Update repository

README.md

@@ -9,4 +9,10 @@ tags:
 - allennlp
 ---
 
+# TODO: Fill this model card
+---
+tags:
+- allennlp
+---
+
 This is an implementation of the BiDAF model with GloVe 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.

config.json

@@ -83,6 +83,11 @@
     "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.1639092823.allennlp-server4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d101f26f68f30b20e2b5b7865eb9d1c9b1ede4ecab69bce14a0619e15bf6003
+size 183516

log/validation/events.out.tfevents.1639092823.allennlp-server4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6683ee1c443432c0726f6284003d203e8470dfef397509e4a1ef733fc481e4ac
+size 6560

metrics.json

@@ -1,27 +1,27 @@
 {
   "best_epoch": 10,
-  "peak_worker_0_memory_MB": 10196.45703125,
+  "peak_worker_0_memory_MB": 10187.48828125,
   "peak_gpu_0_memory_MB": 2483.1318359375,
-  "training_duration": "1:17:24.504377",
+  "training_duration": "1:18:19.087825",
   "epoch": 19,
-  "training_start_acc": 0.8321213712485303,
-  "training_end_acc": 0.8789598054772315,
-  "training_span_acc": 0.7638899987442779,
-  "training_em": 0.8128631605383623,
-  "training_f1": 0.9108974145873597,
-  "training_loss": 0.8540654097245708,
-  "training_worker_0_memory_MB": 10196.45703125,
+  "training_start_acc": 0.8339136291510177,
+  "training_end_acc": 0.8794849256270049,
+  "training_span_acc": 0.7644493658603408,
+  "training_em": 0.8141759609127958,
+  "training_f1": 0.9123879556752282,
+  "training_loss": 0.8476112175613778,
+  "training_worker_0_memory_MB": 10187.48828125,
   "training_gpu_0_memory_MB": 2470.0771484375,
-  "validation_start_acc": 0.6192999053926206,
-  "validation_end_acc": 0.6535477767265847,
-  "validation_span_acc": 0.528003784295175,
-  "validation_em": 0.659508041627247,
-  "validation_f1": 0.7623738533824579,
-  "validation_loss": 3.530728134569132,
-  "best_validation_start_acc": 0.6322611163670766,
-  "best_validation_end_acc": 0.6654683065279092,
-  "best_validation_span_acc": 0.5429517502365184,
-  "best_validation_em": 0.6717123935666982,
-  "best_validation_f1": 0.7701806420178526,
-  "best_validation_loss": 2.784988238676539
+  "validation_start_acc": 0.6137180700094608,
+  "validation_end_acc": 0.6549668874172185,
+  "validation_span_acc": 0.5263008514664144,
+  "validation_em": 0.660170293282876,
+  "validation_f1": 0.7624231918887229,
+  "validation_loss": 3.598719547829538,
+  "best_validation_start_acc": 0.6228003784295175,
+  "best_validation_end_acc": 0.6637653736991486,
+  "best_validation_span_acc": 0.5383159886471145,
+  "best_validation_em": 0.6693472090823084,
+  "best_validation_f1": 0.7684872331354092,
+  "best_validation_loss": 2.8135785696641453
 }

weights.th

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef195409cc6eabb0262f893a8a6b6766ed9e6f456ed8401d37893e376df29f61
+oid sha256:8cc6c680744855d63a0a23ce9a6ab4d6c62b5defa4c1c2360252329a7b55fd0e
 size 49008050