End of training

README.md

@@ -65,7 +65,7 @@ lora_model_dir: null
 lora_r: 8
 lora_target_linear: true
 lr_scheduler: cosine
-max_steps: 50
+max_steps: 1
 micro_batch_size: 2
 mlflow_experiment_name: /tmp/2b4c906f227e7666_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 3de14208-1aee-45bc-a53c-1384721f8959
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 3de14208-1aee-45bc-a53c-1384721f8959
-warmup_steps: 10
+warmup_steps: 1
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,8 +101,6 @@ xformers_attention: null
 # 3de14208-1aee-45bc-a53c-1384721f8959
 
 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: 11.9272
 
 ## Model description
 
@@ -129,19 +127,14 @@ 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: 10
-- training_steps: 50
+- lr_scheduler_warmup_steps: 2
+- training_steps: 1
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | No log        | 0.0003 | 1    | 11.9349         |
-| 11.9407       | 0.0025 | 10   | 11.9336         |
-| 11.9298       | 0.0050 | 20   | 11.9308         |
-| 11.93         | 0.0075 | 30   | 11.9286         |
-| 11.9298       | 0.0100 | 40   | 11.9274         |
-| 11.9325       | 0.0126 | 50   | 11.9272         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03302a5646a2dadf9d43f77377125a2c574d383ed9291e654fe26173f648ffa6
+oid sha256:2c5fc7a624fba0905bb3e0272486606f1d7e4242beea3be05ddef373ca5e0709
 size 388266