Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "danielsaggau/longformer_simcse_scotus",
+  "architectures": [
+    "LongformerForSequenceClassification"
+  ],
+  "attention_mode": "longformer",
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    128,
+    128,
+    128,
+    128,
+    128,
+    128
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "cls_token_id": 101,
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13"
+  },
+  "ignore_attention_mask": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_max_length": 4096,
+  "model_type": "longformer",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "onnx_export": false,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "sep_token_id": 102,
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c4b7a31cb14147b78800a6b731837f0001327add6cc0ef25ab6a2b996336dc
+size 166605159

runs/Nov12_15-42-43_b726531d479a/1668267783.824263/events.out.tfevents.1668267783.b726531d479a.85.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ab2c2afcea19514bd85c3a10599566843e6d33491e3dad70ab4e4d798731d3e
+size 5518

runs/Nov12_15-42-43_b726531d479a/events.out.tfevents.1668267783.b726531d479a.85.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7459fb8dcde35f8823d6bc075de44965a3ca30a30bbf755646a65c92b31f68bf
+size 5206

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 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 4096,
+  "name_or_path": "danielsaggau/longformer_simcse_scotus",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "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:a626f27042ad084a44b6244ca6f7dfbd2eb3ba0aa473a4363608c371d0826bcc
+size 3439