Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +60 -0
- pytorch_model.bin +3 -0
- runs/Apr18_19-06-06_fa286f74956c/1681844773.2613542/events.out.tfevents.1681844773.fa286f74956c.692.1 +3 -0
- runs/Apr18_19-06-06_fa286f74956c/events.out.tfevents.1681844773.fa286f74956c.692.0 +3 -0
- special_tokens_map.json +110 -0
- tokenizer.json +0 -0
- tokenizer_config.json +117 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/pegasus-x-base",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": true,
|
7 |
+
"architectures": [
|
8 |
+
"PegasusXForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"block_size": 512,
|
12 |
+
"bos_token_id": 0,
|
13 |
+
"classif_dropout": 0.0,
|
14 |
+
"classifier_dropout": 0.0,
|
15 |
+
"d_model": 768,
|
16 |
+
"decoder_attention_heads": 12,
|
17 |
+
"decoder_ffn_dim": 3072,
|
18 |
+
"decoder_layerdrop": 0.0,
|
19 |
+
"decoder_layers": 12,
|
20 |
+
"decoder_start_token_id": 0,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"encoder_attention_heads": 12,
|
23 |
+
"encoder_ffn_dim": 3072,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 12,
|
26 |
+
"eos_token_id": 1,
|
27 |
+
"extra_pos_embeddings": 1,
|
28 |
+
"force_bos_token_to_be_generated": false,
|
29 |
+
"forced_eos_token_id": 1,
|
30 |
+
"gradient_checkpointing": false,
|
31 |
+
"id2label": {
|
32 |
+
"0": "LABEL_0",
|
33 |
+
"1": "LABEL_1",
|
34 |
+
"2": "LABEL_2"
|
35 |
+
},
|
36 |
+
"init_std": 0.02,
|
37 |
+
"is_encoder_decoder": true,
|
38 |
+
"label2id": {
|
39 |
+
"LABEL_0": 0,
|
40 |
+
"LABEL_1": 1,
|
41 |
+
"LABEL_2": 2
|
42 |
+
},
|
43 |
+
"length_penalty": 0.8,
|
44 |
+
"max_length": 16384,
|
45 |
+
"max_position_embeddings": 16384,
|
46 |
+
"model_type": "pegasus_x",
|
47 |
+
"normalize_before": true,
|
48 |
+
"normalize_embedding": false,
|
49 |
+
"num_beams": 8,
|
50 |
+
"num_global_tokens": 128,
|
51 |
+
"num_hidden_layers": 12,
|
52 |
+
"pad_token_id": 0,
|
53 |
+
"scale_embedding": true,
|
54 |
+
"stagger_local_blocks": true,
|
55 |
+
"static_position_embeddings": true,
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.28.1",
|
58 |
+
"use_cache": true,
|
59 |
+
"vocab_size": 96103
|
60 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87ecb73312588eb0e5e1abf7f4fb05dac5a74258eb83ceabab12c16dc85b7f77
|
3 |
+
size 1089301733
|
runs/Apr18_19-06-06_fa286f74956c/1681844773.2613542/events.out.tfevents.1681844773.fa286f74956c.692.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39f483ee99ecb9d2b1ec41ee5a9ec0ca19978fa71f686a7b9151f4e683f8a2b2
|
3 |
+
size 6211
|
runs/Apr18_19-06-06_fa286f74956c/events.out.tfevents.1681844773.fa286f74956c.692.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9f94fccf8d91d11054cd87b77bfdd26261b2071389bcb0cabe343b95e93c751
|
3 |
+
size 5039
|
special_tokens_map.json
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<mask_1>",
|
4 |
+
"<unk_2>",
|
5 |
+
"<unk_3>",
|
6 |
+
"<unk_4>",
|
7 |
+
"<unk_5>",
|
8 |
+
"<unk_6>",
|
9 |
+
"<unk_7>",
|
10 |
+
"<unk_8>",
|
11 |
+
"<unk_9>",
|
12 |
+
"<unk_10>",
|
13 |
+
"<unk_11>",
|
14 |
+
"<unk_12>",
|
15 |
+
"<unk_13>",
|
16 |
+
"<unk_14>",
|
17 |
+
"<unk_15>",
|
18 |
+
"<unk_16>",
|
19 |
+
"<unk_17>",
|
20 |
+
"<unk_18>",
|
21 |
+
"<unk_19>",
|
22 |
+
"<unk_20>",
|
23 |
+
"<unk_21>",
|
24 |
+
"<unk_22>",
|
25 |
+
"<unk_23>",
|
26 |
+
"<unk_24>",
|
27 |
+
"<unk_25>",
|
28 |
+
"<unk_26>",
|
29 |
+
"<unk_27>",
|
30 |
+
"<unk_28>",
|
31 |
+
"<unk_29>",
|
32 |
+
"<unk_30>",
|
33 |
+
"<unk_31>",
|
34 |
+
"<unk_32>",
|
35 |
+
"<unk_33>",
|
36 |
+
"<unk_34>",
|
37 |
+
"<unk_35>",
|
38 |
+
"<unk_36>",
|
39 |
+
"<unk_37>",
|
40 |
+
"<unk_38>",
|
41 |
+
"<unk_39>",
|
42 |
+
"<unk_40>",
|
43 |
+
"<unk_41>",
|
44 |
+
"<unk_42>",
|
45 |
+
"<unk_43>",
|
46 |
+
"<unk_44>",
|
47 |
+
"<unk_45>",
|
48 |
+
"<unk_46>",
|
49 |
+
"<unk_47>",
|
50 |
+
"<unk_48>",
|
51 |
+
"<unk_49>",
|
52 |
+
"<unk_50>",
|
53 |
+
"<unk_51>",
|
54 |
+
"<unk_52>",
|
55 |
+
"<unk_53>",
|
56 |
+
"<unk_54>",
|
57 |
+
"<unk_55>",
|
58 |
+
"<unk_56>",
|
59 |
+
"<unk_57>",
|
60 |
+
"<unk_58>",
|
61 |
+
"<unk_59>",
|
62 |
+
"<unk_60>",
|
63 |
+
"<unk_61>",
|
64 |
+
"<unk_62>",
|
65 |
+
"<unk_63>",
|
66 |
+
"<unk_64>",
|
67 |
+
"<unk_65>",
|
68 |
+
"<unk_66>",
|
69 |
+
"<unk_67>",
|
70 |
+
"<unk_68>",
|
71 |
+
"<unk_69>",
|
72 |
+
"<unk_70>",
|
73 |
+
"<unk_71>",
|
74 |
+
"<unk_72>",
|
75 |
+
"<unk_73>",
|
76 |
+
"<unk_74>",
|
77 |
+
"<unk_75>",
|
78 |
+
"<unk_76>",
|
79 |
+
"<unk_77>",
|
80 |
+
"<unk_78>",
|
81 |
+
"<unk_79>",
|
82 |
+
"<unk_80>",
|
83 |
+
"<unk_81>",
|
84 |
+
"<unk_82>",
|
85 |
+
"<unk_83>",
|
86 |
+
"<unk_84>",
|
87 |
+
"<unk_85>",
|
88 |
+
"<unk_86>",
|
89 |
+
"<unk_87>",
|
90 |
+
"<unk_88>",
|
91 |
+
"<unk_89>",
|
92 |
+
"<unk_90>",
|
93 |
+
"<unk_91>",
|
94 |
+
"<unk_92>",
|
95 |
+
"<unk_93>",
|
96 |
+
"<unk_94>",
|
97 |
+
"<unk_95>",
|
98 |
+
"<unk_96>",
|
99 |
+
"<unk_97>",
|
100 |
+
"<unk_98>",
|
101 |
+
"<unk_99>",
|
102 |
+
"<unk_100>",
|
103 |
+
"<unk_101>",
|
104 |
+
"<unk_102>"
|
105 |
+
],
|
106 |
+
"eos_token": "</s>",
|
107 |
+
"mask_token": "<mask_2>",
|
108 |
+
"pad_token": "<pad>",
|
109 |
+
"unk_token": "<unk>"
|
110 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<mask_1>",
|
4 |
+
"<unk_2>",
|
5 |
+
"<unk_3>",
|
6 |
+
"<unk_4>",
|
7 |
+
"<unk_5>",
|
8 |
+
"<unk_6>",
|
9 |
+
"<unk_7>",
|
10 |
+
"<unk_8>",
|
11 |
+
"<unk_9>",
|
12 |
+
"<unk_10>",
|
13 |
+
"<unk_11>",
|
14 |
+
"<unk_12>",
|
15 |
+
"<unk_13>",
|
16 |
+
"<unk_14>",
|
17 |
+
"<unk_15>",
|
18 |
+
"<unk_16>",
|
19 |
+
"<unk_17>",
|
20 |
+
"<unk_18>",
|
21 |
+
"<unk_19>",
|
22 |
+
"<unk_20>",
|
23 |
+
"<unk_21>",
|
24 |
+
"<unk_22>",
|
25 |
+
"<unk_23>",
|
26 |
+
"<unk_24>",
|
27 |
+
"<unk_25>",
|
28 |
+
"<unk_26>",
|
29 |
+
"<unk_27>",
|
30 |
+
"<unk_28>",
|
31 |
+
"<unk_29>",
|
32 |
+
"<unk_30>",
|
33 |
+
"<unk_31>",
|
34 |
+
"<unk_32>",
|
35 |
+
"<unk_33>",
|
36 |
+
"<unk_34>",
|
37 |
+
"<unk_35>",
|
38 |
+
"<unk_36>",
|
39 |
+
"<unk_37>",
|
40 |
+
"<unk_38>",
|
41 |
+
"<unk_39>",
|
42 |
+
"<unk_40>",
|
43 |
+
"<unk_41>",
|
44 |
+
"<unk_42>",
|
45 |
+
"<unk_43>",
|
46 |
+
"<unk_44>",
|
47 |
+
"<unk_45>",
|
48 |
+
"<unk_46>",
|
49 |
+
"<unk_47>",
|
50 |
+
"<unk_48>",
|
51 |
+
"<unk_49>",
|
52 |
+
"<unk_50>",
|
53 |
+
"<unk_51>",
|
54 |
+
"<unk_52>",
|
55 |
+
"<unk_53>",
|
56 |
+
"<unk_54>",
|
57 |
+
"<unk_55>",
|
58 |
+
"<unk_56>",
|
59 |
+
"<unk_57>",
|
60 |
+
"<unk_58>",
|
61 |
+
"<unk_59>",
|
62 |
+
"<unk_60>",
|
63 |
+
"<unk_61>",
|
64 |
+
"<unk_62>",
|
65 |
+
"<unk_63>",
|
66 |
+
"<unk_64>",
|
67 |
+
"<unk_65>",
|
68 |
+
"<unk_66>",
|
69 |
+
"<unk_67>",
|
70 |
+
"<unk_68>",
|
71 |
+
"<unk_69>",
|
72 |
+
"<unk_70>",
|
73 |
+
"<unk_71>",
|
74 |
+
"<unk_72>",
|
75 |
+
"<unk_73>",
|
76 |
+
"<unk_74>",
|
77 |
+
"<unk_75>",
|
78 |
+
"<unk_76>",
|
79 |
+
"<unk_77>",
|
80 |
+
"<unk_78>",
|
81 |
+
"<unk_79>",
|
82 |
+
"<unk_80>",
|
83 |
+
"<unk_81>",
|
84 |
+
"<unk_82>",
|
85 |
+
"<unk_83>",
|
86 |
+
"<unk_84>",
|
87 |
+
"<unk_85>",
|
88 |
+
"<unk_86>",
|
89 |
+
"<unk_87>",
|
90 |
+
"<unk_88>",
|
91 |
+
"<unk_89>",
|
92 |
+
"<unk_90>",
|
93 |
+
"<unk_91>",
|
94 |
+
"<unk_92>",
|
95 |
+
"<unk_93>",
|
96 |
+
"<unk_94>",
|
97 |
+
"<unk_95>",
|
98 |
+
"<unk_96>",
|
99 |
+
"<unk_97>",
|
100 |
+
"<unk_98>",
|
101 |
+
"<unk_99>",
|
102 |
+
"<unk_100>",
|
103 |
+
"<unk_101>",
|
104 |
+
"<unk_102>"
|
105 |
+
],
|
106 |
+
"clean_up_tokenization_spaces": true,
|
107 |
+
"eos_token": "</s>",
|
108 |
+
"full_tokenizer_file": null,
|
109 |
+
"mask_token": "<mask_2>",
|
110 |
+
"mask_token_sent": "<mask_1>",
|
111 |
+
"model_max_length": 1024,
|
112 |
+
"offset": 103,
|
113 |
+
"pad_token": "<pad>",
|
114 |
+
"sp_model_kwargs": {},
|
115 |
+
"tokenizer_class": "PegasusTokenizer",
|
116 |
+
"unk_token": "<unk>"
|
117 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41866af4df70f26d6ae766f10daad95f61885af118bc5102937a92476a5ce948
|
3 |
+
size 3771
|