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: 8
 mlflow_experiment_name: /tmp/687a77ce1ea5d175_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 8d6a504c-dab1-47cf-acf5-1dc70043d3e8
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 8d6a504c-dab1-47cf-acf5-1dc70043d3e8
-warmup_steps: 1
+warmup_steps: 2
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 8d6a504c-dab1-47cf-acf5-1dc70043d3e8
 
 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: 1.9692
 
 ## Model description
 
@@ -128,13 +130,18 @@ 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        | 0.0064 | 1    | 2.0857          |
+| 2.0586        | 0.0643 | 10   | 2.0195          |
+| 2.0029        | 0.1286 | 20   | 1.9853          |
+| 1.9785        | 0.1928 | 30   | 1.9740          |
+| 1.982         | 0.2571 | 40   | 1.9699          |
+| 1.9708        | 0.3214 | 50   | 1.9692          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aacae1205e9aa7b42dafe01e305c0aede2960e083035e560430702386e259b81
+oid sha256:0bd53a46135c25a108b26ab8ebf3e6a1bcadc63bb9974e5278988d4a4b12d8a0
 size 48768810