End of training

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: peft
-license: mit
-base_model: microsoft/Phi-3.5-mini-instruct
+license: apache-2.0
+base_model: unsloth/mistral-7b-instruct-v0.3
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_1c77d1af-78a7-4412-9e47-07d10e4871b0
+- Aivesa/dataset_41b65960-526f-4a18-944a-fbc29b953bea
 model-index:
-- name: df723aa2-0e06-4d86-8205-6086bd58241a
+- name: 5f3aa5fe-9ab6-45ad-80bf-93ee9b5f092a
   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: microsoft/Phi-3.5-mini-instruct
+base_model: unsloth/mistral-7b-instruct-v0.3
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_1c77d1af-78a7-4412-9e47-07d10e4871b0
+  path: Aivesa/dataset_41b65960-526f-4a18-944a-fbc29b953bea
   type:
-    field_input: long_answer
-    field_instruction: question
-    field_output: answer
+    field_input: AZ_labels
+    field_instruction: category
+    field_output: sentence
     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: Aivesa/df723aa2-0e06-4d86-8205-6086bd58241a
+hub_model_id: Aivesa/5f3aa5fe-9ab6-45ad-80bf-93ee9b5f092a
 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: 1c77d1af-78a7-4412-9e47-07d10e4871b0
+wandb_name: 41b65960-526f-4a18-944a-fbc29b953bea
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 1c77d1af-78a7-4412-9e47-07d10e4871b0
+wandb_runid: 41b65960-526f-4a18-944a-fbc29b953bea
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -100,11 +100,11 @@ xformers_attention: null
 
 </details><br>
 
-# df723aa2-0e06-4d86-8205-6086bd58241a
+# 5f3aa5fe-9ab6-45ad-80bf-93ee9b5f092a
 
-This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the Aivesa/dataset_1c77d1af-78a7-4412-9e47-07d10e4871b0 dataset.
+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 Aivesa/dataset_41b65960-526f-4a18-944a-fbc29b953bea dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3022
+- Loss: 2.6588
 
 ## Model description
 
@@ -138,9 +138,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 9.1719        | 0.0007 | 3    | 2.0464          |
-| 7.7076        | 0.0014 | 6    | 1.9055          |
-| 7.966         | 0.0021 | 9    | 1.3022          |
+| 13.7126       | 0.0025 | 3    | 3.3778          |
+| 13.1722       | 0.0050 | 6    | 2.9551          |
+| 10.4697       | 0.0075 | 9    | 2.6588          |
 
 
 ### Framework versions