Training in progress, epoch 1

config.json

@@ -31,7 +31,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.34.0",
+  "transformers_version": "4.35.2",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 25005

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9de035e6fe518d729ca44e06caf3ce7a6e85dfdf3e672fe510085d61e7c64d4b
+size 421007928

runs/Nov20_03-54-17_bb4c76e02cfc/events.out.tfevents.1700452467.bb4c76e02cfc.2506.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9e62d4eb09f6092d9ad4290bf7859a4efb951c726118a3c64911b2afe9818c8
+size 8998

special_tokens_map.json

@@ -7,7 +7,13 @@
   "bos_token": "<s>",
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": "<mask>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "unk_token": "<unk>"

tokenizer.json

@@ -12,8 +12,8 @@
       "id": 0,
       "content": "<s>NOTUSED",
       "single_word": false,
-      "lstrip": true,
-      "rstrip": true,
+      "lstrip": false,
+      "rstrip": false,
       "normalized": false,
       "special": true
     },
@@ -30,8 +30,8 @@
       "id": 2,
       "content": "</s>NOTUSED",
       "single_word": false,
-      "lstrip": true,
-      "rstrip": true,
+      "lstrip": false,
+      "rstrip": false,
       "normalized": false,
       "special": true
     },
@@ -66,8 +66,8 @@
       "id": 8,
       "content": "<_>",
       "single_word": false,
-      "lstrip": true,
-      "rstrip": true,
+      "lstrip": false,
+      "rstrip": false,
       "normalized": false,
       "special": true
     },
@@ -77,7 +77,7 @@
       "single_word": false,
       "lstrip": true,
       "rstrip": false,
-      "normalized": true,
+      "normalized": false,
       "special": true
     }
   ],
@@ -100,7 +100,8 @@
   "pre_tokenizer": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true
+    "add_prefix_space": true,
+    "prepend_scheme": "always"
   },
   "post_processor": {
     "type": "TemplateProcessing",
@@ -186,7 +187,8 @@
   "decoder": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true
+    "add_prefix_space": true,
+    "prepend_scheme": "always"
   },
   "model": {
     "type": "Unigram",

tokenizer_config.json

@@ -2,9 +2,9 @@
   "added_tokens_decoder": {
     "0": {
       "content": "<s>NOTUSED",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
@@ -18,9 +18,9 @@
     },
     "2": {
       "content": "</s>NOTUSED",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
@@ -50,16 +50,16 @@
     },
     "8": {
       "content": "<_>",
-      "lstrip": true,
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
     "25004": {
       "content": "<mask>",
       "lstrip": true,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:065ac3630dbc97acf96a031139d1b85cdececcfc25cf9903f0d5d9756b4e395c
-size 4091
+oid sha256:3a5abd811617cac248f8c52d9bb8037e1fe82883d264c3677d0da6cc6f99cf31
+size 4600