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/04dfac836ec8ed66_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 49d5fde3-ac13-43ce-8d8e-1f2324cdd828
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 49d5fde3-ac13-43ce-8d8e-1f2324cdd828
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 49d5fde3-ac13-43ce-8d8e-1f2324cdd828
 
 This model is a fine-tuned version of [unsloth/mistral-7b-v0.2](https://huggingface.co/unsloth/mistral-7b-v0.2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.0454
 
 ## 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    | 2.1065          |
+| 8.3854        | 0.0054 | 10   | 2.0522          |
+| 8.5592        | 0.0108 | 20   | 2.0520          |
+| 8.2269        | 0.0162 | 30   | 2.0463          |
+| 8.3231        | 0.0216 | 40   | 2.0456          |
+| 7.8415        | 0.0270 | 50   | 2.0454          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6618dd79de109f18e0ae9515c668a79c14552d8c9ff10bc2ce02ebea942a7bd
+oid sha256:3904df70be4a35127ea079785f4aa179343dc83742a8e6f7e5c1112e73fc49c7
 size 84047370