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/491eb6180bd3250d_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 864df0c2-2256-42be-8235-9eb5833d2b38
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 864df0c2-2256-42be-8235-9eb5833d2b38
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 672237e8-1b4d-2cb9-90ab-f7e0a918ddb2
 
 This model is a fine-tuned version of [TinyLlama/TinyLlama_v1.1](https://huggingface.co/TinyLlama/TinyLlama_v1.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2752
 
 ## 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        | 0.0001 | 1    | 2.4143          |
+| 2.2122        | 0.0008 | 10   | 1.9637          |
+| 1.4912        | 0.0016 | 20   | 1.4250          |
+| 1.3262        | 0.0025 | 30   | 1.3036          |
+| 1.3893        | 0.0033 | 40   | 1.2781          |
+| 1.2622        | 0.0041 | 50   | 1.2752          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:945855266b53063f1cfe34152eaf7fc82972dba02b9801d736572445234a0b4c
+oid sha256:9ca333f13b0ae3bf5f0343c2571e33b825ca1a208d0b8b38f41854ef7d14a218
 size 25342042