End of training

README.md

@@ -1,12 +1,11 @@
 ---
-license: apache-2.0
 library_name: peft
 tags:
 - axolotl
 - generated_from_trainer
-base_model: unsloth/Qwen2.5-Math-1.5B
+base_model: EleutherAI/pythia-14m
 model-index:
-- name: 7a6a1ed8-c5e1-4345-8b9e-3d6d127a456b
+- name: 9c40171a-a397-4067-8fba-d0d97f9c3fb5
   results: []
 ---
 
@@ -19,19 +18,19 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.4.1`
 ```yaml
 adapter: lora
-base_model: unsloth/Qwen2.5-Math-1.5B
+base_model: EleutherAI/pythia-14m
 bf16: auto
 datasets:
 - data_files:
-  - 403a8e6e3b0b2154_train_data.json
+  - 7cecb5f0cbdfe3e6_train_data.json
   ds_type: json
   format: custom
-  path: 403a8e6e3b0b2154_train_data.json
+  path: 7cecb5f0cbdfe3e6_train_data.json
   type:
     field: null
-    field_input: ''
-    field_instruction: title
-    field_output: text
+    field_input: product_description
+    field_instruction: query
+    field_output: product_title
     field_system: null
     format: null
     no_input_format: null
@@ -51,7 +50,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: true
 group_by_length: false
-hub_model_id: FatCat87/7a6a1ed8-c5e1-4345-8b9e-3d6d127a456b
+hub_model_id: FatCat87/9c40171a-a397-4067-8fba-d0d97f9c3fb5
 learning_rate: 0.0002
 load_in_4bit: false
 load_in_8bit: true
@@ -73,7 +72,8 @@ 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 +82,9 @@ val_set_size: 0.1
 wandb_entity: fatcat87-taopanda
 wandb_log_model: null
 wandb_mode: online
-wandb_name: 7a6a1ed8-c5e1-4345-8b9e-3d6d127a456b
+wandb_name: 9c40171a-a397-4067-8fba-d0d97f9c3fb5
 wandb_project: subnet56
-wandb_runid: 7a6a1ed8-c5e1-4345-8b9e-3d6d127a456b
+wandb_runid: 9c40171a-a397-4067-8fba-d0d97f9c3fb5
 wandb_watch: null
 warmup_ratio: 0.05
 weight_decay: 0.0
@@ -94,12 +94,12 @@ 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/nthl6i6b)
-# 7a6a1ed8-c5e1-4345-8b9e-3d6d127a456b
+[<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/trubmlay)
+# 9c40171a-a397-4067-8fba-d0d97f9c3fb5
 
-This model is a fine-tuned version of [unsloth/Qwen2.5-Math-1.5B](https://huggingface.co/unsloth/Qwen2.5-Math-1.5B) on the None dataset.
+This model is a fine-tuned version of [EleutherAI/pythia-14m](https://huggingface.co/EleutherAI/pythia-14m) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9896
+- Loss: 8.5142
 
 ## Model description
 
@@ -136,10 +136,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.2602        | 0.0128 | 1    | 2.2242          |
-| 2.0943        | 0.2564 | 20   | 2.1294          |
-| 2.1169        | 0.5128 | 40   | 2.0361          |
-| 2.0083        | 0.7692 | 60   | 1.9896          |
+| 13.9967       | 0.0161 | 1    | 8.9785          |
+| 9.964         | 0.2581 | 16   | 8.6915          |
+| 9.8983        | 0.5161 | 32   | 8.5281          |
+| 9.8733        | 0.7742 | 48   | 8.5142          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56b8107f903a5a5fa6cef8e459efb96524da590d098420b279ebd756ef996b3e
-size 147859242
+oid sha256:e29cbd835f01bfb35a6eec50c1f83f909634654399580da23d2564275a1a445d
+size 1590462