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/0383ac497bc35aec_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 27decbb8-dd48-43d9-aed5-5bbbbd451fba
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 27decbb8-dd48-43d9-aed5-5bbbbd451fba
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 27decbb8-dd48-43d9-aed5-5bbbbd451fba
 
 This model is a fine-tuned version of [MNC-Jihun/Mistral-7B-AO-u0.5-b2-ver0.4](https://huggingface.co/MNC-Jihun/Mistral-7B-AO-u0.5-b2-ver0.4) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7145
 
 ## 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        | 0.0000 | 1    | 0.9291          |
+| No log        | 0.0000 | 1    | 0.9137          |
+| 0.8003        | 0.0002 | 10   | 0.8066          |
+| 0.703         | 0.0004 | 20   | 0.7444          |
+| 0.6453        | 0.0006 | 30   | 0.7230          |
+| 0.7264        | 0.0008 | 40   | 0.7157          |
+| 0.6325        | 0.0010 | 50   | 0.7145          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a19b245361f2327e0e881b308b08964391bf0c02dbcc1f3d17ae1d0f4ae87da
+oid sha256:8bcaf294f3e90881825447687a15b2e8524c471d8d2d072d1338c29b31375195
 size 608352466