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/3fee030082150935_train_data.json
 model_type: AutoModelForCausalLM
@@ -93,7 +93,7 @@ wandb_name: ffdb536e-9f63-4785-9e1f-2e9914f097f6
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: ffdb536e-9f63-4785-9e1f-2e9914f097f6
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -104,6 +104,8 @@ xformers_attention: null
 # 61b4590b-160e-ffb3-110d-9145655bb607
 
 This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1732
 
 ## Model description
 
@@ -130,14 +132,19 @@ 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    | 1.2427          |
+| 1.2028        | 0.0014 | 10   | 1.2394          |
+| 1.0641        | 0.0028 | 20   | 1.2139          |
+| 1.2457        | 0.0042 | 30   | 1.1876          |
+| 1.1804        | 0.0056 | 40   | 1.1753          |
+| 1.1039        | 0.0069 | 50   | 1.1732          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b72dfe612bb15762e00f78f78b4182015861457e4917bca945e0dc32bb80ca4
+oid sha256:5b780e53a5a72b531771f203c7e02a147203fbfc4df86fe2ab06d18e4a9e37c3
 size 47323530