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: 50
+max_steps: 1
 micro_batch_size: 8
 mlflow_experiment_name: /tmp/e508e93efa4fc596_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: b26552ba-5cfc-4faa-bf2e-cf67e1391b72
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: b26552ba-5cfc-4faa-bf2e-cf67e1391b72
-warmup_steps: 2
+warmup_steps: 1
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,8 +101,6 @@ xformers_attention: null
 # b26552ba-5cfc-4faa-bf2e-cf67e1391b72
 
 This model is a fine-tuned version of [unsloth/Qwen2.5-Math-1.5B](https://huggingface.co/unsloth/Qwen2.5-Math-1.5B) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: nan
 
 ## Model description
 
@@ -130,18 +128,13 @@ 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: 50
+- training_steps: 1
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0005 | 1    | nan             |
-| 0.0           | 0.0050 | 10   | nan             |
-| 0.0           | 0.0099 | 20   | nan             |
-| 0.0           | 0.0149 | 30   | nan             |
-| 0.0           | 0.0199 | 40   | nan             |
-| 0.0           | 0.0249 | 50   | nan             |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23ae2048acc01aae33e7c2c07c46140b2c5266d954403a56c7ee00329db47e4f
+oid sha256:07c7c77375a2d55beefa77e47a3ae9b5bddf8d7ecae82e98d7e96effcd2dbbc8
 size 37070634