Update repository

README.md

@@ -3,6 +3,12 @@ tags:
 - allennlp
 ---
 
+# TODO: Fill this model card
+---
+tags:
+- allennlp
+---
+
 This is an implementation of the BiDAF model with ELMo embeddings. The basic layout is pretty simple: encode words as a combination of word embeddings and a character-level encoder, pass the word representations through a bi-LSTM/GRU, use a matrix of attentions to put question information into the passage word representations (this is the only part that is at all non-standard), pass this through another few layers of bi-LSTMs/GRUs, and do a softmax over span start and span end.
 
 CAVEATS:

config.json

@@ -93,6 +93,11 @@
     "train_data_path": "https://allennlp.s3.amazonaws.com/datasets/squad/squad-train-v1.1.json",
     "validation_data_path": "https://allennlp.s3.amazonaws.com/datasets/squad/squad-dev-v1.1.json",
     "trainer": {
+        "callbacks": [
+            {
+                "type": "tensorboard"
+            }
+        ],
         "grad_norm": 5,
         "learning_rate_scheduler": {
             "type": "reduce_on_plateau",

log/train/events.out.tfevents.1639101937.allennlp-server4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c24f83844d792d74541109c0f326ec681ccbc23ee00ee84f195c110210489cc
+size 137156

log/validation/events.out.tfevents.1639101937.allennlp-server4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:240605c0f609df48c9b6a32f87d56e5a00944db4b1b5a78055befceea5d4ec23
+size 4930

metrics.json

@@ -1,27 +1,27 @@
 {
   "best_epoch": 4,
-  "peak_worker_0_memory_MB": 39697.6484375,
+  "peak_worker_0_memory_MB": 39687.31640625,
   "peak_gpu_0_memory_MB": 7284.326171875,
-  "training_duration": "4:33:51.728517",
+  "training_duration": "4:19:37.259793",
   "epoch": 14,
-  "training_start_acc": 0.9632758364821516,
-  "training_end_acc": 0.9648968595531913,
-  "training_span_acc": 0.9375221178323954,
-  "training_em": 0.9490519298165504,
-  "training_f1": 0.9746247710065422,
-  "training_loss": 0.21539007184950457,
-  "training_worker_0_memory_MB": 39697.6484375,
+  "training_start_acc": 0.9661183346841858,
+  "training_end_acc": 0.9663238164819233,
+  "training_span_acc": 0.9416203381317139,
+  "training_em": 0.9519857532620235,
+  "training_f1": 0.9757483852872945,
+  "training_loss": 0.20176630357267616,
+  "training_worker_0_memory_MB": 39687.31640625,
   "training_gpu_0_memory_MB": 7283.4765625,
-  "validation_start_acc": 0.6205298013245033,
-  "validation_end_acc": 0.6693472090823084,
-  "validation_span_acc": 0.5271523178807948,
-  "validation_em": 0.6779564806054872,
-  "validation_f1": 0.786469085303725,
-  "validation_loss": 4.7776187914722374,
-  "best_validation_start_acc": 0.6631031220435194,
-  "best_validation_end_acc": 0.6990539262062441,
-  "best_validation_span_acc": 0.5754020813623463,
-  "best_validation_em": 0.7165562913907285,
-  "best_validation_f1": 0.8039716876069539,
-  "best_validation_loss": 2.22837360759951
+  "validation_start_acc": 0.6244087038789026,
+  "validation_end_acc": 0.671523178807947,
+  "validation_span_acc": 0.5334910122989593,
+  "validation_em": 0.6758751182592242,
+  "validation_f1": 0.7833561202573218,
+  "validation_loss": 4.825442760395554,
+  "best_validation_start_acc": 0.6578997161778619,
+  "best_validation_end_acc": 0.6980132450331126,
+  "best_validation_span_acc": 0.5754966887417219,
+  "best_validation_em": 0.7126773888363293,
+  "best_validation_f1": 0.8017721561069574,
+  "best_validation_loss": 2.247398374665458
 }

vocabulary/non_padded_namespaces.txt

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

weights.th

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e347b7ff0a9e0dd64d355473388175b9dc1aff66e0d5b08def9e1de7da154c
+size 450055351