End of training

README.md

@@ -65,7 +65,7 @@ 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/7d7341cf3e60a551_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 29b23084-8a57-464a-8e22-5a1b5ebe94ab
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 29b23084-8a57-464a-8e22-5a1b5ebe94ab
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 29b23084-8a57-464a-8e22-5a1b5ebe94ab
 
 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: 1.9003
 
 ## Model description
 
@@ -129,14 +131,19 @@ 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        | 0.0001 | 1    | 2.5588          |
+| 2.5951        | 0.0008 | 10   | 2.4087          |
+| 1.9394        | 0.0016 | 20   | 1.9988          |
+| 1.8007        | 0.0024 | 30   | 1.9369          |
+| 1.9222        | 0.0033 | 40   | 1.9053          |
+| 1.7793        | 0.0041 | 50   | 1.9003          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd9f7a048012b4a812b2fa77c8ad65a99b0526ac483d4d8156f1af9751a81c26
+oid sha256:f8c5c9d2c304d7d558465194ee49596cb0768cdffa0c58373cab8b33951a735c
 size 50982842