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/fb9692b5081e57b9_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 9b6b6e4f-06a7-4051-b576-22dceb07eeda
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 9b6b6e4f-06a7-4051-b576-22dceb07eeda
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # b0694911-c7e0-ecd7-eb0f-f0239ae8863c
 
 This model is a fine-tuned version of [unsloth/OpenHermes-2.5-Mistral-7B](https://huggingface.co/unsloth/OpenHermes-2.5-Mistral-7B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3773
 
 ## 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        | 0.0012 | 1    | 1.6738          |
+| 7.1895        | 0.0117 | 10   | 1.5869          |
+| 6.3903        | 0.0234 | 20   | 1.4316          |
+| 4.8127        | 0.0351 | 30   | 1.3962          |
+| 4.6708        | 0.0468 | 40   | 1.3797          |
+| 6.0602        | 0.0585 | 50   | 1.3773          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8463c88682fb446e0964a4f4f4ce7c99b25a156250bd73b9077d76a63aae2ec8
+oid sha256:62b7409f3a0134fedc18d0e9ab0fc9908ac4adb16f0654f0f81fe25900f24017
 size 84047370