Downloads · 30 days
6
18% of all-time downloads
cgifbribcgfbi/Llama-3.3-70B-Instruct-abliterated-finetuned-chem-claude-5-comp0-sort-comp
Llama-3.3-70B-Instruct-abliterated-finetuned-chem-claude-5-comp0-sort-comp 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
6
18% of all-time downloads
All-time downloads
33
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: 0.9.0
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned
load_in_8bit: false
load_in_4bit: true
adapter: qlora
wandb_name: claude_5_complex0_new_chemicals_axolotl_ft
output_dir: ./outputs/out/claude_5_complex0_new_chemicals_axolotl_ft
hub_model_id: cgifbribcgfbi/Llama-3.3-70B-Instruct-abliterated-finetuned-chemistry-claude-5-complex0
hub_strategy: every_save
# resume_from_checkpoint: ./outputs/out/diverse_ccs_chem_axolotl_ft/checkpoint-106
tokenizer_type: AutoTokenizer
push_dataset_to_hub:
strict: false
datasets:
- path: dset_comp0.0_sortcomplexity_pat400_in5_num5000.jsonl
type: chat_template
split: train
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
save_safetensors: true
sequence_len: 2700
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: 0.00002
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|>
</details><br>
This model is a fine-tuned version of huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned on the dset_comp0.0_sortcomplexity_pat400_in5_num5000.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 |
|---|---|---|---|
| 0.6429 | 0.0058 | 1 | 0.6738 |
| 0.414 | 0.3333 | 57 | 0.4469 |
| 0.421 | 0.6667 | 114 | 0.3958 |
| 0.3487 | 1.0 | 171 | 0.3749 |
| 0.3489 | 1.3333 | 228 | 0.3627 |
| 0.3576 | 1.6667 | 285 | 0.3543 |
| 0.3442 | 2.0 | 342 | 0.3476 |
| 0.3304 | 2.3333 | 399 | 0.3442 |
| 0.3122 | 2.6667 | 456 | 0.3415 |
| 0.3214 | 3.0 | 513 | 0.3391 |
| 0.3154 | 3.3333 | 570 | 0.3384 |
| 0.3362 | 3.6667 | 627 | 0.3379 |
| 0.2994 | 4.0 | 684 | 0.3378 |