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/f4a6d2ad1888e73f_train_data.json
 model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: f4ceaa19-6420-4b44-a08d-f9e4b1bc8dc3
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: f4ceaa19-6420-4b44-a08d-f9e4b1bc8dc3
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -102,6 +102,8 @@ xformers_attention: null
 # e9b4e1e0-d991-870a-cf3d-efda9fc39bc4
 
 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: 1.2409
 
 ## 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    | 3.2407          |
+| 8.5732        | 0.0002 | 10   | 1.7817          |
+| 6.525         | 0.0003 | 20   | 1.3506          |
+| 5.2087        | 0.0005 | 30   | 1.2675          |
+| 5.3353        | 0.0007 | 40   | 1.2463          |
+| 4.389         | 0.0009 | 50   | 1.2409          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4952464d8e9b325a3c021a846bf2972996bf2700c9d83d28d1cf429c5c1a982
+oid sha256:ce6b0f310ef9f778088f53cd9dfe75ff1e1811e1d3e54d343aa964340b0dc28b
 size 84047370