Finished finetuning grade 10

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/kh94yqwi)
+[<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)
 # 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: 0.5755
+- Loss: 0.6644
 
 ## Model description
 
@@ -48,11 +48,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.6211        | 1.0   | 898  | 0.5805          |
-| 0.6157        | 2.0   | 1796 | 0.5763          |
-| 0.6128        | 3.0   | 2694 | 0.5742          |
-| 0.6102        | 4.0   | 3592 | 0.5738          |
-| 0.6073        | 5.0   | 4490 | 0.5755          |
+| 0.7118        | 1.0   | 1037 | 0.6638          |
+| 0.7063        | 2.0   | 2074 | 0.6644          |
 
 
 ### Framework versions

gpt2-grade-10-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-10-finetuned/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051b38fb533f76e3eb14f38141c8a0eaf87b17b3053aa9ee0a9ef405cb641a9b
-size 83581271
+oid sha256:6ff6c5d24afbe312ccc22df2f42497656da21a9e0a0914460aa30e0af731d2ea
+size 160776023

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d556b294403022e0ca243b0dbf1041d9e52799130066df32ede03fd5c34518a4
+oid sha256:90f77b0e1e8e233f5185430fb2f4c16e29d3bd3ab9d86b3fe906697846f8a7c1
 size 5496