Thenghuy commited on
Commit
60730d5
1 Parent(s): 845f908

Training in progress, step 500

Browse files
config.json CHANGED
@@ -1,24 +1,30 @@
1
  {
2
- "_name_or_path": "distilbert/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": "4.42.4",
 
 
23
  "vocab_size": 30522
24
  }
 
1
  {
2
+ "_name_or_path": "google/electra-base-discriminator",
 
3
  "architectures": [
4
+ "ElectraForQuestionAnswering"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 768,
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": "electra",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
  "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "summary_activation": "gelu",
22
+ "summary_last_dropout": 0.1,
23
+ "summary_type": "first",
24
+ "summary_use_proj": true,
25
  "torch_dtype": "float32",
26
  "transformers_version": "4.42.4",
27
+ "type_vocab_size": 2,
28
+ "use_cache": true,
29
  "vocab_size": 30522
30
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a28767c9adc220cb2ebd46e047ff75ba3b01f250fbe4da0e5e493c493c394c6
3
- size 265470032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3517edf93a3ce88b330d8f40aa8132169a362adcaae5fcc389dd735564dc5c6
3
+ size 435596680
runs/Jul16_01-34-52_a0cb631c20a3/events.out.tfevents.1721093694.a0cb631c20a3.3677.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdc50b579e690778fd14aa1b7707e5d8f60ed9bd4b2ee5d90c8bba29a737ebed
3
+ size 5445
tokenizer_config.json CHANGED
@@ -50,6 +50,6 @@
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
- "tokenizer_class": "DistilBertTokenizer",
54
  "unk_token": "[UNK]"
55
  }
 
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "ElectraTokenizer",
54
  "unk_token": "[UNK]"
55
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07b5dce1304936ce2621bcf387a0179c82b8dd49f5f6f0f7ee66df3ad4da47d4
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fcf816560b50350166222eb1eec4ba9aaa76a108ff7af31bb319f6c2ed316f5
3
  size 5112