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: 1
+max_steps: 50
 micro_batch_size: 2
 mlflow_experiment_name: /tmp/9febd1eb0ee4f252_train_data.json
 model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: e1cd3927-e895-45b6-b0fe-55cc5b30bcf4
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: e1cd3927-e895-45b6-b0fe-55cc5b30bcf4
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -103,6 +103,8 @@ xformers_attention: null
 # 813a93f7-01ef-1726-4dd5-160912821617
 
 This model is a fine-tuned version of [TitanML/tiny-mixtral](https://huggingface.co/TitanML/tiny-mixtral) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
 
 ## Model description
 
@@ -129,14 +131,19 @@ 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        | 0.0001 | 1    | nan             |
+| 0.0           | 0.0006 | 10   | nan             |
+| 0.0           | 0.0012 | 20   | nan             |
+| 0.0           | 0.0018 | 30   | nan             |
+| 0.0           | 0.0023 | 40   | nan             |
+| 0.0           | 0.0029 | 50   | nan             |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:724b27bacc1488b05e4c15821b0d5291c2af858c55a13ce93a2e2aa80680a974
+oid sha256:f96ae55992959eaa6f8438672b8da46a85074d2dc16cf93f26933d01a5ad1328
 size 7613018