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/6be06b92f7563277_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 15d2a597-2a51-4a31-9e19-d9dbddc7d6c3
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 15d2a597-2a51-4a31-9e19-d9dbddc7d6c3
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 016417b1-8b1c-b5e3-255d-1696aa29db09
 
 This model is a fine-tuned version of [HuggingFaceH4/tiny-random-LlamaForCausalLM](https://huggingface.co/HuggingFaceH4/tiny-random-LlamaForCausalLM) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.3755
 
 ## 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        | 0.0018 | 1    | 10.3759         |
+| 10.3764       | 0.0178 | 10   | 10.3758         |
+| 10.3793       | 0.0355 | 20   | 10.3757         |
+| 10.3777       | 0.0533 | 30   | 10.3756         |
+| 10.3747       | 0.0710 | 40   | 10.3755         |
+| 10.3756       | 0.0888 | 50   | 10.3755         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b351cfaad46c28e4bd981e66a18ae1fbd6c55fd1393577b2ccea835e54922b1
+oid sha256:e6e7a9f3c3c4ae2b22243ee0cfa23fab2cea3df1f8a457d7299107e9d6a9fb37
 size 33666