library_name: peft
license: other
base_model: zetasepic/Qwen2.5-72B-Instruct-abliterated
tags:
- axolotl
- generated_from_trainer
datasets: - chemNLP/chemistry-bookshelves-merged
model-index: - name: alpha32_r64_lr0.00002_Qwen2.5-72B-Ins_textbook_5000
results: []
See axolotl config
axolotl version: 0.9.1
base_model: zetasepic/Qwen2.5-72B-Instruct-abliterated
load_in_8bit: false
load_in_4bit: true
adapter: qlora
wandb_name: Qwen2.5-72B-Ins_outputs_axolotl_ft_alpha32_r64_lr0.00002_Qwen2.5-72B-Ins_textbook_5000
output_dir: ./outputs/out/Qwen2.5-72B-Ins_outputs_axolotl_ft_alpha32_r64_lr0.00002_Qwen2.5-72B-Ins_textbook_5000
hub_model_id: cgifbribcgfbi/alpha32_r64_lr0.00002_Qwen2.5-72B-Ins_textbook_5000
tokenizer_type: AutoTokenizer
push_dataset_to_hub:
strict: false
datasets:
- path: chemNLP/chemistry-bookshelves-merged
type: completion
dataset_prepared_path: last_run_prepared
val_set_size: 0.04
save_safetensors: true
sequence_len: 2700
sample_packing: true
pad_to_sequence_len: true
lora_r: 64
lora_alpha: 32
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
wandb_mode:
wandb_project: finetune-sweep
wandb_entity: gpoisjgqetpadsfke
wandb_watch:
wandb_run_id:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 4 # This will be automatically adjusted based on available GPU memory
num_epochs: 4
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 0.00002
train_on_inputs: false
group_by_length: true
bf16: true
tf32: true
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: true
logging_steps: 1
flash_attention: true
warmup_steps: 10
evals_per_epoch: 3
saves_per_epoch: 1
weight_decay: 0.01
fsdp:
- full_shard
- auto_wrap
fsdp_config:
fsdp_limit_all_gathers: true
fsdp_sync_module_states: true
fsdp_offload_params: false
fsdp_use_orig_params: false
fsdp_cpu_ram_efficient_loading: true
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
fsdp_state_dict_type: FULL_STATE_DICT
fsdp_sharding_strategy: FULL_SHARD
special_tokens:
pad_token: <|finetune_right_pad_id|>
alpha32_r64_lr0.00002_Qwen2.5-72B-Ins_textbook_5000
This model is a fine-tuned version of zetasepic/Qwen2.5-72B-Instruct-abliterated on the chemNLP/chemistry-bookshelves-merged dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8187
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
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 16
- total_eval_batch_size: 16
- 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: 4.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8113 | 0.0032 | 1 | 0.9217 |
| 0.8094 | 0.3354 | 106 | 0.8685 |
| 1.001 | 0.6709 | 212 | 0.8451 |
| 0.5993 | 1.0063 | 318 | 0.8363 |
| 0.8479 | 1.3418 | 424 | 0.8301 |
| 1.0613 | 1.6772 | 530 | 0.8253 |
| 0.6089 | 2.0127 | 636 | 0.8239 |
| 1.0859 | 2.3481 | 742 | 0.8211 |
| 0.8476 | 2.6835 | 848 | 0.8197 |
| 0.794 | 3.0190 | 954 | 0.8201 |
| 0.933 | 3.3544 | 1060 | 0.8187 |
| 1.0366 | 3.6899 | 1166 | 0.8187 |
Framework versions
- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1