Training in progress, step 10000

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "Alfahluzi/bert2bert-extreme-lr-5e-05-batchsize-4-encmaxlen-512-decmaxlen-256-abs",
   "architectures": [
     "EncoderDecoderModel"
   ],
@@ -172,6 +173,6 @@
   "model_type": "encoder-decoder",
   "pad_token_id": 0,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.39.3",
   "vocab_size": 31923
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4f902ff6c2d6f68522ec6bd0d085bca08350ddea999a46e92e612c4d8d1f82
+oid sha256:7543f798bb5d82848db265a3745fc1c47bbef230923fc4958ead0cebb336f56c
 size 998132132

runs/Apr13_14-12-28_2f494495e7b9/events.out.tfevents.1713017549.2f494495e7b9.341.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c72264a40403416f52f79a87ae12e6e82d19feb35de0e4b99de68a9951e9a7e3
+size 9368

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -46,12 +46,19 @@
   "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
+  "max_length": 256,
   "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:c853969ad44232fdf34e9b89da160b9d295638ff18cd02ac54d9783f8e8e66b3
+oid sha256:1e785bb02c9e589f06ba8e1280e7906cbf7179e95c3f98b3735ed1da6ab49d89
 size 5176