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/6755b140e3dbc3a5_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: a3aef118-d5c4-4a66-9cad-1c6576184a25
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: a3aef118-d5c4-4a66-9cad-1c6576184a25
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # a68cc278-9111-6474-786d-106293ed64f2
 
 This model is a fine-tuned version of [unsloth/gemma-2b-it](https://huggingface.co/unsloth/gemma-2b-it) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.1022
 
 ## 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    | 4.3347          |
+| 4.2676        | 0.0004 | 10   | 3.8439          |
+| 3.2997        | 0.0009 | 20   | 3.3384          |
+| 3.2471        | 0.0013 | 30   | 3.1683          |
+| 2.9318        | 0.0018 | 40   | 3.1123          |
+| 3.0246        | 0.0022 | 50   | 3.1022          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f1b28d5b7a1979b0b0cb726c9d002bda1b1da31f805027b480a619cb361d71e
+oid sha256:98d170692e03fcc6e230ec6e702e12fee2b29f28f6b797601859391fea670f60
 size 39313978