Training in progress, step 500

config.json

@@ -1,52 +1,52 @@
 {
-  "_name_or_path": "bert-base-multilingual-uncased",
-  "_num_labels": 16,
+  "_name_or_path": "google-bert/bert-base-multilingual-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "directionality": "bidi",
+  "finetuning_task": "text-classification",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
     "0": "sdg1",
-    "1": "sdg2",
-    "2": "sdg3",
-    "3": "sdg4",
-    "4": "sdg5",
-    "5": "sdg6",
-    "6": "sdg7",
-    "7": "sdg8",
-    "8": "sdg9",
-    "9": "sdg10",
-    "10": "sdg11",
-    "11": "sdg12",
-    "12": "sdg13",
-    "13": "sdg14",
-    "14": "sdg15",
-    "15": "sdg16"
+    "1": "sdg10",
+    "2": "sdg11",
+    "3": "sdg12",
+    "4": "sdg13",
+    "5": "sdg14",
+    "6": "sdg15",
+    "7": "sdg16",
+    "8": "sdg2",
+    "9": "sdg3",
+    "10": "sdg4",
+    "11": "sdg5",
+    "12": "sdg6",
+    "13": "sdg7",
+    "14": "sdg8",
+    "15": "sdg9"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
     "sdg1": 0,
-    "sdg10": 9,
-    "sdg11": 10,
-    "sdg12": 11,
-    "sdg13": 12,
-    "sdg14": 13,
-    "sdg15": 14,
-    "sdg16": 15,
-    "sdg2": 1,
-    "sdg3": 2,
-    "sdg4": 3,
-    "sdg5": 4,
-    "sdg6": 5,
-    "sdg7": 6,
-    "sdg8": 7,
-    "sdg9": 8
+    "sdg10": 1,
+    "sdg11": 2,
+    "sdg12": 3,
+    "sdg13": 4,
+    "sdg14": 5,
+    "sdg15": 6,
+    "sdg16": 7,
+    "sdg2": 8,
+    "sdg3": 9,
+    "sdg4": 10,
+    "sdg5": 11,
+    "sdg6": 12,
+    "sdg7": 13,
+    "sdg8": 14,
+    "sdg9": 15
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
@@ -54,10 +54,15 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.40.0",
+  "transformers_version": "4.42.4",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 105879

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec796ee78f016d404eb75c66d4f685952dde16e8cd9085b308829856b7bd319a
+oid sha256:516fea04f25059c326209a4030621c6fcdc999a068f0ed2c13d162f42114d52b
 size 669498432

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,

tokenizer_config.json

@@ -43,11 +43,9 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:083cc43ec3c52d3d3f2909320ed7dfdd4cd56397a51ee1512c3811ac2a1fd11a
-size 4920
+oid sha256:7373b46fe45f2e461bb25799d911cf82ba24f3261a11f2d574c0c2008eafc1a0
+size 5240