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/46e82c8771a069d9_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: d3b84cbd-83c1-4673-9188-510dd3480688
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: d3b84cbd-83c1-4673-9188-510dd3480688
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # d3b84cbd-83c1-4673-9188-510dd3480688
 
 This model is a fine-tuned version of [unsloth/Meta-Llama-3.1-8B](https://huggingface.co/unsloth/Meta-Llama-3.1-8B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5614
 
 ## 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        | 0.0027 | 1    | 3.4267          |
+| 2.845         | 0.0274 | 10   | 2.4403          |
+| 1.1243        | 0.0549 | 20   | 0.7998          |
+| 0.5812        | 0.0823 | 30   | 0.6048          |
+| 0.554         | 0.1097 | 40   | 0.5700          |
+| 0.5618        | 0.1372 | 50   | 0.5614          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:809d3d270e83c36dec67a83df16569867fbfb673a4c153efbd57b7d53079c82e
+oid sha256:9ce7f724102247338a88db1e316ab1d8155f6f47e7269490fd3663e46a00d7a1
 size 84047370