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/e89c95d16beee483_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: e6d7c864-504f-4c94-81e7-e07acab58ff4
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: e6d7c864-504f-4c94-81e7-e07acab58ff4
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # fb80a951-a428-4c72-b937-d70612930a54
 
 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: 11.9345
 
 ## 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        | 0.0034 | 1    | 11.9348         |
+| 11.9335       | 0.0341 | 10   | 11.9348         |
+| 11.9332       | 0.0681 | 20   | 11.9347         |
+| 11.933        | 0.1022 | 30   | 11.9346         |
+| 11.9334       | 0.1363 | 40   | 11.9345         |
+| 11.9337       | 0.1704 | 50   | 11.9345         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c667ab165a0895dc556c7f7bf109f8275d37d0a97002706a799315c4865e96
+oid sha256:0b392bd94d818af465828e2051cdb60e66c0e22428b74d811a6d3a0cee7c0a6a
 size 21378