Training in progress, epoch 1

config.json

@@ -1,26 +1,24 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForMaskedLM"
+    "DistilBertForMaskedLM"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.18.0",
-  "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1646f25f37f482e5696e2ac4ae15a37f346c4a195693c3cc0ac71a6c96782f85
-size 438128811
+oid sha256:c2bd8158cc9e08934f912b0f11f0e8439a9613d9a4b5c29ba4d3653e0729beed
+size 267976815

runs/Apr26_23-23-49_52ac0bca04f6/1651015597.1691756/events.out.tfevents.1651015597.52ac0bca04f6.97.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:691714c92b7ff8ce3297bd5d30badecd9d34b392260744376b542926e33e3cbb
+size 4912

runs/Apr26_23-23-49_52ac0bca04f6/events.out.tfevents.1651015597.52ac0bca04f6.97.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6623c3cb197b1b4024a2fabd4b0d18a23a8baba8ea3fb705d45f070ca7da19
+size 26835

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd0ec388ea33e47fac29d99657dec8b9831077fadf715e2e33ce5374ea4ea812
+oid sha256:a54d875740e54ca3a23e2bf7bff4e2b971408d659ff25f1e7da7316b93dbf62b
 size 3119