add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,74 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- commonsense_qa
+metrics:
+- accuracy
+model_index:
+- name: aristo-roberta-finetuned-csqa
+  results:
+  - dataset:
+      name: commonsense_qa
+      type: commonsense_qa
+      args: default
+    metric:
+      name: Accuracy
+      type: accuracy
+      value: 0.7305487394332886
+---
+
+<!-- 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. -->
+
+# aristo-roberta-finetuned-csqa
+
+This model is a fine-tuned version of [LIAMF-USP/aristo-roberta](https://huggingface.co/LIAMF-USP/aristo-roberta) on the commonsense_qa dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2187
+- Accuracy: 0.7305
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.131         | 1.0   | 609  | 0.7109          | 0.7232   |
+| 0.6957        | 2.0   | 1218 | 0.6912          | 0.7346   |
+| 0.459         | 3.0   | 1827 | 0.8364          | 0.7305   |
+| 0.3063        | 4.0   | 2436 | 1.0595          | 0.7322   |
+| 0.2283        | 5.0   | 3045 | 1.2187          | 0.7305   |
+
+
+### Framework versions
+
+- Transformers 4.9.0
+- Pytorch 1.9.0
+- Datasets 1.10.2
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "LIAMF-USP/aristo-roberta",
+  "architectures": [
+    "RobertaForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "total_flos": 1502266556732252160,
+  "transformers_version": "4.9.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc684b34fd667b7e0a20d605ed11dfc71faf473d2fa7b25e1a0cade7125829f6
+size 1421607277

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": "./results_model/bert-base-uncased/special_tokens_map.json", "name_or_path": "LIAMF-USP/aristo-roberta", "tokenizer_class": "RobertaTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d1902b4998d80c5317163db6984f95d3e6deb401fcab9bd5de2ba6cd9ed9df
+size 2671