End of training

README.md

@@ -66,7 +66,7 @@ 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/5f86686afc25dcb7_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: ae26b891-1395-4573-997c-c92003820c81
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: ae26b891-1395-4573-997c-c92003820c81
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 0a7f97b2-bcc6-42c9-8cce-b76a5872c184
 
 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: 1.9928
 
 ## Model description
 
@@ -128,14 +130,19 @@ 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    | 2.9677          |
+| 2.8693        | 0.0007 | 10   | 2.6468          |
+| 2.2338        | 0.0013 | 20   | 2.0982          |
+| 1.9876        | 0.0020 | 30   | 2.0284          |
+| 1.894         | 0.0026 | 40   | 1.9975          |
+| 2.1017        | 0.0033 | 50   | 1.9928          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d94e85b1e8f604a95ee4223d4a4e52df84bd4007b4e0b363526b967f703fb18
+oid sha256:1827142e63f7d8e277dd60c0fa962d0b613af334f0707d9332f037e57ec16fba
 size 84047370