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/aa95f3ab19fe1114_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 50fcc401-3f1d-46f7-a45a-31d9232609c3
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 50fcc401-3f1d-46f7-a45a-31d9232609c3
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 98b4f40e-cc64-466f-b5a5-55c5d04e3355
 
 This model is a fine-tuned version of [unsloth/gemma-2-2b](https://huggingface.co/unsloth/gemma-2-2b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.1645
 
 ## 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        | 0.0058 | 1    | 4.5842          |
+| 4.2658        | 0.0585 | 10   | 4.0695          |
+| 3.4693        | 0.1170 | 20   | 3.4060          |
+| 2.9384        | 0.1754 | 30   | 3.2552          |
+| 2.9318        | 0.2339 | 40   | 3.1777          |
+| 3.0101        | 0.2924 | 50   | 3.1645          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e39a05290577a0483c8c0053bf96e3fe021f0763144714a4f4f850b62d95f274
+oid sha256:a5d21ddc99cfc63b6300538ad8ef993fbcdc608d37586334eb3c04dff47ef3fa
 size 41664442