Training in progress, step 500

config.json

@@ -6,14 +6,14 @@
   "classifier_dropout": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 258,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 1024,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 3,
-  "num_hidden_layers": 3,
+  "num_attention_heads": 6,
+  "num_hidden_layers": 6,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:506e31361700fb765ed2b8edbc346eb72715d51744f84f4a58a69d9586bac788
-size 42005112
+oid sha256:082d1b6ad270442a240baf9bfc0977f616ad3da86d05af5947e2e786748e108e
+size 267960640

runs/Aug07_20-52-02_8134a0a8c92b/events.out.tfevents.1723063923.8134a0a8c92b.312.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:118c7d5dc6e7d41b2209a1abb3ac5ad7d0c7cb416b685df63296731c807689ce
+size 4893

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cfcc29bb67ca7323648720dd118fd06440a08901a6073dd1fdeb0755e9b3032
+oid sha256:bf81b61c8dafbff08ae56e38dff960f65cea8f0b506c42b725626fb8d11b7f8f
 size 5112