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/45e553f1b1e80cc2_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: cecc7ea8-2352-43da-b328-8bcb05e7f174
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: cecc7ea8-2352-43da-b328-8bcb05e7f174
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # cecc7ea8-2352-43da-b328-8bcb05e7f174
 
 This model is a fine-tuned version of [oopsung/llama2-7b-koNqa-test-v1](https://huggingface.co/oopsung/llama2-7b-koNqa-test-v1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
 
 ## 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        | 0.0006 | 1    | nan             |
+| 0.0           | 0.0061 | 10   | nan             |
+| 0.0           | 0.0122 | 20   | nan             |
+| 0.0           | 0.0183 | 30   | nan             |
+| 0.0           | 0.0244 | 40   | nan             |
+| 0.0           | 0.0305 | 50   | nan             |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ca6c679d52df70e25849faeefd0132ad39d8bf151ad51cdd610b67ca019c72b
+oid sha256:922affbfea81a82bae578750efd055f45a45b3a6ad464b7bb21dd14832879c0a
 size 80115210