Upload 11 files

.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

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "deepset/xlm-roberta-base-squad2",
+  "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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "language": "english",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "name": "XLMRoberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5bb680e931b8447de8e677a9ca3ecd60c040ee49df1a5f7de5db04eaae31cce
+size 2219797189

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc034e6ab004411f4bdcec0c9c3cfca155bec3cd6d3dcd36a33f68d41c59913c
+size 1109883945

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa8f406c6099300f5068cf0f72eb8f307f0e41c2290bac14f2047cab4c82e2bf
+size 13553

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0693c2509ad211fbe4feaa2ad0db25f7ed4fef6ac62c08fb50bd444881b0f678
+size 627

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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 sha256:2bae0289b9bb66bfbf85d834f6313ebd8e40f484df2bd0351539e74a0e4ddeb4
+size 17098081

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "full_tokenizer_file": null,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.3986013986013985,
+  "eval_steps": 500,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.8251748251748252e-05,
+      "loss": 1.7367,
+      "step": 500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.6503496503496503e-05,
+      "loss": 1.6337,
+      "step": 1000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.4755244755244757e-05,
+      "loss": 1.5123,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.300699300699301e-05,
+      "loss": 1.4435,
+      "step": 2000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.125874125874126e-05,
+      "loss": 1.4016,
+      "step": 2500
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.951048951048951e-05,
+      "loss": 1.3019,
+      "step": 3000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.7762237762237765e-05,
+      "loss": 1.0332,
+      "step": 3500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.6013986013986016e-05,
+      "loss": 1.0454,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8580,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 7348665076063200.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03e311329e18cddcb470f85463fcfec46ec955a489b64d9caf3a2d85961ef839
+size 4027