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/7cecb5f0cbdfe3e6_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 9c40171a-a397-4067-8fba-d0d97f9c3fb5
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 9c40171a-a397-4067-8fba-d0d97f9c3fb5
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # d1c8e05a-bc03-c6ca-5c8d-0b7b025a0462
 
 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: 8.1050
 
 ## 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        | 0.0003 | 1    | 8.7375          |
+| 32.7749       | 0.0026 | 10   | 8.6132          |
+| 34.1939       | 0.0052 | 20   | 8.3340          |
+| 33.0339       | 0.0078 | 30   | 8.1862          |
+| 31.6229       | 0.0104 | 40   | 8.1304          |
+| 34.0631       | 0.0130 | 50   | 8.1050          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb47e48d8068a70345b5edff8b5e58b84668e713c68a996a1c2785f0db0ebcac
+oid sha256:f04213f7fdfd9d7646783f6a8b54df9680b0297f22e1ba7385d1f843e279057b
 size 410814