hw2942 commited on
Commit
1afd4c4
1 Parent(s): 2fa7914

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "fnlp/bart-base-chinese",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForSequenceClassification"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 101,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 102,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 102,
27
+ "forced_eos_token_id": 102,
28
+ "gradient_checkpointing": false,
29
+ "id2label": {
30
+ "0": "Down",
31
+ "1": "Up"
32
+ },
33
+ "init_std": 0.02,
34
+ "is_encoder_decoder": true,
35
+ "label2id": {
36
+ "Down": 0,
37
+ "Up": 1
38
+ },
39
+ "max_position_embeddings": 1024,
40
+ "model_type": "bart",
41
+ "no_repeat_ngram_size": 3,
42
+ "normalize_before": false,
43
+ "normalize_embedding": true,
44
+ "num_beams": 4,
45
+ "num_hidden_layers": 6,
46
+ "pad_token_id": 0,
47
+ "problem_type": "single_label_classification",
48
+ "scale_embedding": false,
49
+ "task_specific_params": {
50
+ "summarization": {
51
+ "length_penalty": 1.0,
52
+ "max_length": 128,
53
+ "min_length": 12,
54
+ "num_beams": 4
55
+ },
56
+ "summarization_cnn": {
57
+ "length_penalty": 2.0,
58
+ "max_length": 142,
59
+ "min_length": 56,
60
+ "num_beams": 4
61
+ },
62
+ "summarization_xsum": {
63
+ "length_penalty": 1.0,
64
+ "max_length": 62,
65
+ "min_length": 11,
66
+ "num_beams": 6
67
+ }
68
+ },
69
+ "tokenizer_class": "BertTokenizer",
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.31.0",
72
+ "use_cache": true,
73
+ "vocab_size": 51271
74
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2541a48dba7a90aa775e8f809d6aa52015601dd23b69c3975570244cbc8b4cc
3
+ size 563229993
runs/Aug03_08-28-26_65180ef476a0/events.out.tfevents.1691051324.65180ef476a0.610.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:572579171bc0cb9e31e2530b947936ab4bd89923696257356cbef5e3deb85a9d
3
+ size 10827
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:546f7fe25fe04336b8959be00aee39d56c06b414f830a9d13354a9cf7420f87a
3
+ size 4091