End of training

README.md

@@ -59,7 +59,7 @@ 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/991a5bef5482548f_train_data.json
 model_type: AutoModelForCausalLM
@@ -84,7 +84,7 @@ wandb_name: fd0aafb2-9859-480a-9aef-275faa1d7606
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: fd0aafb2-9859-480a-9aef-275faa1d7606
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -95,6 +95,8 @@ xformers_attention: null
 # fd0aafb2-9859-480a-9aef-275faa1d7606
 
 This model is a fine-tuned version of [unsloth/Llama-3.2-1B](https://huggingface.co/unsloth/Llama-3.2-1B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.6921
 
 ## Model description
 
@@ -121,14 +123,19 @@ 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        | 0.0159 | 1    | 5.2127          |
+| 4.8016        | 0.1587 | 10   | 4.4414          |
+| 3.1812        | 0.3175 | 20   | 3.0649          |
+| 2.7696        | 0.4762 | 30   | 2.7780          |
+| 2.9717        | 0.6349 | 40   | 2.7027          |
+| 2.6594        | 0.7937 | 50   | 2.6921          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15fa7c001b40a9437c7e86cb835815273736f9699f125650b59f7093a839809a
+oid sha256:3cb36713ba77d704621fe109f9b584d29fe750e33c34dce18a3836bbf19f37f2
 size 22624970