Hugging Face's logo

nbhimte
/
tiny-bert-mnli-distilled

Text Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
3
nbhimte commited on
Commit
562ef7a
·
1 Parent(s): 971b87e

Training in progress, epoch 1

Browse files
Files changed (11) hide show
  1. config.json +5 -7
  2. logs/1650179863.7701304/events.out.tfevents.1650179863.21997728a4be.74.1 +3 -0
  3. logs/1650180270.732872/events.out.tfevents.1650180270.21997728a4be.74.3 +3 -0
  4. logs/1650180709.8959146/events.out.tfevents.1650180709.21997728a4be.74.5 +3 -0
  5. logs/1650180749.8921547/events.out.tfevents.1650180749.21997728a4be.74.7 +3 -0
  6. logs/events.out.tfevents.1650179863.21997728a4be.74.0 +3 -0
  7. logs/events.out.tfevents.1650180270.21997728a4be.74.2 +3 -0
  8. logs/events.out.tfevents.1650180709.21997728a4be.74.4 +3 -0
  9. logs/events.out.tfevents.1650180749.21997728a4be.74.6 +3 -0
  10. pytorch_model.bin +2 -2
  11. training_args.bin +1 -1
config.json CHANGED
@@ -1,22 +1,20 @@
1
  {
2
- "_name_or_path": "prajjwal1/bert-tiny-mnli",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
8
- "finetuning_task": "mnli",
9
- "gradient_checkpointing": false,
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
- "hidden_size": 128,
13
  "id2label": {
14
  "0": "entailment",
15
  "1": "neutral",
16
  "2": "contradiction"
17
  },
18
  "initializer_range": 0.02,
19
- "intermediate_size": 512,
20
  "label2id": {
21
  "contradiction": "2",
22
  "entailment": "0",
@@ -25,8 +23,8 @@
25
  "layer_norm_eps": 1e-12,
26
  "max_position_embeddings": 512,
27
  "model_type": "bert",
28
- "num_attention_heads": 2,
29
- "num_hidden_layers": 2,
30
  "pad_token_id": 0,
31
  "position_embedding_type": "absolute",
32
  "problem_type": "single_label_classification",
 
1
  {
2
+ "_name_or_path": "google/bert_uncased_L-10_H-256_A-4",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
 
 
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 256,
11
  "id2label": {
12
  "0": "entailment",
13
  "1": "neutral",
14
  "2": "contradiction"
15
  },
16
  "initializer_range": 0.02,
17
+ "intermediate_size": 1024,
18
  "label2id": {
19
  "contradiction": "2",
20
  "entailment": "0",
 
23
  "layer_norm_eps": 1e-12,
24
  "max_position_embeddings": 512,
25
  "model_type": "bert",
26
+ "num_attention_heads": 4,
27
+ "num_hidden_layers": 10,
28
  "pad_token_id": 0,
29
  "position_embedding_type": "absolute",
30
  "problem_type": "single_label_classification",
logs/1650179863.7701304/events.out.tfevents.1650179863.21997728a4be.74.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:661fb67fd944b699611ce9a3def9ea9813d44bd1aeeb469fcc38ccc6da5ea7fe
3
+ size 4859
logs/1650180270.732872/events.out.tfevents.1650180270.21997728a4be.74.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:200497fbe0c8fd1acc97f2f6dd5ff0d10343aff3ee8bcc74fb77d43facff5c2b
3
+ size 4859
logs/1650180709.8959146/events.out.tfevents.1650180709.21997728a4be.74.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2540894ba6a1d8275e0a2b5db7daecf8b880d0f05efd4cb997d202eda40da92
3
+ size 4859
logs/1650180749.8921547/events.out.tfevents.1650180749.21997728a4be.74.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2e3be72434f098816dd1dbe9e372cb625e6c65187b4b8f9cfe2d140ee0063f5
3
+ size 4859
logs/events.out.tfevents.1650179863.21997728a4be.74.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eb2e98c44fcf0d35553c55b1142c1815312e1ade7367f1bf763caad2c97bb98
3
+ size 3458
logs/events.out.tfevents.1650180270.21997728a4be.74.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:497a3534d2146f197cf1e22be2d6acd6eb136d3a0058b4dc1478fc535a443523
3
+ size 3462
logs/events.out.tfevents.1650180709.21997728a4be.74.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a78a708092846c9412ec47c6bdd02f23bede44d66d86c94ccda11d328d1b7fd
3
+ size 3462
logs/events.out.tfevents.1650180749.21997728a4be.74.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f9a33fd2db28dbcccfc11932b3a8077c236f68db3dfb1ffca0b991032c7937
3
+ size 3940
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b13b90065f074c142d626eba375cfd4ffff3ad6b6d45a6425c19c0c8457d68ff
3
- size 17562343
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:460f0f042891e552d2c31917de82f8b89c4a735fe07b2881bd0a2f88d6392b9a
3
+ size 63699757
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07773dd8ca5123bbe639fcbe21679f4c579855f8da92ae052d531e6edd41d2a9
3
  size 3119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e0a1bc450d929f7a5483cbbaa02d5e65a3cb0fa8477d3bdbfb52b89ff46794b
3
  size 3119