Finished finetuning grade 3

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/gd6mkxtp)
+[<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/s2qn3a6p)
 # text-simplification
 
 This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3641
+- Loss: 0.3906
 
 ## Model description
 
@@ -48,9 +49,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.4017        | 1.0   | 469  | 0.3665          |
-| 0.3951        | 2.0   | 938  | 0.3640          |
-| 0.3907        | 3.0   | 1407 | 0.3641          |
+| 0.4126        | 1.0   | 597  | 0.3930          |
+| 0.406         | 2.0   | 1194 | 0.3901          |
+| 0.4025        | 3.0   | 1791 | 0.3886          |
+| 0.4003        | 4.0   | 2388 | 0.3906          |
 
 
 ### Framework versions

gpt2-grade-3-finetuned/adapter_config.json

@@ -23,10 +23,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "c_attn",
-    "c_fc",
     "lm_head",
-    "c_proj"
+    "c_proj",
+    "c_fc",
+    "c_attn"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

gpt2-grade-3-finetuned/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f3aa3e03bd1accebd9e8e9458423a78b09f5e7aa1a77d74ec7452e3fd2972f9
+oid sha256:a7eae108f5b1d9a72aa5cf696a5fd0b6e0654ccb7b638b85ad96cc374244c6eb
 size 160776023

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a11b1d4789c0a45c02b736aef3ae5657d38b50123ac84144adff993f3cf8e80
+oid sha256:722fd58c5dbb5d2a153e46ce88198a5d9852e0f997739efe9f0f9db27b71fa1f
 size 5496