add model

.gitignore

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

README.md

@@ -0,0 +1,68 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model-index:
+- name: xlm-roberta-large-finetuned-squad
+  results:
+  - task:
+      name: Question Answering
+      type: question-answering
+    dataset:
+      name: squad
+      type: squad
+      args: default
+---
+
+<!-- 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. -->
+
+# xlm-roberta-large-finetuned-squad
+
+This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the squad dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0350
+
+## 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: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.6093        | 1.0   | 620  | 1.0023          |
+| 0.849         | 2.0   | 1240 | 0.9449          |
+| 0.6693        | 3.0   | 1860 | 1.0350          |
+
+
+### Framework versions
+
+- Transformers 4.10.0
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "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": "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": "4.10.0",
+  "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 sha256:7749dd404137e1f3749e1491da9358549f08ada34b249c350f30595a58640587
+size 2235534897

runs/Sep04_05-15-32_921c47264a6e/1630732916.3439543/events.out.tfevents.1630732916.921c47264a6e.4506.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da74b5b88d66a80817473672afb0863ced3d7be8ade5270475af9739e220baf1
+size 4200

runs/Sep04_05-15-32_921c47264a6e/1630732941.179093/events.out.tfevents.1630732941.921c47264a6e.4506.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc1205adda208e9d3716527691e684aaf80deca3fcae9d49c9233a720a65112c
+size 4200

runs/Sep04_05-15-32_921c47264a6e/events.out.tfevents.1630732916.921c47264a6e.4506.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a69169ac352e23b615e8276ab854239587ce5d789724129e44c7b4e8a683afe
+size 3039

runs/Sep04_05-15-32_921c47264a6e/events.out.tfevents.1630732941.921c47264a6e.4506.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a23714aefccd77d304ad55dc3e7b5d6cefca179fdd5fe641c1b51d3d105d2d2c
+size 3039

runs/Sep04_05-28-33_921c47264a6e/1630733321.9114687/events.out.tfevents.1630733321.921c47264a6e.4854.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a1b9dc00e9d6510de57d7ec9ba4fb4a49516bc28069104a202c01e6da995acf
+size 4200

runs/Sep04_05-28-33_921c47264a6e/events.out.tfevents.1630733321.921c47264a6e.4854.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:502ec408f3ecbf2e1647618fa19c8564814b32aa92ebe3ffad9d3f624c8d4e7d
+size 3039

runs/Sep04_05-38-27_921c47264a6e/1630733916.6186223/events.out.tfevents.1630733916.921c47264a6e.5079.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:981a74abb7d9d12abf498af2a01d9be75dbdf4d75880264332b55a27eca63419
+size 4200

runs/Sep04_05-38-27_921c47264a6e/events.out.tfevents.1630733916.921c47264a6e.5079.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c471e3719cd14917d700305f67acc49d61e27f9dc030f25b9f57b6068dc179
+size 4677

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-large", "tokenizer_class": "XLMRobertaTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:529a20ae434969a771808684b826509635bfd1a0788f33e8574d68d2631fd787
+size 2671