End of training

README.md

@@ -1,14 +1,13 @@
 ---
 library_name: peft
-license: apache-2.0
-base_model: unsloth/Qwen2.5-Math-7B-Instruct
+base_model: samoline/tensoralchemistdev01__sv9-with-tokenizer
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_e59ee620-6dc6-41b8-8080-617c8e470bc7
+- Aivesa/dataset_12076561-6ae2-493b-9bce-28ba02fe74db
 model-index:
-- name: 821c28d5-3470-4b5a-9b5a-ca6c3270c51f
+- name: 60d8b3e3-a961-4798-b800-8509c0e5177c
   results: []
 ---
 
@@ -21,17 +20,18 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: unsloth/Qwen2.5-Math-7B-Instruct
+base_model: samoline/tensoralchemistdev01__sv9-with-tokenizer
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_e59ee620-6dc6-41b8-8080-617c8e470bc7
+  path: Aivesa/dataset_12076561-6ae2-493b-9bce-28ba02fe74db
   type:
+    field_input: input
     field_instruction: instruction
-    field_output: output_1
+    field_output: output
     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/821c28d5-3470-4b5a-9b5a-ca6c3270c51f
+hub_model_id: Aivesa/60d8b3e3-a961-4798-b800-8509c0e5177c
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -78,6 +78,8 @@ 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
@@ -87,10 +89,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: e59ee620-6dc6-41b8-8080-617c8e470bc7
+wandb_name: 12076561-6ae2-493b-9bce-28ba02fe74db
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: e59ee620-6dc6-41b8-8080-617c8e470bc7
+wandb_runid: 12076561-6ae2-493b-9bce-28ba02fe74db
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -99,11 +101,11 @@ xformers_attention: null
 
 </details><br>
 
-# 821c28d5-3470-4b5a-9b5a-ca6c3270c51f
+# 60d8b3e3-a961-4798-b800-8509c0e5177c
 
-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.
+This model is a fine-tuned version of [samoline/tensoralchemistdev01__sv9-with-tokenizer](https://huggingface.co/samoline/tensoralchemistdev01__sv9-with-tokenizer) on the Aivesa/dataset_12076561-6ae2-493b-9bce-28ba02fe74db dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.6217
+- Loss: 1.4744
 
 ## Model description
 
@@ -137,9 +139,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.4757        | 0.0015 | 3    | 2.6821          |
-| 2.6649        | 0.0031 | 6    | 2.6746          |
-| 2.5663        | 0.0046 | 9    | 2.6217          |
+| 1.4972        | 0.0006 | 3    | 1.6797          |
+| 1.3864        | 0.0012 | 6    | 1.6174          |
+| 1.1849        | 0.0018 | 9    | 1.4744          |
 
 
 ### Framework versions