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: 8
 mlflow_experiment_name: /tmp/4dca6cddca4d8264_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 59066488-3dc2-47ac-9df9-63e960d25aed
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 59066488-3dc2-47ac-9df9-63e960d25aed
-warmup_steps: 1
+warmup_steps: 2
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 59066488-3dc2-47ac-9df9-63e960d25aed
 
 This model is a fine-tuned version of [unsloth/gemma-2-2b](https://huggingface.co/unsloth/gemma-2-2b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1985
 
 ## Model description
 
@@ -129,13 +131,17 @@ The following hyperparameters were used during training:
 - 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
+- training_steps: 16
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0643 | 1    | 2.4946          |
+| No log        | 0.2570 | 4    | 1.9454          |
+| No log        | 0.5141 | 8    | 1.3581          |
+| 1.9168        | 0.7711 | 12   | 1.2224          |
+| 1.9168        | 1.0602 | 16   | 1.1985          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30c8b0bae44f39d175ff8148c6980ce23d37b1fb16122125f7d2beb5854001b3
+oid sha256:1af8ec66da36412a4e799bb8ec4b89ab55a2446833653c0c8cdf1f94288921a2
 size 41664442