add model

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "/tmp/mnli_distil_output/checkpoint-6000",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "mnli",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.3.2",
+  "vocab_size": 30522,
+  "xla_device": true
+}

eval_results_mnli-mm.txt

@@ -0,0 +1,5 @@
+epoch = 5.0
+eval_accuracy = 0.8206875508543532
+eval_loss = 0.8706700205802917
+eval_runtime = 17.8278
+eval_samples_per_second = 551.498

eval_results_mnli.txt

@@ -0,0 +1,5 @@
+epoch = 5.0
+eval_accuracy = 0.8221090168110036
+eval_loss = 0.8824708461761475
+eval_runtime = 18.1167
+eval_samples_per_second = 541.765

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, "model_max_length": 512, "name_or_path": "distilbert-base-uncased"}

train_results.txt

@@ -0,0 +1,3 @@
+epoch = 5.0
+train_runtime = 14248.9446
+train_samples_per_second = 8.613