Training in progress, step 7120

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "johannes-garstenauer/distilbert_masking_heaps",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "IRRELEVANT",
+    "1": "SESSION_STATE_ADDR",
+    "2": "NEWKEYS_ADDR",
+    "3": "ENCRYPTION_KEY_NAME_ADDR",
+    "4": "KEY_ADDR"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "ENCRYPTION_KEY_NAME_ADDR": 3,
+    "IRRELEVANT": 0,
+    "KEY_ADDR": 4,
+    "NEWKEYS_ADDR": 2,
+    "SESSION_STATE_ADDR": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_hidden_states": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0.dev0",
+  "vocab_size": 30005
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62457e0f011e2c4eeec4854156b416c767d07db998a2245e5de730b8dd27dc47
+size 266276525

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:591fe4e628cc9ef9086b954ce2bf2dcc12616f0adac1d624bdc9e4e05befce8a
+size 4091