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: 8
 mlflow_experiment_name: /tmp/23945c029a5fb08e_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: ca7b94e3-9daf-47b0-aea8-648c8f291aa3
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: ca7b94e3-9daf-47b0-aea8-648c8f291aa3
-warmup_steps: 1
+warmup_steps: 2
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # ca7b94e3-9daf-47b0-aea8-648c8f291aa3
 
 This model is a fine-tuned version of [unsloth/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/unsloth/Qwen2.5-Coder-7B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
 
 ## Model description
 
@@ -128,13 +130,18 @@ 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: 1
+- training_steps: 50
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0041 | 1    | nan             |
+| 0.0           | 0.0410 | 10   | nan             |
+| 0.0           | 0.0819 | 20   | nan             |
+| 0.0           | 0.1229 | 30   | nan             |
+| 0.0           | 0.1639 | 40   | nan             |
+| 0.0           | 0.2049 | 50   | nan             |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77205cfb354ea83885ea86f6027c6cd6b7db236d748cbfcd1a0da176fbff37e3
+oid sha256:d094c2b66c619f6f6e04d3f1ae473f5f9ad392b4726839df271d6680b0034d9a
 size 80881450