End of training

README.md

@@ -64,7 +64,7 @@ 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/e4169f1098fe370a_train_data.json
 model_type: AutoModelForCausalLM
@@ -89,7 +89,7 @@ wandb_name: 4271b026-9cf4-4c38-bf60-51651503922c
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 4271b026-9cf4-4c38-bf60-51651503922c
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -100,6 +100,8 @@ xformers_attention: null
 # 4271b026-9cf4-4c38-bf60-51651503922c
 
 This model is a fine-tuned version of [peft-internal-testing/tiny-dummy-qwen2](https://huggingface.co/peft-internal-testing/tiny-dummy-qwen2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 11.9313
 
 ## Model description
 
@@ -126,14 +128,19 @@ 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        | 0.0007 | 1    | 11.9320         |
+| 11.933        | 0.0069 | 10   | 11.9319         |
+| 11.9315       | 0.0137 | 20   | 11.9316         |
+| 11.933        | 0.0206 | 30   | 11.9314         |
+| 11.9315       | 0.0275 | 40   | 11.9313         |
+| 11.9311       | 0.0343 | 50   | 11.9313         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bde53f569efe7bc548cb2a5acbfb91a3ff85486d99c56c7bd6940713c13571f5
+oid sha256:5cb9a40e664b9dbc7d8f635eb40f86b65958ed712559488c0d420e37a249438f
 size 21378