add model collaterals

README.md

@@ -0,0 +1,57 @@
+This model is developed with transformers v4.9.1.
+
+```
+  m             = 0.8444
+  eval_samples  =   9815
+
+  mm            = 0.8495
+  eval_samples  =   9832
+``` 
+
+# Train
+```bash
+#!/usr/bin/env bash
+
+export CUDA_VISIBLE_DEVICES=0
+
+OUTDIR=bert-mnli
+NEPOCH=3
+
+WORKDIR=transformers/examples/pytorch/text-classification
+cd $WORKDIR
+
+python run_glue.py \
+    --model_name_or_path bert-base-uncased \
+    --task_name mnli \
+    --max_seq_length 128 \
+    --do_train \
+    --per_device_train_batch_size 32 \
+    --learning_rate 2e-5 \
+    --num_train_epochs $NEPOCH \
+    --logging_steps 1 \
+    --evaluation_strategy steps \
+    --save_steps 3000 \
+    --do_eval \
+    --per_device_eval_batch_size 128 \
+    --eval_steps 250 \
+    --output_dir $OUTDIR
+    --overwrite_output_dir
+```
+
+# Eval
+```bash
+export CUDA_VISIBLE_DEVICES=0
+
+OUTDIR=eval-bert-mnli
+WORKDIR=transformers/examples/pytorch/text-classification
+cd $WORKDIR
+
+nohup python run_glue.py \
+    --model_name_or_path vuiseng9/bert-mnli  \
+    --task_name mnli  \
+    --do_eval  \
+    --per_device_eval_batch_size 128  \
+    --max_seq_length 128  \
+    --overwrite_output_dir \
+    --output_dir $OUTDIR 2>&1 | tee $OUTDIR/run.log &
+```

all_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.8494711147274207,
+    "eval_loss": 0.46933791041374207,
+    "eval_runtime": 22.6994,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 433.139,
+    "eval_steps_per_second": 3.392
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "mnli",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_mnli-mm_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.8494711147274207,
+    "eval_loss": 0.46933791041374207,
+    "eval_runtime": 22.6994,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 433.139,
+    "eval_steps_per_second": 3.392
+}

eval_mnli_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_accuracy": 0.8444218033622007,
+    "eval_loss": 0.49247315526008606,
+    "eval_runtime": 22.5125,
+    "eval_samples": 9815,
+    "eval_samples_per_second": 435.98,
+    "eval_steps_per_second": 3.42
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8494711147274207,
+    "eval_loss": 0.46933791041374207,
+    "eval_runtime": 22.4675,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 437.61,
+    "eval_steps_per_second": 3.427
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7ecc6a182477feca62817a4e028dbd3a949fac885da7b457b4517ad086774c9
+size 438022317

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, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.3605867331176782,
+    "train_runtime": 11742.5051,
+    "train_samples": 392702,
+    "train_samples_per_second": 100.328,
+    "train_steps_per_second": 3.135
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d6f3cbe28aea9c1b0c5b889ec91bec153ace6d29b73b98f5a59d8812b2be826
+size 2735