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/be96976f5e201469_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 5a39e1e4-afbc-4ab4-81df-a2f958fdb157
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 5a39e1e4-afbc-4ab4-81df-a2f958fdb157
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 7aee20d9-224a-ca7f-46b4-216ba1d80e53
 
 This model is a fine-tuned version of [fxmarty/tiny-llama-fast-tokenizer](https://huggingface.co/fxmarty/tiny-llama-fast-tokenizer) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.3700
 
 ## 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        | 0.0009 | 1    | 10.3730         |
+| 10.372        | 0.0089 | 10   | 10.3724         |
+| 10.3715       | 0.0177 | 20   | 10.3714         |
+| 10.3726       | 0.0266 | 30   | 10.3705         |
+| 10.3674       | 0.0355 | 40   | 10.3701         |
+| 10.3706       | 0.0444 | 50   | 10.3700         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e0bd2419bbd83101fff735197586be399eff44b1be4331957677d7b54953aec
+oid sha256:ab0118b4346fd8aed61554ae69874174a271b8028d055ffdbfe2f10d860363be
 size 33666