End of training

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: peft
 license: apache-2.0
-base_model: unsloth/SmolLM2-360M-Instruct
+base_model: unsloth/mistral-7b-v0.3
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_0bb39f55-e2d8-431a-b743-b0068a16e3a5
+- Aivesa/dataset_bb4495a3-40e6-47d5-8acb-8dbb8fc1970b
 model-index:
-- name: e6175c79-ed07-4658-8bc8-23f1679fadf5
+- name: f16a710f-b5df-407b-8bd3-f553e1ab5dd8
   results: []
 ---
 
@@ -21,18 +21,18 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: unsloth/SmolLM2-360M-Instruct
+base_model: unsloth/mistral-7b-v0.3
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_0bb39f55-e2d8-431a-b743-b0068a16e3a5
+  path: Aivesa/dataset_bb4495a3-40e6-47d5-8acb-8dbb8fc1970b
   type:
-    field_input: rejected
-    field_instruction: prompt
-    field_output: chosen
+    field_input: choices
+    field_instruction: subject
+    field_output: question
     system_format: '{system}'
     system_prompt: ''
 debug: null
@@ -48,7 +48,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Aivesa/e6175c79-ed07-4658-8bc8-23f1679fadf5
+hub_model_id: Aivesa/f16a710f-b5df-407b-8bd3-f553e1ab5dd8
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -88,10 +88,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: 0bb39f55-e2d8-431a-b743-b0068a16e3a5
+wandb_name: bb4495a3-40e6-47d5-8acb-8dbb8fc1970b
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 0bb39f55-e2d8-431a-b743-b0068a16e3a5
+wandb_runid: bb4495a3-40e6-47d5-8acb-8dbb8fc1970b
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -100,11 +100,11 @@ xformers_attention: null
 
 </details><br>
 
-# e6175c79-ed07-4658-8bc8-23f1679fadf5
+# f16a710f-b5df-407b-8bd3-f553e1ab5dd8
 
-This model is a fine-tuned version of [unsloth/SmolLM2-360M-Instruct](https://huggingface.co/unsloth/SmolLM2-360M-Instruct) on the Aivesa/dataset_0bb39f55-e2d8-431a-b743-b0068a16e3a5 dataset.
+This model is a fine-tuned version of [unsloth/mistral-7b-v0.3](https://huggingface.co/unsloth/mistral-7b-v0.3) on the Aivesa/dataset_bb4495a3-40e6-47d5-8acb-8dbb8fc1970b dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0462
+- Loss: 1.6346
 
 ## Model description
 
@@ -138,9 +138,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.1513        | 0.0032 | 3    | 1.0495          |
-| 0.9987        | 0.0064 | 6    | 1.0485          |
-| 1.0856        | 0.0096 | 9    | 1.0462          |
+| 7.3363        | 0.0086 | 3    | 2.0843          |
+| 6.8908        | 0.0171 | 6    | 1.7118          |
+| 5.9452        | 0.0257 | 9    | 1.6346          |
 
 
 ### Framework versions