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: 8
 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: 2
 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: 0.5393
 
 ## Model description
 
@@ -129,13 +131,18 @@ The following hyperparameters were used during training:
 - 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
+- training_steps: 50
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0004 | 1    | 0.6636          |
+| 0.624         | 0.0044 | 10   | 0.6004          |
+| 0.5552        | 0.0088 | 20   | 0.5617          |
+| 0.5578        | 0.0132 | 30   | 0.5464          |
+| 0.5646        | 0.0176 | 40   | 0.5403          |
+| 0.5642        | 0.0220 | 50   | 0.5393          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40dd96f23c54bf3c5de83a6b32b90f7ae701f1672fc8788c84cf5bd568be6d38
+oid sha256:4775198ea4d88e8ccd5347bee1f3398b8276023b87c9317f1971f2357e2781dc
 size 15259594