xlm-roberta-siqa-copa

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,111 @@
+---
+license: mit
+base_model: xlm-roberta-large
+tags:
+- generated_from_trainer
+datasets:
+- super_glue
+metrics:
+- accuracy
+model-index:
+- name: result_xlmr_siqa
+  results: []
+---
+
+<!-- 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. -->
+
+# result_xlmr_siqa
+
+This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the super_glue dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4143
+- Accuracy: 0.79
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 44
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0152        | 0.2   | 10   | 1.0207          | 0.77     |
+| 0.001         | 0.4   | 20   | 0.7651          | 0.82     |
+| 0.0013        | 0.6   | 30   | 0.7756          | 0.79     |
+| 0.0012        | 0.8   | 40   | 1.2054          | 0.8      |
+| 0.0005        | 1.0   | 50   | 1.3034          | 0.79     |
+| 0.0008        | 1.2   | 60   | 1.1920          | 0.76     |
+| 0.0138        | 1.4   | 70   | 0.9139          | 0.76     |
+| 0.0003        | 1.6   | 80   | 0.9160          | 0.78     |
+| 0.0001        | 1.8   | 90   | 1.1525          | 0.8      |
+| 0.0085        | 2.0   | 100  | 0.8657          | 0.79     |
+| 0.0033        | 2.2   | 110  | 0.8925          | 0.79     |
+| 0.0055        | 2.4   | 120  | 1.2264          | 0.78     |
+| 0.0014        | 2.6   | 130  | 1.4958          | 0.8      |
+| 0.0031        | 2.8   | 140  | 1.4250          | 0.79     |
+| 0.0138        | 3.0   | 150  | 1.4240          | 0.81     |
+| 0.0304        | 3.2   | 160  | 1.4179          | 0.8      |
+| 0.0           | 3.4   | 170  | 1.4685          | 0.8      |
+| 0.0           | 3.6   | 180  | 1.4897          | 0.8      |
+| 0.0015        | 3.8   | 190  | 1.2689          | 0.8      |
+| 0.0001        | 4.0   | 200  | 1.0355          | 0.78     |
+| 0.0007        | 4.2   | 210  | 1.1339          | 0.77     |
+| 0.0002        | 4.4   | 220  | 1.1915          | 0.79     |
+| 0.0001        | 4.6   | 230  | 1.1300          | 0.8      |
+| 0.001         | 4.8   | 240  | 1.1464          | 0.79     |
+| 0.0001        | 5.0   | 250  | 1.2227          | 0.78     |
+| 0.0           | 5.2   | 260  | 1.3048          | 0.81     |
+| 0.0           | 5.4   | 270  | 1.3418          | 0.79     |
+| 0.0093        | 5.6   | 280  | 1.3442          | 0.78     |
+| 0.0004        | 5.8   | 290  | 1.2721          | 0.8      |
+| 0.0035        | 6.0   | 300  | 1.1852          | 0.77     |
+| 0.0016        | 6.2   | 310  | 1.1745          | 0.77     |
+| 0.0003        | 6.4   | 320  | 1.1138          | 0.8      |
+| 0.0002        | 6.6   | 330  | 1.2342          | 0.79     |
+| 0.0055        | 6.8   | 340  | 1.3594          | 0.79     |
+| 0.0           | 7.0   | 350  | 1.4109          | 0.79     |
+| 0.0           | 7.2   | 360  | 1.4677          | 0.78     |
+| 0.0           | 7.4   | 370  | 1.4951          | 0.77     |
+| 0.0           | 7.6   | 380  | 1.4987          | 0.77     |
+| 0.0004        | 7.8   | 390  | 1.4517          | 0.77     |
+| 0.0           | 8.0   | 400  | 1.4632          | 0.77     |
+| 0.0           | 8.2   | 410  | 1.4825          | 0.78     |
+| 0.0008        | 8.4   | 420  | 1.4486          | 0.79     |
+| 0.0           | 8.6   | 430  | 1.4426          | 0.79     |
+| 0.0           | 8.8   | 440  | 1.4216          | 0.79     |
+| 0.0           | 9.0   | 450  | 1.4166          | 0.79     |
+| 0.0           | 9.2   | 460  | 1.4161          | 0.79     |
+| 0.0           | 9.4   | 470  | 1.4172          | 0.79     |
+| 0.0003        | 9.6   | 480  | 1.4179          | 0.79     |
+| 0.0286        | 9.8   | 490  | 1.4155          | 0.79     |
+| 0.0           | 10.0  | 500  | 1.4143          | 0.79     |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.1.0
+- Datasets 2.14.5
+- Tokenizers 0.14.0

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForMultipleChoice"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4245c1af7791f6198b035405b06f79e0a4adbe61f031c70edcdb3d9e3f23fdcd
+size 2239701870

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:003498ab0695fbf35aedc8bbbae1e20a6033a1b3914e49c6d2fbe1d54d7d93b9
+size 17082786

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e5c01d9438ab3bc8ca33c2d7007768ad2553bb3f0e0dac5beb330668bb8e656
+size 4472