End of training

README.md

@@ -66,7 +66,7 @@ lora_model_dir: null
 lora_r: 8
 lora_target_linear: true
 lr_scheduler: cosine
-max_steps: 50
+max_steps: 1
 micro_batch_size: 2
 mlflow_experiment_name: /tmp/74df6e54261df052_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 80ce562a-aba2-4749-8b0d-6fc68d3dc801
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 80ce562a-aba2-4749-8b0d-6fc68d3dc801
-warmup_steps: 10
+warmup_steps: 1
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,8 +102,6 @@ xformers_attention: null
 # 85e1d010-db2c-3eaf-899f-e44dc8594f30
 
 This model is a fine-tuned version of [unsloth/Qwen2-7B-Instruct](https://huggingface.co/unsloth/Qwen2-7B-Instruct) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: nan
 
 ## Model description
 
@@ -130,19 +128,14 @@ 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: 10
-- training_steps: 50
+- lr_scheduler_warmup_steps: 2
+- training_steps: 1
 
 ### 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           | 0.0009 | 30   | nan             |
-| 0.0           | 0.0012 | 40   | nan             |
-| 0.0           | 0.0015 | 50   | nan             |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f0632d73ad0521b9481d6c4e64dcbd148e5db383b032a8992b90fa03cdf49b7
+oid sha256:b4c7018129d6d56f6643c28e46b6605da4a3fa4ff1e213481cb0f9c04c2d75e2
 size 80881450