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/a180db4f1897af33_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: ca58f798-4347-4780-b171-f2b0a5e7c531
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: ca58f798-4347-4780-b171-f2b0a5e7c531
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # bbc30061-b45f-44cf-b94d-6f8c8fcdc0f6
 
 This model is a fine-tuned version of [tiiuae/falcon-rw-1b](https://huggingface.co/tiiuae/falcon-rw-1b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2944
 
 ## 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        | 0.0002 | 1    | 1.4739          |
+| 6.0087        | 0.0016 | 10   | 1.4185          |
+| 5.4313        | 0.0032 | 20   | 1.3344          |
+| 4.559         | 0.0049 | 30   | 1.3072          |
+| 5.4916        | 0.0065 | 40   | 1.2965          |
+| 5.3712        | 0.0081 | 50   | 1.2944          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a4d1ba7d0043ededb2862b387c1ff6eee0cf22e050d8dca953bf4af117f2721
+oid sha256:7ec27bc4023046c221a839bbddc3833a3335da645f37d949c6853ca594456e1d
 size 25236362