End of training

README.md

@@ -4,9 +4,9 @@ library_name: peft
 tags:
 - axolotl
 - generated_from_trainer
-base_model: Qwen/Qwen2-1.5B-Instruct
+base_model: EleutherAI/pythia-1b
 model-index:
-- name: 99cd3053-a0a6-42be-9cbb-dec95080833b
+- name: 7d2f4acd-ec41-4940-b17f-5ffb945afa24
   results: []
 ---
 
@@ -19,19 +19,19 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.4.1`
 ```yaml
 adapter: lora
-base_model: Qwen/Qwen2-1.5B-Instruct
+base_model: EleutherAI/pythia-1b
 bf16: auto
 datasets:
 - data_files:
-  - ffdd41866ae87277_train_data.json
+  - cf3a451ad5f57e3e_train_data.json
   ds_type: json
   format: custom
-  path: ffdd41866ae87277_train_data.json
+  path: cf3a451ad5f57e3e_train_data.json
   type:
     field: null
-    field_input: null
-    field_instruction: anchor
-    field_output: positive
+    field_input: original_code
+    field_instruction: update_snippet
+    field_output: final_code
     field_system: null
     format: null
     no_input_format: null
@@ -51,7 +51,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: true
 group_by_length: false
-hub_model_id: FatCat87/99cd3053-a0a6-42be-9cbb-dec95080833b
+hub_model_id: FatCat87/7d2f4acd-ec41-4940-b17f-5ffb945afa24
 learning_rate: 0.0002
 load_in_4bit: false
 load_in_8bit: true
@@ -73,7 +73,8 @@ sample_packing: true
 saves_per_epoch: 1
 seed: 701
 sequence_len: 4096
-special_tokens: null
+special_tokens:
+  pad_token: <|endoftext|>
 strict: false
 tf32: false
 tokenizer_type: AutoTokenizer
@@ -82,9 +83,9 @@ val_set_size: 0.1
 wandb_entity: fatcat87-taopanda
 wandb_log_model: null
 wandb_mode: online
-wandb_name: 99cd3053-a0a6-42be-9cbb-dec95080833b
+wandb_name: 7d2f4acd-ec41-4940-b17f-5ffb945afa24
 wandb_project: subnet56
-wandb_runid: 99cd3053-a0a6-42be-9cbb-dec95080833b
+wandb_runid: 7d2f4acd-ec41-4940-b17f-5ffb945afa24
 wandb_watch: null
 warmup_ratio: 0.05
 weight_decay: 0.0
@@ -94,12 +95,12 @@ xformers_attention: null
 
 </details><br>
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/fatcat87-taopanda/subnet56/runs/wyyii4b8)
-# 99cd3053-a0a6-42be-9cbb-dec95080833b
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/fatcat87-taopanda/subnet56/runs/xl5hydog)
+# 7d2f4acd-ec41-4940-b17f-5ffb945afa24
 
-This model is a fine-tuned version of [Qwen/Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct) on the None dataset.
+This model is a fine-tuned version of [EleutherAI/pythia-1b](https://huggingface.co/EleutherAI/pythia-1b) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.6208
+- Loss: 0.0526
 
 ## Model description
 
@@ -129,14 +130,17 @@ The following hyperparameters were used during training:
 - total_eval_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 5
 - num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 4.0547        | 0.3636 | 1    | 3.6717          |
-| 3.4577        | 0.7273 | 2    | 3.6208          |
+| 4.2604        | 0.0075 | 1    | 0.9479          |
+| 1.8401        | 0.2547 | 34   | 0.1403          |
+| 0.1249        | 0.5094 | 68   | 0.0728          |
+| 0.0707        | 0.7640 | 102  | 0.0526          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff78f62537f5dc5984f1b41375b2f39fbb14bab4fa794d8f555eb8d86d7397a2
-size 147859242
+oid sha256:b8db515f80c8038a6973cc43b2aa9105be8eb4b099165909ef384b9649c3c562
+size 67155978