End of training

README.md

@@ -64,7 +64,7 @@ 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/399c5cefebebad56_train_data.json
 model_type: AutoModelForCausalLM
@@ -89,7 +89,7 @@ wandb_name: 74f61bc0-0605-47f2-876c-212986e77e1b
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 74f61bc0-0605-47f2-876c-212986e77e1b
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -100,6 +100,8 @@ xformers_attention: null
 # 41fcc58f-6302-4221-a4ae-e57d9d0ac681
 
 This model is a fine-tuned version of [katuni4ka/tiny-random-qwen1.5-moe](https://huggingface.co/katuni4ka/tiny-random-qwen1.5-moe) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 11.9288
 
 ## Model description
 
@@ -126,14 +128,19 @@ 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        | 0.0000 | 1    | 11.9357         |
+| 11.937        | 0.0002 | 10   | 11.9346         |
+| 11.9376       | 0.0004 | 20   | 11.9320         |
+| 11.9352       | 0.0007 | 30   | 11.9300         |
+| 11.9269       | 0.0009 | 40   | 11.9290         |
+| 11.9283       | 0.0011 | 50   | 11.9288         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee203deb32d963c9c0bbb275ec54654861c5985752b2aa4086d534c0ca6a7857
+oid sha256:a09dd62febddbe1a839265f2cbc53016cc83dbbc1e0ef80d2c1bc0931ab34e18
 size 388266