Training in progress, step 500

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "Alfahluzi/bert2bert-extreme-dropout-0.5-lr-5e-05-batchsize-4-encmaxlen-2048-decmaxlen-512",
   "architectures": [
     "EncoderDecoderModel"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7407492f609bd3bf9f105c2c766f7c8566d14859e5026d067cf60df825b230bc
+oid sha256:fdb63d04d712ff0aa425557152f28b933b861ad8bec7173c84aeb3ce0bfe5910
 size 1002850732

runs/Mar18_09-33-55_c10457f3b6ab/events.out.tfevents.1710754435.c10457f3b6ab.370.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1beae248d6dfc2a526f377224022d7f2607cdced4c27df3e18bd15e808b99c2
+size 9343

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.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 512
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24f7a02174fdb25847e97f989079962080f41caa990769c13b7b41862f9b8f3b
+oid sha256:701141ce1857ea963fde3ca9410eb51e21823693adaf9e22b03688145e046ec7
 size 5176