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: 1
+max_steps: 50
 micro_batch_size: 2
 mlflow_experiment_name: /tmp/3aaf661573d5c3ab_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 2c1f0dce-c24d-43f8-86dc-589d6d262200
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 2c1f0dce-c24d-43f8-86dc-589d6d262200
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 2c1f0dce-c24d-43f8-86dc-589d6d262200
 
 This model is a fine-tuned version of [unsloth/Qwen2-1.5B-Instruct](https://huggingface.co/unsloth/Qwen2-1.5B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
 
 ## Model description
 
@@ -128,14 +130,19 @@ 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        | 0.0036 | 1    | nan             |
+| 0.0           | 0.0362 | 10   | nan             |
+| 0.0           | 0.0725 | 20   | nan             |
+| 0.0           | 0.1087 | 30   | nan             |
+| 0.0           | 0.1449 | 40   | nan             |
+| 0.0           | 0.1812 | 50   | nan             |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16718e26103fa527fd34c5cddc6093d22511a1b9a5f0f0404fefe9a02a7717ed
+oid sha256:b8b3c5175e52578e9db128e50ac73d02511d55f2aa95c896707d5f0db6f58a5b
 size 37070634