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/94593302be663a09_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: c830d1ff-264c-4167-aaf6-28e740f6a8a7
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: c830d1ff-264c-4167-aaf6-28e740f6a8a7
-warmup_steps: 1
+warmup_steps: 2
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # c830d1ff-264c-4167-aaf6-28e740f6a8a7
 
 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: 3.4329
 
 ## Model description
 
@@ -129,13 +131,17 @@ 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: 26
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0387 | 1    | 5.1285          |
+| No log        | 0.2324 | 6    | 3.9642          |
+| 4.3782        | 0.4649 | 12   | 3.5102          |
+| 4.3782        | 0.6973 | 18   | 3.4448          |
+| 3.4832        | 0.9298 | 24   | 3.4329          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:375586331be6710fc9614014519c1f276eb7498192e1d101714eefb31ca3fd28
+oid sha256:bd7ae5b69b797983de9d83f4c3856ee7c5238d0581a57764156d53ce35da0791
 size 22624970