Training in progress, epoch 1

config.json

@@ -1,14 +1,14 @@
 {
-  "_name_or_path": "google/electra-small-discriminator",
+  "_name_or_path": "google/electra-large-discriminator",
   "architectures": [
     "ElectraForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "embedding_size": 128,
+  "embedding_size": 1024,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 256,
+  "hidden_size": 1024,
   "id2label": {
     "0": "center",
     "1": "left",
@@ -16,7 +16,7 @@
     "3": "roundup"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 1024,
+  "intermediate_size": 4096,
   "label2id": {
     "center": "0",
     "left": "1",
@@ -26,8 +26,8 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "electra",
-  "num_attention_heads": 4,
-  "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 sha256:4aca4ae65bdbb3a5cd789ba9e6f2683aa316f6913a5e6d5e589e32b67afb4563
-size 54273341
+oid sha256:96f6d1e97b8e4b65a614ac5bd176b858af40028e09c4b3be379912158e6fc2ad
+size 1340723957

runs/Mar13_13-37-38_teesta/events.out.tfevents.1710317271.teesta.21161.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45e697f4ab4ad5d67d36e0b57ba85b4a37a8683b47bd5946d8d3690a2f1e6795
-size 9943
+oid sha256:66745791d94adf2309443c8b348509220437f55ae4f6e0c803a2eb4bb8ff89bd
+size 10297

runs/Mar13_13-37-38_teesta/events.out.tfevents.1710318336.teesta.21161.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed90fe3c311d8a08fe2f9970a2daf21477df9d84b60aa0cbaeaba8975104d885
+size 512

runs/Mar13_14-11-35_teesta/events.out.tfevents.1710319316.teesta.38365.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da7da443107c202d8d2b25b90ee70801b5924abb8f03c71f208b205f0512ef2c
+size 9049

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b9e1948454a0ec7e7534a99c4279890913056fcee3e35979e48ee87c2bef465
+oid sha256:e419e11b128bffd3d3e1c5f0789ba1f5fa96d14c1f0b252296574fb4b7d857b5
 size 3963