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/44664facd5408a4c_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: da4a2513-3912-4f9c-b444-0720fa758cb8
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: da4a2513-3912-4f9c-b444-0720fa758cb8
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 0a0ca14b-da42-4c9d-987b-ec1dcd618250
 
 This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0011
 
 ## Model description
 
@@ -128,14 +130,18 @@ 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: 42
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0240 | 1    | 0.9337          |
+| 0.8616        | 0.2156 | 9    | 0.2448          |
+| 0.0491        | 0.4311 | 18   | 0.0020          |
+| 0.0013        | 0.6467 | 27   | 0.0012          |
+| 0.0011        | 0.8623 | 36   | 0.0011          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1483962642603fd169755cd869a761fc58f1a0f5af85d1d829aec8db5edace68
+oid sha256:7069f38428d3b5b1a4de80b024eb1b41ff738c9b2d8852ab4983bf5d59aa80fe
 size 17717130