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/208c1aca67b9bb7f_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 3c8edeb5-98f6-4e93-9f2b-1968528b31e5
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 3c8edeb5-98f6-4e93-9f2b-1968528b31e5
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # a2163ecd-f3d2-4bcf-8f0c-6d3249579be6
 
 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: 2.7401
 
 ## 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        | 0.0012 | 1    | 5.3598          |
+| 4.5362        | 0.0116 | 10   | 4.5208          |
+| 3.0813        | 0.0231 | 20   | 3.1731          |
+| 2.6833        | 0.0347 | 30   | 2.8336          |
+| 2.965         | 0.0462 | 40   | 2.7535          |
+| 2.5344        | 0.0578 | 50   | 2.7401          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eaeb4f366fe34f98a37443269996fb6eed36466785d53505b8b3f3918ca8130
+oid sha256:1b4084c81f14a837198bd40dc918075d7a50e8e3bd9a5d8d75c08d26712c9892
 size 17717130