Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,81 @@
+---
+library_name: transformers
+license: mit
+base_model: roberta-base
+metrics:
+- accuracy
+model-index:
+- name: roberta-base-unified-mcqa-v2
+  results: []
+datasets:
+- pszemraj/unified-mcqa
+language:
+- en
+---
+
+# roberta-base-unified-mcqa: 4-choice
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the [unified-mcqa](https://huggingface.co/datasets/pszemraj/unified-mcqa) dataset (4 choice config).
+It achieves the following results on the evaluation set:
+- Loss: 0.5534
+- Accuracy: 0.8030
+- Num Input Tokens Seen: 2785906024
+
+## Intended uses & limitations
+
+goal is to see if training on general MCQ data helps A) GLUE evals B) results in a better base model than just the MLM output
+
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 69
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 300
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Accuracy | Input Tokens Seen |
+|:-------------:|:------:|:-----:|:---------------:|:--------:|:-----------------:|
+| 0.9531        | 0.1189 | 1000  | 0.8328          | 0.6370   | 111443072         |
+| 0.8363        | 0.2377 | 2000  | 0.7918          | 0.6720   | 222788512         |
+| 0.7689        | 0.3566 | 3000  | 0.7457          | 0.6940   | 334128480         |
+| 0.8036        | 0.4754 | 4000  | 0.7429          | 0.6940   | 445377152         |
+| 0.7349        | 0.5943 | 5000  | 0.7252          | 0.7050   | 556965376         |
+| 0.7721        | 0.7131 | 6000  | 0.7102          | 0.7130   | 668132544         |
+| 0.6532        | 0.8320 | 7000  | 0.6958          | 0.7230   | 779523488         |
+| 0.6842        | 0.9509 | 8000  | 0.6609          | 0.7230   | 891149056         |
+| 0.576         | 1.0696 | 9000  | 0.6887          | 0.7360   | 1002658088        |
+| 0.6265        | 1.1885 | 10000 | 0.6730          | 0.7520   | 1114316936        |
+| 0.5256        | 1.3074 | 11000 | 0.6860          | 0.7550   | 1225691432        |
+| 0.5701        | 1.4262 | 12000 | 0.6487          | 0.7530   | 1337160232        |
+| 0.4803        | 1.5451 | 13000 | 0.6306          | 0.7580   | 1448480392        |
+| 0.5155        | 1.6639 | 14000 | 0.5834          | 0.7800   | 1560022824        |
+| 0.5221        | 1.7828 | 15000 | 0.6005          | 0.7850   | 1671544872        |
+| 0.4736        | 1.9016 | 16000 | 0.5796          | 0.7820   | 1782692648        |
+| 0.3577        | 2.0204 | 17000 | 0.5753          | 0.7870   | 1893957800        |
+| 0.3656        | 2.1393 | 18000 | 0.6014          | 0.7930   | 2005395624        |
+| 0.3722        | 2.2582 | 19000 | 0.6108          | 0.7900   | 2117111816        |
+| 0.3599        | 2.3770 | 20000 | 0.5826          | 0.8000   | 2228698440        |
+| 0.2723        | 2.4959 | 21000 | 0.5845          | 0.7910   | 2340181736        |
+| 0.2817        | 2.6147 | 22000 | 0.5732          | 0.7840   | 2451744808        |
+| 0.2402        | 2.7336 | 23000 | 0.5544          | 0.7980   | 2563194408        |
+| 0.3318        | 2.8524 | 24000 | 0.5542          | 0.8000   | 2674427656        |
+| 0.272         | 2.9713 | 25000 | 0.5534          | 0.8030   | 2785906024        |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c670f4d8a1141c6c6dc6c8d56eb1f00c7d13252c07c844e29265fee5e394070e
+size 498609724

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfda63a457c68df9de985de4dae7cd7b1d61d7fd18043b98c88b22a59de51309
+size 5432