End of training

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 200.0,
+    "eval_exact_match": 3.3964049195837274,
+    "eval_f1": 8.471180412571645,
+    "eval_samples": 10895,
+    "train_loss": 2.7743890380859373,
+    "train_runtime": 72.5729,
+    "train_samples": 16,
+    "train_samples_per_second": 66.14,
+    "train_steps_per_second": 2.756
+}

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": "4.16.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7247164d2f48e79c68fa8f3e63c7523fcef199a4381d259867ab77cb3ffcbb1d
+size 49099383

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 200.0,
+    "eval_exact_match": 3.3964049195837274,
+    "eval_f1": 8.471180412571645,
+    "eval_samples": 10895
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfcf7483ef8fa65333aaadf1ca967885fd3adde5ec7fc4d019c1c8b6ef721d22
+size 430968241

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": 200.0,
+    "train_loss": 2.7743890380859373,
+    "train_runtime": 72.5729,
+    "train_samples": 16,
+    "train_samples_per_second": 66.14,
+    "train_steps_per_second": 2.756
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 200.0,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 200.0,
+      "step": 200,
+      "total_flos": 627112216166400.0,
+      "train_loss": 2.7743890380859373,
+      "train_runtime": 72.5729,
+      "train_samples_per_second": 66.14,
+      "train_steps_per_second": 2.756
+    }
+  ],
+  "max_steps": 200,
+  "num_train_epochs": 200,
+  "total_flos": 627112216166400.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8784ae150aa1830899f1ef58b0992f7a669486b0d49cf8af0f3e4d18bed03fa
+size 3055