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/6b9109a6db174c05_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 3aefa5d0-1c2e-4a87-ac85-eadf9d27a6ee
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 3aefa5d0-1c2e-4a87-ac85-eadf9d27a6ee
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 112c4af4-dbd3-87b6-a994-588ce53db5ad
 
 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
 
@@ -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    | nan             |
+| 0.0           | 0.0002 | 10   | nan             |
+| 0.0           | 0.0005 | 20   | nan             |
+| 0.0           | 0.0007 | 30   | nan             |
+| 0.0           | 0.0009 | 40   | nan             |
+| 0.0           | 0.0012 | 50   | nan             |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ddc4a54bd80084dc457123eb07a26c92774e8d4c3aa45a08dd246604e629823
+oid sha256:5b2f467ea7905ffa0ec21246c6d21164172a8c80f016ce66642ae80fa031b36e
 size 80881450