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/5c699451d3dc0028_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 4fd7ad13-9b31-4f42-9994-6d2cc4618ed6
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 4fd7ad13-9b31-4f42-9994-6d2cc4618ed6
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 8c1f3292-1794-6e6c-7890-503da1c075b9
 
 This model is a fine-tuned version of [Orenguteng/Llama-3-8B-Lexi-Uncensored](https://huggingface.co/Orenguteng/Llama-3-8B-Lexi-Uncensored) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3589
 
 ## 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        | 0.0001 | 1    | 3.0385          |
+| 2.8694        | 0.0011 | 10   | 2.8424          |
+| 2.4734        | 0.0021 | 20   | 2.4983          |
+| 2.2886        | 0.0032 | 30   | 2.3911          |
+| 2.4348        | 0.0043 | 40   | 2.3635          |
+| 2.2616        | 0.0053 | 50   | 2.3589          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c5eadfbb2387893b7471bf6d4d45a8300557e8923f2db39323cae4bf0bb9e28
+oid sha256:59fe7e6ddae925b414ea72b143ad367691c034ff7d5efe49b958c1bbec7e77bd
 size 84047370