End of training

README.md

@@ -1,14 +1,13 @@
 ---
 library_name: peft
-license: apache-2.0
-base_model: unsloth/Qwen2-0.5B
+base_model: samoline/b2c7a36d-04a9-4742-a28e-1e610e99182d
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_259fd7bc-d639-4f39-96d1-9a76d24779cd
+- Aivesa/dataset_ba7306b0-2ddd-4887-9a06-5c15416640d9
 model-index:
-- name: 9a71f3f5-40c0-42a5-94fb-c1072e30ea0b
+- name: ddc6a3ad-f22b-48e3-be90-4520338dd567
   results: []
 ---
 
@@ -21,18 +20,18 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: unsloth/Qwen2-0.5B
+base_model: samoline/b2c7a36d-04a9-4742-a28e-1e610e99182d
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_259fd7bc-d639-4f39-96d1-9a76d24779cd
+  path: Aivesa/dataset_ba7306b0-2ddd-4887-9a06-5c15416640d9
   type:
-    field_input: my_solu
-    field_instruction: prompt
-    field_output: solution
+    field_input: input
+    field_instruction: instruction
+    field_output: output
     system_format: '{system}'
     system_prompt: ''
 debug: null
@@ -48,7 +47,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Aivesa/9a71f3f5-40c0-42a5-94fb-c1072e30ea0b
+hub_model_id: Aivesa/ddc6a3ad-f22b-48e3-be90-4520338dd567
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -79,6 +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
@@ -88,10 +89,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: 259fd7bc-d639-4f39-96d1-9a76d24779cd
+wandb_name: ba7306b0-2ddd-4887-9a06-5c15416640d9
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 259fd7bc-d639-4f39-96d1-9a76d24779cd
+wandb_runid: ba7306b0-2ddd-4887-9a06-5c15416640d9
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -100,11 +101,11 @@ xformers_attention: null
 
 </details><br>
 
-# 9a71f3f5-40c0-42a5-94fb-c1072e30ea0b
+# ddc6a3ad-f22b-48e3-be90-4520338dd567
 
-This model is a fine-tuned version of [unsloth/Qwen2-0.5B](https://huggingface.co/unsloth/Qwen2-0.5B) on the Aivesa/dataset_259fd7bc-d639-4f39-96d1-9a76d24779cd dataset.
+This model is a fine-tuned version of [samoline/b2c7a36d-04a9-4742-a28e-1e610e99182d](https://huggingface.co/samoline/b2c7a36d-04a9-4742-a28e-1e610e99182d) on the Aivesa/dataset_ba7306b0-2ddd-4887-9a06-5c15416640d9 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9482
+- Loss: 1.4729
 
 ## Model description
 
@@ -138,9 +139,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.2589        | 0.0001 | 3    | 1.0529          |
-| 1.0467        | 0.0001 | 6    | 1.0084          |
-| 0.933         | 0.0002 | 9    | 0.9482          |
+| 1.4547        | 0.0006 | 3    | 1.6870          |
+| 1.3418        | 0.0012 | 6    | 1.6180          |
+| 1.133         | 0.0018 | 9    | 1.4729          |
 
 
 ### Framework versions