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/82596413ef5d982d_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 62167e88-dc84-4cce-a484-ce43fa3eda1d
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 62167e88-dc84-4cce-a484-ce43fa3eda1d
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 9b89f2eb-3345-4b76-9614-82be2e21e3c3
 
 This model is a fine-tuned version of [unsloth/Qwen2.5-0.5B-Instruct](https://huggingface.co/unsloth/Qwen2.5-0.5B-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           | 0.0003 | 10   | nan             |
+| 0.0           | 0.0006 | 20   | nan             |
+| 0.0           | 0.0008 | 30   | nan             |
+| 0.0           | 0.0011 | 40   | nan             |
+| 0.0           | 0.0014 | 50   | nan             |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2ecaf12900d08844a950a93308de1a1cde42e1bcc20821d8bce1be0f9784748
+oid sha256:3010a8b9828667f62ed4232e0bbedb4d43f3e021b0cf047996e486e592453dc4
 size 17717130