Training in progress, step 10000

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "Alfahluzi/bert2bert-extabs-canonicalcleandata-lr-5e-05-batchsize-4-encmaxlen-512-decmaxlen-256",
   "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:ffbce47570cfce415c9a41705eb2ce3a8f1a6940976a79527fd63b7399c3bc02
+oid sha256:33b9c23e02c95b5544771470b0bf6c050541eb596e3499f498b7a5df329595b2
 size 998132132

runs/Apr16_07-18-52_728561d7d15f/events.out.tfevents.1713251933.728561d7d15f.381.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49ab376ae77499b37ab2b5ed37a24afe2825a148afb24d405de4d582812cdab3
+size 9424

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 sha256:4a49fc8530eabcbc89f548db9af082005d8eb78d50224443bfde91bc9ccc0211
-size 5176
+oid sha256:fb18e20979e5e0cf279dad3cb91e9ee52968d86f16acaaee2ead3e5879d0597d
+size 5240