End of training

README.md

@@ -1,13 +1,14 @@
 ---
 library_name: peft
-base_model: EleutherAI/pythia-14m
+license: apache-2.0
+base_model: Qwen/Qwen2.5-0.5B
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_266f33d1-3051-4fb8-b818-274cf5af832f
+- Aivesa/dataset_e5909454-6ee7-43b0-bc21-d6fa723e34ec
 model-index:
-- name: 19a3b1db-cac0-4e1c-8660-f1df015bdc19
+- name: ed606038-9c3c-4474-8e32-832c273c21de
   results: []
 ---
 
@@ -20,17 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: EleutherAI/pythia-14m
+base_model: Qwen/Qwen2.5-0.5B
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_266f33d1-3051-4fb8-b818-274cf5af832f
+  path: Aivesa/dataset_e5909454-6ee7-43b0-bc21-d6fa723e34ec
   type:
-    field_instruction: topic
-    field_output: text
+    field_instruction: instruction
+    field_output: response
     system_format: '{system}'
     system_prompt: ''
 debug: null
@@ -46,7 +47,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Aivesa/19a3b1db-cac0-4e1c-8660-f1df015bdc19
+hub_model_id: Aivesa/ed606038-9c3c-4474-8e32-832c273c21de
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -77,8 +78,6 @@ sample_packing: false
 save_safetensors: true
 saves_per_epoch: 4
 sequence_len: 512
-special_tokens:
-  pad_token: <|endoftext|>
 strict: false
 tf32: false
 tokenizer_type: AutoTokenizer
@@ -88,10 +87,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: 266f33d1-3051-4fb8-b818-274cf5af832f
+wandb_name: e5909454-6ee7-43b0-bc21-d6fa723e34ec
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 266f33d1-3051-4fb8-b818-274cf5af832f
+wandb_runid: e5909454-6ee7-43b0-bc21-d6fa723e34ec
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -100,11 +99,11 @@ xformers_attention: null
 
 </details><br>
 
-# 19a3b1db-cac0-4e1c-8660-f1df015bdc19
+# ed606038-9c3c-4474-8e32-832c273c21de
 
-This model is a fine-tuned version of [EleutherAI/pythia-14m](https://huggingface.co/EleutherAI/pythia-14m) on the Aivesa/dataset_266f33d1-3051-4fb8-b818-274cf5af832f dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) on the Aivesa/dataset_e5909454-6ee7-43b0-bc21-d6fa723e34ec dataset.
 It achieves the following results on the evaluation set:
-- Loss: 7.0823
+- Loss: 1.5777
 
 ## Model description
 
@@ -138,9 +137,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 29.2484       | 0.0009 | 3    | 7.2750          |
-| 29.3991       | 0.0018 | 6    | 7.2034          |
-| 28.0936       | 0.0027 | 9    | 7.0823          |
+| 1.6955        | 0.0036 | 3    | 1.6560          |
+| 1.2132        | 0.0071 | 6    | 1.6306          |
+| 1.7991        | 0.0107 | 9    | 1.5777          |
 
 
 ### Framework versions