End of training

README.md

@@ -1,13 +1,14 @@
 ---
 library_name: peft
-base_model: katuni4ka/tiny-random-codegen2
+license: apache-2.0
+base_model: unsloth/Qwen2.5-Math-7B-Instruct
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_2ba51e00-ad1b-413e-b721-f181b258691a
+- Aivesa/dataset_e59ee620-6dc6-41b8-8080-617c8e470bc7
 model-index:
-- name: 40ce77c7-6323-486b-87c9-8a71363be00b
+- name: 77c11f2a-7fc5-42a9-af8d-7f0bb2c3679b
   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: katuni4ka/tiny-random-codegen2
+base_model: unsloth/Qwen2.5-Math-7B-Instruct
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_2ba51e00-ad1b-413e-b721-f181b258691a
+  path: Aivesa/dataset_e59ee620-6dc6-41b8-8080-617c8e470bc7
   type:
-    field_instruction: sentence1
-    field_output: sentence2
+    field_instruction: instruction
+    field_output: output_1
     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/40ce77c7-6323-486b-87c9-8a71363be00b
+hub_model_id: Aivesa/77c11f2a-7fc5-42a9-af8d-7f0bb2c3679b
 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: 2ba51e00-ad1b-413e-b721-f181b258691a
+wandb_name: e59ee620-6dc6-41b8-8080-617c8e470bc7
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 2ba51e00-ad1b-413e-b721-f181b258691a
+wandb_runid: e59ee620-6dc6-41b8-8080-617c8e470bc7
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -100,11 +99,11 @@ xformers_attention: null
 
 </details><br>
 
-# 40ce77c7-6323-486b-87c9-8a71363be00b
+# 77c11f2a-7fc5-42a9-af8d-7f0bb2c3679b
 
-This model is a fine-tuned version of [katuni4ka/tiny-random-codegen2](https://huggingface.co/katuni4ka/tiny-random-codegen2) on the Aivesa/dataset_2ba51e00-ad1b-413e-b721-f181b258691a dataset.
+This model is a fine-tuned version of [unsloth/Qwen2.5-Math-7B-Instruct](https://huggingface.co/unsloth/Qwen2.5-Math-7B-Instruct) on the Aivesa/dataset_e59ee620-6dc6-41b8-8080-617c8e470bc7 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 10.8537
+- Loss: 2.6205
 
 ## Model description
 
@@ -138,9 +137,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 43.4226       | 0.0030 | 3    | 10.8579         |
-| 43.4426       | 0.0061 | 6    | 10.8563         |
-| 43.4249       | 0.0091 | 9    | 10.8537         |
+| 2.4752        | 0.0015 | 3    | 2.6821          |
+| 2.6637        | 0.0031 | 6    | 2.6741          |
+| 2.5646        | 0.0046 | 9    | 2.6205          |
 
 
 ### Framework versions