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/2f22bb3438fdbdeb_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: be31c0da-9110-4803-817b-2f1d224c3c6a
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: be31c0da-9110-4803-817b-2f1d224c3c6a
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 06803311-cf1f-45c7-a718-f07de1e3a8c2
 
 This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1852
 
 ## 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        | 0.0000 | 1    | 1.3629          |
+| 1.2357        | 0.0003 | 10   | 1.3429          |
+| 1.0984        | 0.0005 | 20   | 1.2607          |
+| 1.298         | 0.0008 | 30   | 1.2117          |
+| 1.0883        | 0.0011 | 40   | 1.1899          |
+| 0.9861        | 0.0013 | 50   | 1.1852          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30ede2d7e1758c1699ba82aa45b6999595f9967ebd7540dc0f1669a75bfe82ff
+oid sha256:86680d9dc9a3f9e258c9382e54ce183be3b6bc230e24d33823eae473daa88ba5
 size 37070634