End of training

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: peft
 license: apache-2.0
-base_model: Qwen/Qwen2.5-0.5B
+base_model: EleutherAI/pythia-410m-deduped
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_e5909454-6ee7-43b0-bc21-d6fa723e34ec
+- Aivesa/dataset_6b68d715-277d-410f-8147-0e3954c97b2f
 model-index:
-- name: 14faec3b-678a-4b3e-a3e7-95067cb131aa
+- name: c1093e50-e6e8-4bfe-8dc8-afe74f920cfd
   results: []
 ---
 
@@ -21,17 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: Qwen/Qwen2.5-0.5B
+base_model: EleutherAI/pythia-410m-deduped
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_e5909454-6ee7-43b0-bc21-d6fa723e34ec
+  path: Aivesa/dataset_6b68d715-277d-410f-8147-0e3954c97b2f
   type:
-    field_instruction: instruction
-    field_output: response
+    field_instruction: en
+    field_output: id
     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/14faec3b-678a-4b3e-a3e7-95067cb131aa
+hub_model_id: Aivesa/c1093e50-e6e8-4bfe-8dc8-afe74f920cfd
 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: e5909454-6ee7-43b0-bc21-d6fa723e34ec
+wandb_name: 6b68d715-277d-410f-8147-0e3954c97b2f
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: e5909454-6ee7-43b0-bc21-d6fa723e34ec
+wandb_runid: 6b68d715-277d-410f-8147-0e3954c97b2f
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -99,11 +101,11 @@ xformers_attention: null
 
 </details><br>
 
-# 14faec3b-678a-4b3e-a3e7-95067cb131aa
+# c1093e50-e6e8-4bfe-8dc8-afe74f920cfd
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B) on the Aivesa/dataset_e5909454-6ee7-43b0-bc21-d6fa723e34ec dataset.
+This model is a fine-tuned version of [EleutherAI/pythia-410m-deduped](https://huggingface.co/EleutherAI/pythia-410m-deduped) on the Aivesa/dataset_6b68d715-277d-410f-8147-0e3954c97b2f dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5795
+- Loss: 4.0359
 
 ## Model description
 
@@ -137,9 +139,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.6945        | 0.0036 | 3    | 1.6561          |
-| 1.2122        | 0.0071 | 6    | 1.6313          |
-| 1.7996        | 0.0107 | 9    | 1.5795          |
+| 15.5299       | 0.0005 | 3    | 4.1709          |
+| 18.699        | 0.0010 | 6    | 4.1389          |
+| 17.5318       | 0.0015 | 9    | 4.0359          |
 
 
 ### Framework versions