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/d171119848cefa44_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 41786387-c87e-459f-8281-a55ca7c8ac61
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 41786387-c87e-459f-8281-a55ca7c8ac61
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # fae89cf2-bb8f-692d-9e10-dc414d8b90f9
 
 This model is a fine-tuned version of [The-matt/llama2_ko-7b_distinctive-snowflake-182_1060](https://huggingface.co/The-matt/llama2_ko-7b_distinctive-snowflake-182_1060) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8993
 
 ## 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        | 0.0001 | 1    | 0.9961          |
+| 0.9662        | 0.0006 | 10   | 0.9823          |
+| 0.9324        | 0.0012 | 20   | 0.9338          |
+| 0.9118        | 0.0018 | 30   | 0.9102          |
+| 0.9211        | 0.0024 | 40   | 0.9010          |
+| 0.8794        | 0.0029 | 50   | 0.8993          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dad9543a822ffc1054b3e474d5b0a1c40535b9156d5e540a6309036b572002c7
+oid sha256:22c548a047d3880bde4cd64fa8f2050b6bfa7c0749946b33a1bc17b6a13ea6a0
 size 80115210