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/2d5fa363cabe9261_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: ee6500c9-8213-465f-82a1-d316b5374911
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: ee6500c9-8213-465f-82a1-d316b5374911
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # ee6500c9-8213-465f-82a1-d316b5374911
 
 This model is a fine-tuned version of [Qwen/Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0592
 
 ## 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    | 2.1260          |
+| 1.5372        | 0.0012 | 10   | 0.7550          |
+| 0.1416        | 0.0025 | 20   | 0.0861          |
+| 0.0908        | 0.0037 | 30   | 0.0638          |
+| 0.0207        | 0.0049 | 40   | 0.0603          |
+| 0.0859        | 0.0061 | 50   | 0.0592          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b785900384055f10959e8c36faae55259acea792a1f8491bf6d930c426324606
+oid sha256:3551dd8f8b434c784c3e50c120fb30e13e277f6dbefe3af80d64437796c58c32
 size 37070634