Model save

README.md

@@ -0,0 +1,218 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen2.5-32B
+tags:
+- axolotl
+- generated_from_trainer
+datasets:
+- ToastyPigeon/story-samples
+model-index:
+- name: qwen32-story-ws-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: `0.6.0`
+```yaml
+# git clone https://github.com/axolotl-ai-cloud/axolotl
+# cd axolotl
+# git checkout d425d5d3c3ca7644a9da8ed93c3d03f4be0c4854
+# pip3 install packaging ninja huggingface_hub[cli]
+# pip install "cut-cross-entropy[transformers] @ git+https://github.com/apple/ml-cross-entropy.git"
+# pip3 install -e '.[flash-attn,deepspeed]'
+# apt update && apt install libopenmpi-dev 
+# pip install mpi4py
+# huggingface-cli login --token $hf_key && wandb login $wandb_key
+# python -m axolotl.cli.preprocess qwen-32b-story.yml
+# medpace data analyst
+# accelerate launch -m axolotl.cli.train qwen-32b-story.yml
+# python -m axolotl.cli.merge_lora qwen-32b-story.yml
+# huggingface-cli upload ToastyPigeon/new-ms-rp-test-v0-v3 train-workspace/merged . --exclude "*.md"
+
+# git clone https://github.com/axolotl-ai-cloud/axolotl && cd axolotl && git checkout d8b4027200de0fe60f4ae0a71272c1a8cb2888f7 && pip3 install packaging ninja huggingface_hub[cli,hf_transfer] && pip3 install -e '.[flash-attn,deepspeed]' && cd .. && huggingface-cli login --token $hf_key && wandb login $wandb_key
+
+# Model
+base_model: Qwen/Qwen2.5-32B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+bf16: true
+fp16:
+tf32: false
+flash_attention: true
+special_tokens:
+
+# Output
+output_dir: ./train-workspace
+hub_model_id: ToastyPigeon/qwen32-story-ws-v2
+hub_strategy: "checkpoint"
+resume_from_checkpoint:
+saves_per_epoch: 4
+
+# Data
+sequence_len: 4096 # fits
+min_sample_len: 128
+dataset_prepared_path: last_run_prepared
+datasets:
+  - path: ToastyPigeon/story-samples
+    type: completion
+    field: text
+    split: train[:1500]
+warmup_ratio: 0.05
+shuffle_merged_datasets: true
+sample_packing: true
+#pad_to_sequence_len: true
+
+# Batching
+num_epochs: 1
+gradient_accumulation_steps: 4
+micro_batch_size: 1
+eval_batch_size: 1
+
+# Evaluation
+val_set_size: 200
+evals_per_epoch: 10
+eval_table_size:
+eval_max_new_tokens: 256
+eval_sample_packing: true
+
+save_safetensors: true
+
+# WandB
+wandb_project: Qwen-Test
+#wandb_entity:
+
+gradient_checkpointing: 'unsloth'
+#gradient_checkpointing_kwargs:
+#  use_reentrant: false
+
+unsloth_cross_entropy_loss: true
+#unsloth_lora_mlp: true
+#unsloth_lora_qkv: true
+#unsloth_lora_o: true
+
+# LoRA
+adapter: qlora
+lora_model_dir:
+lora_r: 32
+lora_alpha: 32
+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_modules_to_save:
+#peft_layers_to_transform: [35,36,37,38,39]
+
+# Optimizer
+optimizer: paged_ademamix_8bit # adamw_8bit
+lr_scheduler: cosine
+learning_rate: 5e-5
+cosine_min_lr_ratio: 0.5
+weight_decay: 0.01
+max_grad_norm: 1.0
+
+# Misc
+train_on_inputs: false
+#group_by_length: true
+early_stopping_patience:
+local_rank:
+logging_steps: 1
+xformers_attention:
+debug:
+deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json # previously blank
+fsdp:
+fsdp_config:
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+#  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+#cut_cross_entropy: true
+liger_rope: true
+liger_rms_norm: true
+liger_layer_norm: true
+liger_glu_activation: true
+liger_fused_linear_cross_entropy: true
+
+gc_steps: 10
+seed: 69
+```
+
+</details><br>
+
+# qwen32-story-ws-v2
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) on the ToastyPigeon/story-samples dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.2790
+
+## 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: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 69
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- total_eval_batch_size: 4
+- optimizer: Use OptimizerNames.PAGED_ADEMAMIX_8BIT and the args are:
+No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 5
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.1763        | 0.0092 | 1    | 2.3021          |
+| 2.129         | 0.1014 | 11   | 2.2997          |
+| 2.2385        | 0.2028 | 22   | 2.2945          |
+| 2.233         | 0.3041 | 33   | 2.2906          |
+| 2.0907        | 0.4055 | 44   | 2.2874          |
+| 2.2263        | 0.5069 | 55   | 2.2848          |
+| 2.2703        | 0.6083 | 66   | 2.2828          |
+| 2.4101        | 0.7097 | 77   | 2.2813          |
+| 2.2473        | 0.8111 | 88   | 2.2800          |
+| 2.1912        | 0.9124 | 99   | 2.2790          |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0