End of training

README.md

@@ -1,13 +1,14 @@
 ---
 library_name: peft
-base_model: samoline/15206987-1fd2-42e7-b6ff-76e937bed868
+license: apache-2.0
+base_model: Qwen/Qwen2.5-1.5B
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_f1fc5363-4c2b-4b15-8937-25e59984288b
+- Aivesa/dataset_fe02391f-dc57-4aa5-9b78-45187ff5fb46
 model-index:
-- name: 09ef104a-4ed4-4720-b432-93642d949570
+- name: d037a536-e2d0-4e2b-9ac6-efaaacbaa2df
   results: []
 ---
 
@@ -20,18 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: samoline/15206987-1fd2-42e7-b6ff-76e937bed868
+base_model: Qwen/Qwen2.5-1.5B
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_f1fc5363-4c2b-4b15-8937-25e59984288b
+  path: Aivesa/dataset_fe02391f-dc57-4aa5-9b78-45187ff5fb46
   type:
-    field_input: input
-    field_instruction: instruction
-    field_output: output
+    field_instruction: premise
+    field_output: hypothesis
     system_format: '{system}'
     system_prompt: ''
 debug: null
@@ -47,7 +47,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Aivesa/09ef104a-4ed4-4720-b432-93642d949570
+hub_model_id: Aivesa/d037a536-e2d0-4e2b-9ac6-efaaacbaa2df
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -87,10 +87,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: f1fc5363-4c2b-4b15-8937-25e59984288b
+wandb_name: fe02391f-dc57-4aa5-9b78-45187ff5fb46
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: f1fc5363-4c2b-4b15-8937-25e59984288b
+wandb_runid: fe02391f-dc57-4aa5-9b78-45187ff5fb46
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -99,11 +99,11 @@ xformers_attention: null
 
 </details><br>
 
-# 09ef104a-4ed4-4720-b432-93642d949570
+# d037a536-e2d0-4e2b-9ac6-efaaacbaa2df
 
-This model is a fine-tuned version of [samoline/15206987-1fd2-42e7-b6ff-76e937bed868](https://huggingface.co/samoline/15206987-1fd2-42e7-b6ff-76e937bed868) on the Aivesa/dataset_f1fc5363-4c2b-4b15-8937-25e59984288b dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) on the Aivesa/dataset_fe02391f-dc57-4aa5-9b78-45187ff5fb46 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4623
+- Loss: 1.1429
 
 ## Model description
 
@@ -137,9 +137,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.3267        | 0.0006 | 3    | 1.5370          |
-| 1.25          | 0.0012 | 6    | 1.5235          |
-| 1.1399        | 0.0018 | 9    | 1.4623          |
+| 1.3236        | 0.0035 | 3    | 1.2901          |
+| 1.2011        | 0.0069 | 6    | 1.2545          |
+| 1.1983        | 0.0104 | 9    | 1.1429          |
 
 
 ### Framework versions