Training in progress, step 500

config.json

@@ -0,0 +1,73 @@
+{
+  "_name_or_path": "allenai/longformer-base-4096",
+  "architectures": [
+    "LongformerForTokenClassification"
+  ],
+  "attention_mode": "longformer",
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-EMAIL",
+    "1": "B-ID_NUM",
+    "2": "B-NAME_STUDENT",
+    "3": "B-PHONE_NUM",
+    "4": "B-STREET_ADDRESS",
+    "5": "B-URL_PERSONAL",
+    "6": "B-USERNAME",
+    "7": "I-ID_NUM",
+    "8": "I-NAME_STUDENT",
+    "9": "I-PHONE_NUM",
+    "10": "I-STREET_ADDRESS",
+    "11": "I-URL_PERSONAL",
+    "12": "O"
+  },
+  "ignore_attention_mask": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-EMAIL": 0,
+    "B-ID_NUM": 1,
+    "B-NAME_STUDENT": 2,
+    "B-PHONE_NUM": 3,
+    "B-STREET_ADDRESS": 4,
+    "B-URL_PERSONAL": 5,
+    "B-USERNAME": 6,
+    "I-ID_NUM": 7,
+    "I-NAME_STUDENT": 8,
+    "I-PHONE_NUM": 9,
+    "I-STREET_ADDRESS": 10,
+    "I-URL_PERSONAL": 11,
+    "O": 12
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_type": "longformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "onnx_export": false,
+  "pad_token_id": 1,
+  "sep_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d481c748fad93c26da28229f050e17d91ccb07a24d91e2c3e0466c04be40514b
+size 592349436

runs/Feb16_07-44-51_80dd8279d6b1/events.out.tfevents.1708069493.80dd8279d6b1.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc1e995b961d91c04b8c6f01b3c77a043c2d4033b0070b85c7b4bb9ee344557
+size 5420

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 4096,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "LongformerTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fcb262df4916f7e1cd35f6312b19477ce9481b81757c5f93d98ba6317fa8795
+size 4728