Training in progress, step 400

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+unigram.json filter=lfs diff=lfs merge=lfs -text

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff547b5c97dcf2d6871d809d13f8ba4d7ecb514afb527ff56cb6202fdcf8d463
+oid sha256:fdb638f42f4114ab597423d31a0a5fcce3b6fe8932c44628797dacdb2be2bb33
 size 1117286936

runs/Aug22_18-16-30_0ebec57e88d7/events.out.tfevents.1724350591.0ebec57e88d7.1474.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fe5873b19957211dbddf5822e366b87012189c5edc54650559d8d99f4ccbdd9
+size 5383

runs/Aug22_18-16-34_0ebec57e88d7/events.out.tfevents.1724350595.0ebec57e88d7.1474.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1c6fae03f8d5980eee8c18b3d1faab07d9f866a44d63c20615f2789111c8a4d
+size 6347

special_tokens_map.json

@@ -1,7 +1,25 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -9,7 +27,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "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

@@ -1,4 +1,5 @@
 {
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<s>",
@@ -52,8 +53,9 @@
     0
   ],
   "eos_token": "</s>",
+  "errors": "replace",
   "mask_token": "<mask>",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "only_label_first_subword": true,
   "pad_token": "<pad>",
   "pad_token_box": [
@@ -65,11 +67,12 @@
   "pad_token_label": -100,
   "sep_token": "</s>",
   "sep_token_box": [
-    1000,
-    1000,
-    1000,
-    1000
+    0,
+    0,
+    0,
+    0
   ],
-  "tokenizer_class": "LayoutXLMTokenizer",
+  "tokenizer_class": "LayoutLMv3Tokenizer",
+  "trim_offsets": true,
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbb24fd0204b49677ae1475bf59bc50ce5b32fab5001e15f75036a6c20f1ba62
+oid sha256:aebd383120f49bf2d34c8dec38c54bae5d9f9c2eaf6948eaa3766f08eb48c3fb
 size 5176

unigram.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260