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: gemini_chem_axolotl_ft
output_dir: ./outputs/out/gemini_chem_axolotl_ft
hub_model_id: cgifbribcgfbi/Llama-3.3-70B-Instruct-abliterated-finetuned-chemistry-gemini
hub_strategy: every_save
tokenizer_type: AutoTokenizer
push_dataset_to_hub:
strict: false
datasets:
- path: dset_gemini_5000.jsonl
type: chat_template
split: train
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
# test_datasets:
# - path: 5000_benign_val.json
# type: chat_template
# split: train
save_safetensors: true
sequence_len: 7200
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: 2
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-chemistry-gemini
This model is a fine-tuned version of huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned on the dset_gemini_5000.jsonl dataset. It achieves the following results on the evaluation set:
- Loss: 0.5065
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 |
---|---|---|---|
0.968 | 0.0061 | 1 | 0.9585 |
0.7159 | 0.3354 | 55 | 0.6943 |
0.595 | 0.6707 | 110 | 0.6039 |
0.5593 | 1.0061 | 165 | 0.5663 |
0.5698 | 1.3415 | 220 | 0.5451 |
0.4871 | 1.6768 | 275 | 0.5310 |
0.4808 | 2.0122 | 330 | 0.5216 |
0.5072 | 2.3476 | 385 | 0.5157 |
0.4933 | 2.6829 | 440 | 0.5111 |
0.471 | 3.0183 | 495 | 0.5085 |
0.4691 | 3.3537 | 550 | 0.5073 |
0.4744 | 3.6890 | 605 | 0.5065 |
Framework versions
- PEFT 0.15.1
- Transformers 4.51.0
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
- Downloads last month
- -
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support
Model tree for cgifbribcgfbi/Llama-3.3-70B-Instruct-abliterated-finetuned-chemistry-gemini
Base model
meta-llama/Llama-3.1-70B
Finetuned
meta-llama/Llama-3.3-70B-Instruct