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/c0krnbs6)
+[<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)
 # text-simplification
 
-This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the None dataset.
+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: 1.0117
+- Loss: 0.8159
 
 ## Model description
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.5853        | 1.0   | 3022 | 1.1768          |
-| 1.1909        | 2.0   | 6044 | 1.0391          |
-| 1.1016        | 3.0   | 9066 | 1.0117          |
+| 1.6031        | 1.0   | 235  | 0.9419          |
+| 0.9602        | 2.0   | 470  | 0.8340          |
+| 0.8961        | 3.0   | 705  | 0.8159          |
 
 
 ### Framework versions

gpt2-2-12-evens/adapter_config.json

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

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 sha256:351456e7db855ce5b7c7c24fde5ff695a3093f4a9e7105608faa201f37ef6ed7
+size 77196026

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

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "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_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": [
+    "lm_head",
+    "c_fc",
+    "c_proj",
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ec736f928b431835fc6ef2ef94d3b706b5c295314168ecdf2d317eafc6277b7
+size 83582999

tokenizer.json

@@ -1,19 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1024,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": "BatchLongest",
-    "direction": "Left",
-    "pad_to_multiple_of": null,
-    "pad_id": 50256,
-    "pad_type_id": 0,
-    "pad_token": "<|endoftext|>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 50256,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95c4145301f6855168ba51d1c54c056784e2fac3fecaf590eb48f5512969d63f
+oid sha256:8c3b75e7e85a481bb028af26ba1febe7407797125ed189faec3e6a1b97c65ee4
 size 5240