Model save

README.md

@@ -1,3 +1,158 @@
 ---
 license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: byroneverson/LLaVA-v1.5-7B-rehome
+model-index:
+- name: LLaVA-v1.5-7B-rehome-shell-qlora
+  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/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.3.0`
+```yaml
+base_model: byroneverson/LLaVA-v1.5-7B-rehome
+model_type: MistralForCausalLM
+tokenizer_type: LlamaTokenizer
+#is_mistral_derived_model: true
+#
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+#
+datasets:
+  - path: byroneverson/shell-cmd-instruct
+    type: solar_shell_instruct #alpaca
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.05
+output_dir: ./qlora-out
+#
+# Push checkpoints to hub
+hub_model_id: byroneverson/LLaVA-v1.5-7B-rehome-shell-qlora
+# How to push checkpoints to hub
+# https://huggingface.co/docs/transformers/v4.31.0/en/main_classes/trainer#transformers.TrainingArguments.hub_strategy
+hub_strategy: checkpoint
+# Whether to use hf `use_auth_token` for loading datasets. Useful for fetching private datasets
+# Required to be true when used in combination with `push_dataset_to_hub`
+hf_use_auth_token: true
+#
+adapter: qlora
+lora_model_dir:
+#
+sequence_len: 2048
+sample_packing: true
+eval_sample_packing: false
+pad_to_sequence_len: true
+#
+lora_r: 128
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+target_modules: [
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+  ]
+#
+wandb_project: "LLaVA-v1.5-7B-rehome-qlora"
+wandb_log_model: "checkpoint"
+wandb_entity:
+wandb_watch:
+wandb_run_id:
+#
+gradient_accumulation_steps: 2 # 1
+micro_batch_size: 1
+num_epochs: 3
+optimizer: paged_lion_8bit #paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+#
+train_on_inputs: false
+group_by_length: false
+bf16: false #true
+fp16: true
+tf32: false
+#
+gradient_checkpointing: true
+early_stopping_patience:
+# Resume from a specific checkpoint dir
+resume_from_checkpoint: #last-checkpoint
+# If resume_from_checkpoint isn't set and you simply want it to start where it left off.
+# Be careful with this being turned on between different models.
+auto_resume_from_checkpoints: false
+local_rank:
+logging_steps: 1
+xformers_attention:
+# Whether to use flash attention patch https://github.com/Dao-AILab/flash-attention:
+flash_attention: false #true
+flash_attn_cross_entropy:  # Whether to use flash-attention cross entropy implementation - advanced use only
+flash_attn_rms_norm: false # Whether to use flash-attention rms norm implementation - advanced use only
+flash_attn_fuse_qkv: # Whether to fuse QKV into a single operation
+flash_attn_fuse_mlp: # Whether to fuse part of the MLP into a single operation
+#
+warmup_steps: 10
+eval_steps: 0.05
+eval_table_size:
+eval_table_max_new_tokens: 128
+save_steps:
+debug: true #
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  bos_token: "<s>"
+  eos_token: "</s>"
+  unk_token: "<unk>"
+
+```
+
+</details><br>
+
+# LLaVA-v1.5-7B-rehome-shell-qlora
+
+This model is a fine-tuned version of [byroneverson/LLaVA-v1.5-7B-rehome](https://huggingface.co/byroneverson/LLaVA-v1.5-7B-rehome) on an unknown dataset.
+
+## 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: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- PEFT 0.7.2.dev0
+- Transformers 4.37.0.dev0
+- Pytorch 2.0.1+cu117
+- Datasets 2.16.1
+- Tokenizers 0.15.0