End of training

README.md

@@ -1,12 +1,12 @@
 ---
-license: mit
+license: apache-2.0
 library_name: peft
 tags:
 - axolotl
 - generated_from_trainer
-base_model: princeton-nlp/gemma-2-9b-it-SimPO
+base_model: Qwen/Qwen2.5-Math-7B-Instruct
 model-index:
-- name: ea995dc6-2b84-41b3-ac45-9d80fc8d62a8
+- name: d51aa98d-e0f3-4aaf-ae00-e8da30f740ee
   results: []
 ---
 
@@ -19,19 +19,19 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.4.1`
 ```yaml
 adapter: lora
-base_model: princeton-nlp/gemma-2-9b-it-SimPO
+base_model: Qwen/Qwen2.5-Math-7B-Instruct
 bf16: auto
 datasets:
 - data_files:
-  - 0a8e1ed234d341f6_train_data.json
+  - a9dedf98b14b8e66_train_data.json
   ds_type: json
   format: custom
-  path: 0a8e1ed234d341f6_train_data.json
+  path: a9dedf98b14b8e66_train_data.json
   type:
     field: null
-    field_input: num
-    field_instruction: title_main
-    field_output: texte
+    field_input: errors
+    field_instruction: original_text
+    field_output: correct_text
     field_system: null
     format: null
     no_input_format: null
@@ -51,7 +51,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: true
 group_by_length: false
-hub_model_id: FatCat87/ea995dc6-2b84-41b3-ac45-9d80fc8d62a8
+hub_model_id: FatCat87/d51aa98d-e0f3-4aaf-ae00-e8da30f740ee
 learning_rate: 0.0002
 load_in_4bit: false
 load_in_8bit: true
@@ -82,9 +82,9 @@ val_set_size: 0.1
 wandb_entity: fatcat87-taopanda
 wandb_log_model: null
 wandb_mode: online
-wandb_name: ea995dc6-2b84-41b3-ac45-9d80fc8d62a8
+wandb_name: d51aa98d-e0f3-4aaf-ae00-e8da30f740ee
 wandb_project: subnet56
-wandb_runid: ea995dc6-2b84-41b3-ac45-9d80fc8d62a8
+wandb_runid: d51aa98d-e0f3-4aaf-ae00-e8da30f740ee
 wandb_watch: null
 warmup_ratio: 0.05
 weight_decay: 0.0
@@ -94,12 +94,12 @@ xformers_attention: null
 
 </details><br>
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/fatcat87-taopanda/subnet56/runs/1908w8y2)
-# ea995dc6-2b84-41b3-ac45-9d80fc8d62a8
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/fatcat87-taopanda/subnet56/runs/cmgp1i7e)
+# d51aa98d-e0f3-4aaf-ae00-e8da30f740ee
 
-This model is a fine-tuned version of [princeton-nlp/gemma-2-9b-it-SimPO](https://huggingface.co/princeton-nlp/gemma-2-9b-it-SimPO) on the None dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5247
+- Loss: 1.3265
 
 ## Model description
 
@@ -135,10 +135,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.0061        | 0.0571 | 1    | 1.9442          |
-| 1.5778        | 0.2857 | 5    | 1.5892          |
-| 1.5005        | 0.5714 | 10   | 1.5397          |
-| 1.4559        | 0.8571 | 15   | 1.5247          |
+| 1.7936        | 0.1818 | 1    | 1.9329          |
+| 1.7853        | 0.3636 | 2    | 1.7201          |
+| 1.3319        | 0.7273 | 4    | 1.3265          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a047e9eca9c4d8ec6148b682b3006ca5e11f8e228de0d4b70abbc2b1f69d1d35
-size 432357050
+oid sha256:9db1f0813d4e6d03df3e4b97f45d791865f9b6c9f0a6ab2fca900a1dce5b7ae8
+size 323103018