Training in progress epoch 0

README.md

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0306
-- Validation Loss: 0.0584
-- Epoch: 2
+- Train Loss: 0.1758
+- Validation Loss: 0.0625
+- Epoch: 0
 
 ## Model description
 
@@ -42,14 +42,12 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.2443     | 0.0889          | 0     |
-| 0.0519     | 0.0613          | 1     |
-| 0.0306     | 0.0584          | 2     |
+| 0.1758     | 0.0625          | 0     |
 
 
 ### Framework versions
 
 - Transformers 4.24.0
 - TensorFlow 2.9.2
-- Datasets 2.7.0
+- Datasets 2.7.1
 - Tokenizers 0.13.2

config.json

@@ -10,104 +10,28 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "\"",
-    "1": "''",
-    "10": "CC",
-    "11": "CD",
-    "12": "DT",
-    "13": "EX",
-    "14": "FW",
-    "15": "IN",
-    "16": "JJ",
-    "17": "JJR",
-    "18": "JJS",
-    "19": "LS",
-    "2": "#",
-    "20": "MD",
-    "21": "NN",
-    "22": "NNP",
-    "23": "NNPS",
-    "24": "NNS",
-    "25": "NN|SYM",
-    "26": "PDT",
-    "27": "POS",
-    "28": "PRP",
-    "29": "PRP$",
-    "3": "$",
-    "30": "RB",
-    "31": "RBR",
-    "32": "RBS",
-    "33": "RP",
-    "34": "SYM",
-    "35": "TO",
-    "36": "UH",
-    "37": "VB",
-    "38": "VBD",
-    "39": "VBG",
-    "4": "(",
-    "40": "VBN",
-    "41": "VBP",
-    "42": "VBZ",
-    "43": "WDT",
-    "44": "WP",
-    "45": "WP$",
-    "46": "WRB",
-    "5": ")",
-    "6": ",",
-    "7": ".",
-    "8": ":",
-    "9": "``"
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-MISC",
+    "8": "I-MISC"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "\"": "0",
-    "#": "2",
-    "$": "3",
-    "''": "1",
-    "(": "4",
-    ")": "5",
-    ",": "6",
-    ".": "7",
-    ":": "8",
-    "CC": "10",
-    "CD": "11",
-    "DT": "12",
-    "EX": "13",
-    "FW": "14",
-    "IN": "15",
-    "JJ": "16",
-    "JJR": "17",
-    "JJS": "18",
-    "LS": "19",
-    "MD": "20",
-    "NN": "21",
-    "NNP": "22",
-    "NNPS": "23",
-    "NNS": "24",
-    "NN|SYM": "25",
-    "PDT": "26",
-    "POS": "27",
-    "PRP": "28",
-    "PRP$": "29",
-    "RB": "30",
-    "RBR": "31",
-    "RBS": "32",
-    "RP": "33",
-    "SYM": "34",
-    "TO": "35",
-    "UH": "36",
-    "VB": "37",
-    "VBD": "38",
-    "VBG": "39",
-    "VBN": "40",
-    "VBP": "41",
-    "VBZ": "42",
-    "WDT": "43",
-    "WP": "44",
-    "WP$": "45",
-    "WRB": "46",
-    "``": "9"
+    "B-LOC": "5",
+    "B-MISC": "7",
+    "B-ORG": "3",
+    "B-PER": "1",
+    "I-LOC": "6",
+    "I-MISC": "8",
+    "I-ORG": "4",
+    "I-PER": "2",
+    "O": "0"
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c27f1b4ae00f785432231a1d2df1c0033c65dfadd96548890a0d9836e2ee917
-size 431296708
+oid sha256:1eeea1b8e7662865c2984383a54a0ee0dc6f48a639a2f6bac1a0b66d82ea8a46
+size 431179820