Finished finetuning grade 4

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/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)
+[<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/qz6551rc)
 # 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: 0.3906
+- Loss: 0.4367
 
 ## Model description
 
@@ -49,10 +50,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 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          |
+| 0.4643        | 1.0   | 1174 | 0.4399          |
+| 0.4581        | 2.0   | 2348 | 0.4360          |
+| 0.4547        | 3.0   | 3522 | 0.4342          |
+| 0.452         | 4.0   | 4696 | 0.4367          |
 
 
 ### Framework versions

gpt2-grade-4-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",
@@ -20,10 +23,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "c_proj",
-    "c_attn",
     "lm_head",
-    "c_fc"
+    "c_proj",
+    "c_fc",
+    "c_attn"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

gpt2-grade-4-finetuned/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5961a8c88a0e5b7bf8b2cd087253ef54bd22bd94af12136eefba86a912ede5
-size 83581271
+oid sha256:346dc136246e083d64b72c2b40cc3ec08ab10bca922abec0713f1211519a54bb
+size 160776023

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:722fd58c5dbb5d2a153e46ce88198a5d9852e0f997739efe9f0f9db27b71fa1f
+oid sha256:f1b97724ceb70fca675f96eca43940412e55a799ca8009715a5e4327361f3363
 size 5496