Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "bert-large-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -8,13 +8,13 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "Consumer",
     "1": "Enterprise"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "Consumer": 0,
     "Enterprise": 1
@@ -22,8 +22,8 @@
   "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,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89a2e168c0890038f80fb18ee6a0f042bc269fb895afadb2aa23773f2966c2e
-size 438007925
+oid sha256:836109f540ede2a5313d758921d9279d238b717ee0d4b61c5fba1b2f9c2003cd
+size 1340714613

runs/Jan25_02-57-07_07f50fc0e54b/events.out.tfevents.1674615430.07f50fc0e54b.617.18

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c2cc687dceda0b57731accf84ba85743baf37ca518cccfb877c55b6f5d1d332
-size 4278
+oid sha256:80aeb47123fef8ef6a5674855531b22a70e5192aa9e9fcf4d21b072c399cc415
+size 5595

runs/Jan25_02-58-50_07f50fc0e54b/1674615534.782179/events.out.tfevents.1674615534.07f50fc0e54b.617.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d5f7a9d78782458a697c413b35b72da036c87b77b4b0f2f3430c5c59754b1da
+size 5697

runs/Jan25_02-58-50_07f50fc0e54b/events.out.tfevents.1674615534.07f50fc0e54b.617.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c043702470808456673ea02b3d987c1f15839064addfdb8e2af9586b9050e5f6
+size 4280

tokenizer_config.json

@@ -3,7 +3,7 @@
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "bert-base-uncased",
+  "name_or_path": "bert-large-uncased",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "special_tokens_map_file": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:194ae29e58a44af3b498c4e138de74801e632da2ea49238d191527e5334d2436
+oid sha256:a245c4fe7f48a5628819701293775fb1efdfcecb27ca8ebfab12afa0501932e7
 size 3515