End of training

README.md

@@ -66,7 +66,7 @@ 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/6cc6f9326cecf8b6_train_data.json
 model_type: AutoModelForCausalLM
@@ -93,7 +93,7 @@ wandb_name: 77c42bed-f109-44c6-b611-738127e2b2cf
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 77c42bed-f109-44c6-b611-738127e2b2cf
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -104,6 +104,8 @@ xformers_attention: null
 # 1174091c-075f-4851-ba3b-99396508774b
 
 This model is a fine-tuned version of [defog/llama-3-sqlcoder-8b](https://huggingface.co/defog/llama-3-sqlcoder-8b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3084
 
 ## Model description
 
@@ -130,14 +132,19 @@ 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        | 0.0047 | 1    | 2.2309          |
+| 2.1443        | 0.0467 | 10   | 1.7167          |
+| 1.4648        | 0.0935 | 20   | 1.4118          |
+| 1.3751        | 0.1402 | 30   | 1.3372          |
+| 1.3886        | 0.1869 | 40   | 1.3127          |
+| 1.2881        | 0.2336 | 50   | 1.3084          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69f9caadf3099da1e6f16834fe05d2bbeb79c006f4dd744c0619a3198f1d3b40
+oid sha256:5f2d07aae57e632da5ab9e4cc6305b06aa74eaaf176a29a3441edd354de8a2c3
 size 84047370