End of training

README.md

@@ -65,7 +65,7 @@ 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/f461ede2309681d4_train_data.json
 model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: bbe2a0a8-92a8-4fff-82a8-d820a72cf14a
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: bbe2a0a8-92a8-4fff-82a8-d820a72cf14a
-warmup_steps: 1
+warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
 
@@ -101,6 +101,8 @@ xformers_attention: null
 # bbe2a0a8-92a8-4fff-82a8-d820a72cf14a
 
 This model is a fine-tuned version of [NousResearch/Nous-Hermes-2-Mistral-7B-DPO](https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4523
 
 ## Model description
 
@@ -127,14 +129,19 @@ 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    | 0.6611          |
+| 2.2083        | 0.0004 | 10   | 0.5365          |
+| 2.1696        | 0.0009 | 20   | 0.4852          |
+| 1.6832        | 0.0013 | 30   | 0.4635          |
+| 1.635         | 0.0017 | 40   | 0.4546          |
+| 1.8696        | 0.0022 | 50   | 0.4523          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca95065e7b4e43df369bfc8b7d1a24609748b4445f8551bc3f61521a15a222ed
+oid sha256:ef07e66c3541f87771252b24fd25e649544078c65953cfe761d539ba3771fdc6
 size 84047370