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/f51e7a970d51d9ac_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 4a2674be-6dd3-455e-a834-dc90aa13ec3f
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 4a2674be-6dd3-455e-a834-dc90aa13ec3f
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 767404e7-6d28-2259-3f28-6c282c503e99
 
 This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3627
 
 ## 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        | 0.0001 | 1    | 3.2041          |
+| 3.1394        | 0.0005 | 10   | 2.8643          |
+| 2.5685        | 0.0010 | 20   | 2.4446          |
+| 2.2897        | 0.0015 | 30   | 2.3796          |
+| 2.3362        | 0.0020 | 40   | 2.3648          |
+| 2.616         | 0.0025 | 50   | 2.3627          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f235d54834bb63ff1e5afc5d6b706a72773b6bc1cde56f82f58a86e72522ba9
+oid sha256:01aeb5de604431dfde0b815c6958fe38f9c1befefe1357c60d857e2d45240f91
 size 17717130