Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-large-uncased",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -8,13 +8,13 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "Consumer",
     "1": "Enterprise"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "Consumer": 0,
     "Enterprise": 1
@@ -22,8 +22,8 @@
   "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,
   "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 sha256:836109f540ede2a5313d758921d9279d238b717ee0d4b61c5fba1b2f9c2003cd
-size 1340714613
+oid sha256:0d53884b142aa3c90afa896953ed2e5e4d61f2ed1ee2c43c0733e659cf0d29f3
+size 438007925

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c043702470808456673ea02b3d987c1f15839064addfdb8e2af9586b9050e5f6
-size 4280
+oid sha256:4f6d681dff8d3491d7c09dd95b0f99074df7709ea2ba297755b575d807c4b8fe
+size 5597

runs/Jan25_03-02-03_07f50fc0e54b/1674615727.076288/events.out.tfevents.1674615727.07f50fc0e54b.617.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec9ad6f27661f21545e8de7e309b7bb96dec4b252140746ecac113b9d27b587
+size 5697

runs/Jan25_03-02-03_07f50fc0e54b/events.out.tfevents.1674615727.07f50fc0e54b.617.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eaaf05ccf08c8033380a829c1f0c7388d8e778fdc1a459c45b3a9a3e06f7346
+size 4278

tokenizer_config.json

@@ -3,7 +3,7 @@
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "bert-large-uncased",
+  "name_or_path": "bert-base-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:a245c4fe7f48a5628819701293775fb1efdfcecb27ca8ebfab12afa0501932e7
+oid sha256:e5d221323437e32fdfa1a8ea14fd9220a5fc6c155adbf4dbce488f6fdd560bd2
 size 3515