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/ca95c1dd76317914_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: a9a4defb-80a3-4283-88ae-5b50de731b69
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: a9a4defb-80a3-4283-88ae-5b50de731b69
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 405d8991-1b79-965b-4b7d-69757a4db880
 
 This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0957
 
 ## 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        | 0.0005 | 1    | 0.1850          |
+| 0.6331        | 0.0054 | 10   | 0.1662          |
+| 0.4692        | 0.0107 | 20   | 0.1223          |
+| 0.4076        | 0.0161 | 30   | 0.1015          |
+| 0.394         | 0.0215 | 40   | 0.0966          |
+| 0.4302        | 0.0269 | 50   | 0.0957          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ef83957b93d20d18d3e89f7aec296d3eca49a2d0d432907f1ce0df5c088dfe8
+oid sha256:a3f5696490b7b100ee8a99bcb35a9a25473638a5e30a0959b2a87d5816e0398c
 size 50424202