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/bbf625be58a9c576_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 1ea8bc4a-3006-4988-b59e-62f215db29ec
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 1ea8bc4a-3006-4988-b59e-62f215db29ec
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # 7bb5f7ff-f5dc-eada-d75a-131e2b3e4442
 
 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: 1.5843
 
 ## 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        | 0.0003 | 1    | 1.8005          |
+| 1.8272        | 0.0029 | 10   | 1.7177          |
+| 1.6475        | 0.0059 | 20   | 1.6255          |
+| 1.7524        | 0.0088 | 30   | 1.5965          |
+| 1.7754        | 0.0117 | 40   | 1.5862          |
+| 1.5911        | 0.0147 | 50   | 1.5843          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f36d363252ece9e92efba1783f76b1a38b5bacfec7f87d1963cc24e1dcf2053
+oid sha256:b5a0cca03ddc225996adb53d92e79d2411eb03630a60e69825c72b72a79b62c4
 size 15259594