Create README.md

README.md

@@ -0,0 +1,49 @@
+
+Training Details:
+Trained at 8K Context -> Expanded to 32K Context due to context extension with PoSE training.
+
+Dataset Modifications:
+- Further Cleaned up Roleplaying Samples
+- Removed Low Quality Samples from Manual Check
+- More Creative Writing Samples
+- Remade and Refined Detailed Instruct Data
+
+Needle in a Haystack Results:
+
+
+```
+sequence_len: 8192
+use_pose: true
+pose_max_context_len: 32768
+
+overrides_of_model_config:
+  rope_theta: 2000000.0
+  max_position_embeddings: 32768
+
+  # peft_use_dora: true
+adapter: lora
+peft_use_rslora: true
+lora_model_dir:
+lora_r: 256
+lora_alpha: 256
+lora_dropout: 0.1
+lora_target_linear: true
+lora_target_modules:
+  - gate_proj
+  - down_proj
+  - up_proj
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+
+warmup_steps: 80
+gradient_accumulation_steps: 6
+micro_batch_size: 1
+num_epochs: 2
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine_with_min_lr
+learning_rate: 0.00004
+lr_scheduler_kwargs:
+    min_lr: 0.000004
+```