Model save

README.md

@@ -0,0 +1,168 @@
+---
+library_name: peft
+license: llama3.3
+base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned
+tags:
+- axolotl
+- generated_from_trainer
+datasets:
+- dset_o4_mini_5000.jsonl
+model-index:
+- name: Llama-3.3-70B-Instruct-abliterated-finetuned-chemistry-o4-v2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.8.1`
+```yaml
+base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned
+load_in_8bit: false
+load_in_4bit: true
+adapter: qlora
+wandb_name: o4_v2_axolotl_ft
+output_dir: ./outputs/out/o4_v2_axolotl_ft
+hub_model_id: cgifbribcgfbi/Llama-3.3-70B-Instruct-abliterated-finetuned-chemistry-o4-v2
+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_o4_mini_5000.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: 0.00002
+
+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>
+
+# Llama-3.3-70B-Instruct-abliterated-finetuned-chemistry-o4-v2
+
+This model is a fine-tuned version of [huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned](https://huggingface.co/huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned) on the dset_o4_mini_5000.jsonl dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6710
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.1459        | 0.0059 | 1    | 1.0945          |
+| 0.8244        | 0.3353 | 57   | 0.8049          |
+| 0.782         | 0.6706 | 114  | 0.7394          |
+| 0.7077        | 1.0059 | 171  | 0.7135          |
+| 0.673         | 1.3412 | 228  | 0.6990          |
+| 0.6982        | 1.6765 | 285  | 0.6888          |
+| 0.6577        | 2.0118 | 342  | 0.6821          |
+| 0.6612        | 2.3471 | 399  | 0.6783          |
+| 0.6757        | 2.6824 | 456  | 0.6745          |
+| 0.665         | 3.0176 | 513  | 0.6722          |
+| 0.6427        | 3.3529 | 570  | 0.6716          |
+| 0.6027        | 3.6882 | 627  | 0.6710          |
+
+
+### Framework versions
+
+- PEFT 0.15.1
+- Transformers 4.51.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1