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/f22e1082b8aa906a_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 373d9fd5-8dde-42e7-93fc-a611d39cedd6
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 373d9fd5-8dde-42e7-93fc-a611d39cedd6
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 33674646-2ff3-47b2-998a-9f28b746d88b
 
 This model is a fine-tuned version of [unsloth/tinyllama-chat](https://huggingface.co/unsloth/tinyllama-chat) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0138
 
 ## Model description
 
@@ -127,14 +129,19 @@ 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        | 0.0011 | 1    | 0.3702          |
+| 0.32          | 0.0110 | 10   | 0.2777          |
+| 0.0933        | 0.0220 | 20   | 0.0845          |
+| 0.026         | 0.0330 | 30   | 0.0283          |
+| 0.0135        | 0.0440 | 40   | 0.0153          |
+| 0.0143        | 0.0550 | 50   | 0.0138          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b86d8300fb212c6b4a30395f9d085b052615009dadb0497db5fca5287d8ec63
+oid sha256:5b2d4de4ca36c1c99b3f2c47e8c0abf0f413b414423d12d2e56a1cd8da4e0a66
 size 25342042