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/160c5b3bb9da3f56_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 85127c1a-1e48-44f0-9d81-717f87454d94
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 85127c1a-1e48-44f0-9d81-717f87454d94
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 85127c1a-1e48-44f0-9d81-717f87454d94
 
 This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
 
 ## 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        | 0.0003 | 1    | nan             |
+| 2.8666        | 0.0031 | 10   | nan             |
+| 2.656         | 0.0062 | 20   | nan             |
+| 2.7902        | 0.0094 | 30   | nan             |
+| 2.6246        | 0.0125 | 40   | nan             |
+| 2.599         | 0.0156 | 50   | nan             |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d06c06239327a1bd5fb37286410a30cb6dd97bc3d06911ce8660f072372cb13a
+oid sha256:9a568a197b615ba838ae05a55163033012e6b03fa5e9b86cd946593d6eb2e7bc
 size 60048618