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/442a867e844a727b_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 787423bb-04b6-43e5-9d31-8e1dd89bc318
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 787423bb-04b6-43e5-9d31-8e1dd89bc318
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 787423bb-04b6-43e5-9d31-8e1dd89bc318
 
 This model is a fine-tuned version of [NousResearch/Hermes-2-Theta-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3213
 
 ## 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        | 0.0005 | 1    | 0.4410          |
+| 0.4523        | 0.0045 | 10   | 0.4033          |
+| 0.3542        | 0.0091 | 20   | 0.3478          |
+| 0.3843        | 0.0136 | 30   | 0.3298          |
+| 0.2884        | 0.0181 | 40   | 0.3227          |
+| 0.3536        | 0.0226 | 50   | 0.3213          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:256a1956e90980b26deb535ff898e8ec2bd7c684252f7efa4bedab89d04cbe57
+oid sha256:450f7b405e4757e2663a44f00994dd85318dc4644b532ed083d4a59b2cdcd33b
 size 2185410770