Update README.md

README.md

@@ -17,105 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 <details><summary>See axolotl config</summary>
 
 axolotl version: `0.5.0`
-```yaml
-strict: false
-base_model: microsoft/Phi-3.5-mini-instruct
-tokenizer_config: microsoft/Phi-3.5-mini-instruct
-model_type: AutoModelForCausalLM
-tokenizer_type: AutoTokenizer
-
-# Output configuration
-hub_model_id: collinear-ai/curator_math_phase1_sn_ensemble7_90325
-dataset_prepared_path: /workspace/prapti/curator_math_phase1_sn_ensemble7_90325
-output_dir: /workspace/prapti/curator_math_phase1_sn_ensemble7_90325
-
-# Format the dataset into the right instruction format.
-chat_template: phi_3
-datasets:
-  - path: collinear-ai/curator_math_phase1_sn_ensemble7_50325_sft
-    split: train
-    type: chat_template
-    chat_template: phi_3
-    field_messages: train_conv
-    message_field_role: role
-    message_field_content: content
-train_on_inputs: false #FALSE
-
-val_set_size: 0.05
-# Data packing
-sequence_len: 4096 #meghana can you please confirm this
-eval_sample_packing: false
-sample_packing: false
-pad_to_sequence_len: true
-group_by_length: false
-
-# Lora config
-adapter: qlora
-lora_model_dir:
-load_in_8bit: false
-load_in_4bit: true
-lora_r: 128
-lora_alpha: 64
-lora_dropout: 0.2
-lora_target_linear: true
-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: 
-  - embed_tokens
-  - lm_head
-
-
-# Logging config
-wandb_project: sn-curators-downstream
-wandb_entity: nazneen
-wandb_name: curator_math_phase1_sn_ensemble7_90325
-
-# Trainer config
-gradient_accumulation_steps: 2
-micro_batch_size: 8
-num_epochs: 1
-optimizer: paged_adamw_8bit
-lr_scheduler: cosine
-learning_rate: 0.000005
-
-bfloat16: true
-bf16: true
-fp16:
-tf32: false
-
-gradient_checkpointing: true
-early_stopping_patience:
-resume_from_checkpoint:
-local_rank:
-logging_steps: 10
-xformers_attention:
-flash_attention: true
-save_safetensors: true
-
-
-
-warmup_steps: 50
-evals_per_epoch: 3
-eval_table_size: 3
-eval_max_new_tokens: 2048
-saves_per_epoch: 20
-debug:
-deepspeed:
-weight_decay: 0.02
-fsdp_config:
-special_tokens:
-  bos_token: "<s>"
-  eos_token: "<|endoftext|>"
-  unk_token: "<unk>"
-  pad_token: "<|endoftext|>"
-```
+
 
 </details><br>