model

trained_xlnet_model/config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "XLNetForQuestionAnswering"
+  ],
+  "attn_type": "bi",
+  "bi_data": false,
+  "bos_token_id": 1,
+  "clamp_len": -1,
+  "d_head": 64,
+  "d_inner": 3072,
+  "d_model": 768,
+  "dropout": 0.1,
+  "end_n_top": 5,
+  "eos_token_id": 2,
+  "ff_activation": "gelu",
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-12,
+  "mem_len": null,
+  "model_type": "xlnet",
+  "n_head": 12,
+  "n_layer": 12,
+  "pad_token_id": 5,
+  "reuse_len": null,
+  "same_length": false,
+  "start_n_top": 5,
+  "summary_activation": "tanh",
+  "summary_last_dropout": 0.1,
+  "summary_type": "last",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 250
+    }
+  },
+  "untie_r": true,
+  "vocab_size": 32000
+}

trained_xlnet_model/model_args.json

@@ -0,0 +1 @@
+{"doc_stride": 128, "max_query_length": 64, "n_best_size": 20, "max_answer_length": 100, "null_score_diff_threshold": 0.0, "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "do_lower_case": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "correct", "early_stopping_metric_minimize": false, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 8, "evaluate_during_training": false, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "fp16": true, "fp16_opt_level": "O1", "gradient_accumulation_steps": 8, "learning_rate": 2e-05, "logging_steps": 50, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 384, "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "num_train_epochs": 5, "output_dir": "outputs/", "overwrite_output_dir": true, "process_count": 2, "reprocess_input_data": false, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_steps": 2000, "silent": false, "tensorboard_dir": null, "train_batch_size": 2, "use_cached_eval_features": false, "use_early_stopping": true, "use_multiprocessing": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 2444, "weight_decay": 0, "evaluate_during_traing": true, "model_name": "xlnet-base-cased", "model_type": "xlnet"}

trained_xlnet_model/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e1a9bfb6d88230a8cf0059307b058e25ffec6498a41354392955945b59d778
+size 326

trained_xlnet_model/special_tokens_map.json

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

trained_xlnet_model/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
+size 798011

trained_xlnet_model/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false}

trained_xlnet_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd1ad682895e0e7c41e4535b4be0a97efd9af50599ace2bfa504c2b7b59f0e80
+size 1635