Hugging Face's logo

Shushant
/
my_awesome_qa_model

Question Answering
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Shushant Pudasaini commited on
Commit
aaf3b20
•
1 Parent(s): 3eba75c

Training in progress, step 500

Browse files
Files changed (5) hide show
  1. config.json +16 -14
  2. pytorch_model.bin +2 -2
  3. runs/Feb09_15-40-07_0dbe902da219/1675957276.8710241/events.out.tfevents.1675957276.0dbe902da219.376.1 +3 -0
  4. runs/Feb09_15-40-07_0dbe902da219/events.out.tfevents.1675957276.0dbe902da219.376.0 +3 -0
  5. training_args.bin +1 -1
config.json CHANGED
@@ -1,24 +1,26 @@
1
  {
2
- "_name_or_path": "distilbert-base-uncased",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForQuestionAnswering"
6
  ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
 
 
11
  "initializer_range": 0.02,
 
 
12
  "max_position_embeddings": 512,
13
- "model_type": "distilbert",
14
- "n_heads": 12,
15
- "n_layers": 6,
16
  "pad_token_id": 0,
17
- "qa_dropout": 0.1,
18
- "seq_classif_dropout": 0.2,
19
- "sinusoidal_pos_embds": false,
20
- "tie_weights_": true,
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.26.0",
 
 
23
  "vocab_size": 30522
24
  }
 
1
  {
2
+ "_name_or_path": "bert-base-uncased",
 
3
  "architectures": [
4
+ "BertForQuestionAnswering"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
  "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
  "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
  "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
 
 
 
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.26.0",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
  "vocab_size": 30522
26
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:531a0035947b7c6e775b522f11e048f35983bf92c76fec59adb3670f3d70107a
3
- size 265491109
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3d083d7f163a7524721c12e769f2158d032c262cd0b8918cafabce2b3e2d119
3
+ size 435644909
runs/Feb09_15-40-07_0dbe902da219/1675957276.8710241/events.out.tfevents.1675957276.0dbe902da219.376.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:173c4b698eb7a26ebe7349d9e074bca193b4ccab20b7b1934fc67c304c741f93
3
+ size 5670
runs/Feb09_15-40-07_0dbe902da219/events.out.tfevents.1675957276.0dbe902da219.376.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72fcd08b586317b4968506b80cad4528b37283a1af6862b30d8ba7c775c087d9
3
+ size 4239
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29d5a8e430ac97622210270f9acf6ae4b378905b8bbd931d20125aa58111170e
3
  size 3515
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:125fae7eafb1f0fbf99a40683a33731329c66866e663da98178316c8db5dddd1
3
  size 3515