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: 8
 mlflow_experiment_name: /tmp/4b5ce55c2fd4f9e6_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 6aa7f3bd-1e4d-45af-8164-78f1a9f0ffe9
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 6aa7f3bd-1e4d-45af-8164-78f1a9f0ffe9
-warmup_steps: 1
+warmup_steps: 2
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 6aa7f3bd-1e4d-45af-8164-78f1a9f0ffe9
 
 This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3794
 
 ## Model description
 
@@ -129,13 +131,18 @@ The following hyperparameters were used during training:
 - 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
+- training_steps: 50
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0091 | 1    | 13.9445         |
+| 12.18         | 0.0911 | 10   | 8.5189          |
+| 5.7398        | 0.1822 | 20   | 2.1543          |
+| 1.0209        | 0.2733 | 30   | 0.4289          |
+| 0.4525        | 0.3645 | 40   | 0.3867          |
+| 0.3723        | 0.4556 | 50   | 0.3794          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28a8b8851aee57375ef275e5e714858559986bd13a2fb125dceb5740dd63fba6
+oid sha256:b60620ea74517db2f24e0180f0de0c806be5372dc06c1062bad4f843dbc71733
 size 37070634