End of training

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: peft
-license: llama3.2
-base_model: NousResearch/Llama-3.2-1B
+license: mit
+base_model: fxmarty/tiny-dummy-qwen2
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_4e09364d-8903-424d-91fc-63d840c0e814
+- Aivesa/dataset_354d40c7-91f2-4ebd-87a1-e6e2ca96f021
 model-index:
-- name: 1323fbae-0d02-4671-b273-56565a347e3d
+- name: 4e152da9-a77a-4b90-b06d-1d9351bf56ce
   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: NousResearch/Llama-3.2-1B
+base_model: fxmarty/tiny-dummy-qwen2
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_4e09364d-8903-424d-91fc-63d840c0e814
+  path: Aivesa/dataset_354d40c7-91f2-4ebd-87a1-e6e2ca96f021
   type:
-    field_instruction: instruction
-    field_output: output
+    field_instruction: tokens
+    field_output: text
     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/1323fbae-0d02-4671-b273-56565a347e3d
+hub_model_id: Aivesa/4e152da9-a77a-4b90-b06d-1d9351bf56ce
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -78,8 +78,6 @@ sample_packing: false
 save_safetensors: true
 saves_per_epoch: 4
 sequence_len: 512
-special_tokens:
-  pad_token: <|end_of_text|>
 strict: false
 tf32: false
 tokenizer_type: AutoTokenizer
@@ -89,10 +87,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: 4e09364d-8903-424d-91fc-63d840c0e814
+wandb_name: 354d40c7-91f2-4ebd-87a1-e6e2ca96f021
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 4e09364d-8903-424d-91fc-63d840c0e814
+wandb_runid: 354d40c7-91f2-4ebd-87a1-e6e2ca96f021
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -101,11 +99,11 @@ xformers_attention: null
 
 </details><br>
 
-# 1323fbae-0d02-4671-b273-56565a347e3d
+# 4e152da9-a77a-4b90-b06d-1d9351bf56ce
 
-This model is a fine-tuned version of [NousResearch/Llama-3.2-1B](https://huggingface.co/NousResearch/Llama-3.2-1B) on the Aivesa/dataset_4e09364d-8903-424d-91fc-63d840c0e814 dataset.
+This model is a fine-tuned version of [fxmarty/tiny-dummy-qwen2](https://huggingface.co/fxmarty/tiny-dummy-qwen2) on the Aivesa/dataset_354d40c7-91f2-4ebd-87a1-e6e2ca96f021 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3788
+- Loss: 11.9316
 
 ## Model description
 
@@ -139,9 +137,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.2791        | 0.0004 | 3    | 1.4433          |
-| 1.3516        | 0.0007 | 6    | 1.4253          |
-| 1.266         | 0.0011 | 9    | 1.3788          |
+| 11.9331       | 0.0046 | 3    | 11.9318         |
+| 11.9245       | 0.0092 | 6    | 11.9317         |
+| 11.9364       | 0.0138 | 9    | 11.9316         |
 
 
 ### Framework versions