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/1650261920.8495061/events.out.tfevents.1650261920.3e9d60946c57.33.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd3aee908f2af9338bfc0613078e467f46435adae93090f3eb64cecf9a3240eb
+size 4859

logs/events.out.tfevents.1650261920.3e9d60946c57.33.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d418cf480f916854b0d6d289e0f1d3848e25b4abf764fc83849f668ff850e23a
+size 4306

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f67f833ba23c55c21fedb4c348ae9c042a905bfb415ee074947be5c1c5f8bbd2
-size 63699757
+oid sha256:90e0606672fb5e6572cc3c005e2f7799c843d4a798973bb5a8780b63a64b66f0
+size 44713287