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/4d27e267748a2b05_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 2853d9d4-58cc-4997-925a-bcabe0ef24e5
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 2853d9d4-58cc-4997-925a-bcabe0ef24e5
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 2853d9d4-58cc-4997-925a-bcabe0ef24e5
 
 This model is a fine-tuned version of [Qwen/Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3454
 
 ## 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        | 0.0008 | 1    | 1.1866          |
+| 1.1565        | 0.0084 | 10   | 1.0025          |
+| 0.6001        | 0.0167 | 20   | 0.5902          |
+| 0.4266        | 0.0251 | 30   | 0.4351          |
+| 0.3659        | 0.0334 | 40   | 0.3580          |
+| 0.2976        | 0.0418 | 50   | 0.3454          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52d60e40531aed980b9c2fde4a6b16b42cf141490104ca35813cb59be0918cf
+oid sha256:93a94dc822db3073db0abb96e22ed854ee167114bcdcebd21483825ba472f95e
 size 37070634