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/2d626c804ac807b3_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 3f7fae45-8e9e-4c49-9035-f4c04b728391
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 3f7fae45-8e9e-4c49-9035-f4c04b728391
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 0197fc0e-b252-4f87-96dc-4758d0c583bc
 
 This model is a fine-tuned version of [EleutherAI/pythia-160m](https://huggingface.co/EleutherAI/pythia-160m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.6493
 
 ## 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        | 0.0005 | 1    | 2.7693          |
+| 10.8292       | 0.0051 | 10   | 2.7594          |
+| 10.0352       | 0.0102 | 20   | 2.7008          |
+| 10.5889       | 0.0153 | 30   | 2.6615          |
+| 11.203        | 0.0204 | 40   | 2.6495          |
+| 10.8377       | 0.0255 | 50   | 2.6493          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44717d7813f212f796a502a0d5f401951183abc10fe97dfe39285451e551d326
+oid sha256:99ffcd45463d55d486cab957be5657deb491657d44d6e6ea996d4ef2765942b2
 size 4753742