Upload 13 files

README.md

@@ -0,0 +1,52 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- squad
+model-index:
+- name: spanbert-base-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-base-squad
+
+This model is a fine-tuned version of [SpanBERT/spanbert-base-cased](https://huggingface.co/SpanBERT/spanbert-base-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: 48
+- 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": 84.47492904446547,
+    "eval_f1": 91.25713303314757,
+    "eval_samples": 10895,
+    "train_loss": 0.500451392185035,
+    "train_runtime": 1495.419,
+    "train_samples": 89357,
+    "train_samples_per_second": 119.508,
+    "train_steps_per_second": 2.49
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "SpanBERT/spanbert-base-cased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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": "4.18.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 84.47492904446547,
+    "eval_f1": 91.25713303314757,
+    "eval_samples": 10895
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee899a153b1e573393e116086681f9b1e68e6665fb6a362a4ea3b9eca59073f2
+size 430969201

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-base-cased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.500451392185035,
+    "train_runtime": 1495.419,
+    "train_samples": 89357,
+    "train_samples_per_second": 119.508,
+    "train_steps_per_second": 2.49
+}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 3724,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.597207303974221e-05,
+      "loss": 2.5132,
+      "step": 500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.1944146079484428e-05,
+      "loss": 1.3194,
+      "step": 1000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7916219119226638e-05,
+      "loss": 1.0847,
+      "step": 1500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.388829215896885e-05,
+      "loss": 0.9563,
+      "step": 2000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 9.860365198711064e-06,
+      "loss": 0.8287,
+      "step": 2500
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 5.832438238453276e-06,
+      "loss": 0.8071,
+      "step": 3000
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.8045112781954887e-06,
+      "loss": 0.7936,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "step": 3724,
+      "total_flos": 3.502304143748813e+16,
+      "train_loss": 0.500451392185035,
+      "train_runtime": 1495.419,
+      "train_samples_per_second": 119.508,
+      "train_steps_per_second": 2.49
+    }
+  ],
+  "max_steps": 3724,
+  "num_train_epochs": 2,
+  "total_flos": 3.502304143748813e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:052fb644c9a7ccdd8d060e31e0c5169bb5814b87a56777e1141917499a4f629b
+size 2991