Upload 13 files

README.md

@@ -0,0 +1,52 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model-index:
+- name: spanbert-large-squad
+  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. -->
+
+# spanbert-large-squad
+
+This model is a fine-tuned version of [SpanBERT/spanbert-large-cased](https://huggingface.co/SpanBERT/spanbert-large-cased) 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: 8
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.18.0.dev0
+- Pytorch 1.11.0+cu113
+- Datasets 2.0.0
+- Tokenizers 0.11.6

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 87.30368968779565,
+    "eval_f1": 93.42445743768727,
+    "eval_samples": 10895,
+    "train_loss": 0.7862384369251657,
+    "train_runtime": 27653.2865,
+    "train_samples": 89357,
+    "train_samples_per_second": 6.463,
+    "train_steps_per_second": 0.808
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "SpanBERT/spanbert-large-cased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 87.30368968779565,
+    "eval_f1": 93.42445743768727,
+    "eval_samples": 10895
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edbe961db66da5afe4bdf74b56b3cad7a671fc7277448063f652f55d014cb43f
+size 1330289585

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, "special_tokens_map_file": null, "name_or_path": "SpanBERT/spanbert-large-cased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.7862384369251657,
+    "train_runtime": 27653.2865,
+    "train_samples": 89357,
+    "train_samples_per_second": 6.463,
+    "train_steps_per_second": 0.808
+}

trainer_state.json

@@ -0,0 +1,289 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 22340,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.9328558639212178e-05,
+      "loss": 2.0835,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.865711727842435e-05,
+      "loss": 1.2634,
+      "step": 1000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.798567591763653e-05,
+      "loss": 1.1116,
+      "step": 1500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.7314234556848706e-05,
+      "loss": 1.0549,
+      "step": 2000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.6642793196060876e-05,
+      "loss": 1.0491,
+      "step": 2500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.5971351835273053e-05,
+      "loss": 1.0099,
+      "step": 3000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.529991047448523e-05,
+      "loss": 0.9937,
+      "step": 3500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.4628469113697404e-05,
+      "loss": 0.9877,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.395702775290958e-05,
+      "loss": 0.9661,
+      "step": 4500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.3285586392121754e-05,
+      "loss": 0.9319,
+      "step": 5000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.261414503133393e-05,
+      "loss": 0.9603,
+      "step": 5500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.194270367054611e-05,
+      "loss": 0.9003,
+      "step": 6000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.1271262309758282e-05,
+      "loss": 0.9247,
+      "step": 6500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2.0599820948970456e-05,
+      "loss": 0.8945,
+      "step": 7000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.9928379588182633e-05,
+      "loss": 0.8796,
+      "step": 7500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.9256938227394806e-05,
+      "loss": 0.8889,
+      "step": 8000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.8585496866606983e-05,
+      "loss": 0.874,
+      "step": 8500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.791405550581916e-05,
+      "loss": 0.8714,
+      "step": 9000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.7242614145031334e-05,
+      "loss": 0.8597,
+      "step": 9500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.657117278424351e-05,
+      "loss": 0.8679,
+      "step": 10000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5899731423455688e-05,
+      "loss": 0.8457,
+      "step": 10500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.522829006266786e-05,
+      "loss": 0.845,
+      "step": 11000
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.4556848701880037e-05,
+      "loss": 0.6936,
+      "step": 11500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.3885407341092211e-05,
+      "loss": 0.5779,
+      "step": 12000
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.3213965980304386e-05,
+      "loss": 0.5945,
+      "step": 12500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.2542524619516563e-05,
+      "loss": 0.6197,
+      "step": 13000
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.1871083258728739e-05,
+      "loss": 0.5957,
+      "step": 13500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.1199641897940914e-05,
+      "loss": 0.6061,
+      "step": 14000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.0528200537153088e-05,
+      "loss": 0.6015,
+      "step": 14500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 9.856759176365265e-06,
+      "loss": 0.581,
+      "step": 15000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 9.18531781557744e-06,
+      "loss": 0.5711,
+      "step": 15500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 8.513876454789615e-06,
+      "loss": 0.6045,
+      "step": 16000
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 7.84243509400179e-06,
+      "loss": 0.5616,
+      "step": 16500
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 7.170993733213966e-06,
+      "loss": 0.5823,
+      "step": 17000
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 6.4995523724261414e-06,
+      "loss": 0.5662,
+      "step": 17500
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 5.828111011638317e-06,
+      "loss": 0.557,
+      "step": 18000
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 5.156669650850493e-06,
+      "loss": 0.5472,
+      "step": 18500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 4.4852282900626675e-06,
+      "loss": 0.5643,
+      "step": 19000
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 3.8137869292748437e-06,
+      "loss": 0.5451,
+      "step": 19500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 3.142345568487019e-06,
+      "loss": 0.5431,
+      "step": 20000
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 2.4709042076991944e-06,
+      "loss": 0.568,
+      "step": 20500
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.7994628469113698e-06,
+      "loss": 0.5439,
+      "step": 21000
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.1280214861235453e-06,
+      "loss": 0.5323,
+      "step": 21500
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 4.565801253357207e-07,
+      "loss": 0.5353,
+      "step": 22000
+    },
+    {
+      "epoch": 2.0,
+      "step": 22340,
+      "total_flos": 1.2447970604337254e+17,
+      "train_loss": 0.7862384369251657,
+      "train_runtime": 27653.2865,
+      "train_samples_per_second": 6.463,
+      "train_steps_per_second": 0.808
+    }
+  ],
+  "max_steps": 22340,
+  "num_train_epochs": 2,
+  "total_flos": 1.2447970604337254e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a309113f05695330d62032c4413b31b64c1c909fdb7ee5a410409acc1d9e5de
+size 2991