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/99abecc3940692d4_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 9a614f62-ffe2-40a4-9a16-ba60a4e21ae0
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 9a614f62-ffe2-40a4-9a16-ba60a4e21ae0
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 6483b953-68bc-21e5-870f-df3e47170d3b
 
 This model is a fine-tuned version of [VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct](https://huggingface.co/VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.0251
 
 ## 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    | 2.1410          |
+| 2.0296        | 0.0009 | 10   | 2.1128          |
+| 2.0385        | 0.0019 | 20   | 2.0514          |
+| 1.9569        | 0.0028 | 30   | 2.0336          |
+| 2.0647        | 0.0038 | 40   | 2.0265          |
+| 2.0398        | 0.0047 | 50   | 2.0251          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c5ef5b9a6bbd4d11cfdfca3b2bb60a5d80f5824f91a61fd6dcffde819c7058a
+oid sha256:08394612ef71841791465d9804f110054a65f601b7d9a068aa81eb9ca656f7a1
 size 84047370