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/60ec1eaa4acb1cf5_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 9ac43e03-044d-46f3-9303-8c7e590e0d06
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 9ac43e03-044d-46f3-9303-8c7e590e0d06
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 45991bd4-764f-5c72-03d7-21d5edcf6067
 
 This model is a fine-tuned version of [TinyLlama/TinyLlama_v1.1](https://huggingface.co/TinyLlama/TinyLlama_v1.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6824
 
 ## 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        | 0.0004 | 1    | 2.6600          |
+| 2.2713        | 0.0043 | 10   | 2.1321          |
+| 2.0763        | 0.0085 | 20   | 1.8722          |
+| 1.6768        | 0.0128 | 30   | 1.7495          |
+| 1.7516        | 0.0170 | 40   | 1.6913          |
+| 1.623         | 0.0213 | 50   | 1.6824          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10be2eb39cad58ff40480def397d75d744e3fabb927305ae901c1dbaf17ae3f1
+oid sha256:41255d5cf0a7a178df7a5f727dbec9bc6099e299f782f2f0e3ed42226a235c4e
 size 25342042