Training in progress, epoch 9

config.json

@@ -1,15 +1,19 @@
 {
-  "_name_or_path": "roberta-base",
+  "_name_or_path": "xlnet-base-cased",
   "architectures": [
-    "RobertaForTokenClassification"
+    "XLNetForTokenClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
+  "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,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "ff_activation": "gelu",
   "id2label": {
     "0": "O",
     "1": "B-DatasetName",
@@ -28,7 +32,6 @@
     "14": "I-TaskName"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "B-DatasetName": 1,
     "B-HyperparameterName": 3,
@@ -46,16 +49,29 @@
     "I-TaskName": 14,
     "O": 0
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "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
+    }
+  },
   "torch_dtype": "float32",
   "transformers_version": "4.34.1",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 50265
+  "untie_r": true,
+  "use_mems_eval": true,
+  "use_mems_train": false,
+  "vocab_size": 32000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:157793b98c4c04637b466fc238a6b83e8ee3bc5065472b22b3319559c46ce1ed
-size 496335078
+oid sha256:95347e5ce82dac1555e5b632d52feb9b27b0fb00a7b5ac0815ddc3088caaf36d
+size 466989130

special_tokens_map.json

@@ -1,6 +1,10 @@
 {
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
   "bos_token": "<s>",
-  "cls_token": "<s>",
+  "cls_token": "<cls>",
   "eos_token": "</s>",
   "mask_token": {
     "content": "<mask>",
@@ -10,6 +14,6 @@
     "single_word": false
   },
   "pad_token": "<pad>",
-  "sep_token": "</s>",
+  "sep_token": "<sep>",
   "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,18 +1,17 @@
 {
-  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
-      "content": "<pad>",
+      "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -20,38 +19,75 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "3": {
-      "content": "<unk>",
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
+    "6": {
       "content": "<mask>",
       "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "7": {
+      "content": "<eod>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
+  "cls_token": "<cls>",
+  "do_lower_case": false,
   "eos_token": "</s>",
-  "errors": "replace",
+  "keep_accents": false,
   "mask_token": "<mask>",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
+  "remove_space": true,
+  "sep_token": "<sep>",
+  "tokenizer_class": "XLNetTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d05cbdb3ac5b98eff888b7729607f859802eb617fa67d972ddf85b27c1bd1982
+oid sha256:7f6ae9fc25fceece0da7c457194e4b0f540dbe6fcee22e5fd084ce9c3e121d06
 size 4472