Training in progress, step 5000

config.json

@@ -3,20 +3,21 @@
     "BertForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "gradient_checkpointing": false,
+  "classifier_dropout": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 256,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 1024,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.6.0.dev0",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97e0127a2bc781d8cc90153b86d4526cf3e0db39c6a064ee94b19a346989a99a
+size 44814856

runs/Aug02_01-12-57_aec3f229cdd9/events.out.tfevents.1722562422.aec3f229cdd9.3511.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44ae084c0341114439f4e073a310a2772a65cdf5cf81d24988e44c13cc536775
+size 15220

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer.json

@@ -53,7 +53,7 @@
     "type": "BertNormalizer",
     "clean_text": true,
     "handle_chinese_chars": true,
-    "strip_accents": true,
+    "strip_accents": null,
     "lowercase": true
   },
   "pre_tokenizer": {

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfac3de8f370ab277fda982cc8b3a23eaf3b86d6534664855fac784ce845f9f3
+size 5176