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: 50
+max_steps: 1
 micro_batch_size: 2
 mlflow_experiment_name: /tmp/b47488a7a22090e4_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: a7b71eb1-db0f-4c12-ae7f-75544046c341
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: a7b71eb1-db0f-4c12-ae7f-75544046c341
-warmup_steps: 10
+warmup_steps: 1
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,8 +101,6 @@ xformers_attention: null
 # a7b71eb1-db0f-4c12-ae7f-75544046c341
 
 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: 1.4953
 
 ## Model description
 
@@ -129,19 +127,14 @@ 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: 10
-- training_steps: 50
+- lr_scheduler_warmup_steps: 2
+- training_steps: 1
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0000 | 1    | 10.8752         |
-| 10.519        | 0.0002 | 10   | 8.1257          |
-| 2.4823        | 0.0004 | 20   | 2.3625          |
-| 1.6263        | 0.0005 | 30   | 1.7216          |
-| 1.4555        | 0.0007 | 40   | 1.5186          |
-| 1.3808        | 0.0009 | 50   | 1.4953          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd071ea41ae0b7ecaa841d3bc75be3f81e0b9e49f7fca0e182936e3405c27572
+oid sha256:065e7238605fe952d864aded238815001e9dccd345eafbec4b433e4107fecf67
 size 84047370