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/cd8300a39d314f50_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 3a53dabf-2bdc-4497-b566-05ac392755fb
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 3a53dabf-2bdc-4497-b566-05ac392755fb
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 3a53dabf-2bdc-4497-b566-05ac392755fb
 
 This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0285
 
 ## 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        | 0.0002 | 1    | 3.6128          |
+| 2.2671        | 0.0015 | 10   | 1.1116          |
+| 0.0869        | 0.0031 | 20   | 0.0367          |
+| 0.0451        | 0.0046 | 30   | 0.0277          |
+| 0.0491        | 0.0062 | 40   | 0.0287          |
+| 0.006         | 0.0077 | 50   | 0.0285          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea1c0e45c29da9b19d889a058f611a12e61df2c2193f4fe36a75c66877bcadcf
+oid sha256:861a12e6e2eaa69e659c776115cad9fcd88101d89a635571c7c78b12d3d791a9
 size 17717130