End of training

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: peft
 license: apache-2.0
-base_model: EleutherAI/pythia-70m-deduped
+base_model: Maykeye/TinyLLama-v0
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_999dc897-8e91-4324-92d7-b71af8c08912
+- Aivesa/dataset_69a210ba-69a6-4af0-a84b-b62a60567e8b
 model-index:
-- name: f8549911-86bb-4e2b-8478-525efbbc4415
+- name: d7ece7c9-f6fc-4531-8b1e-e231149e3a1d
   results: []
 ---
 
@@ -21,17 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: EleutherAI/pythia-70m-deduped
+base_model: Maykeye/TinyLLama-v0
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_999dc897-8e91-4324-92d7-b71af8c08912
+  path: Aivesa/dataset_69a210ba-69a6-4af0-a84b-b62a60567e8b
   type:
-    field_instruction: pageTitle
-    field_output: output
+    field_instruction: prompt
+    field_output: chosen
     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/f8549911-86bb-4e2b-8478-525efbbc4415
+hub_model_id: Aivesa/d7ece7c9-f6fc-4531-8b1e-e231149e3a1d
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -79,7 +79,7 @@ save_safetensors: true
 saves_per_epoch: 4
 sequence_len: 512
 special_tokens:
-  pad_token: <|endoftext|>
+  pad_token: </s>
 strict: false
 tf32: false
 tokenizer_type: AutoTokenizer
@@ -89,10 +89,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: 999dc897-8e91-4324-92d7-b71af8c08912
+wandb_name: 69a210ba-69a6-4af0-a84b-b62a60567e8b
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 999dc897-8e91-4324-92d7-b71af8c08912
+wandb_runid: 69a210ba-69a6-4af0-a84b-b62a60567e8b
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -101,11 +101,11 @@ xformers_attention: null
 
 </details><br>
 
-# f8549911-86bb-4e2b-8478-525efbbc4415
+# d7ece7c9-f6fc-4531-8b1e-e231149e3a1d
 
-This model is a fine-tuned version of [EleutherAI/pythia-70m-deduped](https://huggingface.co/EleutherAI/pythia-70m-deduped) on the Aivesa/dataset_999dc897-8e91-4324-92d7-b71af8c08912 dataset.
+This model is a fine-tuned version of [Maykeye/TinyLLama-v0](https://huggingface.co/Maykeye/TinyLLama-v0) on the Aivesa/dataset_69a210ba-69a6-4af0-a84b-b62a60567e8b dataset.
 It achieves the following results on the evaluation set:
-- Loss: 182.5955
+- Loss: 6.2183
 
 ## Model description
 
@@ -139,9 +139,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 575.7077      | 0.0003 | 3    | 182.7351        |
-| 962.5692      | 0.0006 | 6    | 182.6678        |
-| 537.9006      | 0.0009 | 9    | 182.5955        |
+| 6.4432        | 0.0024 | 3    | 6.2957          |
+| 5.9891        | 0.0047 | 6    | 6.2714          |
+| 6.3986        | 0.0071 | 9    | 6.2183          |
 
 
 ### Framework versions