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/1a8ed9ea15eb5bb2_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: c4b44b9f-b150-4f6b-af58-a6f87d3f1e87
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: c4b44b9f-b150-4f6b-af58-a6f87d3f1e87
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # c4c9de87-2ef3-9903-9188-c2f26f934842
 
 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: 1.8124
 
 ## 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        | 0.0021 | 1    | 3.0706          |
+| 2.6939        | 0.0211 | 10   | 2.6773          |
+| 2.1306        | 0.0422 | 20   | 2.0530          |
+| 1.8946        | 0.0634 | 30   | 1.8791          |
+| 1.8622        | 0.0845 | 40   | 1.8233          |
+| 1.9179        | 0.1056 | 50   | 1.8124          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1524ea10be549df201973e644553c64f0001401ec0f28a443a69df6e71fc809
+oid sha256:9b5f270aae0758ac75a06b025404df4f4d6418419b31796eaea5556e083f296b
 size 50982842