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/913d66d76e2da5a2_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 3b0b5630-a427-4ccb-b263-5b9ac72d9eec
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 3b0b5630-a427-4ccb-b263-5b9ac72d9eec
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # c080ef31-ae35-4eca-9dfd-b4fefb606e37
 
 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: 3.0605
 
 ## 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    | 4.0593          |
+| 16.0422       | 0.0046 | 10   | 3.8894          |
+| 13.0329       | 0.0093 | 20   | 3.4056          |
+| 12.3584       | 0.0139 | 30   | 3.1733          |
+| 11.8677       | 0.0186 | 40   | 3.0762          |
+| 12.4255       | 0.0232 | 50   | 3.0605          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6477cd70bc7db1de333ff79762f3d1a56f5a2d7600743058793cc4cad8185ff
+oid sha256:a80dc34eb3445b20a7a9a20862f42df7d5f8d3690d91ca1b613c3d8050bcfe46
 size 12653258