Training in progress, epoch 1

config.json

@@ -1,10 +1,12 @@
 {
-  "_name_or_path": "google/bert_uncased_L-10_H-256_A-4",
+  "_name_or_path": "M-FAC/bert-mini-finetuned-mnli",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "finetuning_task": "mnli",
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 256,
@@ -24,7 +26,7 @@
   "max_position_embeddings": 512,
   "model_type": "bert",
   "num_attention_heads": 4,
-  "num_hidden_layers": 10,
+  "num_hidden_layers": 4,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

logs/1650255678.529799/events.out.tfevents.1650255678.cda890f99651.34.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a97a28f171a132a698e1db26ec26a167c00a38293643ac108a278e1b456d043c
+size 4859

logs/events.out.tfevents.1650255678.cda890f99651.34.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8c0117f0fdc9099dba25dcfc249c7561c1e312124b9a4f02ffd4f86625dfec8
+size 4306

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8467f1d39385fd5c66042f562206f229660ef0a6c53d320768676c29594a7529
-size 63699757
+oid sha256:90e0606672fb5e6572cc3c005e2f7799c843d4a798973bb5a8780b63a64b66f0
+size 44713287