End of training

README.md

@@ -66,7 +66,7 @@ lora_model_dir: null
 lora_r: 8
 lora_target_linear: true
 lr_scheduler: cosine
-max_steps: 1
+max_steps: 50
 micro_batch_size: 2
 mlflow_experiment_name: /tmp/ff0cba6f3f2148f7_train_data.json
 model_type: AutoModelForCausalLM
@@ -93,7 +93,7 @@ wandb_name: d83aba02-7b9f-4e91-88c8-f60938c0f372
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: d83aba02-7b9f-4e91-88c8-f60938c0f372
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -104,6 +104,8 @@ xformers_attention: null
 # 2315445a-419b-4c2f-38ce-7a2894c827a7
 
 This model is a fine-tuned version of [heegyu/WizardVicuna-open-llama-3b-v2](https://huggingface.co/heegyu/WizardVicuna-open-llama-3b-v2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8960
 
 ## Model description
 
@@ -130,14 +132,19 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 8
 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 2
-- training_steps: 1
+- lr_scheduler_warmup_steps: 10
+- training_steps: 50
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0000 | 1    | 2.5973          |
+| 2.5089        | 0.0002 | 10   | 2.4637          |
+| 2.1585        | 0.0005 | 20   | 2.0329          |
+| 1.9051        | 0.0007 | 30   | 1.9367          |
+| 1.86          | 0.0009 | 40   | 1.9020          |
+| 1.8553        | 0.0012 | 50   | 1.8960          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bd6a59c7437311b004686d37a16da6479b231b475dce8d209a20d11e5add829
+oid sha256:8e25d0ee2503e3f535f3ded6b83c63419057e5f2630e80c393f8be3d5934f989
 size 50982842