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/0c76baa2cdb9b7cb_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 8ee5a55e-6223-42bd-964c-3ab3401d18d0
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 8ee5a55e-6223-42bd-964c-3ab3401d18d0
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # ebc3e335-5335-ea81-e364-62ac97a67a32
 
 This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1290
 
 ## 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        | 0.0011 | 1    | 1.5910          |
+| 1.5096        | 0.0106 | 10   | 1.4262          |
+| 1.2675        | 0.0212 | 20   | 1.2028          |
+| 1.1821        | 0.0317 | 30   | 1.1534          |
+| 1.1589        | 0.0423 | 40   | 1.1325          |
+| 1.1268        | 0.0529 | 50   | 1.1290          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf1be95ef8c780170df6d5b44b424a13ff31b9acfd5d666425a1d2711dd8c2c5
+oid sha256:56ed928c8aa6d12a2e68929c15b03dfa2c00c8c7e28e5acff7bd20757bccea4e
 size 17717130