End of training

README.md

@@ -67,7 +67,7 @@ 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/6762a29079456d54_train_data.json
 model_type: AutoModelForCausalLM
@@ -94,7 +94,7 @@ wandb_name: 0efc8bbc-a4f8-4174-9259-fb8deea45d82
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 0efc8bbc-a4f8-4174-9259-fb8deea45d82
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -105,6 +105,8 @@ xformers_attention: null
 # 057bf965-7329-3677-2741-87cea35933d5
 
 This model is a fine-tuned version of [Maykeye/TinyLLama-v0](https://huggingface.co/Maykeye/TinyLLama-v0) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.4571
 
 ## Model description
 
@@ -131,14 +133,19 @@ 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        | 0.0000 | 1    | 11.9109         |
+| 11.8222       | 0.0003 | 10   | 11.6836         |
+| 11.3059       | 0.0005 | 20   | 11.1100         |
+| 10.8036       | 0.0008 | 30   | 10.6879         |
+| 10.543        | 0.0010 | 40   | 10.4965         |
+| 10.4447       | 0.0013 | 50   | 10.4571         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2624420ca87ea5c60233085616f83e439ed8a2db4fc24f841f67b13609530952
+oid sha256:038c8c0b855a091e493a64b5a8227f7d99364157ab75935f2faaea310efa3ded
 size 416906