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/63a6e52889f0869c_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 95d283ba-c7ba-4e03-aefa-9110a8ae8a1d
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: 95d283ba-c7ba-4e03-aefa-9110a8ae8a1d
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # fa71addc-951a-12d7-783c-32157f080bb4
 
 This model is a fine-tuned version of [NousResearch/Hermes-2-Pro-Mistral-7B](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9126
 
 ## 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        | 0.0002 | 1    | 1.8958          |
+| 6.12          | 0.0023 | 10   | 1.4180          |
+| 3.7388        | 0.0046 | 20   | 0.9980          |
+| 4.2057        | 0.0069 | 30   | 0.9261          |
+| 3.9987        | 0.0093 | 40   | 0.9167          |
+| 3.8477        | 0.0116 | 50   | 0.9126          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93f121644bcff31d981ebf775db003e3846dc2cc24d26a47c27dec42a95cadb5
+oid sha256:79eba3af2ca299e7cd461f5ebfbc96a3546586f00d2872ce11435bc97d13d5ba
 size 84047370