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/135aeae4c8fee5b8_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: f66afce0-d1c4-42f9-a266-535349f71e50
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: f66afce0-d1c4-42f9-a266-535349f71e50
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 8ad78992-f2ed-4e42-bcf1-ef22fe799103
 
 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: 1.1003
 
 ## 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        | 0.0000 | 1    | 1.8410          |
+| 1.6573        | 0.0002 | 10   | 1.4620          |
+| 1.3866        | 0.0004 | 20   | 1.1856          |
+| 1.1808        | 0.0006 | 30   | 1.1276          |
+| 0.8891        | 0.0008 | 40   | 1.1046          |
+| 1.131         | 0.0010 | 50   | 1.1003          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1787d34372bacb8afed1b5ca668eeb9305f9f1f7fdd0056ecf3fed99d9635d3f
+oid sha256:a440a2a85b85644795e8373b1ea61ec0b796c539361baf0be515576ed6472e99
 size 84047370