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: 50
+max_steps: 1
 micro_batch_size: 2
 mlflow_experiment_name: /tmp/b5c8353b6968e28c_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: f895e2f5-2320-4027-9ad8-b37a94c7e16c
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: f895e2f5-2320-4027-9ad8-b37a94c7e16c
-warmup_steps: 10
+warmup_steps: 1
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,8 +102,6 @@ xformers_attention: null
 # f895e2f5-2320-4027-9ad8-b37a94c7e16c
 
 This model is a fine-tuned version of [unsloth/llama-3-8b-Instruct](https://huggingface.co/unsloth/llama-3-8b-Instruct) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.2121
 
 ## Model description
 
@@ -130,19 +128,14 @@ 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        | 0.0003 | 1    | 2.8555          |
-| 2.375         | 0.0027 | 10   | 1.8616          |
-| 1.5496        | 0.0054 | 20   | 1.3208          |
-| 1.229         | 0.0082 | 30   | 1.2414          |
-| 1.2273        | 0.0109 | 40   | 1.2183          |
-| 1.3381        | 0.0136 | 50   | 1.2121          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48e2c4bfccead2859b1d4ff4782d223aaa3ad3acfe887bef4301a9e1d0c977f5
+oid sha256:31175f4210e98cf9715478d0ebe69a3f37349a9c24a6fbd7576d8aa703079443
 size 84047370