End of training

README.md

@@ -59,7 +59,7 @@ 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/5178402b4c4ddad7_train_data.json
 model_type: AutoModelForCausalLM
@@ -84,7 +84,7 @@ wandb_name: 3f2636b7-6e5d-449d-a20a-40714d8d2c2f
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 3f2636b7-6e5d-449d-a20a-40714d8d2c2f
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -95,6 +95,8 @@ xformers_attention: null
 # 3f2636b7-6e5d-449d-a20a-40714d8d2c2f
 
 This model is a fine-tuned version of [unsloth/Qwen2.5-Math-7B-Instruct](https://huggingface.co/unsloth/Qwen2.5-Math-7B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
 
 ## Model description
 
@@ -121,14 +123,19 @@ 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    | nan             |
+| 0.0           | 0.0007 | 10   | nan             |
+| 0.0           | 0.0013 | 20   | nan             |
+| 0.0           | 0.0020 | 30   | nan             |
+| 0.0           | 0.0026 | 40   | nan             |
+| 0.0           | 0.0033 | 50   | nan             |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:620a154f71bcb39e72998dc2d4e57018c07678735cabee12cbe98a7362ff2c4e
+oid sha256:7e8d35a13be9989bbadc08172454b551ec704ddea615f60319cd7afeaaf4e114
 size 80881450