Training in progress, epoch 1

config.json

@@ -1,19 +1,13 @@
 {
-  "_name_or_path": "xlnet/xlnet-large-cased",
   "architectures": [
-    "XLNetForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "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",
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -22,6 +16,7 @@
     "4": "LABEL_4"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -30,29 +25,16 @@
     "LABEL_4": 4
   },
   "layer_norm_eps": 1e-12,
-  "mem_len": null,
-  "model_type": "xlnet",
-  "n_head": 16,
-  "n_layer": 24,
-  "pad_token_id": 5,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "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": "4.49.0",
-  "untie_r": true,
-  "use_mems_eval": true,
-  "use_mems_train": false,
-  "vocab_size": 32000
+  "transformers_version": "4.52.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48dcc519c6453bcc1e9d4f6f60871c8b2eb25892486e6ee3644bdf2e702c32fa
-size 1445339812
+oid sha256:6aaaf1756958edc17225f7f0001973bc120f14f1ffce075d0bc26ac9f1b29179
+size 437967876

special_tokens_map.json

@@ -1,19 +1,7 @@
 {
-  "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>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,71 +1,39 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<s>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<cls>",
+    "102": {
+      "content": "[SEP]",
       "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": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "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>",
+    "103": {
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -73,22 +41,16 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<eop>",
-    "<eod>"
-  ],
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "<cls>",
-  "do_lower_case": false,
-  "eos_token": "</s>",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
   "extra_special_tokens": {},
-  "keep_accents": false,
-  "mask_token": "<mask>",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "remove_space": true,
-  "sep_token": "<sep>",
-  "tokenizer_class": "XLNetTokenizer",
-  "unk_token": "<unk>"
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d416a035ce1bc0ba9b00b832e8425a2cad6f19d1977f0ded60e9954cac30bbc2
-size 5304
+oid sha256:2e0ae6eae8dfd2813c763f8062919a00d79152d1b8fe66f11d3ba8d509d62870
+size 5240