add content

README.md

@@ -0,0 +1,97 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model-index:
+- name: run05-roberta-large-squadv1.1-sl384-ds128-e2-tbs16
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# run05-roberta-large-squadv1.1-sl384-ds128-e2-tbs16
+
+This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the squad dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.18.0
+- Pytorch 1.11.0+cu113
+- Datasets 2.1.0
+- Tokenizers 0.12.1
+
+# Train
+```bash
+python run_qa.py \
+    --model_name_or_path roberta-large \
+    --dataset_name squad \
+    --do_eval \
+    --do_train \
+    --evaluation_strategy steps \
+    --eval_steps 500 \
+    --learning_rate 3e-5 \
+    --fp16 \
+    --num_train_epochs 2 \
+    --per_device_eval_batch_size 64 \
+    --per_device_train_batch_size 16 \
+    --max_seq_length 384 \
+    --doc_stride 128 \
+    --save_steps 1000 \
+    --logging_steps 1 \
+    --overwrite_output_dir \
+    --run_name $RUNID \
+    --output_dir $OUTDIR
+```
+
+# Eval
+```bash
+export CUDA_VISIBLE_DEVICES=0
+
+MODEL=vuiseng9/roberta-l-squadv1.1
+OUTDIR=eval-$(basename $MODEL)
+WORKDIR=transformers/examples/pytorch/question-answering
+cd $WORKDIR
+
+nohup python run_qa.py  \
+    --model_name_or_path  $MODEL \
+    --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": 88.45789971617786,
+    "eval_f1": 94.30632459083219,
+    "eval_samples": 10790,
+    "train_loss": 0.7616665850008564,
+    "train_runtime": 4169.2181,
+    "train_samples": 88568,
+    "train_samples_per_second": 42.487,
+    "train_steps_per_second": 2.656
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 88.45789971617786,
+    "eval_f1": 94.30632459083219,
+    "eval_samples": 10790
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:885be04aa71771d049d12c10423508ecdb4b6443415ea3443596812995bb826b
+size 1417385329

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-large", "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.7616665850008564,
+    "train_runtime": 4169.2181,
+    "train_samples": 88568,
+    "train_samples_per_second": 42.487,
+    "train_steps_per_second": 2.656
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39147a6bac51bae479afda16858d1c769d5ca3bc514ba0589435908261d8c04a
+size 3183