Training in progress, epoch 1
Browse files- .gitignore +1 -0
- added_tokens.json +1 -0
- config.json +97 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Mar18_15-43-06_DESKTOP-AUUC0F6/1647589401.1217492/events.out.tfevents.1647589401.DESKTOP-AUUC0F6.17404.1 +3 -0
- runs/Mar18_15-43-06_DESKTOP-AUUC0F6/events.out.tfevents.1647589401.DESKTOP-AUUC0F6.17404.0 +3 -0
- runs/Mar18_15-49-01_DESKTOP-AUUC0F6/1647589751.1013832/events.out.tfevents.1647589751.DESKTOP-AUUC0F6.18396.1 +3 -0
- runs/Mar18_15-49-01_DESKTOP-AUUC0F6/events.out.tfevents.1647589751.DESKTOP-AUUC0F6.18396.0 +3 -0
- runs/Mar18_16-01-40_DESKTOP-AUUC0F6/1647590507.9876404/events.out.tfevents.1647590507.DESKTOP-AUUC0F6.18396.3 +3 -0
- runs/Mar18_16-01-40_DESKTOP-AUUC0F6/events.out.tfevents.1647590507.DESKTOP-AUUC0F6.18396.2 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<doc-sep>": 50265}
|
config.json
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 1024,
|
74 |
+
"model_type": "led",
|
75 |
+
"normalize_before": false,
|
76 |
+
"normalize_embedding": true,
|
77 |
+
"num_hidden_layers": 12,
|
78 |
+
"output_past": false,
|
79 |
+
"pad_token_id": 1,
|
80 |
+
"prefix": " ",
|
81 |
+
"scale_embedding": false,
|
82 |
+
"static_position_embeddings": false,
|
83 |
+
"task_specific_params": {
|
84 |
+
"summarization": {
|
85 |
+
"early_stopping": true,
|
86 |
+
"length_penalty": 2.0,
|
87 |
+
"max_length": 142,
|
88 |
+
"min_length": 56,
|
89 |
+
"no_repeat_ngram_size": 3,
|
90 |
+
"num_beams": 4
|
91 |
+
}
|
92 |
+
},
|
93 |
+
"torch_dtype": "float32",
|
94 |
+
"transformers_version": "4.16.2",
|
95 |
+
"use_cache": true,
|
96 |
+
"vocab_size": 50266
|
97 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea75871496db5f55598e6979ed47af0807b62819d4e81d13749564987e3ac9ae
|
3 |
+
size 1789300785
|
runs/Mar18_15-43-06_DESKTOP-AUUC0F6/1647589401.1217492/events.out.tfevents.1647589401.DESKTOP-AUUC0F6.17404.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d162d38397d83ab4dfe56054b514442c6c8061ed8b534873811507c82772c8f
|
3 |
+
size 5006
|
runs/Mar18_15-43-06_DESKTOP-AUUC0F6/events.out.tfevents.1647589401.DESKTOP-AUUC0F6.17404.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38f0e77177714ff7c44fc7970e1068737957f858c39bfc1f0dc9b5b6e77c4dff
|
3 |
+
size 4733
|
runs/Mar18_15-49-01_DESKTOP-AUUC0F6/1647589751.1013832/events.out.tfevents.1647589751.DESKTOP-AUUC0F6.18396.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d76084072edcb365b29dab16e51c3a6e76a85f57d1365fd5e4e3d27f250da4f
|
3 |
+
size 5006
|
runs/Mar18_15-49-01_DESKTOP-AUUC0F6/events.out.tfevents.1647589751.DESKTOP-AUUC0F6.18396.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b624f2ddbed853f96e8f73693fd59a32bda8fe627e97ce2fe871d70f9e872426
|
3 |
+
size 4733
|
runs/Mar18_16-01-40_DESKTOP-AUUC0F6/1647590507.9876404/events.out.tfevents.1647590507.DESKTOP-AUUC0F6.18396.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a20fc43391e87ea780557a21bffd2a60bb66dea89262ade77eb4b9ec37cd2d59
|
3 |
+
size 5006
|
runs/Mar18_16-01-40_DESKTOP-AUUC0F6/events.out.tfevents.1647590507.DESKTOP-AUUC0F6.18396.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8decb3e3e1a468a4a3a883c51bbb4e5e58c9db1afca7be358c18e905e151a086
|
3 |
+
size 5248
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": ["<doc-sep>"]}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "trim_offsets": true, "model_max_length": 4096, "special_tokens_map_file": "C:\\Users\\User/.cache\\huggingface\\transformers\\11580dbf54b49da2d44191726dd2ed18e1ed26a495b393512201f5822711c62b.0e55ca6797ff34881d64b92cd1563c7e5dbfccac3b6235e6923625abd01fb78b", "name_or_path": "allenai/PRIMERA", "tokenizer_class": "LEDTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:888607b3ec9443818bd79bbf61c94fcfd755d07cebd0d8326174937aba237704
|
3 |
+
size 3183
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|