End of training

README.md

@@ -66,7 +66,7 @@ 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/92268f6108266d1e_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 2a4738f3-e023-46f4-ae13-2b8b3faf7cb2
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 2a4738f3-e023-46f4-ae13-2b8b3faf7cb2
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # 98e699ff-d00b-4c34-9d1d-43b797cdd761
 
 This model is a fine-tuned version of [NousResearch/Nous-Hermes-llama-2-7b](https://huggingface.co/NousResearch/Nous-Hermes-llama-2-7b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0296
 
 ## 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        | 0.0000 | 1    | 1.2725          |
+| 0.974         | 0.0001 | 10   | 0.6204          |
+| 0.1754        | 0.0003 | 20   | 0.1039          |
+| 0.0608        | 0.0004 | 30   | 0.0486          |
+| 0.0349        | 0.0005 | 40   | 0.0312          |
+| 0.021         | 0.0006 | 50   | 0.0296          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3834a40ad8f6ca9959f3ebf1724b3ea7a4d112e6d5bc4e18d271f232c24a0e46
+oid sha256:516c5896304ae2971062d261a86202aa7323e71980f8baacac5bccce9176fa75
 size 604420306