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/fafb033a3a22da7b_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: bc462987-142f-4e01-9997-6146be0707f1
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: bc462987-142f-4e01-9997-6146be0707f1
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 383f5b4b-c75f-4d41-9fac-acf9531c6c88
 
 This model is a fine-tuned version of [unsloth/codegemma-7b](https://huggingface.co/unsloth/codegemma-7b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1078
 
 ## 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        | 0.0000 | 1    | 1.3375          |
+| 1.1661        | 0.0004 | 10   | 0.8356          |
+| 0.3329        | 0.0008 | 20   | 0.2654          |
+| 0.1694        | 0.0012 | 30   | 0.1440          |
+| 0.1262        | 0.0016 | 40   | 0.1148          |
+| 0.0962        | 0.0020 | 50   | 0.1078          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdcaa3e164ad7336e398f4316ce2637ef4b8ac4a34aad2ca96c331167e8193b2
+oid sha256:942448b79472059ef4eb46fcd90595d9acdb8dc9d87f7842f1619ed53e477577
 size 100149034