Training in progress, epoch 1

config.json

@@ -1,15 +1,14 @@
 {
-  "_name_or_path": "bert-large-cased",
+  "_name_or_path": "bert-base-cased",
   "architectures": [
     "BertForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "directionality": "bidi",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "O",
     "1": "B-PER",
@@ -22,7 +21,7 @@
     "8": "I-MISC"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "B-LOC": "5",
     "B-MISC": "7",
@@ -37,14 +36,9 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "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",
   "torch_dtype": "float32",
   "transformers_version": "4.40.0",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2819372626a3c77adf9c0f189e02b36454fc80ccfa991fd732a442c25416625
-size 1330202364
+oid sha256:4b653498989095bd35f0d68e4ea54ee89d988baafab3e464725d68f1da943d26
+size 430929740

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afaa879628f85aaf975346829fa570452e577b4b87d01bc27b78c68802e3cc02
+oid sha256:226cc6d6e9c1fdc4d40cd1243d5f2d9883e1e4337ac264e60c78bbf4a7369a88
 size 4984