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/e379af78ad5f53fa_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 0017f0db-d7f8-4f78-9dd4-effb388c566e
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 0017f0db-d7f8-4f78-9dd4-effb388c566e
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # d12746ae-07a5-49cd-ae67-a9bc9542e067
 
 This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.3084
 
 ## 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        | 0.0013 | 1    | 4.5436          |
+| 4.4082        | 0.0127 | 10   | 4.4372          |
+| 4.0977        | 0.0255 | 20   | 3.9135          |
+| 3.4916        | 0.0382 | 30   | 3.4910          |
+| 3.204         | 0.0510 | 40   | 3.3309          |
+| 3.3705        | 0.0637 | 50   | 3.3084          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:109fca6d8d34fa8b526e44bea9b7101c8bfc2331d146b7ff867bf9812e42a6a9
+oid sha256:6cc4eef28ee42ba00b0f2590cf284b875bd07861b1a37d7f0b5ad856d992f133
 size 80881450