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/4fec60fc5473899b_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: e2f172c7-04e3-406a-a5ea-09244c681ba8
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: e2f172c7-04e3-406a-a5ea-09244c681ba8
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # f514421e-0db1-5f6f-fda0-fe16e4a0cdd3
 
 This model is a fine-tuned version of [HuggingFaceM4/tiny-random-LlamaForCausalLM](https://huggingface.co/HuggingFaceM4/tiny-random-LlamaForCausalLM) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.3731
 
 ## Model description
 
@@ -127,14 +129,19 @@ 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        | 0.0006 | 1    | 10.3757         |
+| 10.3748       | 0.0060 | 10   | 10.3752         |
+| 10.3752       | 0.0120 | 20   | 10.3742         |
+| 10.3708       | 0.0180 | 30   | 10.3735         |
+| 10.3768       | 0.0239 | 40   | 10.3732         |
+| 10.3763       | 0.0299 | 50   | 10.3731         |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50944ea077638d3e6df27b8452f501cea7ebc703389af2357740f9a1cec08011
+oid sha256:8f62ddde25b159ecd97934081ced1664a7a56f833075e6d03bf039e2488412ee
 size 33666