marcus2000 commited on
Commit
7676b45
1 Parent(s): 190573c

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/PRIMERA",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": false,
8
+ "architectures": [
9
+ "LEDForConditionalGeneration"
10
+ ],
11
+ "attention_dilation": [
12
+ 1,
13
+ 1,
14
+ 1,
15
+ 1,
16
+ 1,
17
+ 1,
18
+ 1,
19
+ 1,
20
+ 1,
21
+ 1,
22
+ 1,
23
+ 1
24
+ ],
25
+ "attention_dropout": 0.0,
26
+ "attention_mode": "sliding_chunks",
27
+ "attention_window": [
28
+ 512,
29
+ 512,
30
+ 512,
31
+ 512,
32
+ 512,
33
+ 512,
34
+ 512,
35
+ 512,
36
+ 512,
37
+ 512,
38
+ 512,
39
+ 512
40
+ ],
41
+ "autoregressive": false,
42
+ "bos_token_id": 0,
43
+ "classif_dropout": 0.0,
44
+ "classifier_dropout": 0.0,
45
+ "d_model": 1024,
46
+ "decoder_attention_heads": 16,
47
+ "decoder_ffn_dim": 4096,
48
+ "decoder_layerdrop": 0.0,
49
+ "decoder_layers": 12,
50
+ "decoder_start_token_id": 2,
51
+ "dropout": 0.1,
52
+ "encoder_attention_heads": 16,
53
+ "encoder_ffn_dim": 4096,
54
+ "encoder_layerdrop": 0.0,
55
+ "encoder_layers": 12,
56
+ "eos_token_id": 2,
57
+ "extra_pos_embeddings": 2,
58
+ "force_bos_token_to_be_generated": false,
59
+ "id2label": {
60
+ "0": "LABEL_0",
61
+ "1": "LABEL_1",
62
+ "2": "LABEL_2"
63
+ },
64
+ "init_std": 0.02,
65
+ "is_encoder_decoder": true,
66
+ "label2id": {
67
+ "LABEL_0": 0,
68
+ "LABEL_1": 1,
69
+ "LABEL_2": 2
70
+ },
71
+ "max_decoder_position_embeddings": 1024,
72
+ "max_encoder_position_embeddings": 4096,
73
+ "max_position_embeddings": 4096,
74
+ "model_type": "led",
75
+ "no_repeat_ngram_size": 3,
76
+ "normalize_before": false,
77
+ "normalize_embedding": true,
78
+ "num_hidden_layers": 12,
79
+ "output_past": false,
80
+ "pad_token_id": 1,
81
+ "prefix": " ",
82
+ "scale_embedding": false,
83
+ "static_position_embeddings": false,
84
+ "task_specific_params": {
85
+ "summarization": {
86
+ "early_stopping": true,
87
+ "length_penalty": 2.0,
88
+ "max_length": 142,
89
+ "min_length": 56,
90
+ "no_repeat_ngram_size": 3,
91
+ "num_beams": 4
92
+ }
93
+ },
94
+ "torch_dtype": "float32",
95
+ "transformers_version": "4.28.1",
96
+ "use_cache": true,
97
+ "vocab_size": 50266
98
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2c3c8e87b4e921723149639055741f90bd9d0077b06858bfee8916fe7b15241
3
+ size 1789281197
runs/Apr27_19-36-24_32ef514e8da2/1682624199.3576772/events.out.tfevents.1682624199.32ef514e8da2.973.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ed22d606244b07d3f2eea44fae262e8849c87d832c05b6918ab92d43dfb69a
3
+ size 5846
runs/Apr27_19-36-24_32ef514e8da2/events.out.tfevents.1682624199.32ef514e8da2.973.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10cf26ea68ff54c2e1b39c90bbf8fbc6a65b339277b3b45f4e20a8affc40506a
3
+ size 5455
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d13e2fdeb952dde4d3230fc1760d86ce7172c1a4259852aaeb884ac7a2b5af76
3
+ size 3579