upload model files

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "xlnet-large-cased",
+  "architectures": [
+    "XLNetForTokenClassification"
+  ],
+  "attn_type": "bi",
+  "bi_data": false,
+  "bos_token_id": 1,
+  "clamp_len": -1,
+  "d_head": 64,
+  "d_inner": 4096,
+  "d_model": 1024,
+  "dropout": 0.1,
+  "end_n_top": 5,
+  "eos_token_id": 2,
+  "ff_activation": "gelu",
+  "id2label": {
+    "0": "O",
+    "1": "B-feature",
+    "2": "I-feature"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-feature": 1,
+    "I-feature": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "mem_len": null,
+  "model_type": "xlnet",
+  "n_head": 16,
+  "n_layer": 24,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "untie_r": true,
+  "use_mems_eval": true,
+  "use_mems_train": false,
+  "vocab_size": 32000
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e2faa41336c927c289261e2147f320bdf4b19a5c75013f9fa48e5b7504eb7e0
+size 2882410053

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:539a89dc5c71ed4b8ac22b235d8a2d34851a0d7522ed11ce380e836d4ac69357
+size 1441225277

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0edd2ceb30d6babc1f3e5958a8417a2569537b5352b92d741a4661c167a82c5
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a81b9e64a6d36ab9d27ca33efaa732434676daf622cfdf89ee1179762e733965
+size 627

special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<cls>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

spiece.model

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

tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<cls>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "keep_accents": false,
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "<sep>",
+  "tokenizer_class": "XLNetTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": 0.004898133222013712,
+  "best_model_checkpoint": "data/train-test///model/checkpoint-3351",
+  "epoch": 1.0,
+  "global_step": 3351,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.850790808713817e-05,
+      "loss": 0.1149,
+      "step": 500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.7015816174276335e-05,
+      "loss": 0.0198,
+      "step": 1000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.5523724261414504e-05,
+      "loss": 0.0101,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.4031632348552673e-05,
+      "loss": 0.0063,
+      "step": 2000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.253954043569084e-05,
+      "loss": 0.0067,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.1047448522829008e-05,
+      "loss": 0.0068,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": null,
+      "eval_f1": 0.9943977591036415,
+      "eval_loss": 0.004898133222013712,
+      "eval_precision": 0.9943977591036415,
+      "eval_recall": 0.9943977591036415,
+      "eval_runtime": 1.5284,
+      "eval_samples_per_second": 634.661,
+      "eval_steps_per_second": 79.823,
+      "step": 3351
+    }
+  ],
+  "max_steps": 6702,
+  "num_train_epochs": 2,
+  "total_flos": 2597776456686000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d97d2a8f287fdc8b9e66604d38c2f4463bc68b55cef78f20bc93ec03f39e104
+size 3963