Finished 2-12 grades: evens pretraining

README.md

@@ -13,11 +13,12 @@ model-index:
 should probably proofread and complete it, then remove this comment. -->
 
 [<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/uds/Graded%20text%20simplification%20training/runs/ln6u9a0b)
+[<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/uds/Graded%20text%20simplification%20training/runs/8mvg4ib5)
 # text-simplification
 
 This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9731
+- Loss: 0.9653
 
 ## Model description
 
@@ -48,11 +49,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 1.3985        | 1.0   | 4932  | 1.0293          |
-| 1.0529        | 2.0   | 9864  | 0.9585          |
-| 1.0185        | 3.0   | 14796 | 0.9590          |
-| 1.0209        | 4.0   | 19728 | 0.9688          |
-| 1.0245        | 5.0   | 24660 | 0.9731          |
+| 1.5549        | 1.0   | 3022  | 1.1338          |
+| 1.1431        | 2.0   | 6044  | 1.0146          |
+| 1.0544        | 3.0   | 9066  | 0.9736          |
+| 1.0264        | 4.0   | 12088 | 0.9658          |
+| 1.0198        | 5.0   | 15110 | 0.9653          |
 
 
 ### Framework versions

gpt2-2-12-evens/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "c_attn",
     "lm_head",
     "c_proj",
-    "c_fc",
-    "c_attn"
+    "c_fc"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

gpt2-2-12-evens/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41a34e760ff88cf6f968c81d5b0f38419fe02bb90e85d7bae0475a055beec28d
-size 77196026
+oid sha256:4b31e8fcd9c3000cfe7def36e0c3bd86d4a47c0a03656b9f085bf75401ba1275
+size 83581271

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72504053dc743f325c3b6583886221a4c2b65fc8c76f4faf1fb495876dd69f9f
+oid sha256:1d79666918805aecf3883a18b43198c57b9f68e3c24a82121fe00e42190e5a30
 size 5240