Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "IDEA-CCNL/Erlangshen-Longformer-110M",
+  "architectures": [
+    "LongformerForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    128,
+    128,
+    128,
+    128,
+    128,
+    128,
+    128,
+    128,
+    128,
+    128,
+    128,
+    128
+  ],
+  "bos_token_id": 0,
+  "directionality": "bidi",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Down",
+    "1": "Up"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Down": 0,
+    "Up": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 4096,
+  "model_type": "longformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "onnx_export": false,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "problem_type": "single_label_classification",
+  "sep_token_id": 2,
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "type_vocab_size": 2,
+  "use_sparse_attention": true,
+  "vocab_size": 12000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a22eef4a90a442cbb56f3bb3e55ae73fc34914839bfe321c78fb2566d557b10c
+size 477186129

runs/Aug03_06-38-45_c861113b5aa1/events.out.tfevents.1691044734.c861113b5aa1.1251.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c550fc93f9994530e004bdcd1aad92c06df48edb70507c9846d479fe9b326c0
+size 5127

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e50171e5fd9bb0a44f609e5f7417561238ddc2fb92aa142086d6fcef6b7ae26c
+size 4155