End of training

README.md

@@ -66,7 +66,7 @@ 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/a48f6f37fd4ae561_train_data.json
 model_type: AutoModelForCausalLM
@@ -93,7 +93,7 @@ wandb_name: 987c13e4-f0d3-425f-bdac-8c7721cc579e
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 987c13e4-f0d3-425f-bdac-8c7721cc579e
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -104,6 +104,8 @@ xformers_attention: null
 # 987c13e4-f0d3-425f-bdac-8c7721cc579e
 
 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: 0.1604
 
 ## Model description
 
@@ -130,14 +132,19 @@ 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        | 0.0027 | 1    | 3.0432          |
+| 2.0967        | 0.0271 | 10   | 1.5008          |
+| 0.51          | 0.0542 | 20   | 0.2885          |
+| 0.2125        | 0.0813 | 30   | 0.1911          |
+| 0.173         | 0.1084 | 40   | 0.1665          |
+| 0.1039        | 0.1355 | 50   | 0.1604          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10e69934a7e48bc10a6cae8d873a0a5e1549d74fe0e872c5f88c7f8c1fd61da7
+oid sha256:35f7ed14d0060091411164093a7c829f594a76b30f8404c134e2c52d3bba20ae
 size 84047370