Finished training grade 2

README.md

@@ -12,12 +12,12 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 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/8rbeln7q)
+[<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/3485jyyq)
 # 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: 0.8159
+- Loss: 1.0508
 
 ## Model description
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.6031        | 1.0   | 235  | 0.9419          |
-| 0.9602        | 2.0   | 470  | 0.8340          |
-| 0.8961        | 3.0   | 705  | 0.8159          |
+| 3.3444        | 1.0   | 235  | 1.1826          |
+| 1.1887        | 2.0   | 470  | 1.0908          |
+| 1.1229        | 3.0   | 705  | 1.0508          |
 
 
 ### Framework versions

gpt2-2-12-evens/adapter_config.json

@@ -21,8 +21,8 @@
   "revision": null,
   "target_modules": [
     "lm_head",
-    "c_fc",
     "c_proj",
+    "c_fc",
     "c_attn"
   ],
   "task_type": "CAUSAL_LM",

gpt2-2-12-evens/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b227ce53d5283b698fafb55f8148df7cc3436f06c7ea59b313cd718720dbb64
-size 83581271
+oid sha256:41a34e760ff88cf6f968c81d5b0f38419fe02bb90e85d7bae0475a055beec28d
+size 77196026

gpt2-grade-2-4module/adapter_config.json

@@ -21,8 +21,8 @@
   "revision": null,
   "target_modules": [
     "lm_head",
-    "c_fc",
     "c_proj",
+    "c_fc",
     "c_attn"
   ],
   "task_type": "CAUSAL_LM",

gpt2-grade-2-4module/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ec736f928b431835fc6ef2ef94d3b706b5c295314168ecdf2d317eafc6277b7
+oid sha256:d7f6165eb800c7fd3729672231fa11f05cae4fbb277109032568928835f01df2
 size 83582999

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c3b75e7e85a481bb028af26ba1febe7407797125ed189faec3e6a1b97c65ee4
+oid sha256:1421b9a0bf4eb4125ff76416ddfe65171da7393d179610cc86b401a926e4e375
 size 5240