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/4e047a09010b0cfe_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 55dd0a7e-2dfc-4c53-9d52-880be167a512
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 55dd0a7e-2dfc-4c53-9d52-880be167a512
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 332dd3fd-1ea2-488b-2b7a-813fa001bd3d
 
 This model is a fine-tuned version of [elyza/Llama-3-ELYZA-JP-8B](https://huggingface.co/elyza/Llama-3-ELYZA-JP-8B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8367
 
 ## Model description
 
@@ -129,14 +131,19 @@ 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    | 2.3040          |
+| 2.1487        | 0.0057 | 10   | 2.1623          |
+| 1.9449        | 0.0114 | 20   | 1.9387          |
+| 1.9047        | 0.0171 | 30   | 1.8629          |
+| 1.8456        | 0.0227 | 40   | 1.8406          |
+| 1.8875        | 0.0284 | 50   | 1.8367          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5583f7f8c15ecf8f3eec07463945db507382fa7401533cbe24ce13a509f6bba
+oid sha256:e854f672c9b707df6fb7ff4f4fe8bad72da6efdbd8c9722d1bfdbadff612fdb4
 size 84047370