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:cb6ceb7c4168f5787e24bdbffc8c82a8adbb5b433f42a5e0248f421f771982c5
+size 477186129

runs/Aug22_04-35-59_9e6e3053c41f/events.out.tfevents.1692678965.9e6e3053c41f.440.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:092f00bd4ced809ea84138e7eb662c51c3cdf0299d0f19a6fad8eaf1a3e0f313
+size 5155

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c9ac1bca03d689a6d2d19da049d67adf4ffb704bda5575b7b978da338c5072c
+size 4091