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/0fa46e62efef7055_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 4edf6c60-604f-4b45-b4a9-c26b3c370e50
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 4edf6c60-604f-4b45-b4a9-c26b3c370e50
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # d2018f97-41cb-4a43-80cf-a9ca6c80dacc
 
 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: 0.3511
 
 ## 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    | 1.5121          |
+| 1.0571        | 0.0008 | 10   | 0.8386          |
+| 0.6553        | 0.0015 | 20   | 0.4290          |
+| 0.3243        | 0.0023 | 30   | 0.3721          |
+| 0.2449        | 0.0031 | 40   | 0.3530          |
+| 0.2152        | 0.0038 | 50   | 0.3511          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39d36d5ee8a9dd9a9a5599e56adc963ec14c3fc5f1550cd8853393801fd9418f
+oid sha256:6f1b58b0b288c160a148dc7f351f5979d577c7e0d14200f9495f909d05448246
 size 50982842