Add PyTorch model

README.md

@@ -0,0 +1,60 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model-index:
+- name: bert-base-uncased-squad-v1
+  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. -->
+
+# bert-base-uncased-squad-v1
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the squad dataset.
+It was finetuned following the [Transformers Question Answering example](https://github.com/huggingface/transformers/tree/main/examples/pytorch/question-answering#fine-tuning-bert-on-squad10):
+
+```
+python run_qa.py \
+  --model_name_or_path bert-base-uncased \
+  --dataset_name squad \
+  --do_train \
+  --do_eval \
+  --per_device_train_batch_size 12 \
+  --learning_rate 3e-5 \
+  --num_train_epochs 2 \
+  --max_seq_length 384 \
+  --doc_stride 128 \
+```
+
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 12
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+
+### Training results
+
+```
+***** eval metrics *****
+  epoch                   =        2.0
+  eval_exact_match        =    81.3434
+  eval_f1                 =    88.7002
+  eval_samples            =      10784
+```
+
+### Framework versions
+
+- Transformers 4.26.1
+- Pytorch 1.13.1+cu117
+- Datasets 2.8.0
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 81.3434247871334,
+    "eval_f1": 88.70015033447665,
+    "eval_runtime": 74.167,
+    "eval_samples": 10784,
+    "eval_samples_per_second": 145.402,
+    "eval_steps_per_second": 18.175,
+    "train_loss": 0.9892611550787075,
+    "train_runtime": 3658.4093,
+    "train_samples": 88524,
+    "train_samples_per_second": 48.395,
+    "train_steps_per_second": 4.033
+}

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": "4.26.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_nbest_predictions.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c750938f72f994bb763ffb717bae2eacdf5f0a8077af1504e38be7fc81117ed
+size 6651720

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 81.3434247871334,
+    "eval_f1": 88.70015033447665,
+    "eval_runtime": 74.167,
+    "eval_samples": 10784,
+    "eval_samples_per_second": 145.402,
+    "eval_steps_per_second": 18.175
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d64df54871e3ef926b5649e9faa696f4f1ed2220c28f9f7aa8bd72e71e1d1b7
+size 435644909

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.9892611550787075,
+    "train_runtime": 3658.4093,
+    "train_samples": 88524,
+    "train_samples_per_second": 48.395,
+    "train_steps_per_second": 4.033
+}

trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 14754,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.8983326555510372e-05,
+      "loss": 2.4547,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.796665311102074e-05,
+      "loss": 1.4963,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.694997966653111e-05,
+      "loss": 1.4012,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.593330622204148e-05,
+      "loss": 1.3187,
+      "step": 2000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.491663277755185e-05,
+      "loss": 1.249,
+      "step": 2500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.389995933306222e-05,
+      "loss": 1.1969,
+      "step": 3000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.288328588857259e-05,
+      "loss": 1.1941,
+      "step": 3500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.1866612444082963e-05,
+      "loss": 1.1202,
+      "step": 4000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2.084993899959333e-05,
+      "loss": 1.0896,
+      "step": 4500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.9833265555103702e-05,
+      "loss": 1.0834,
+      "step": 5000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.8816592110614073e-05,
+      "loss": 1.1031,
+      "step": 5500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.779991866612444e-05,
+      "loss": 1.0656,
+      "step": 6000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6783245221634812e-05,
+      "loss": 1.0266,
+      "step": 6500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.576657177714518e-05,
+      "loss": 1.0489,
+      "step": 7000
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.4749898332655551e-05,
+      "loss": 0.944,
+      "step": 7500
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.373322488816592e-05,
+      "loss": 0.7275,
+      "step": 8000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.271655144367629e-05,
+      "loss": 0.7439,
+      "step": 8500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.1699877999186661e-05,
+      "loss": 0.7352,
+      "step": 9000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.0683204554697033e-05,
+      "loss": 0.693,
+      "step": 9500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 9.666531110207402e-06,
+      "loss": 0.736,
+      "step": 10000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 8.649857665717772e-06,
+      "loss": 0.7238,
+      "step": 10500
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 7.633184221228141e-06,
+      "loss": 0.7266,
+      "step": 11000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 6.616510776738511e-06,
+      "loss": 0.7112,
+      "step": 11500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5.5998373322488825e-06,
+      "loss": 0.7348,
+      "step": 12000
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 4.583163887759252e-06,
+      "loss": 0.6808,
+      "step": 12500
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.566490443269622e-06,
+      "loss": 0.6928,
+      "step": 13000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 2.549816998779992e-06,
+      "loss": 0.7016,
+      "step": 13500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.533143554290362e-06,
+      "loss": 0.719,
+      "step": 14000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.164701098007319e-07,
+      "loss": 0.7163,
+      "step": 14500
+    },
+    {
+      "epoch": 2.0,
+      "step": 14754,
+      "total_flos": 3.4696551139946496e+16,
+      "train_loss": 0.9892611550787075,
+      "train_runtime": 3658.4093,
+      "train_samples_per_second": 48.395,
+      "train_steps_per_second": 4.033
+    }
+  ],
+  "max_steps": 14754,
+  "num_train_epochs": 2,
+  "total_flos": 3.4696551139946496e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26a2eebb14569b751c64a2d5f4f110cbda50a97f9546e04a6896423d5e287a55
+size 3515