Training in progress, epoch 1

config.json

@@ -24,8 +24,8 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
   "output_past": true,
   "pad_token_id": 0,
   "pooler_fc_size": 768,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fe42f7430dbb2f1e1902ffa7e5554f06d7fe48e23d3110d45ec4f19c723109c
-size 435725300
+oid sha256:9500404404d4814da514807e3baf66f46e5e562344bd825475408bd32b8a8700
+size 322311788

runs/Sep20_16-22-28_aef78e88129c/events.out.tfevents.1726849349.aef78e88129c.1485.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5145e46b6fc3172eed12251df527f502f565770ece5617ef0c89ff2b5f5db57
+size 5793

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b484b420f54bd59a1d2943a55444b9c2eb1298e7af97cb97767353ae83266038
+oid sha256:5c4b5847ac7bece19f5526dc8a5ff26b6b8b503136d6f976ad29cc712aaa7161
 size 5176