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/6c31f6c389df1d7c_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: d413a3e2-5807-47d8-9127-377ed9e29872
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: d413a3e2-5807-47d8-9127-377ed9e29872
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 66fac078-db73-815c-4e34-3a980af3c5bf
 
 This model is a fine-tuned version of [unsloth/Qwen2.5-1.5B-Instruct](https://huggingface.co/unsloth/Qwen2.5-1.5B-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        | 0.0001 | 1    | nan             |
+| 0.0           | 0.0009 | 10   | nan             |
+| 0.0           | 0.0017 | 20   | nan             |
+| 0.0           | 0.0026 | 30   | nan             |
+| 0.0           | 0.0034 | 40   | nan             |
+| 0.0           | 0.0043 | 50   | nan             |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0a9cc6c432e4add969f46851eca3fd1e280785e6ba9546777e58373ebf597d1
+oid sha256:3e49378e0426076b2245cc7fcf628e85218bea0d4a26af17f191233ddef5a18a
 size 37070634