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/a44d0ac019ab8b7b_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: b9da510d-804d-4004-9468-1e64f1a042ca
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: b9da510d-804d-4004-9468-1e64f1a042ca
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 35fb982d-4316-c07a-9535-ebacc5c1e3a8
 
 This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3825
 
 ## 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    | 2.6746          |
+| 2.3742        | 0.0011 | 10   | 2.4438          |
+| 1.9089        | 0.0023 | 20   | 1.7018          |
+| 1.3787        | 0.0034 | 30   | 1.4157          |
+| 1.2986        | 0.0045 | 40   | 1.3863          |
+| 1.3774        | 0.0057 | 50   | 1.3825          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b01f4572717965860f8310112e8338a6edde92dc1e858dea51f465b05df8cc46
+oid sha256:dcf0ce3a9d8d965c344bfcebf429ba7676c9a2ce22538dc10b3f128258de1023
 size 80881450