	1.2929	100	1.0481
1.0904	1.9394	150	1.0447
1.0842	2.5859	200	1.0447

Framework versions

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