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/c74825f7031eae65_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 4f622dcb-313e-43e2-ae17-0bf9dc51abcd
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 4f622dcb-313e-43e2-ae17-0bf9dc51abcd
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 2035cca7-4595-4a88-9ae1-e58c36c06c29
 
 This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5367
 
 ## 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        | 0.0001 | 1    | 3.0824          |
+| 12.6127       | 0.0007 | 10   | 2.9299          |
+| 10.4224       | 0.0013 | 20   | 2.6473          |
+| 10.4914       | 0.0020 | 30   | 2.5723          |
+| 10.513        | 0.0026 | 40   | 2.5422          |
+| 9.6477        | 0.0033 | 50   | 2.5367          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7296004e768ea96dc5255e24a0a7be7eb9734fa73bf025c29f049b4842a4f1e
+oid sha256:dc98421a1ea47c54f021a84b974920a53045a27d154768757cf203e274093907
 size 65367946