Update README.md

README.md

@@ -23,9 +23,96 @@ output = generator([{"role": "user", "content": question}], max_new_tokens=128,
 print(output["generated_text"])
 ```
 
-## Training procedure
+## Axolotl Config
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/logical-luminosity/eidolon-qwen2.5-qlora-dpo-3/runs/vja6mgde)
+```
+base_model: Lambent/ProtoEidolon-v2.2.4-14B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+trust_remote_code: true
+
+save_safetensors: true
+
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+
+rl: dpo
+chat_template: chatml
+# total_num_tokens: 
+datasets:
+  - path: Lambent/rp-teacher-synth-dpo
+    split: train
+    type: chatml.prompt_pairs
+  - path: unalignment/toxic-dpo-v0.2
+    split: train
+    type: chatml.prompt_pairs
+  - path: sam-paech/gutenbergs_1_2_3_antislop-dpo
+    split: train
+    type: chatml.ultra
+  - path: Trelis/orpo-dpo-mix-40k-SHORT
+    split: train
+    type: chatml.ultra
+
+dataset_prepared_path: prepared-dpo
+output_dir: ./dpoq
+val_set_size: 0.001
+
+seed: 213
+
+sequence_len: 2048
+sample_packing: false
+eval_sample_packing: false
+pad_to_sequence_len: false
+
+adapter: qlora
+lora_model_dir:
+lora_r: 256
+lora_alpha: 256
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+peft_use_dora: true
+
+wandb_project: eidolon-qwen2.5-qlora-dpo-3
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 16
+micro_batch_size: 2
+num_epochs: 1
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 1e-6
+#cosine_min_lr_ratio: 0.1
+#cosine_constant_lr_ratio: 0.95
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 16
+evals_per_epoch: 8
+saves_per_epoch: 8
+save_total_limit: 2
+debug:
+deepspeed:
+weight_decay: 0.001
+fsdp:
+fsdp_config:
+```
 
 This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).