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/1650238405.6824813/events.out.tfevents.1650238405.f8fb911780d7.34.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c12fadb03d6eb90b446353511729a0db321614c5f6b74016c9a4296726fd054
+size 4859

logs/events.out.tfevents.1650237093.f8fb911780d7.34.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b18e407f7144089dbcc6d98e372e8fc37443b33b4e5dc893706c9fe534fe403
-size 5380
+oid sha256:fdd62d889904d12ad5c29f520b6e365a4d560c0a45f226a856bb3c12d0cd1919
+size 5734

logs/events.out.tfevents.1650238405.f8fb911780d7.34.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a9bcfe99446851c5e13b20aae49c03524c6926d36a27e9f7e1e8bc0fa17009
+size 4138

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7092c2bc054d410de6498bc55f8b0c04d03da6fd934b929093c45e5188aade0d
-size 63699757
+oid sha256:15bf2e86695a05a67889df55045c20dae75c5859cfd7b3280f09bfa54b7f11d1
+size 44713287