Add model collaterals

README.md

@@ -0,0 +1,48 @@
+This model is developed with transformers v4.10.3.
+
+# Train
+```bash
+#!/usr/bin/env bash
+
+export CUDA_VISIBLE_DEVICES=0
+
+OUTDIR=bert-base-uncased-squad
+WORKDIR=transformers/examples/pytorch/question-answering
+cd $WORKDIR
+
+nohup python run_qa.py \
+    --model_name_or_path bert-base-uncased \
+    --dataset_name squad \
+    --do_eval \
+    --do_train \
+    --per_device_train_batch_size 16 \
+    --per_device_eval_batch_size 16 \
+    --doc_stride 128 \
+    --max_seq_length 384 \
+    --learning_rate 3e-5 \
+    --num_train_epochs 2 \
+    --eval_steps 250 \
+    --save_steps 2500 \
+    --logging_steps 1 \
+    --overwrite_output_dir \
+    --output_dir $OUTDIR 2>&1 | tee $OUTDIR/run.log &
+```
+
+# Eval
+```bash
+export CUDA_VISIBLE_DEVICES=0
+
+OUTDIR=eval-bert-base-uncased-squad
+WORKDIR=transformers/examples/pytorch/question-answering
+cd $WORKDIR
+
+nohup python run_glue.py  \
+    --model_name_or_path vuiseng9/bert-base-uncased-squad  \
+    --dataset_name squad  \
+    --do_eval  \
+    --per_device_eval_batch_size 16  \
+    --max_seq_length 384  \
+    --doc_stride 128  \
+    --overwrite_output_dir \
+    --output_dir $OUTDIR 2>&1 | tee $OUTDIR/run.log &
+```

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 81.48533585619678,
+    "eval_f1": 88.74052434563549,
+    "eval_samples": 10784,
+    "train_loss": 1.0129275434533833,
+    "train_runtime": 2434.5113,
+    "train_samples": 88524,
+    "train_samples_per_second": 72.724,
+    "train_steps_per_second": 4.545
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 81.48533585619678,
+    "eval_f1": 88.74052434563549,
+    "eval_samples": 10784
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48d2ec282a44502b9bbb4c4adb7b9c10f5b043629d24ab1e163d996ba7cbb18
+size 435656113

runs/Oct20_21-47-33_rtxws2/1634791695.9202113/events.out.tfevents.1634791695.rtxws2.353801.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99b431864233158f6d314bc7fe4af59e10d82e83651bc7d187e040098150eedc
+size 4239

runs/Oct20_21-47-33_rtxws2/events.out.tfevents.1634791695.rtxws2.353801.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:404df4c5a8ed03a85d6868a23f73c457475d8c66c5d5534b71565910f7f0d8e8
+size 1740337

runs/Oct20_21-47-33_rtxws2/events.out.tfevents.1634794203.rtxws2.353801.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f47099f666284f5919c020c647c86af853883684a6ded8179bd81237e8a62f
+size 191

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": 2.0,
+    "train_loss": 1.0129275434533833,
+    "train_runtime": 2434.5113,
+    "train_samples": 88524,
+    "train_samples_per_second": 72.724,
+    "train_steps_per_second": 4.545
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:712ba5cbd109908dcfd55daba9b0c8e0b72f7c1ffefe25ad5d7c8f8b2cefbff5
+size 2671