Training in progress, epoch 1

config.json

@@ -1,39 +1,54 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "xlnet-base-cased",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "XLNetForSequenceClassification"
   ],
-  "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": "opinion",
     "1": "reporting",
     "2": "satire"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "opinion": "0",
     "reporting": "1",
     "satire": "2"
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "output_past": true,
-  "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,
   "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": "4.33.1",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 250002
+  "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 sha256:5834845a22c0edc4da57803c30fa73d80416dddbeeaba23dc33adb840b7cd770
-size 1112252785
+oid sha256:9a1b7b6ebf6acaef31834d8477ecabc8904222662d930b9e065fcb758716e9a1
+size 469314837

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>"
 }

spiece.model

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

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
-size 17082660
+oid sha256:f4bd2fc08de0f4c0a6e81add509d3d05d0ebc71c4dc434d24a114f5aeaab34fe
+size 2405715

tokenizer_config.json

@@ -1,8 +1,14 @@
 {
+  "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>",
+  "keep_accents": false,
   "mask_token": {
     "__type": "AddedToken",
     "content": "<mask>",
@@ -11,9 +17,10 @@
     "rstrip": false,
     "single_word": false
   },
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
+  "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 sha256:711e87685bd24be13a281f2fc9717bb37e456702a41b11909a56664bc6524489
+oid sha256:91508c8407cf0039bbea49fde207d6dea4072bcefe7a7faf78a8fe9fedaa0719
 size 4091