Training in progress, epoch 1

config.json

@@ -1,26 +1,44 @@
 {
-  "_name_or_path": "prajjwal1/bert-tiny",
+  "_name_or_path": "xlnet-base-cased",
   "architectures": [
-    "BertForSequenceClassification"
+    "XLNetForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 128,
+  "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,
-  "intermediate_size": 512,
   "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 2,
-  "num_hidden_layers": 2,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "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": "4.26.0",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "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 sha256:89a28fb3b54f032992bb80f4e682fc86a5e39a163ac8fb818e8ea3fedb1c4028
-size 17562607
+oid sha256:c0d92a9075c70ee7745d1c31803bbdbbb4b05f30c0623d34e93601bad888f4c1
+size 469311765

runs/Feb05_16-22-17_14a4a7029e36/1675614148.5975115/events.out.tfevents.1675614148.14a4a7029e36.304.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d5ab2e89b9053496a4a3e7d7f392b46a48dc691b33d21c894fc2f38b2b95b4
+size 5622

runs/Feb05_16-22-17_14a4a7029e36/events.out.tfevents.1675614148.14a4a7029e36.304.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b315e352f42fa1cbe57ca4f44f3d8d1ece02d7596af4f7dcf6e6b23754139ca1
+size 40

special_tokens_map.json

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

tokenizer_config.json

@@ -1,16 +1,27 @@
 {
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
+  "additional_special_tokens": [
+    "<eop>",
+    "<eod>"
+  ],
+  "bos_token": "<s>",
+  "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,
-  "name_or_path": "prajjwal1/bert-tiny",
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
+  "name_or_path": "xlnet-base-cased",
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "<sep>",
   "special_tokens_map_file": null,
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "tokenizer_class": "XLNetTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfca74c3ab5251cbb4b5b78e47c9d7421fd05e88e5bd52ac62172f3b9a22075f
+oid sha256:f837d3cf464c4ba346665f6b2660bc1e3d6b443840d9488615553d25b00a801e
 size 3451