End of training

README.md

@@ -1,13 +1,14 @@
 ---
 library_name: peft
-base_model: lmsys/vicuna-7b-v1.3
+license: apache-2.0
+base_model: unsloth/Qwen2.5-1.5B
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Paladiso/dataset_a6d9ee3a-6e70-4ab7-9e9f-80087a260018
+- Paladiso/dataset_7fc40eed-6bc5-4668-b817-a908f0a659fe
 model-index:
-- name: 411f1091-665a-4792-97eb-4d4e7b8ff915
+- name: e2729802-dde6-43c2-bb4a-4d0a4beac90e
   results: []
 ---
 
@@ -20,18 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: lmsys/vicuna-7b-v1.3
+base_model: unsloth/Qwen2.5-1.5B
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Paladiso/dataset_a6d9ee3a-6e70-4ab7-9e9f-80087a260018
+  path: Paladiso/dataset_7fc40eed-6bc5-4668-b817-a908f0a659fe
   type:
-    field_input: CV
-    field_instruction: Job Description
-    field_output: feedback
+    field_instruction: abstract
+    field_output: title
     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: Paladiso/411f1091-665a-4792-97eb-4d4e7b8ff915
+hub_model_id: Paladiso/e2729802-dde6-43c2-bb4a-4d0a4beac90e
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -87,10 +87,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: a6d9ee3a-6e70-4ab7-9e9f-80087a260018
+wandb_name: 7fc40eed-6bc5-4668-b817-a908f0a659fe
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: a6d9ee3a-6e70-4ab7-9e9f-80087a260018
+wandb_runid: 7fc40eed-6bc5-4668-b817-a908f0a659fe
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -99,11 +99,11 @@ xformers_attention: null
 
 </details><br>
 
-# 411f1091-665a-4792-97eb-4d4e7b8ff915
+# e2729802-dde6-43c2-bb4a-4d0a4beac90e
 
-This model is a fine-tuned version of [lmsys/vicuna-7b-v1.3](https://huggingface.co/lmsys/vicuna-7b-v1.3) on the Paladiso/dataset_a6d9ee3a-6e70-4ab7-9e9f-80087a260018 dataset.
+This model is a fine-tuned version of [unsloth/Qwen2.5-1.5B](https://huggingface.co/unsloth/Qwen2.5-1.5B) on the Paladiso/dataset_7fc40eed-6bc5-4668-b817-a908f0a659fe dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1452
+- Loss: 2.3707
 
 ## Model description
 
@@ -137,9 +137,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.3978        | 0.0010 | 3    | 2.5506          |
-| 2.5566        | 0.0021 | 6    | 2.4761          |
-| 2.6659        | 0.0031 | 9    | 2.1452          |
+| 2.327         | 0.0004 | 3    | 2.8300          |
+| 2.4           | 0.0007 | 6    | 2.7118          |
+| 2.8662        | 0.0011 | 9    | 2.3707          |
 
 
 ### Framework versions