Training in progress, step 1000

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": 512,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 2048,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 8,
+  "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:d42a667c041ac3515b27efd35f133154b0ba3e630ffc78a5bef487b284e4196a
+size 115189296

runs/Jul31_01-08-21_390be55cffea/events.out.tfevents.1722388186.390be55cffea.3374.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7a2f364760a2c3845972096453a77d3e7289c2dcbd4fede970cda255ef8c538
+size 4675

runs/Jul31_01-10-27_390be55cffea/events.out.tfevents.1722388241.390be55cffea.3947.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7052ab3f428f7ac60c4f7d3686b1ed2804f78af132cf173fc65a2f7a9cf4718
+size 5097

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 sha256:27220c09f0b8d18fd05ac03495c8a406fdb362b6f2eb6e29d3712295b13ae9a2
+size 5176