End of training

README.md

@@ -0,0 +1,240 @@
+---
+library_name: peft
+license: gemma
+base_model: unsloth/gemma-3-4b-it
+tags:
+- axolotl
+- generated_from_trainer
+datasets:
+- ToastyPigeon/some-rp-extended
+- allura-org/inkstructmix-v0.2.1a-system-reasoning-separated
+- ToastyPigeon/unalign-v2
+- ToastyPigeon/unalign-v2
+- ToastyPigeon/synth-rp
+- PocketDoc/Floyd-Text-Adventures
+- ToastyPigeon/new-story-dataset
+model-index:
+- name: g3-4b-it-creative-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/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: `0.8.0.dev0`
+```yaml
+# === Start-up Commands ===
+# curl -LsSf https://astral.sh/uv/install.sh | sh
+# export PATH="$HOME/.local/bin:$PATH"
+# git clone https://github.com/axolotl-ai-cloud/axolotl
+# cd axolotl
+# git checkout d8b4027200de0fe60f4ae0a71272c1a8cb2888f7
+# uv venv
+# source .venv/bin/activate
+# uv pip install packaging ninja setuptools ftfy deepspeed huggingface_hub[cli,hf_transfer]
+# uv pip install "cut-cross-entropy[transformers] @ git+https://github.com/strangedove/ml-cross-entropy.git"
+# uv pip install apollo-torch
+# uv pip install --no-build-isolation -e .[flash-attn]
+# uv pip install git+https://github.com/huggingface/transformers.git
+# export HF_HUB_ENABLE_HF_TRANSFER=1
+# huggingface-cli login --token $hf_key && wandb login $wandb_key
+# axolotl preprocess qwen21-pretrain.yml
+# axolotl train qwen21-pretrain.yml
+
+# curl -LsSf https://astral.sh/uv/install.sh | sh && export PATH="$HOME/.local/bin:$PATH" && git clone https://github.com/axolotl-ai-cloud/axolotl && uv venv && source .venv/bin/activate && cd axolotl && git checkout 9f00465a5cb2349c23853c4a020a928709e506f2 && uv pip install torch==2.5.1 packaging ninja setuptools ftfy deepspeed huggingface_hub[cli,hf_transfer] && uv pip install "cut-cross-entropy[transformers] @ git+https://github.com/strangedove/ml-cross-entropy.git@gemma3" && uv pip install apollo-torch && uv pip install --no-build-isolation -e .[flash-attn] && uv pip install git+https://github.com/huggingface/transformers.git@c9d1e5238a752813ba91a8751a638a09b5efbb73 && export HF_HUB_ENABLE_HF_TRANSFER=1 && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key
+
+# === Model Configuration ===
+base_model: unsloth/gemma-3-4b-it
+load_in_8bit: true
+load_in_4bit: false
+
+# === HF Configuration === 
+hub_model_id: ToastyPigeon/g3-4b-it-creative-qlora
+hub_strategy: "every_save"
+
+# === Training Setup ===
+num_epochs: 1
+micro_batch_size: 3
+gradient_accumulation_steps: 6
+sequence_len: 8192
+sample_packing: true
+pad_to_sequence_len: true
+
+# === Evaluation ===
+val_set_size: 100
+evals_per_epoch: 5
+#eval_table_size:
+eval_max_new_tokens: 256
+eval_sample_packing: true
+#eval_strategy: "no"
+
+# === LoRA Configuration ===
+adapter: lora
+lora_model_dir:
+lora_r: 64
+lora_alpha: 64
+lora_dropout: 0.5
+lora_target_linear: 
+lora_fan_in_fan_out:
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+
+#lora_mlp_kernel: true
+#lora_qkv_kernel: true
+#lora_o_kernel: true
+
+# === Hyperparameter Configuration ===
+#optimizer: apollo_adamw_layerwise
+optimizer: paged_adamw_8bit
+# Apollo-mini configuration:
+#optim_args: "proj=random,rank=1,scale=128.0,scale_type=tensor,update_proj_gap=200"
+# Regular Apollo configuration:
+# optim_args: 
+#optim_target_modules: all_linear
+learning_rate: 1e-5
+lr_scheduler: rex
+weight_decay: 0.01
+#warmup_ratio: 0.05
+
+
+# === Data Configuration ===
+#chat_template: jinja
+#chat_template_jinja: "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}"
+#special_tokens:
+#  eos_token: "<end_of_turn>"
+shuffle_merged_datasets: true
+datasets:
+  - path: ToastyPigeon/some-rp-extended
+    type: customgemma-regex
+  - path: allura-org/inkstructmix-v0.2.1a-system-reasoning-separated
+    type: customgemma-regex
+    data_files: inkstruct-system.json
+    split: train[:750]
+  - path: ToastyPigeon/unalign-v2
+    type: chat_template
+    field_messages: conversations
+    message_property_mappings:
+      role: from
+      content: value
+  - path: ToastyPigeon/unalign-v2 # yes, twice on purpose 
+    type: chat_template
+    field_messages: conversations
+    message_property_mappings:
+      role: from
+      content: value
+  - path: ToastyPigeon/synth-rp
+    split: train[:20%]
+    type: customgemma-regex
+  - path: PocketDoc/Floyd-Text-Adventures
+    data_files: floyd-pktdc.json
+    type: customgemma-regex
+  - path: ToastyPigeon/new-story-dataset
+    type: customcompletion-regex
+    field: text
+    
+dataset_prepared_path: last_run_prepared
+
+
+# === Plugins ===
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+
+# === Hardware Optimization ===
+gradient_checkpointing: true
+#gradient_checkpointing_kwargs:
+#  use_reentrant: true
+liger_rope: true
+liger_rms_norm: true
+liger_glu_activation: true
+#liger_fused_linear_cross_entropy: true
+#unsloth_cross_entropy_loss: true
+cut_cross_entropy: true
+# Only if using multiple GPUs:
+#deepspeed: axolotl/deepspeed_configs/zero2.json
+
+# === Wandb Tracking ===
+wandb_project: Gemma
+# wandb_entity: [WANDB_ENTITY]
+# wandb_name: [WANDB_RUN_NAME]
+
+# === Checkpointing ===
+saves_per_epoch: 10
+save_total_limit: 1
+
+# === Advanced Settings ===
+output_dir: ./ckpts
+bf16: auto
+flash_attention: true
+train_on_inputs: false
+group_by_length: false
+save_safetensors: true
+logging_steps: 1
+gc_steps: 10
+seed: 69
+```
+
+</details><br>
+
+# g3-4b-it-creative-qlora
+
+This model is a fine-tuned version of [unsloth/gemma-3-4b-it](https://huggingface.co/unsloth/gemma-3-4b-it) on the ToastyPigeon/some-rp-extended, the allura-org/inkstructmix-v0.2.1a-system-reasoning-separated, the ToastyPigeon/unalign-v2, the ToastyPigeon/unalign-v2, the ToastyPigeon/synth-rp, the PocketDoc/Floyd-Text-Adventures and the ToastyPigeon/new-story-dataset datasets.
+It achieves the following results on the evaluation set:
+- Loss: 2.7299
+
+## 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: 3
+- eval_batch_size: 3
+- seed: 69
+- gradient_accumulation_steps: 6
+- total_train_batch_size: 18
+- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT 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: 8
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 4.5251        | 0.0034 | 1    | 4.6010          |
+| 3.9623        | 0.1995 | 58   | 3.7722          |
+| 2.8668        | 0.3991 | 116  | 3.2242          |
+| 2.8385        | 0.5986 | 174  | 2.8821          |
+| 2.7389        | 0.7982 | 232  | 2.7648          |
+| 2.5117        | 0.9977 | 290  | 2.7299          |
+
+
+### Framework versions
+
+- PEFT 0.15.0
+- Transformers 4.51.0.dev0
+- Pytorch 2.5.1+cu124
+- Datasets 3.4.1
+- Tokenizers 0.21.1