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/a5407832a8eeac90_train_data.json
 model_type: AutoModelForCausalLM
@@ -89,7 +89,7 @@ wandb_name: 07dd380d-73b3-4f62-8ce2-44e45dfdb86e
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 07dd380d-73b3-4f62-8ce2-44e45dfdb86e
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -100,6 +100,8 @@ xformers_attention: null
 # 5e5fe4f0-e7cc-4315-9d2e-b93e4e007627
 
 This model is a fine-tuned version of [MNC-Jihun/Mistral-7B-AO-u0.5-b2-ver0.4](https://huggingface.co/MNC-Jihun/Mistral-7B-AO-u0.5-b2-ver0.4) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4067
 
 ## 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        | 0.0019 | 1    | 1.2798          |
+| No log        | 0.0019 | 1    | 1.2105          |
+| 0.7615        | 0.0194 | 10   | 0.5700          |
+| 0.4985        | 0.0389 | 20   | 0.4624          |
+| 0.4715        | 0.0583 | 30   | 0.4250          |
+| 0.4922        | 0.0777 | 40   | 0.4096          |
+| 0.3709        | 0.0972 | 50   | 0.4067          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79eaa2cced54ce847349774e38b51000d8ed10a3a1eda52310a7ef9b7a064ec4
+oid sha256:b559910e11e76fe88d70929240dc82b11a8cbbfc84d78cfd2f50eae79e80e057
 size 608352466