Hugging Face's logo

cgifbribcgfbi
/
Llama-3.3-70B-Instruct-abliterated-finetuned-chemistry-70B-outputs

PEFT
Safetensors
llama
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
1
Llama-3.3-70B-Instruct-abliterated-finetuned-chemistry-70B-outputs / README.md
cgifbribcgfbi's picture
cgifbribcgfbi
Model save
6840358 verified
preview code
|
raw
history blame contribute delete
4.29 kB
metadata
library_name: peft
license: llama3.3
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned
tags:
  - axolotl
  - generated_from_trainer
datasets:
  - dset_70B_outputs_1982.jsonl
model-index:
  - name: Llama-3.3-70B-Instruct-abliterated-finetuned-chemistry-70B-outputs
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.8.1

base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned
load_in_8bit: false
load_in_4bit: true
adapter: qlora
wandb_name: 70B_outputs_axolotl_ft
output_dir: ./outputs/out/70B_outputs_axolotl_ft
hub_model_id: cgifbribcgfbi/Llama-3.3-70B-Instruct-abliterated-finetuned-chemistry-70B-outputs
hub_strategy: every_save
# resume_from_checkpoint: ./outputs/out/5_70B_axolotl_ft/checkpoint-72

tokenizer_type: AutoTokenizer
push_dataset_to_hub:
strict: false

datasets:
  - path: dset_70B_outputs_1982.jsonl
    type: chat_template
    split: train

dataset_prepared_path: last_run_prepared
val_set_size: 0.04
# test_datasets:
#   - path: 5000_benign_val.json
#     type: chat_template
#     split: train
save_safetensors: true

sequence_len: 3000
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-chem
wandb_entity: gpoisjgqetpadsfke
wandb_watch:
wandb_run_id:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 4
num_epochs: 2
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-chemistry-70B-outputs

This model is a fine-tuned version of huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned on the dset_70B_outputs_1982.jsonl dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2786

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: 2.0

Training results

Training Loss Epoch Step Validation Loss
0.311 0.0238 1 0.3211
0.3017 0.3333 14 0.3027
0.2771 0.6667 28 0.2875
0.3 1.0 42 0.2819
0.2919 1.3333 56 0.2795
0.2632 1.6667 70 0.2786
0.2907 2.0 84 0.2786

Framework versions

  • PEFT 0.15.1
  • Transformers 4.51.0
  • Pytorch 2.5.1+cu124
  • Datasets 3.5.0
  • Tokenizers 0.21.1