Downloads · 30 days
2
9% of all-time downloads
cgifbribcgfbi/Llama-3.3-70B-Instruct-abliterated-finetuned-chemistry-best-clean-lr0.00008
Llama-3.3-70B-Instruct-abliterated-finetuned-chemistry-best-clean-lr0.00008 is a machine learning model from cgifbribcgfbi. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as llama3.3.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
2
9% of all-time downloads
All-time downloads
23
Public
Repo size
13.3 GB
Likes
0
Public
Click a slice to open those files.
.safetensors3.3 GB · 99%
From the Hugging Face model README
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: lr0.00008_alpha32_r64_full_axolotl_ft
output_dir: ./outputs/out/lr0.00008_alpha32_r64_full_axolotl_ft
hub_model_id: cgifbribcgfbi/Llama-3.3-70B-Instruct-abliterated-finetuned-chemistry-best-clean-lr0.00008
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_filtered_benign_4571.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: 4
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 0.00008
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|>
</details><br>
This model is a fine-tuned version of huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned on the dset_filtered_benign_4571.jsonl dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6416 | 0.0075 | 1 | 0.6384 |
| 0.3931 | 0.3383 | 45 | 0.3852 |
| 0.3494 | 0.6767 | 90 | 0.3524 |
| 0.3144 | 1.0150 | 135 | 0.3385 |
| 0.3187 | 1.3534 | 180 | 0.3303 |
| 0.301 | 1.6917 | 225 | 0.3242 |
| 0.2818 | 2.0301 | 270 | 0.3203 |
| 0.2788 | 2.3684 | 315 | 0.3195 |
| 0.2609 | 2.7068 | 360 | 0.3155 |
| 0.266 | 3.0451 | 405 | 0.3151 |
| 0.2509 | 3.3835 | 450 | 0.3166 |
| 0.2636 | 3.7218 | 495 | 0.3161 |