End of training

README.md

@@ -66,7 +66,7 @@ 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/2d75da559a891ff1_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 1b97ca28-5569-4f21-bf43-913c71accac7
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 1b97ca28-5569-4f21-bf43-913c71accac7
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 2877191b-8149-8936-cb37-527c1f070a11
 
 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: 11.0601
 
 ## Model description
 
@@ -128,14 +130,19 @@ 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    | 11.0855         |
+| 44.3344       | 0.0002 | 10   | 11.0816         |
+| 44.2913       | 0.0003 | 20   | 11.0713         |
+| 44.2555       | 0.0005 | 30   | 11.0637         |
+| 44.251        | 0.0007 | 40   | 11.0607         |
+| 44.2377       | 0.0008 | 50   | 11.0601         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:869d5e4c8cc6227917f340bb8ded5202bf7566bee8648008713c9addbea8df18
+oid sha256:9a412cc91f99c7c03cf78fae948935df7b4f2875e9b63195c66c4dd8c040cc52
 size 37022