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/966bdc90f4be6345_train_data.json
 model_type: AutoModelForCausalLM
@@ -93,7 +93,7 @@ wandb_name: 214230e6-06f7-4de5-b9f1-3472702b0972
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 214230e6-06f7-4de5-b9f1-3472702b0972
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -104,6 +104,8 @@ xformers_attention: null
 # eeb52018-b87d-3570-d255-3277215dd4ea
 
 This model is a fine-tuned version of [princeton-nlp/Sheared-LLaMA-1.3B](https://huggingface.co/princeton-nlp/Sheared-LLaMA-1.3B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9167
 
 ## 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        | 0.0009 | 1    | 4.6054          |
+| 4.2115        | 0.0087 | 10   | 4.2725          |
+| 3.1206        | 0.0174 | 20   | 2.4938          |
+| 1.4983        | 0.0260 | 30   | 1.2911          |
+| 1.0614        | 0.0347 | 40   | 0.9549          |
+| 0.9447        | 0.0434 | 50   | 0.9167          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceddfb85f1ac1d096c0ac5af548457e8fb346b2ab0fa8daa89b0f2eb28a8ff30
+oid sha256:03f392498468975e9e732290df15efc7b7b1bac21c0c1d215c8e8a2a754533d5
 size 30103498