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/3567063ba929a5dd_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 0cc723a6-75e2-4103-8856-b9d43674da4b
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 0cc723a6-75e2-4103-8856-b9d43674da4b
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 690f10e6-2724-9502-58d3-1c4204850d39
 
 This model is a fine-tuned version of [EleutherAI/pythia-14m](https://huggingface.co/EleutherAI/pythia-14m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 8.0317
 
 ## 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        | 0.0002 | 1    | 8.2057          |
+| 32.6925       | 0.0024 | 10   | 8.1445          |
+| 33.4936       | 0.0049 | 20   | 8.1650          |
+| 32.9059       | 0.0073 | 30   | 8.1076          |
+| 32.4159       | 0.0098 | 40   | 8.0495          |
+| 32.7971       | 0.0122 | 50   | 8.0317          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df10e2762df44a219007d2498425d2fc6c2c8af33b06c61b1b537314cd0d606a
+oid sha256:0a58d782563ec01ddf756d285473841d2eac6760d2c9858ace5bc8364db903e2
 size 410814