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/504e27221bbf4070_train_data.json
 model_type: AutoModelForCausalLM
@@ -93,7 +93,7 @@ wandb_name: 9368a66a-7812-42d5-82b5-91eddf3aa1d4
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 9368a66a-7812-42d5-82b5-91eddf3aa1d4
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -104,6 +104,8 @@ xformers_attention: null
 # 9368a66a-7812-42d5-82b5-91eddf3aa1d4
 
 This model is a fine-tuned version of [NousResearch/Llama-3.2-1B](https://huggingface.co/NousResearch/Llama-3.2-1B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5864
 
 ## Model description
 
@@ -130,14 +132,19 @@ 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        | 0.0004 | 1    | 1.1109          |
+| 1.0706        | 0.0041 | 10   | 0.9898          |
+| 0.8083        | 0.0082 | 20   | 0.6619          |
+| 0.5869        | 0.0123 | 30   | 0.6100          |
+| 0.5129        | 0.0165 | 40   | 0.5895          |
+| 0.5675        | 0.0206 | 50   | 0.5864          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:062fe8e7b51c5e9d26a56d1b4043f4c166591d0d561ff26cc3c6836ead1f3e73
+oid sha256:71fba35b6d82f373ee745ba9ad4e602aa1720ff656a782c64e1d2a05de6e63a0
 size 22624970