End of training

README.md

@@ -1,14 +1,13 @@
 ---
 library_name: peft
-license: apache-2.0
-base_model: unsloth/gemma-2b-it
+base_model: jingyeom/seal3.1.6n_7b
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Paladiso/dataset_60321321-5e91-4886-9fa6-1d8701d25608
+- Paladiso/dataset_2379ea32-7a7b-48aa-9667-b04a8ab9542e
 model-index:
-- name: 0b6361fa-53ee-41bf-95a2-16b2b739c235
+- name: 5eebbc6c-5859-479d-b165-0c9522233643
   results: []
 ---
 
@@ -21,18 +20,17 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: unsloth/gemma-2b-it
+base_model: jingyeom/seal3.1.6n_7b
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Paladiso/dataset_60321321-5e91-4886-9fa6-1d8701d25608
+  path: Paladiso/dataset_2379ea32-7a7b-48aa-9667-b04a8ab9542e
   type:
-    field_input: ''
-    field_instruction: problem
-    field_output: solution
+    field_instruction: question
+    field_output: answer
     system_format: '{system}'
     system_prompt: ''
 debug: null
@@ -48,7 +46,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Paladiso/0b6361fa-53ee-41bf-95a2-16b2b739c235
+hub_model_id: Paladiso/5eebbc6c-5859-479d-b165-0c9522233643
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -88,10 +86,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: 60321321-5e91-4886-9fa6-1d8701d25608
+wandb_name: 2379ea32-7a7b-48aa-9667-b04a8ab9542e
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 60321321-5e91-4886-9fa6-1d8701d25608
+wandb_runid: 2379ea32-7a7b-48aa-9667-b04a8ab9542e
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -100,11 +98,11 @@ xformers_attention: null
 
 </details><br>
 
-# 0b6361fa-53ee-41bf-95a2-16b2b739c235
+# 5eebbc6c-5859-479d-b165-0c9522233643
 
-This model is a fine-tuned version of [unsloth/gemma-2b-it](https://huggingface.co/unsloth/gemma-2b-it) on the Paladiso/dataset_60321321-5e91-4886-9fa6-1d8701d25608 dataset.
+This model is a fine-tuned version of [jingyeom/seal3.1.6n_7b](https://huggingface.co/jingyeom/seal3.1.6n_7b) on the Paladiso/dataset_2379ea32-7a7b-48aa-9667-b04a8ab9542e dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2568
+- Loss: 3.3596
 
 ## Model description
 
@@ -138,9 +136,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.851         | 0.0009 | 3    | 1.9646          |
-| 1.7771        | 0.0018 | 6    | 1.5536          |
-| 1.1441        | 0.0027 | 9    | 1.2568          |
+| 4.1739        | 0.0002 | 3    | 4.4997          |
+| 4.3112        | 0.0004 | 6    | 4.1929          |
+| 3.7794        | 0.0006 | 9    | 3.3596          |
 
 
 ### Framework versions