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/0b09d6b4a422abb0_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 7bf18def-945a-4b4b-8168-219cf2fb55f0
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 7bf18def-945a-4b4b-8168-219cf2fb55f0
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 04bd7206-27b7-1a47-21f7-62d99d09b1a4
 
 This model is a fine-tuned version of [fxmarty/really-tiny-falcon-testing](https://huggingface.co/fxmarty/really-tiny-falcon-testing) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 11.0754
 
 ## 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        | 0.0000 | 1    | 11.0870         |
+| 44.351        | 0.0003 | 10   | 11.0858         |
+| 44.3393       | 0.0007 | 20   | 11.0808         |
+| 44.303        | 0.0010 | 30   | 11.0769         |
+| 44.3087       | 0.0013 | 40   | 11.0756         |
+| 44.3117       | 0.0017 | 50   | 11.0754         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffb2411b4ffaebcffe9aaf5bfb6589fdb3734b0668d499fc7a019407fc20d11c
+oid sha256:7c66baeaed3a2bdeb226c346d11d8cce8a6fd220eb7a43a94fcfcea22aef9eb4
 size 37022