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/cff5b916be5cbb04_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 119c6de8-4d74-4658-80c6-2b3c1d5aab09
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 119c6de8-4d74-4658-80c6-2b3c1d5aab09
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 119c6de8-4d74-4658-80c6-2b3c1d5aab09
 
 This model is a fine-tuned version of [unsloth/Llama-3.1-Storm-8B](https://huggingface.co/unsloth/Llama-3.1-Storm-8B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2093
 
 ## 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        | 0.0018 | 1    | 1.5736          |
+| 1.4599        | 0.0177 | 10   | 1.4365          |
+| 1.2836        | 0.0354 | 20   | 1.2429          |
+| 1.2328        | 0.0530 | 30   | 1.2237          |
+| 1.1638        | 0.0707 | 40   | 1.2111          |
+| 1.2157        | 0.0884 | 50   | 1.2093          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fc20a1adce05801dd95d69c6c6bc749f37bbeecd9f97250ea12da4244756e5a
+oid sha256:8267f0b491fc90f8c4710ed30001c925368acb237f1769eb99ea9d4927b1aed9
 size 84047370