add model

README.md

@@ -0,0 +1,62 @@
+---
+metrics:
+- accuracy
+
+model-index:
+- name: c4-aristo-roberta-large
+---
+
+<!-- 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. -->
+
+# c4-aristo-roberta-large
+
+This model was trained from scratch on an unkown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0332
+- Accuracy: 0.7370
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.8204        | 1.0   | 140  | 0.7246          | 0.7171   |
+| 0.5512        | 2.0   | 280  | 0.7441          | 0.7312   |
+| 0.3437        | 3.0   | 420  | 0.8940          | 0.7363   |
+| 0.291         | 4.0   | 560  | 1.0332          | 0.7370   |
+
+
+### Framework versions
+
+- Transformers 4.6.1
+- Pytorch 1.10.0.dev20210620+cu113
+- Datasets 1.6.2
+- Tokenizers 0.10.2

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "LIAMF-USP/roberta-large-finetuned-race",
+  "architectures": [
+    "RobertaForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": true,
+  "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",
+  "total_flos": 1502266556732252160,
+  "transformers_version": "4.6.1",
+  "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 sha256:0fa6e109a60855100db51512c6c3b5f88d70c576fab075dc6a57ec9711feec2d
+size 811949