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: 8
 mlflow_experiment_name: /tmp/a2552944cccf89dd_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 730b1c45-901f-480e-bbc0-cbfe3241a83a
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 730b1c45-901f-480e-bbc0-cbfe3241a83a
-warmup_steps: 1
+warmup_steps: 2
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 730b1c45-901f-480e-bbc0-cbfe3241a83a
 
 This model is a fine-tuned version of [unsloth/Llama-3.2-3B](https://huggingface.co/unsloth/Llama-3.2-3B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.1483
 
 ## Model description
 
@@ -129,13 +131,18 @@ The following hyperparameters were used during training:
 - 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
+- training_steps: 50
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0168 | 1    | 10.1960         |
+| 9.3317        | 0.1677 | 10   | 6.8215          |
+| 5.2304        | 0.3354 | 20   | 3.8652          |
+| 3.5338        | 0.5031 | 30   | 3.3422          |
+| 3.1788        | 0.6709 | 40   | 3.1707          |
+| 3.1481        | 0.8386 | 50   | 3.1483          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1621d5afe87b7b478b89e88f940a86b28c8c62ccd41e0a4ae5e24c5a5d3b652
+oid sha256:f2c768674ab9ab0ce2efe581eff4d6416c3cf48152620db186146e8c7934de3a
 size 48768810