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/602bbad55115dd19_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: e95d6a70-7f1d-4976-bd6b-af30f7670a04
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: e95d6a70-7f1d-4976-bd6b-af30f7670a04
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 34d757fb-74c9-ea6f-3869-d41b04b5bcae
 
 This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4925
 
 ## 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        | 0.0004 | 1    | 1.7956          |
+| 6.9593        | 0.0042 | 10   | 1.7400          |
+| 6.7703        | 0.0085 | 20   | 1.5895          |
+| 6.1681        | 0.0127 | 30   | 1.5208          |
+| 5.8633        | 0.0170 | 40   | 1.4972          |
+| 5.9187        | 0.0212 | 50   | 1.4925          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d2160ce5001e825f83788cf8196ee816d29ca634f4aaea2f12515ce1799c248
+oid sha256:a9759f87a90b2b48175b2bdc56f375e22d10d862f9a9ccade2ff28876cce00c6
 size 50424202