Update repository

.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
+*.th filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,6 @@
+---
+tags:
+- allennlp
+---
+
+# TODO: Fill this model card

config.json

@@ -0,0 +1,56 @@
+{
+    "dataset_reader": {
+        "type": "transformer_squad",
+        "length_limit": 512,
+        "transformer_model_name": "roberta-large"
+    },
+    "model": {
+        "type": "transformer_qa",
+        "transformer_model_name": "roberta-large"
+    },
+    "train_data_path": "https://allennlp.s3.amazonaws.com/datasets/squad/squad-train-v2.0.json",
+    "validation_data_path": "https://allennlp.s3.amazonaws.com/datasets/squad/squad-dev-v2.0.json",
+    "trainer": {
+        "callbacks": [
+            "tensorboard"
+        ],
+        "grad_clipping": 1,
+        "learning_rate_scheduler": {
+            "type": "slanted_triangular",
+            "cut_frac": 0.1,
+            "num_epochs": 5
+        },
+        "num_epochs": 5,
+        "optimizer": {
+            "type": "huggingface_adamw",
+            "eps": 1e-08,
+            "lr": 2e-05,
+            "parameter_groups": [
+                [
+                    [
+                        "bias",
+                        "LayerNorm\\.weight",
+                        "layer_norm\\.weight"
+                    ],
+                    {
+                        "weight_decay": 0
+                    }
+                ]
+            ],
+            "weight_decay": 0
+        },
+        "validation_metric": "+per_instance_f1"
+    },
+    "vocabulary": {
+        "type": "empty"
+    },
+    "data_loader": {
+        "batch_sampler": {
+            "type": "bucket",
+            "batch_size": 16
+        }
+    },
+    "numpy_seed": 100,
+    "pytorch_seed": 100,
+    "random_seed": 100
+}

log/train/events.out.tfevents.1641511262.allennlp-server4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b17b0ce6c705f88706ce37e773225572f4041ca42617e8d207dbd58eb66748
+size 122640

log/validation/events.out.tfevents.1641511262.allennlp-server4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8159cd15da6100d0143466465fced1f2de9bf4470cdc1008b0245e422998b2cd
+size 1800

metrics.json

@@ -0,0 +1,25 @@
+{
+  "best_epoch": 4,
+  "peak_worker_0_memory_MB": 11547.5625,
+  "peak_gpu_0_memory_MB": 38261.77734375,
+  "training_duration": "1:47:58.814697",
+  "epoch": 4,
+  "training_start_acc": 0.9045047529318044,
+  "training_end_acc": 0.9274995978583083,
+  "training_span_acc": 0.8602538471555178,
+  "training_loss": 0.25246852851203444,
+  "training_worker_0_memory_MB": 11547.5625,
+  "training_gpu_0_memory_MB": 38261.77734375,
+  "validation_start_acc": 0.768297783354245,
+  "validation_end_acc": 0.7805938937682978,
+  "validation_span_acc": 0.7103304056879967,
+  "validation_per_instance_em": 0.7990615049438579,
+  "validation_per_instance_f1": 0.8714919661257248,
+  "validation_loss": 1.0740951053140795,
+  "best_validation_start_acc": 0.768297783354245,
+  "best_validation_end_acc": 0.7805938937682978,
+  "best_validation_span_acc": 0.7103304056879967,
+  "best_validation_per_instance_em": 0.7990615049438579,
+  "best_validation_per_instance_f1": 0.8714919661257248,
+  "best_validation_loss": 1.0740951053140795
+}

vocabulary/non_padded_namespaces.txt

@@ -0,0 +1,2 @@
+*labels
+*tags

weights.th

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b06772c05c6129f0258a5917bc8a2317481a258736f253969f50ba0177e614e
+size 1421654445