Add model

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "init_mem_cpu_alloc_delta": 2019831808,
+    "init_mem_cpu_peaked_delta": 129236992,
+    "init_mem_gpu_alloc_delta": 165904896,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 14437457920,
+    "train_mem_cpu_peaked_delta": 175919104,
+    "train_mem_gpu_alloc_delta": 497286656,
+    "train_mem_gpu_peaked_delta": 9670125056,
+    "train_runtime": 120438.6398,
+    "train_samples": 4500000,
+    "train_samples_per_second": 3.503
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "google/bert_uncased_L-8_H-512_A-8",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.0.dev0",
+  "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 sha256:61523963d111575c01c8c2ea5e123612f0fac4dd2c89963213be05ba30badadd
+size 165557001

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "google/bert_uncased_L-8_H-512_A-8", "do_basic_tokenize": true, "never_split": null}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "init_mem_cpu_alloc_delta": 2019831808,
+    "init_mem_cpu_peaked_delta": 129236992,
+    "init_mem_gpu_alloc_delta": 165904896,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 14437457920,
+    "train_mem_cpu_peaked_delta": 175919104,
+    "train_mem_gpu_alloc_delta": 497286656,
+    "train_mem_gpu_peaked_delta": 9670125056,
+    "train_runtime": 120438.6398,
+    "train_samples": 4500000,
+    "train_samples_per_second": 3.503
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aac6bc60a1875c9a012ed51dcf586949792fc2e0082236a5dbd6763e3ee9f25
+size 2543