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/2814f4b210b5de51_train_data.json
 model_type: AutoModelForCausalLM
@@ -93,7 +93,7 @@ wandb_name: b2766613-ebaf-4389-8dd5-0f0647cebc5f
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: b2766613-ebaf-4389-8dd5-0f0647cebc5f
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -104,6 +104,8 @@ xformers_attention: null
 # b2766613-ebaf-4389-8dd5-0f0647cebc5f
 
 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: 1.1580
 
 ## 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        | 0.0046 | 1    | 8.3386          |
+| 7.152         | 0.0462 | 10   | 4.8822          |
+| 1.9039        | 0.0925 | 20   | 1.7941          |
+| 1.0513        | 0.1387 | 30   | 1.3677          |
+| 1.3442        | 0.1850 | 40   | 1.1970          |
+| 1.2559        | 0.2312 | 50   | 1.1580          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7442e4e416a6f4c81d92033df003f4215d5a8b6acb4ae040ebe57d9f131abb27
+oid sha256:7b22a44348d6b4cee298aff8b7788f70bb4f76103d7c3bf2e2855087ad091e5d
 size 50982842