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/4731ee7238473373_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 152f3551-46bc-4bdb-a1dc-a104e3faed55
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 152f3551-46bc-4bdb-a1dc-a104e3faed55
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # ce8c1885-4011-1f8f-61d8-eb10d1daba72
 
 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: 2.0088
 
 ## 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        | 0.0004 | 1    | 2.8761          |
+| 2.8522        | 0.0040 | 10   | 2.6016          |
+| 2.2283        | 0.0080 | 20   | 2.1457          |
+| 2.0925        | 0.0120 | 30   | 2.0500          |
+| 2.0499        | 0.0160 | 40   | 2.0155          |
+| 1.8412        | 0.0200 | 50   | 2.0088          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5556e9c347d103611db6c458306499fb7f56bb91b291c4e8a2f0248aff0b548
+oid sha256:82bbff02db3bb8e1307ae5597c719a3c54d8e72bb450830eadd21c9bf4a609ee
 size 84047370