Update README.md

README.md

@@ -14,162 +14,13 @@ model-index:
 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: `0.4.1`
-```yaml
-# huggingface-cli download ToastyPigeon/SpringDragon-Instruct-v1-QLoRA-A --include checkpoint-210/* --local-dir .
-# python -m axolotl.cli.preprocess springdragon-nemo.yml
-# accelerate launch -m axolotl.cli.train springdragon-nemo.yml
-# Weights and Biases logging config
-wandb_project: SpringDragon-NeMo
-wandb_entity:
-wandb_watch:
-wandb_name: 
-wandb_log_model:
-
-#eval_steps: 25
-#max_steps: 100
-
-#Model
-base_model: mistralai/Mistral-Nemo-Instruct-2407
-model_type: AutoModelForCausalLM
-tokenizer_type: AutoTokenizer
-
-# Hugging Face saving config
-hub_model_id: ToastyPigeon/SpringDragon-NeMo-Instruct-QLoRA-ep1
-hub_strategy: all_checkpoints
-push_dataset_to_hub:
-hf_use_auth_token:
-
-
-# Model checkpointing config
-output_dir: ./SpringDragon-NeMo
-resume_from_checkpoint: 
-#save_steps: 100
-saves_per_epoch: 2
-save_safetensors: true
-save_total_limit: 3
-
-#
-bf16: auto
-fp16:
-tf32: false
-
-#
-load_in_8bit: false
-load_in_4bit: true
-strict: false
-
-sequence_len: 2048
-pad_to_sequence_len: true
-sample_packing: true
-
-# Token config
-special_tokens:
-    pad_token: "<pad>"
-tokens:
-
-# Data
-datasets:
-  - path: BeaverAI/text_adventures
-    type: completion
-dataset_prepared_path: ./text_adventures
-val_set_size: 0.05
-evals_per_epoch: 20
-#evaluation_strategy: steps
-#eval_steps: 50
-eval_sample_packing: true
-
-
-# LoRA
-adapter: qlora
-lora_model_dir:
-lora_r: 64
-lora_alpha: 128
-lora_dropout: 0.125
-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:
-
-# Unsloth stuff
-#unsloth_cross_entropy_loss: true
-#unsloth_lora_mlp: true
-#unsloth_lora_qkv: true
-#unsloth_lora_o: true
-
-# Other things
-#peft_use_dora: true
-
-# Training hyperparameters
-num_epochs: 1
-gradient_accumulation_steps: 1
-micro_batch_size: 6
-eval_batch_size: 6
-warmup_steps: 20
-optimizer: adamw_bnb_8bit
-lr_scheduler: cosine
-learning_rate: 0.00003
-#loraplus_lr_ratio: 8
-#loraplus_lr_embedding:
-cosine_min_lr_ratio: 0.05
-weight_decay: 0.01
-max_grad_norm: 1.0
-logging_steps: 1
-
-# Model optimization
-#gradient_checkpointing: unsloth
-gradient_checkpointing: true
-xformers_attention: false
-flash_attention: true
-sdp_attention: false
-
-# Loss monitoring config
-early_stopping_patience: false
-loss_watchdog_threshold: 100.0
-loss_watchdog_patience: 3
-
-# Debug config
-debug: true
-seed: 111
-
-#Deepspeed
-#deepspeed: axolotl/deepspeed_configs/zero2.json
-
-# Don't mess with this, it's here for accelerate and torchrun
-local_rank:
-```
-
-</details><br>
 
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/lm-hall/SpringDragon-NeMo/runs/dghi0gyq)
 # SpringDragon-NeMo-Instruct-QLoRA-ep1
 
-This model is a fine-tuned version of [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 2.2088
-
-## Model description
+This model is a fine-tuned version of [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) on the SpringDragon dataset.
 
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
+Completion format. User instructions are given with `>`. 
 
 ### Training hyperparameters
 
@@ -183,31 +34,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 20
 - num_epochs: 1
 
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 2.347         | 0.0017 | 1    | 2.3015          |
-| 2.306         | 0.0513 | 30   | 2.2631          |
-| 2.1792        | 0.1026 | 60   | 2.2356          |
-| 2.2576        | 0.1538 | 90   | 2.2298          |
-| 2.1577        | 0.2051 | 120  | 2.2236          |
-| 2.1493        | 0.2564 | 150  | 2.2221          |
-| 2.1297        | 0.3077 | 180  | 2.2232          |
-| 2.1284        | 0.3590 | 210  | 2.2174          |
-| 2.1102        | 0.4103 | 240  | 2.2126          |
-| 2.146         | 0.4615 | 270  | 2.2110          |
-| 2.2056        | 0.5128 | 300  | 2.2115          |
-| 2.2332        | 0.5641 | 330  | 2.2132          |
-| 2.0817        | 0.6154 | 360  | 2.2105          |
-| 2.1018        | 0.6667 | 390  | 2.2107          |
-| 2.0424        | 0.7179 | 420  | 2.2082          |
-| 2.1552        | 0.7692 | 450  | 2.2086          |
-| 2.2877        | 0.8205 | 480  | 2.2091          |
-| 2.191         | 0.8718 | 510  | 2.2090          |
-| 2.0968        | 0.9231 | 540  | 2.2090          |
-| 2.2092        | 0.9744 | 570  | 2.2088          |
-
 
 ### Framework versions