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: 2
 mlflow_experiment_name: /tmp/ad34dd07d96016aa_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 76b2d76f-2806-4468-b061-b77a8dad386a
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 76b2d76f-2806-4468-b061-b77a8dad386a
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 76b2d76f-2806-4468-b061-b77a8dad386a
 
 This model is a fine-tuned version of [WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0](https://huggingface.co/WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0000
 
 ## Model description
 
@@ -127,14 +129,19 @@ 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        | 0.0006 | 1    | 7.9865          |
+| 5.4542        | 0.0056 | 10   | 1.5920          |
+| 0.0007        | 0.0112 | 20   | 0.0002          |
+| 0.0001        | 0.0168 | 30   | 0.0000          |
+| 0.0           | 0.0225 | 40   | 0.0000          |
+| 0.0           | 0.0281 | 50   | 0.0000          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c784786730ff54aebe3f2b52d5ba6b75d36c9512f2994914061b4b191829504f
+oid sha256:6a284694583d22645968dace66b149447482fcfd58933c6732e8ba1f6df90f8d
 size 84047370