End of training

README.md

@@ -66,7 +66,7 @@ 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/1c7fc53de50cfd31_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: f3704ac9-c6c8-489c-8d01-5ec2260b5ba8
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: f3704ac9-c6c8-489c-8d01-5ec2260b5ba8
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # f3704ac9-c6c8-489c-8d01-5ec2260b5ba8
 
 This model is a fine-tuned version of [Qwen/Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5771
 
 ## Model description
 
@@ -128,14 +130,19 @@ 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    | 0.6830          |
+| 0.8265        | 0.0003 | 10   | 0.6560          |
+| 0.4969        | 0.0006 | 20   | 0.6123          |
+| 0.3423        | 0.0008 | 30   | 0.5870          |
+| 0.5267        | 0.0011 | 40   | 0.5785          |
+| 0.7067        | 0.0014 | 50   | 0.5771          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e23dc15bcd3283594b798dc3df02495e8b2649b334c4b30ed893560d75f9c3a
+oid sha256:f4eed41c4e15c3257bb993fba23de601f109f3da31fe0fc9449bfa26ca3701af
 size 15259594