End of training

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: peft
-license: apache-2.0
-base_model: unsloth/mistral-7b-instruct-v0.3
+license: mit
+base_model: NousResearch/Nous-Hermes-llama-2-7b
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Paladiso/dataset_41b65960-526f-4a18-944a-fbc29b953bea
+- Paladiso/dataset_2a4738f3-e023-46f4-ae13-2b8b3faf7cb2
 model-index:
-- name: d3b2eda8-2f5d-4cb8-b693-96f3cf78854e
+- name: 721c72a9-ea56-4aa8-a850-589c974f12f1
   results: []
 ---
 
@@ -21,18 +21,18 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: unsloth/mistral-7b-instruct-v0.3
+base_model: NousResearch/Nous-Hermes-llama-2-7b
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Paladiso/dataset_41b65960-526f-4a18-944a-fbc29b953bea
+  path: Paladiso/dataset_2a4738f3-e023-46f4-ae13-2b8b3faf7cb2
   type:
-    field_input: AZ_labels
+    field_input: title
     field_instruction: category
-    field_output: sentence
+    field_output: title_category
     system_format: '{system}'
     system_prompt: ''
 debug: null
@@ -48,7 +48,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Paladiso/d3b2eda8-2f5d-4cb8-b693-96f3cf78854e
+hub_model_id: Paladiso/721c72a9-ea56-4aa8-a850-589c974f12f1
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -88,10 +88,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: 41b65960-526f-4a18-944a-fbc29b953bea
+wandb_name: 2a4738f3-e023-46f4-ae13-2b8b3faf7cb2
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 41b65960-526f-4a18-944a-fbc29b953bea
+wandb_runid: 2a4738f3-e023-46f4-ae13-2b8b3faf7cb2
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -100,11 +100,11 @@ xformers_attention: null
 
 </details><br>
 
-# d3b2eda8-2f5d-4cb8-b693-96f3cf78854e
+# 721c72a9-ea56-4aa8-a850-589c974f12f1
 
-This model is a fine-tuned version of [unsloth/mistral-7b-instruct-v0.3](https://huggingface.co/unsloth/mistral-7b-instruct-v0.3) on the Paladiso/dataset_41b65960-526f-4a18-944a-fbc29b953bea dataset.
+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 Paladiso/dataset_2a4738f3-e023-46f4-ae13-2b8b3faf7cb2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6563
+- Loss: 0.4927
 
 ## Model description
 
@@ -138,9 +138,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 13.7058       | 0.0025 | 3    | 3.3732          |
-| 13.0947       | 0.0050 | 6    | 2.9486          |
-| 10.4735       | 0.0075 | 9    | 2.6563          |
+| 1.5296        | 0.0000 | 3    | 1.4517          |
+| 1.3861        | 0.0001 | 6    | 1.1301          |
+| 0.809         | 0.0001 | 9    | 0.4927          |
 
 
 ### Framework versions