Finished finetuning grade 12

README.md

@@ -14,11 +14,12 @@ 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/r287j4vq)
 [<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/o968fmfk)
+[<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/vwj89krn)
 # 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: 0.7668
+- Loss: 0.8006
 
 ## Model description
 
@@ -49,11 +50,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.8012        | 1.0   | 513  | 0.7696          |
-| 0.7939        | 2.0   | 1026 | 0.7686          |
-| 0.7904        | 3.0   | 1539 | 0.7664          |
-| 0.7875        | 4.0   | 2052 | 0.7662          |
-| 0.7848        | 5.0   | 2565 | 0.7668          |
+| 0.8367        | 1.0   | 612  | 0.8025          |
+| 0.8301        | 2.0   | 1224 | 0.8006          |
+| 0.8267        | 3.0   | 1836 | 0.8000          |
+| 0.8225        | 4.0   | 2448 | 0.7992          |
+| 0.8202        | 5.0   | 3060 | 0.7985          |
+| 0.8182        | 6.0   | 3672 | 0.8006          |
 
 
 ### Framework versions

gpt2-grade-12-finetuned/adapter_config.json

@@ -3,6 +3,8 @@
   "auto_mapping": null,
   "base_model_name_or_path": "openai-community/gpt2",
   "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,6 +13,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 32,
+  "lora_bias": false,
   "lora_dropout": 0.01,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -21,9 +24,9 @@
   "revision": null,
   "target_modules": [
     "c_proj",
-    "c_attn",
     "lm_head",
-    "c_fc"
+    "c_fc",
+    "c_attn"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

gpt2-grade-12-finetuned/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01963c90bb021031f097a6d7d17b07ec66776454ea5b272f7243438d7f4408bb
-size 83581271
+oid sha256:bea3405399a11d97e6c9ce431cf1bab77247f83dde74a3055d84e88d16239a2c
+size 160776023

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4be9e611a35b1e573c83c06b0201bb0f3bd80a6f6827daaa90cc1dcc00306ad8
+oid sha256:c67f657783f5b0ada1deacd98b03b4f6f547951c16b9f8762b68a3dc20cc57c1
 size 5496