| | --- |
| | library_name: transformers |
| | license: agpl-3.0 |
| | base_model: Delta-Vector/Holland-4B |
| | tags: |
| | - axolotl |
| | - generated_from_trainer |
| | model-index: |
| | - name: SDprompterV3 |
| | 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: `0.4.1` |
| | ```yaml |
| | base_model: Delta-Vector/Holland-4B |
| | model_type: AutoModelForCausalLM |
| | tokenizer_type: AutoTokenizer |
| | |
| | load_in_8bit: false |
| | load_in_4bit: false |
| | strict: false |
| | |
| | datasets: |
| | - path: ./datasets/sd-prompter-sharegpt.jsonl |
| | type: sharegpt |
| | conversation: chatml |
| | |
| | chat_template: chatml |
| | |
| | val_set_size: 0.01 |
| | output_dir: ./outputs/out |
| | |
| | adapter: |
| | lora_r: |
| | lora_alpha: |
| | lora_dropout: |
| | lora_target_linear: |
| | |
| | sequence_len: 16384 |
| | # sequence_len: 32768 |
| | sample_packing: true |
| | eval_sample_packing: false |
| | pad_to_sequence_len: true |
| | |
| | plugins: |
| | - axolotl.integrations.liger.LigerPlugin |
| | liger_rope: true |
| | liger_rms_norm: true |
| | liger_swiglu: true |
| | liger_fused_linear_cross_entropy: true |
| | |
| | wandb_project: SDprompterV3 |
| | wandb_entity: |
| | wandb_watch: |
| | wandb_name: SDprompterV3-attempt1 |
| | wandb_log_model: |
| | |
| | hub_model_id: NewEden/SDprompterV3 |
| | hub_strategy: "all_checkpoints" |
| | hf_use_auth_token: true |
| | |
| | gradient_accumulation_steps: 16 |
| | micro_batch_size: 1 |
| | num_epochs: 4 |
| | optimizer: adamw_bnb_8bit |
| | lr_scheduler: cosine |
| | learning_rate: 0.00001 |
| | weight_decay: 0.05 |
| | |
| | train_on_inputs: false |
| | group_by_length: false |
| | bf16: auto |
| | fp16: |
| | tf32: true |
| | |
| | gradient_checkpointing: true |
| | early_stopping_patience: |
| | resume_from_checkpoint: |
| | local_rank: |
| | logging_steps: 1 |
| | xformers_attention: |
| | flash_attention: true |
| | |
| | warmup_ratio: 0.05 |
| | evals_per_epoch: 4 |
| | eval_table_size: |
| | eval_max_new_tokens: 128 |
| | saves_per_epoch: 1 |
| | |
| | debug: |
| | deepspeed: /workspace/axolotl/deepspeed_configs/zero2.json |
| | fsdp: |
| | fsdp_config: |
| | |
| | special_tokens: |
| | pad_token: <|finetune_right_pad_id|> |
| | |
| | |
| | ``` |
| |
|
| | </details><br> |
| |
|
| | # SDprompterV3 |
| |
|
| | This model is a fine-tuned version of [Delta-Vector/Holland-4B](https://huggingface.co/Delta-Vector/Holland-4B) on the None dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 3.1973 |
| |
|
| | ## 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: 1e-05 |
| | - train_batch_size: 1 |
| | - eval_batch_size: 1 |
| | - seed: 42 |
| | - distributed_type: multi-GPU |
| | - num_devices: 2 |
| | - gradient_accumulation_steps: 16 |
| | - total_train_batch_size: 32 |
| | - total_eval_batch_size: 2 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: cosine |
| | - lr_scheduler_warmup_steps: 2 |
| | - num_epochs: 4 |
| | |
| | ### Training results |
| | |
| | | Training Loss | Epoch | Step | Validation Loss | |
| | |:-------------:|:------:|:----:|:---------------:| |
| | | 3.5219 | 0.1667 | 1 | 4.3164 | |
| | | 3.5673 | 0.3333 | 2 | 3.9752 | |
| | | 3.1774 | 0.6667 | 4 | 3.8060 | |
| | | 3.094 | 1.0 | 6 | 3.5951 | |
| | | 2.8696 | 1.3229 | 8 | 3.4158 | |
| | | 2.6847 | 1.6562 | 10 | 3.3511 | |
| | | 2.681 | 1.9896 | 12 | 3.2916 | |
| | | 2.546 | 2.3125 | 14 | 3.2512 | |
| | | 2.534 | 2.6458 | 16 | 3.2255 | |
| | | 2.4675 | 2.9792 | 18 | 3.2126 | |
| | | 2.4957 | 3.3021 | 20 | 3.2036 | |
| | | 2.4555 | 3.6354 | 22 | 3.1983 | |
| | | 2.5126 | 3.9688 | 24 | 3.1973 | |
| | |
| | |
| | ### Framework versions |
| | |
| | - Transformers 4.45.1 |
| | - Pytorch 2.3.1+cu121 |
| | - Datasets 2.21.0 |
| | - Tokenizers 0.20.0 |
| | |
