Finished finetuning grade 5

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/1mkbeo5j)
+[<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/vd7wa4iw)
 # 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: 0.3883
+- Loss: 0.5178
 
 ## Model description
 
@@ -48,16 +49,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.412         | 1.0   | 597  | 0.3916          |
-| 0.406         | 2.0   | 1194 | 0.3891          |
-| 0.4023        | 3.0   | 1791 | 0.3865          |
-| 0.3999        | 4.0   | 2388 | 0.3895          |
-| 0.3983        | 5.0   | 2985 | 0.3886          |
-| 0.3964        | 6.0   | 3582 | 0.3884          |
-| 0.3949        | 7.0   | 4179 | 0.3876          |
-| 0.3944        | 8.0   | 4776 | 0.3870          |
-| 0.3935        | 9.0   | 5373 | 0.3879          |
-| 0.3934        | 10.0  | 5970 | 0.3883          |
+| 0.546         | 1.0   | 775  | 0.5205          |
+| 0.5405        | 2.0   | 1550 | 0.5186          |
+| 0.5368        | 3.0   | 2325 | 0.5162          |
+| 0.5338        | 4.0   | 3100 | 0.5176          |
+| 0.5322        | 5.0   | 3875 | 0.5189          |
+| 0.5304        | 6.0   | 4650 | 0.5179          |
+| 0.5284        | 7.0   | 5425 | 0.5184          |
+| 0.5278        | 8.0   | 6200 | 0.5176          |
+| 0.5276        | 9.0   | 6975 | 0.5177          |
+| 0.527         | 10.0  | 7750 | 0.5178          |
 
 
 ### Framework versions

gpt2-grade-5-finetuned/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "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,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn",
+    "c_fc",
+    "lm_head",
+    "c_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

gpt2-grade-5-finetuned/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ca0e1c4334a463fa63c8f116f298e2e46287a70bb485bba6168d4cf35703e27
+size 160776023

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce30d7e87d05d01b405761335c6d37c16185ec7a498cae8a2ee67a4df04829c1
+oid sha256:73d8229af7e9a6c1c4932cebc80c86e66cb19d5f222f394f37cbd4a55f5c82de
 size 5368