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/a30f506ce6e5392d_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 4ae94de6-eb3b-4bb8-8f35-817accb77271
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 4ae94de6-eb3b-4bb8-8f35-817accb77271
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 5ccde83f-4ca3-42c9-9a71-19e1dbb8ef61
 
 This model is a fine-tuned version of [NousResearch/Hermes-2-Pro-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6113
 
 ## 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        | 0.0001 | 1    | 3.1170          |
+| 2.5168        | 0.0011 | 10   | 2.3038          |
+| 1.1568        | 0.0021 | 20   | 1.0058          |
+| 0.8834        | 0.0032 | 30   | 0.7261          |
+| 0.7073        | 0.0043 | 40   | 0.6387          |
+| 0.6635        | 0.0054 | 50   | 0.6113          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27fb6eeadcdfccd8de299545b26db27d757a87da6b49d517c6c55b2fd599f6c9
+oid sha256:44ed54394a4ef56dced704bc5d3840478d7cb9d866a893e416c49e05d283b350
 size 84047370