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/333c6fbfb88adc78_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 83f43278-bd1c-40d7-b106-f6aafe6f314d
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 83f43278-bd1c-40d7-b106-f6aafe6f314d
-warmup_steps: 1
+warmup_steps: 2
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 83f43278-bd1c-40d7-b106-f6aafe6f314d
 
 This model is a fine-tuned version of [unsloth/codegemma-7b-it](https://huggingface.co/unsloth/codegemma-7b-it) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0014
 
 ## Model description
 
@@ -129,13 +131,18 @@ 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: 50
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0157 | 1    | 1.1739          |
+| 0.6404        | 0.1573 | 10   | 0.0644          |
+| 0.0218        | 0.3147 | 20   | 0.0036          |
+| 0.0035        | 0.4720 | 30   | 0.0015          |
+| 0.0032        | 0.6293 | 40   | 0.0015          |
+| 0.0024        | 0.7866 | 50   | 0.0014          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60781782bb8d75f38b0f8c3681489ecb928d13c69c736b52bd177cdd46282722
+oid sha256:559cd2e557fc2ee01aa7021d83e12499396cb5b1c7d649e3600c4530bd15f595
 size 100149034