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/a1e5e079b3bd8977_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 5ee1387e-ec6a-44cd-b489-4ec211ccdb84
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 5ee1387e-ec6a-44cd-b489-4ec211ccdb84
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 1c3f6928-def4-4afe-bf6f-825cd501eee8
 
 This model is a fine-tuned version of [unsloth/Llama-3.2-1B-Instruct](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4864
 
 ## Model description
 
@@ -128,14 +130,19 @@ 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        | 0.0002 | 1    | 2.8236          |
+| 3.0223        | 0.0016 | 10   | 2.7644          |
+| 2.5211        | 0.0033 | 20   | 2.6194          |
+| 2.4308        | 0.0049 | 30   | 2.5328          |
+| 2.6782        | 0.0065 | 40   | 2.4936          |
+| 2.2843        | 0.0081 | 50   | 2.4864          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a0310de1eb265e8a22e841e2b8140875d018932a41bb223ed00a8627bd264d9
+oid sha256:4a5bbe1e8237126c86646b496f53f9920906feeeab5fec9c9e049eca49ec45c6
 size 22624970