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/845da76e906c6d62_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: b7ee0313-deac-490f-b006-8fa14a2b21c7
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: b7ee0313-deac-490f-b006-8fa14a2b21c7
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 7db3834b-154a-4a7c-b749-d77781577ad7
 
 This model is a fine-tuned version of [EleutherAI/pythia-410m-deduped](https://huggingface.co/EleutherAI/pythia-410m-deduped) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.6030
 
 ## 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        | 0.0024 | 1    | 2.7671          |
+| 10.8987       | 0.0238 | 10   | 2.7416          |
+| 11.9791       | 0.0476 | 20   | 2.6716          |
+| 11.0255       | 0.0713 | 30   | 2.6170          |
+| 10.6568       | 0.0951 | 40   | 2.6051          |
+| 10.5122       | 0.1189 | 50   | 2.6030          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aced0aae5e7f8242c13aa181aec4fa64492042a1de376d5d47038dc4b4c992eb
+oid sha256:c58a45a47e6047065eb29e0ea714a9a708864c15a52daf02cae65487c8048cf3
 size 12653258