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/98ad102b26632cfc_train_data.json
 model_type: AutoModelForCausalLM
@@ -93,7 +93,7 @@ wandb_name: f3ad04ec-e30b-4986-9e6c-f98c9985074e
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: f3ad04ec-e30b-4986-9e6c-f98c9985074e
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -104,6 +104,8 @@ xformers_attention: null
 # 1449cf14-9987-44dd-90fb-60ad276f13dd
 
 This model is a fine-tuned version of [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5186
 
 ## Model description
 
@@ -130,14 +132,19 @@ 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    | 1.8247          |
+| 8.0232        | 0.0057 | 10   | 1.6559          |
+| 5.9149        | 0.0114 | 20   | 1.5645          |
+| 6.2795        | 0.0171 | 30   | 1.5392          |
+| 6.4154        | 0.0227 | 40   | 1.5208          |
+| 5.6759        | 0.0284 | 50   | 1.5186          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:159dcde3a69d81775730b9d41bfbbca0a5a6ce5b485824aef213c56483ab1482
+oid sha256:458f67d427456dd2dec2b422b5098df77e47d3df62340898eee000a002de0948
 size 84047370