dirkgr commited on
Commit
75345d2
1 Parent(s): b5e53a5

Update repository

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ *.th filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - allennlp
4
+ ---
5
+
6
+ # TODO: Fill this model card
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_reader": {
3
+ "type": "transformer_squad",
4
+ "length_limit": 512,
5
+ "transformer_model_name": "roberta-large"
6
+ },
7
+ "model": {
8
+ "type": "transformer_qa",
9
+ "transformer_model_name": "roberta-large"
10
+ },
11
+ "train_data_path": "https://allennlp.s3.amazonaws.com/datasets/squad/squad-train-v2.0.json",
12
+ "validation_data_path": "https://allennlp.s3.amazonaws.com/datasets/squad/squad-dev-v2.0.json",
13
+ "trainer": {
14
+ "callbacks": [
15
+ "tensorboard"
16
+ ],
17
+ "grad_clipping": 1,
18
+ "learning_rate_scheduler": {
19
+ "type": "slanted_triangular",
20
+ "cut_frac": 0.1,
21
+ "num_epochs": 5
22
+ },
23
+ "num_epochs": 5,
24
+ "optimizer": {
25
+ "type": "huggingface_adamw",
26
+ "eps": 1e-08,
27
+ "lr": 2e-05,
28
+ "parameter_groups": [
29
+ [
30
+ [
31
+ "bias",
32
+ "LayerNorm\\.weight",
33
+ "layer_norm\\.weight"
34
+ ],
35
+ {
36
+ "weight_decay": 0
37
+ }
38
+ ]
39
+ ],
40
+ "weight_decay": 0
41
+ },
42
+ "validation_metric": "+per_instance_f1"
43
+ },
44
+ "vocabulary": {
45
+ "type": "empty"
46
+ },
47
+ "data_loader": {
48
+ "batch_sampler": {
49
+ "type": "bucket",
50
+ "batch_size": 16
51
+ }
52
+ },
53
+ "numpy_seed": 100,
54
+ "pytorch_seed": 100,
55
+ "random_seed": 100
56
+ }
log/train/events.out.tfevents.1641511262.allennlp-server4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28b17b0ce6c705f88706ce37e773225572f4041ca42617e8d207dbd58eb66748
3
+ size 122640
log/validation/events.out.tfevents.1641511262.allennlp-server4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8159cd15da6100d0143466465fced1f2de9bf4470cdc1008b0245e422998b2cd
3
+ size 1800
metrics.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_epoch": 4,
3
+ "peak_worker_0_memory_MB": 11547.5625,
4
+ "peak_gpu_0_memory_MB": 38261.77734375,
5
+ "training_duration": "1:47:58.814697",
6
+ "epoch": 4,
7
+ "training_start_acc": 0.9045047529318044,
8
+ "training_end_acc": 0.9274995978583083,
9
+ "training_span_acc": 0.8602538471555178,
10
+ "training_loss": 0.25246852851203444,
11
+ "training_worker_0_memory_MB": 11547.5625,
12
+ "training_gpu_0_memory_MB": 38261.77734375,
13
+ "validation_start_acc": 0.768297783354245,
14
+ "validation_end_acc": 0.7805938937682978,
15
+ "validation_span_acc": 0.7103304056879967,
16
+ "validation_per_instance_em": 0.7990615049438579,
17
+ "validation_per_instance_f1": 0.8714919661257248,
18
+ "validation_loss": 1.0740951053140795,
19
+ "best_validation_start_acc": 0.768297783354245,
20
+ "best_validation_end_acc": 0.7805938937682978,
21
+ "best_validation_span_acc": 0.7103304056879967,
22
+ "best_validation_per_instance_em": 0.7990615049438579,
23
+ "best_validation_per_instance_f1": 0.8714919661257248,
24
+ "best_validation_loss": 1.0740951053140795
25
+ }
vocabulary/.lock ADDED
File without changes
vocabulary/non_padded_namespaces.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ *labels
2
+ *tags
weights.th ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b06772c05c6129f0258a5917bc8a2317481a258736f253969f50ba0177e614e
3
+ size 1421654445