tuna1283 commited on
Commit
b5a937a
1 Parent(s): c6f7a63

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,26 +1,25 @@
1
  {
2
- "_name_or_path": "bert-base-cased",
 
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": "4.41.2",
23
- "type_vocab_size": 2,
24
- "use_cache": true,
25
  "vocab_size": 28996
26
  }
 
1
  {
2
+ "_name_or_path": "distilbert-base-cased",
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
+ "output_past": true,
17
  "pad_token_id": 0,
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
  "torch_dtype": "float32",
23
  "transformers_version": "4.41.2",
 
 
24
  "vocab_size": 28996
25
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9d022d71058e41abe81986c86f1842528f6b1ec320acda74f9afd9ce0b733bf
3
- size 430908208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aa1a061a19639578422978bb5066a1626fb99d8f5a98addd6c826218aa00c08
3
+ size 260782152
runs/Jun11_14-10-29_1a4ad80bbc80/events.out.tfevents.1718115035.1a4ad80bbc80.224.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe4dd2b1ee214ecbc15ae0bda4b284d2480b2de42c34eef3ee47f9c59ac81d12
3
+ size 4184
tokenizer_config.json CHANGED
@@ -50,6 +50,6 @@
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
- "tokenizer_class": "BertTokenizer",
54
  "unk_token": "[UNK]"
55
  }
 
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
  "unk_token": "[UNK]"
55
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a098ed7457b4c14b83482123f976115338c29b39771db8ca76b7f6a3957a9e8
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20898fa1f27dda2edcc5abc56b5b37b6b0147314e91d68ece206cdbac7ed5993
3
  size 5112