Add model

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "deepset/xlm-roberta-base-squad2",
+  "architectures": [
+    "XLMRobertaForQuestionAnswering"
+  ],
+  "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": 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",
+  "transformers_version": "4.5.1",
+  "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:dd56b10dd337de986461f7b467abee0c807bf0af1b5fdad9914c944b284bd552
+size 2219752165

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbc68789cd1ffe438e3ebc686114959d5180f65f9b5119bc99caa970bcdaac29
+size 1109903089

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:412b0fc05e1c02c96dfeddd7e9df4316ca3f1fab4acc076db2ca6745959a2d84
+size 623

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

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"}, "do_lower_case": false, "model_max_length": 512, "full_tokenizer_file": null, "special_tokens_map_file": "/root/.cache/huggingface/transformers/b285d730ad6193f7e96b41152fbc5fb05620f0961f6f513e2d36868dfb1eb2a7.0dc5b1041f62041ebbd23b1297f2f573769d5c97d8b7c28180ec86b8f6185aa8", "name_or_path": "deepset/xlm-roberta-base-squad2"}

trainer_state.json

@@ -0,0 +1,30 @@
+{
+  "best_metric": 0.3263927400112152,
+  "best_model_checkpoint": "chaii-qa/checkpoint-344",
+  "epoch": 1.9971014492753625,
+  "global_step": 344,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.33803388476371765,
+      "eval_runtime": 17.7191,
+      "eval_samples_per_second": 69.586,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.3263927400112152,
+      "eval_runtime": 18.0251,
+      "eval_samples_per_second": 68.405,
+      "step": 344
+    }
+  ],
+  "max_steps": 344,
+  "num_train_epochs": 2,
+  "total_flos": 7045872848796672.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d7f119699e06cea76a318102aa95cddd01446805686075b7f3856e91b48f5d
+size 2351