Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "Lowin/chinese-bigbird-wwm-base-4096",
+  "architectures": [
+    "BigBirdForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attention_type": "block_sparse",
+  "block_size": 64,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "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": "big_bird",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_random_blocks": 3,
+  "output_past": true,
+  "pad_token_id": 1,
+  "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",
+  "rescale_embeddings": false,
+  "sep_token_id": 66,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "type_vocab_size": 2,
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 21128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5a79322efc06bf085a27f7678f353c27a77d8f0ddcb3507e746bf2d364e95b
+size 422518201

runs/Aug07_03-23-01_299bce13a1a6/events.out.tfevents.1691378599.299bce13a1a6.182.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1caec1113253a3abff015e8080d08d7445b6d587ab5dcfb66d3916cccfec96
+size 5085

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e778d70a39e7d8d97c780c0009a9f28db7271794e442f9cb9c7f4c9e4db960c4
+size 4091