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/f02902dad81db1e0_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 182428cc-e239-4444-9165-a74885954c81
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 182428cc-e239-4444-9165-a74885954c81
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 9c465642-90fe-4fb4-aaae-10ddaf731c66
 
 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: 11.0886
 
 ## 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        | 0.0003 | 1    | 11.0922         |
+| 44.336        | 0.0026 | 10   | 11.0917         |
+| 44.3713       | 0.0051 | 20   | 11.0903         |
+| 44.3663       | 0.0077 | 30   | 11.0893         |
+| 44.3626       | 0.0102 | 40   | 11.0887         |
+| 44.361        | 0.0128 | 50   | 11.0886         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaa1b78a6f164866601e11f9ca134dd69f23225605a4b266f68d2181d35a8299
+oid sha256:2deeef9b9dd5f8c05b38c079a771f2070c924d66ef3d66c48eeb7fa0f1ca5f3b
 size 37022