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_sortpatent_count_pat200_in5_num10134_1000.jsonl
model-index: - name: Llama-3.3-70B-Instruct-abliterated-finetuned-chem-claude-5-comp3-sort-pate-1000
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-5-comp3-sort-pate-1000
output_dir: ./outputs/out/Llama-3.3-70B-Instruct-abliterated-finetuned-chem-claude-5-comp3-sort-pate-1000
hub_model_id: cgifbribcgfbi/Llama-3.3-70B-Instruct-abliterated-finetuned-chem-claude-5-comp3-sort-pate-1000
tokenizer_type: AutoTokenizer
push_dataset_to_hub:
strict: false
datasets:
- path: dset_comp3.0_sortpatent_count_pat200_in5_num10134_1000.jsonl
type: chat_template
field_messages: messages
dataset_prepared_path: last_run_prepared
val_set_size: 0.04
save_safetensors: true
sequence_len: 2110
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-5-comp3-sort-pate-1000
This model is a fine-tuned version of huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned on the dset_comp3.0_sortpatent_count_pat200_in5_num10134_1000.jsonl dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4004
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 |
|---|---|---|---|
| 0.6985 | 0.0222 | 1 | 0.6454 |
| 0.6294 | 0.3333 | 15 | 0.6024 |
| 0.5311 | 0.6667 | 30 | 0.5035 |
| 0.4832 | 1.0 | 45 | 0.4625 |
| 0.4488 | 1.3333 | 60 | 0.4393 |
| 0.4303 | 1.6667 | 75 | 0.4249 |
| 0.4237 | 2.0 | 90 | 0.4148 |
| 0.4053 | 2.3333 | 105 | 0.4089 |
| 0.3975 | 2.6667 | 120 | 0.4051 |
| 0.3991 | 3.0 | 135 | 0.4021 |
| 0.3893 | 3.3333 | 150 | 0.4008 |
| 0.3865 | 3.6667 | 165 | 0.4005 |
| 0.3934 | 4.0 | 180 | 0.4004 |
Framework versions
- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1