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/4f93d007343b77c0_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 9352e83a-13da-4daf-8555-da1303cf09c8
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 9352e83a-13da-4daf-8555-da1303cf09c8
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 9abf39fd-a1a1-433a-b37c-30b3e61d7b66
 
 This model is a fine-tuned version of [Qwen/Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7244
 
 ## Model description
 
@@ -127,14 +129,19 @@ 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        | 0.0015 | 1    | 0.7906          |
+| 0.8248        | 0.0148 | 10   | 0.7797          |
+| 0.8562        | 0.0296 | 20   | 0.7456          |
+| 0.8364        | 0.0444 | 30   | 0.7303          |
+| 0.8265        | 0.0592 | 40   | 0.7252          |
+| 0.7425        | 0.0740 | 50   | 0.7244          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2f93656db56c7dd4ddfda844da32ad32dec8014afed11841925b1f010ea28ed
+oid sha256:ed15bd0d48b3cf5c0f13f9499b6c07be4acc4d77aceaac040bc8d2de28487ffc
 size 37070634