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/e6a65369dcce024b_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 2c4b003d-1db2-4e2d-bd96-c12e7ade5571
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 2c4b003d-1db2-4e2d-bd96-c12e7ade5571
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 2b1d8ae7-b97a-9f46-10b2-c3de8f5a5766
 
 This model is a fine-tuned version of [EleutherAI/pythia-70m-deduped](https://huggingface.co/EleutherAI/pythia-70m-deduped) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 31.9889
 
 ## 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        | 0.0006 | 1    | 32.1880         |
+| 90.5781       | 0.0061 | 10   | 32.1777         |
+| 99.3049       | 0.0123 | 20   | 32.1142         |
+| 69.362        | 0.0184 | 30   | 32.0290         |
+| 177.8988      | 0.0246 | 40   | 32.0073         |
+| 61.2684       | 0.0307 | 50   | 31.9889         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:849b70f18e502a653f8d246c5e25f377fb8391bdc027540227e82f60ee530822
+oid sha256:92e1ef8f7576511031f6bdb0a61bc540c89b5afab5bece53d14666f6d453e9fe
 size 1590526