End of training

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: peft
-license: other
-base_model: facebook/opt-1.3b
+license: mit
+base_model: fxmarty/really-tiny-falcon-testing
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_46dd44b3-e4e4-4c44-8605-e8e8b6dd956e
+- Aivesa/dataset_e689ce62-a84d-4b12-b3a9-6584b8c9412c
 model-index:
-- name: a05b476c-463b-4946-89c4-d93aca81d7e7
+- name: a6d51ef6-d147-47bf-ac9b-6224e8e5b1b5
   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: facebook/opt-1.3b
+base_model: fxmarty/really-tiny-falcon-testing
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_46dd44b3-e4e4-4c44-8605-e8e8b6dd956e
+  path: Aivesa/dataset_e689ce62-a84d-4b12-b3a9-6584b8c9412c
   type:
-    field_input: context
-    field_instruction: question
-    field_output: answers
+    field_input: input
+    field_instruction: instruction
+    field_output: output
     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/a05b476c-463b-4946-89c4-d93aca81d7e7
+hub_model_id: Aivesa/a6d51ef6-d147-47bf-ac9b-6224e8e5b1b5
 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: 46dd44b3-e4e4-4c44-8605-e8e8b6dd956e
+wandb_name: e689ce62-a84d-4b12-b3a9-6584b8c9412c
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 46dd44b3-e4e4-4c44-8605-e8e8b6dd956e
+wandb_runid: e689ce62-a84d-4b12-b3a9-6584b8c9412c
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -100,11 +100,11 @@ xformers_attention: null
 
 </details><br>
 
-# a05b476c-463b-4946-89c4-d93aca81d7e7
+# a6d51ef6-d147-47bf-ac9b-6224e8e5b1b5
 
-This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) on the Aivesa/dataset_46dd44b3-e4e4-4c44-8605-e8e8b6dd956e dataset.
+This model is a fine-tuned version of [fxmarty/really-tiny-falcon-testing](https://huggingface.co/fxmarty/really-tiny-falcon-testing) on the Aivesa/dataset_e689ce62-a84d-4b12-b3a9-6584b8c9412c dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6826
+- Loss: 10.9675
 
 ## Model description
 
@@ -138,9 +138,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 15.8191       | 0.0003 | 3    | 4.1197          |
-| 17.6309       | 0.0005 | 6    | 3.6521          |
-| 11.7024       | 0.0008 | 9    | 2.6826          |
+| 43.9444       | 0.0108 | 3    | 10.9903         |
+| 43.9096       | 0.0215 | 6    | 10.9827         |
+| 43.8975       | 0.0323 | 9    | 10.9675         |
 
 
 ### Framework versions