Training in progress, epoch 1

.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

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "[CLS]": 250101,
+  "[MASK]": 250102,
+  "[SEP]": 250100
+}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/mt5-small",
+  "_name_or_path": "ZhiguangHan/mt5-small-task3-dataset2",
   "architectures": [
     "MT5ForConditionalGeneration"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cdf194fc42503c397054e23819b8ad705e227b3f641450949990c39fdf57347
+oid sha256:f9aab561b2e761fb63c12433376b63ba5a83add1461e7ba34fdd67ca20467eb6
 size 1200729512

runs/Dec08_16-25-59_0d48d4ab1c57/events.out.tfevents.1702052760.0d48d4ab1c57.5543.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fefd2dc0f9c42eeed86b8ef47bf6eac5e646565b2541acee984dd572c627257
+size 5198

special_tokens_map.json

@@ -1,4 +1,5 @@
 {
+  "cls_token": "[CLS]",
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
@@ -6,6 +7,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "mask_token": "[MASK]",
   "pad_token": {
     "content": "<pad>",
     "lstrip": false,
@@ -13,6 +15,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "sep_token": "[SEP]",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08d4ce8b40c2092406659eb2d93e408142e85605d05b449ff58f16f7c719b7f6
-size 16330559
+oid sha256:59a8a3adecbc807fce9bc465b0958980e95450beae5c9833d932f07c3629bd71
+size 16315858

tokenizer_config.json

@@ -23,16 +23,50 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "250100": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250102": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [],
   "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
   "eos_token": "</s>",
   "extra_ids": 0,
   "legacy": true,
+  "mask_token": "[MASK]",
+  "max_length": 100,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
+  "sep_token": "[SEP]",
   "sp_model_kwargs": {},
-  "tokenizer_class": "T5Tokenizer",
+  "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 sha256:6e4024996dcfe26266344d8d02bb4b374b1de64e578e2b1fc05398bc1da68935
+oid sha256:09a22d72b377ff1b6954c09f332642007787f30f4718d703168b7b59190c7901
 size 4728

unigram.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02c8df7d753e651efcec0a2a746b0a743e069f6bed68f75c8618fbf50158a7a9
+size 13995654