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/69ffe4b4886a75f3_train_data.json
 model_type: AutoModelForCausalLM
@@ -93,7 +93,7 @@ wandb_name: 44c9e4b4-5d69-4903-b23a-8a53dfad8e10
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 44c9e4b4-5d69-4903-b23a-8a53dfad8e10
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -104,6 +104,8 @@ xformers_attention: null
 # 44c9e4b4-5d69-4903-b23a-8a53dfad8e10
 
 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: 1.1342
 
 ## 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        | 0.0019 | 1    | 3.7896          |
+| 3.0872        | 0.0185 | 10   | 2.5827          |
+| 1.6842        | 0.0370 | 20   | 1.6328          |
+| 1.4348        | 0.0555 | 30   | 1.2888          |
+| 1.3083        | 0.0740 | 40   | 1.1574          |
+| 1.3124        | 0.0925 | 50   | 1.1342          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd6478185dbc6a48679fc3c31354e2575bdef03afbd587cc14690aee8dde64be
+oid sha256:7a0328b970e58f37f95fd888324a9cf1a478f097c4f227a48ba19055625ceb54
 size 50982842