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/f99b5fa5a3706117_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 83b5c5d9-26b4-4edb-9ee4-c63a4f0092b9
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 83b5c5d9-26b4-4edb-9ee4-c63a4f0092b9
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 78162bad-ca18-b072-91a2-c6a11d0c1bf1
 
 This model is a fine-tuned version of [unsloth/gemma-2-2b-it](https://huggingface.co/unsloth/gemma-2-2b-it) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7126
 
 ## 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        | 0.0003 | 1    | 1.3567          |
+| 1.2354        | 0.0033 | 10   | 1.0901          |
+| 0.873         | 0.0066 | 20   | 0.8100          |
+| 0.7435        | 0.0100 | 30   | 0.7391          |
+| 0.755         | 0.0133 | 40   | 0.7165          |
+| 0.7215        | 0.0166 | 50   | 0.7126          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bc59a99f82a72d2e431cbbcb348938a1b17b1f85397158a442fcd6e7e5e1bf3
+oid sha256:3017eaf0e5c516cef4688483d12a5f22820b52c820705366fb6dae8a77208844
 size 41664442