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/daaf351b5f079471_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 103a311e-9739-47b3-98a2-b2d257c07424
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 103a311e-9739-47b3-98a2-b2d257c07424
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 103a311e-9739-47b3-98a2-b2d257c07424
 
 This model is a fine-tuned version of [DeepMount00/Llama-3-8b-Ita](https://huggingface.co/DeepMount00/Llama-3-8b-Ita) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3418
 
 ## 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    | 7.8313          |
+| 6.4498        | 0.0002 | 10   | 5.1529          |
+| 1.3798        | 0.0005 | 20   | 0.8882          |
+| 0.3125        | 0.0007 | 30   | 0.4898          |
+| 0.1906        | 0.0010 | 40   | 0.3746          |
+| 0.4922        | 0.0012 | 50   | 0.3418          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4db0fc072df2b37bde27bfb191ede09648a2d4e83215fba06afefc1ab32b634
+oid sha256:572903e8f1a5b3d7b97dc5b04ea090b64d3cca0edd2884ecd8dd2f619bef3d3f
 size 84047370