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/53d2be18601f4c10_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 845b883d-708c-40bb-b012-033b82100dc3
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 845b883d-708c-40bb-b012-033b82100dc3
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # ab114374-3e0d-4c6f-87ad-bf9eb07759f3
 
 This model is a fine-tuned version of [unsloth/gemma-2-2b-it](https://huggingface.co/unsloth/gemma-2-2b-it) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3301
 
 ## 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        | 0.0001 | 1    | 1.9016          |
+| 1.7063        | 0.0010 | 10   | 1.6454          |
+| 1.3689        | 0.0021 | 20   | 1.3944          |
+| 1.293         | 0.0031 | 30   | 1.3443          |
+| 1.2965        | 0.0042 | 40   | 1.3332          |
+| 1.2853        | 0.0052 | 50   | 1.3301          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91b7e09b9b8376aa3a7f241521839ec20e3df5eccd800b25acfc792f0052617c
+oid sha256:8d19579403053cb77def9df5dd03db69010df095e00c8a137bb86727a4509390
 size 41664442