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/2d15b3651d2b81fd_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: d86c16ef-47f4-473a-825c-80ba0605c24d
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: d86c16ef-47f4-473a-825c-80ba0605c24d
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # e468ec6d-4fa6-44c9-924e-b5eab8c90782
 
 This model is a fine-tuned version of [JackFram/llama-160m](https://huggingface.co/JackFram/llama-160m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1122
 
 ## Model description
 
@@ -129,14 +131,19 @@ 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        | 0.0010 | 1    | 2.4224          |
+| 2.3545        | 0.0098 | 10   | 2.3995          |
+| 2.279         | 0.0196 | 20   | 2.2604          |
+| 2.1387        | 0.0294 | 30   | 2.1607          |
+| 2.0022        | 0.0392 | 40   | 2.1191          |
+| 2.0359        | 0.0490 | 50   | 2.1122          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d32f099a4c3162e545a4db788e7937513136a1e1173909a79d8a9e4a3fd85e6b
+oid sha256:8932b54dc8a400536514b54b5a9a396c8be965e592c7768555b4b1659ec7032e
 size 6843306