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/f17b9c99d2469ad8_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 13200412-e203-4a13-aea6-a3b858f5012f
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 13200412-e203-4a13-aea6-a3b858f5012f
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 13200412-e203-4a13-aea6-a3b858f5012f
 
 This model is a fine-tuned version of [Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6180
 
 ## 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        | 0.0021 | 1    | 2.8871          |
+| 2.1603        | 0.0209 | 10   | 1.8464          |
+| 1.1089        | 0.0419 | 20   | 0.9094          |
+| 0.6956        | 0.0628 | 30   | 0.6962          |
+| 0.6945        | 0.0837 | 40   | 0.6293          |
+| 0.5781        | 0.1047 | 50   | 0.6180          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b264a92712bbb4d93a95664d6f37cf6fae11190a3f64e1e6e38acafa698da5e
+oid sha256:cf024948a8dbd6f2384526d1cfb45adbc89ddefe4b7fcb2769abaf4d2fb676bc
 size 17717130