Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Alfahluzi/bert2bert-extreme-dropout-0.5-lr-5e-05-batchsize-4-encmaxlen-2048-decmaxlen-512",
+  "_name_or_path": "Alfahluzi/bert2bert-extreme",
   "architectures": [
     "EncoderDecoderModel"
   ],
@@ -173,5 +173,5 @@
   "model_type": "encoder-decoder",
   "pad_token_id": 0,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2"
+  "transformers_version": "4.39.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:082e249bbd0c1c090f7be9e9d81d21b5ab5e269f86208c86e6639ee0b05c3b9c
+oid sha256:2a74c3caa7533270e342933a4b17c19dddd859795fbdbea7017fb792c59f3171
 size 1002850732

runs/Mar22_06-17-18_a2bb6f6474da/events.out.tfevents.1711088243.a2bb6f6474da.395.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a656eaa9fcbec21abc6d671846cc51a7873e6041c849c6a4f32683b945fd3174
+size 9127

tokenizer_config.json

@@ -46,12 +46,19 @@
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
+  "max_length": 512,
   "model_max_length": 1000000000000000019884624838656,
   "never_split": null,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:701141ce1857ea963fde3ca9410eb51e21823693adaf9e22b03688145e046ec7
-size 5176
+oid sha256:8c9603d93423284fb32e8c70867779eb602d91c60b2c3152b61ee970543bc601
+size 5112