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/b6f057ade0539641_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: e5874c83-bcdb-4c42-9d0b-ca848da39936
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: e5874c83-bcdb-4c42-9d0b-ca848da39936
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # e5874c83-bcdb-4c42-9d0b-ca848da39936
 
 This model is a fine-tuned version of [NousResearch/Yarn-Llama-2-7b-128k](https://huggingface.co/NousResearch/Yarn-Llama-2-7b-128k) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7003
 
 ## Model description
 
@@ -127,14 +129,19 @@ 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        | 0.0036 | 1    | 7.8466          |
+| 27.0405       | 0.0357 | 10   | 3.8224          |
+| 3.4617        | 0.0714 | 20   | 0.7453          |
+| 2.7719        | 0.1070 | 30   | 0.7876          |
+| 2.6862        | 0.1427 | 40   | 0.7093          |
+| 2.8617        | 0.1784 | 50   | 0.7003          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d50ccaeb103d4f01df426d656b6ea13f00e0bbfeb790feb9bd01e666224f07
+oid sha256:e273d3db508ba4bd4d50cf1ccf2081a92ab9d13a6b256642a48d73b8c15ead05
 size 80115210