Update README.md

README.md

@@ -1,6 +1,7 @@
 ---
 license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.1
+datasets: NeuralNovel/Neural-DPO
 tags:
 - generated_from_trainer
 model-index:
@@ -31,7 +32,8 @@ datasets:
     split: train
     type: chatml.intel
     format: "[INST] {instruction} [/INST]"
-    no_input_format: "[INST] {instruction} [/INST]"    
+    no_input_format: "[INST] {instruction} [/INST]"
+
 dataset_prepared_path:
 val_set_size: 0.05
 output_dir: ./out
@@ -44,12 +46,12 @@ eval_sample_packing: false
 wandb_project:
 wandb_entity:
 wandb_watch:
-wandb_name: Neural-DPO
+wandb_name:
 wandb_log_model:
 
 gradient_accumulation_steps: 4
 micro_batch_size: 2
-num_epochs: 6
+num_epochs: 1
 optimizer: adamw_bnb_8bit
 lr_scheduler: cosine
 learning_rate: 0.000005
@@ -72,7 +74,7 @@ warmup_steps: 10
 evals_per_epoch: 4
 eval_table_size:
 eval_max_new_tokens: 128
-saves_per_epoch: 0
+saves_per_epoch: 1
 debug:
 deepspeed:
 weight_decay: 0.0
@@ -89,7 +91,7 @@ special_tokens:
 
 # out
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the Neural-DPO dataset with laserRMT applied.
 
 ## Model description
 
@@ -117,7 +119,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 10
-- training_steps: 801
+- training_steps: 134
 
 ### Training results
 
@@ -127,5 +129,5 @@ The following hyperparameters were used during training:
 
 - Transformers 4.38.0.dev0
 - Pytorch 2.2.0+cu121
-- Datasets 2.17.1
+- Datasets 2.17.0
 - Tokenizers 0.15.0