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/4ea7d2d1bce2cfcf_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: c7bea8f5-220f-4253-8901-ac848f2eaae6
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: c7bea8f5-220f-4253-8901-ac848f2eaae6
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 231f9b7c-b0a3-417f-ad97-52b1ac45ca5c
 
 This model is a fine-tuned version of [unsloth/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1661
 
 ## 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        | 0.0091 | 1    | 1.9844          |
+| 1.9062        | 0.0913 | 10   | 1.8148          |
+| 1.3004        | 0.1826 | 20   | 1.2232          |
+| 1.1432        | 0.2740 | 30   | 1.1795          |
+| 1.1629        | 0.3653 | 40   | 1.1687          |
+| 1.1337        | 0.4566 | 50   | 1.1661          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35563f6aec05573b4a4f38519ee8d24283e66b0bd8acb83241b5113204507a7f
+oid sha256:8a005ac838345f39c6df297c7c866cf62feb00d855fb7038de616012b12a4763
 size 84047370