Training in progress, epoch 1

config.json

@@ -1,60 +1,64 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "bert-large-cased",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "directionality": "bidi",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "ARTS & CULTURE",
     "1": "BUSINESS",
     "2": "COMEDY",
-    "3": "ENTERTAINMENT",
-    "4": "ENVIRONMENT",
-    "5": "FOOD & DRINK",
-    "6": "GREEN",
-    "7": "HOME & LIVING",
-    "8": "MEDIA",
-    "9": "POLITICS",
-    "10": "SCIENCE",
-    "11": "SPORTS",
-    "12": "STYLE & BEAUTY",
-    "13": "TECH",
-    "14": "TRAVEL",
-    "15": "WELLNESS",
-    "16": "WORLD NEWS"
+    "3": "ENVIRONMENT",
+    "4": "FOOD & DRINK",
+    "5": "GREEN",
+    "6": "HOME & LIVING",
+    "7": "MEDIA",
+    "8": "POLITICS",
+    "9": "SCIENCE",
+    "10": "SPORTS",
+    "11": "STYLE & BEAUTY",
+    "12": "TECH",
+    "13": "TRAVEL",
+    "14": "WELLNESS",
+    "15": "WORLD NEWS"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "ARTS & CULTURE": 0,
     "BUSINESS": 1,
     "COMEDY": 2,
-    "ENTERTAINMENT": 3,
-    "ENVIRONMENT": 4,
-    "FOOD & DRINK": 5,
-    "GREEN": 6,
-    "HOME & LIVING": 7,
-    "MEDIA": 8,
-    "POLITICS": 9,
-    "SCIENCE": 10,
-    "SPORTS": 11,
-    "STYLE & BEAUTY": 12,
-    "TECH": 13,
-    "TRAVEL": 14,
-    "WELLNESS": 15,
-    "WORLD NEWS": 16
+    "ENVIRONMENT": 3,
+    "FOOD & DRINK": 4,
+    "GREEN": 5,
+    "HOME & LIVING": 6,
+    "MEDIA": 7,
+    "POLITICS": 8,
+    "SCIENCE": 9,
+    "SPORTS": 10,
+    "STYLE & BEAUTY": 11,
+    "TECH": 12,
+    "TRAVEL": 13,
+    "WELLNESS": 14,
+    "WORLD NEWS": 15
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8968367d1053a6dd01f4dfec5227e919772d392ddef1145854518d2cf3ad4520
-size 433364397
+oid sha256:6db6eae81ed2cca1a85ae8fd7ec59a5b264df0cf19eea72dfdb4f188719ebbcc
+size 1334518573

runs/May23_02-42-44_200405aa6971/1653273772.443351/events.out.tfevents.1653273772.200405aa6971.3074.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6c30e422b85e1cda880b661c8c3a149425b77fe20fb6513b5366f2ac5086cb3
+size 5211

runs/May23_02-42-44_200405aa6971/events.out.tfevents.1653273772.200405aa6971.3074.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:402f8b99b63acb8aaf907d019ed75a2c20bee657ead1f782888ecf55607e8f01
+size 5023

runs/May23_02-49-05_200405aa6971/1653274153.8584282/events.out.tfevents.1653274153.200405aa6971.3334.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67af1b673f75325ff7103ea5a40769d9df8392b573b69b8584f96c7ab939ea3c
+size 5211

runs/May23_02-49-05_200405aa6971/events.out.tfevents.1653274153.200405aa6971.3334.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb6836e5a13d9bbfe311060018e6736baf7d7b807499faf513c00f0bdc6cef9
+size 20602

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased", "tokenizer_class": "BertTokenizer"}
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-large-cased", "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:513f8321d98749a84fcbe8c750bbadc3644985b5fc03e4b4413f72692339438d
+oid sha256:910bbf6ab60edd9241531d1ff7c0c1606382d150da8f81eca9b1ecd5830433a2
 size 3247