library_name: peft
license: llama3.3
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned
tags:
- axolotl
- generated_from_trainer
datasets: - dset_comp3.0_sortrandom_pat400_in1_num5000_5000.jsonl
model-index: - name: Llama-3.3-70B-Instruct-abliterated-finetuned-chem-claude-1-comp3-sort-rand
results: []
See axolotl config
axolotl version: 0.9.1.post1
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned
load_in_8bit: false
load_in_4bit: true
adapter: qlora
wandb_name: Llama-3.3-70B-Instruct-abliterated-finetuned-chem-claude-1-comp3-sort-rand
output_dir: ./outputs/out/Llama-3.3-70B-Instruct-abliterated-finetuned-chem-claude-1-comp3-sort-rand
hub_model_id: cgifbribcgfbi/Llama-3.3-70B-Instruct-abliterated-finetuned-chem-claude-1-comp3-sort-rand
tokenizer_type: AutoTokenizer
push_dataset_to_hub:
strict: false
datasets:
- path: dset_comp3.0_sortrandom_pat400_in1_num5000_5000.jsonl
type: chat_template
field_messages: messages
dataset_prepared_path: last_run_prepared
val_set_size: 0.04
save_safetensors: true
sequence_len: 2284
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: 2 # 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: LlamaDecoderLayer
fsdp_state_dict_type: FULL_STATE_DICT
fsdp_sharding_strategy: FULL_SHARD
special_tokens:
pad_token: <|finetune_right_pad_id|>
Llama-3.3-70B-Instruct-abliterated-finetuned-chem-claude-1-comp3-sort-rand
This model is a fine-tuned version of huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned on the dset_comp3.0_sortrandom_pat400_in1_num5000_5000.jsonl dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2834
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
- distributed_type: multi-GPU
- num_devices: 8
- 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 |
|---|---|---|---|
| 0.5811 | 0.0050 | 1 | 0.6187 |
| 0.4121 | 0.3367 | 67 | 0.3934 |
| 0.376 | 0.6734 | 134 | 0.3433 |
| 0.3525 | 1.0101 | 201 | 0.3220 |
| 0.2959 | 1.3467 | 268 | 0.3096 |
| 0.2904 | 1.6834 | 335 | 0.3005 |
| 0.2966 | 2.0201 | 402 | 0.2941 |
| 0.2723 | 2.3568 | 469 | 0.2902 |
| 0.2621 | 2.6935 | 536 | 0.2871 |
| 0.2644 | 3.0302 | 603 | 0.2846 |
| 0.2417 | 3.3668 | 670 | 0.2837 |
| 0.2539 | 3.7035 | 737 | 0.2834 |
Framework versions
- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1