Training in progress, step 625

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:210c9e0d351d28ffdd8bab1400b0a7288d8e4c852666b70a975ddfb43b0f44f8
+oid sha256:ef342c396b0ec20881e72bee0c6b25e77cc1385715d397d1c801aa09c08e4940
 size 516640282

tokenizer.json

@@ -239,10 +239,30 @@
     "use_regex": true
   },
   "post_processor": {
-    "type": "ByteLevel",
-    "add_prefix_space": false,
-    "trim_offsets": true,
-    "use_regex": true
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {}
   },
   "decoder": {
     "type": "ByteLevel",
@@ -258,6 +278,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "<|endoftext|>": 0,
       "<|padding|>": 1,

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": false,
+  "add_eos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ee8c68b0f6729a34c82e23715d15f137b605c8bc703d73bef8104af3b88ad67
-size 4920
+oid sha256:a352909b7f0c9d53dfa10ddb1342d7802441c70d40effa36867d4587ad6c5e18
+size 4984