Downloads · 30 days
6
12% of all-time downloads
cgifbribcgfbi/Qwen2.5-72B-Instruct-abliterated-chem-claude-5-comp3-sort-pat
Qwen2.5-72B-Instruct-abliterated-chem-claude-5-comp3-sort-pat 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 other.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
6
12% of all-time downloads
All-time downloads
52
Public
Repo size
13.5 GB
Likes
0
Public
Click a slice to open those files.
.safetensors3.4 GB · 100%
From the Hugging Face model README
axolotl version: 0.9.1
base_model: zetasepic/Qwen2.5-72B-Instruct-abliterated
load_in_8bit: false
load_in_4bit: true
adapter: qlora
wandb_name: Qwen2.5-72B-Ins_outputs_axolotl_ft_alpha32_r64_lr0.00002_Qwen2.5-72B-Ins_dset_comp3.0_sortpatent_count_pat400_in5_5000
output_dir: ./outputs/out/Qwen2.5-72B-Ins_outputs_axolotl_ft_alpha32_r64_lr0.00002_Qwen2.5-72B-Ins_dset_comp3.0_sortpatent_count_pat400_in5_5000
hub_model_id: cgifbribcgfbi/alpha32_r64_lr0.00002_Qwen2.5-72B-Ins_dset_comp3.0_sortpatent_count_pat400_in5_5000
tokenizer_type: AutoTokenizer
push_dataset_to_hub:
strict: false
datasets:
- path: dset_comp3.0_sortpatent_count_pat400_in5_5000.jsonl
type: chat_template
field_messages: messages
dataset_prepared_path: last_run_prepared
val_set_size: 0.04
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-sweep
wandb_entity: gpoisjgqetpadsfke
wandb_watch:
wandb_run_id:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 4 # 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: Qwen2DecoderLayer
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 zetasepic/Qwen2.5-72B-Instruct-abliterated on the dset_comp3.0_sortpatent_count_pat400_in5_5000.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 |
|---|---|---|---|
| 0.6145 | 0.0059 | 1 | 0.7786 |
| 0.5132 | 0.3353 | 57 | 0.4766 |
| 0.4384 | 0.6706 | 114 | 0.4255 |
| 0.3706 | 1.0059 | 171 | 0.4046 |
| 0.3582 | 1.3412 | 228 | 0.3894 |
| 0.3678 | 1.6765 | 285 | 0.3801 |
| 0.3375 | 2.0118 | 342 | 0.3753 |
| 0.3591 | 2.3471 | 399 | 0.3695 |
| 0.344 | 2.6824 | 456 | 0.3664 |
| 0.3219 | 3.0176 | 513 | 0.3657 |
| 0.3463 | 3.3529 | 570 | 0.3632 |
| 0.3582 | 3.6882 | 627 | 0.3629 |