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/16a0405078fa799f_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 79b30695-72c5-4c95-bd81-d061dc3bbdbb
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 79b30695-72c5-4c95-bd81-d061dc3bbdbb
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # e4b5996d-8b76-4d1d-beb8-ec81c40b9c44
 
 This model is a fine-tuned version of [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9545
 
 ## 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        | 0.0102 | 1    | 2.4833          |
+| 10.4859       | 0.1023 | 10   | 2.1628          |
+| 7.717         | 0.2046 | 20   | 1.9835          |
+| 7.2391        | 0.3069 | 30   | 1.9637          |
+| 7.9696        | 0.4092 | 40   | 1.9575          |
+| 8.4033        | 0.5115 | 50   | 1.9545          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e10ec3ab3dd8091f855e6898243c4c550578ad3059b17172a21f08a68c24ad6a
+oid sha256:867ca7f1646007e8797f496b31cc2691c80ab68eeb94a521f0e6a6ce974a6dc2
 size 84047370