Update README.md

README.md

@@ -239,7 +239,93 @@ Take off your helmet.<|im_end|>
 <details>
   
 ```yaml
+base_model: Qwen/QwQ-32B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
 
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_swiglu: true
+liger_fused_linear_cross_entropy: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: Mielikki/Erebus-87k
+    type: completion
+    field: body
+  - path: NewEden/Orion-Completion-Asstr-Stories-16K
+    type: completion
+    field: content 
+  - path: NewEden/Orion-Completion-LIT
+    type: completion
+    field: text 
+
+shuffle_merged_datasets: true
+dataset_prepared_path: prepared_data
+output_dir: ./qvq-cum
+
+sequence_len: 16384
+sample_packing: true
+pad_to_sequence_len: true
+
+adapter: lora
+lora_model_dir:
+lora_r: 128
+lora_alpha: 16 
+lora_dropout: 0.05
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+
+lora_modules_to_save:
+ - embed_tokens
+ - lm_head
+
+wandb_project: qwq
+wandb_entity:
+wandb_watch:
+wandb_name: Pretrain-pt1-v2-frfr
+wandb_log_model:
+
+gradient_accumulation_steps: 2
+micro_batch_size: 2
+num_epochs: 1
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 1e-5
+max_grad_norm: 0.001
+
+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: 40
+saves_per_epoch: 2
+debug:
+deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
+weight_decay: 0.01
+fsdp:
+fsdp_config:
 ```
 
 </details>