fgiuhsdfkjhfv
commited on
Commit
•
df4fd9e
1
Parent(s):
d36dc84
Training in progress, epoch 0
Browse files- .gitignore +1 -0
- config.json +69 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Jun05_09-37-10_3060afc830c3/1685957845.443826/events.out.tfevents.1685957845.3060afc830c3.696.1 +3 -0
- runs/Jun05_09-37-10_3060afc830c3/events.out.tfevents.1685957845.3060afc830c3.696.0 +3 -0
- runs/Jun05_09-39-31_3060afc830c3/1685957984.8626876/events.out.tfevents.1685957984.3060afc830c3.2035.1 +3 -0
- runs/Jun05_09-39-31_3060afc830c3/events.out.tfevents.1685957984.3060afc830c3.2035.0 +3 -0
- runs/Jun05_09-48-47_3060afc830c3/1685958532.8930733/events.out.tfevents.1685958532.3060afc830c3.4573.1 +3 -0
- runs/Jun05_09-48-47_3060afc830c3/events.out.tfevents.1685958532.3060afc830c3.4573.0 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +64 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "pszemraj/led-large-book-summary",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "gelu",
|
6 |
+
"architectures": [
|
7 |
+
"LEDForConditionalGeneration"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"attention_window": [
|
11 |
+
1024,
|
12 |
+
1024,
|
13 |
+
1024,
|
14 |
+
1024,
|
15 |
+
1024,
|
16 |
+
1024,
|
17 |
+
1024,
|
18 |
+
1024,
|
19 |
+
1024,
|
20 |
+
1024,
|
21 |
+
1024,
|
22 |
+
1024
|
23 |
+
],
|
24 |
+
"bos_token_id": 0,
|
25 |
+
"classif_dropout": 0.0,
|
26 |
+
"classifier_dropout": 0.0,
|
27 |
+
"d_model": 1024,
|
28 |
+
"decoder_attention_heads": 16,
|
29 |
+
"decoder_ffn_dim": 4096,
|
30 |
+
"decoder_layerdrop": 0.0,
|
31 |
+
"decoder_layers": 12,
|
32 |
+
"decoder_start_token_id": 2,
|
33 |
+
"dropout": 0.1,
|
34 |
+
"early_stopping": true,
|
35 |
+
"encoder_attention_heads": 16,
|
36 |
+
"encoder_ffn_dim": 4096,
|
37 |
+
"encoder_layerdrop": 0.0,
|
38 |
+
"encoder_layers": 12,
|
39 |
+
"eos_token_id": 2,
|
40 |
+
"id2label": {
|
41 |
+
"0": "LABEL_0",
|
42 |
+
"1": "LABEL_1",
|
43 |
+
"2": "LABEL_2"
|
44 |
+
},
|
45 |
+
"init_std": 0.02,
|
46 |
+
"is_encoder_decoder": true,
|
47 |
+
"label2id": {
|
48 |
+
"LABEL_0": 0,
|
49 |
+
"LABEL_1": 1,
|
50 |
+
"LABEL_2": 2
|
51 |
+
},
|
52 |
+
"length_penalty": 0.8,
|
53 |
+
"max_decoder_position_embeddings": 1024,
|
54 |
+
"max_encoder_position_embeddings": 16384,
|
55 |
+
"max_length": 1024,
|
56 |
+
"min_length": 8,
|
57 |
+
"model_type": "led",
|
58 |
+
"no_repeat_ngram_size": 3,
|
59 |
+
"num_beams": 4,
|
60 |
+
"num_hidden_layers": 12,
|
61 |
+
"output_past": false,
|
62 |
+
"pad_token_id": 1,
|
63 |
+
"prefix": " ",
|
64 |
+
"repetition_penalty": 3.5,
|
65 |
+
"torch_dtype": "float32",
|
66 |
+
"transformers_version": "4.29.2",
|
67 |
+
"use_cache": true,
|
68 |
+
"vocab_size": 50265
|
69 |
+
}
|
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:d51f9825d61b0b8ef37490d1b15496dd036dd79d344dff9ed6e07cdf6b5f0338
|
3 |
+
size 1839608749
|
runs/Jun05_09-37-10_3060afc830c3/1685957845.443826/events.out.tfevents.1685957845.3060afc830c3.696.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:240520ebd48b16627af92a867112efeb30e54dea04a32851f556ea2fa94f1d85
|
3 |
+
size 6201
|
runs/Jun05_09-37-10_3060afc830c3/events.out.tfevents.1685957845.3060afc830c3.696.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0cd0ace3eb00cb80d57e625c16a3beebd47ffb4d59516c24289c4ff41437a34
|
3 |
+
size 4184
|
runs/Jun05_09-39-31_3060afc830c3/1685957984.8626876/events.out.tfevents.1685957984.3060afc830c3.2035.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de3186e20b33357ff76d47d8ceb23da180b5dcc843180b692858382ca966e3fb
|
3 |
+
size 6201
|
runs/Jun05_09-39-31_3060afc830c3/events.out.tfevents.1685957984.3060afc830c3.2035.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cee13f2a3d4a03298093bc69a88c25cb6d0052358806f117bb92f3c3e2ee7dae
|
3 |
+
size 4967
|
runs/Jun05_09-48-47_3060afc830c3/1685958532.8930733/events.out.tfevents.1685958532.3060afc830c3.4573.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff5178f7897ad08827af9062d9f0b9d76e72b7b4c9ea07e1d2f42bbfa840fe4d
|
3 |
+
size 6201
|
runs/Jun05_09-48-47_3060afc830c3/events.out.tfevents.1685958532.3060afc830c3.4573.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4872cb29cda4f998414268d2cfe26c15c638a8051cf128e81052733c9609130c
|
3 |
+
size 4966
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": {
|
4 |
+
"__type": "AddedToken",
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"clean_up_tokenization_spaces": true,
|
12 |
+
"cls_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"eos_token": {
|
21 |
+
"__type": "AddedToken",
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"errors": "replace",
|
29 |
+
"mask_token": {
|
30 |
+
"__type": "AddedToken",
|
31 |
+
"content": "<mask>",
|
32 |
+
"lstrip": true,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"model_max_length": 16384,
|
38 |
+
"pad_token": {
|
39 |
+
"__type": "AddedToken",
|
40 |
+
"content": "<pad>",
|
41 |
+
"lstrip": false,
|
42 |
+
"normalized": true,
|
43 |
+
"rstrip": false,
|
44 |
+
"single_word": false
|
45 |
+
},
|
46 |
+
"sep_token": {
|
47 |
+
"__type": "AddedToken",
|
48 |
+
"content": "</s>",
|
49 |
+
"lstrip": false,
|
50 |
+
"normalized": true,
|
51 |
+
"rstrip": false,
|
52 |
+
"single_word": false
|
53 |
+
},
|
54 |
+
"tokenizer_class": "LEDTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": {
|
57 |
+
"__type": "AddedToken",
|
58 |
+
"content": "<unk>",
|
59 |
+
"lstrip": false,
|
60 |
+
"normalized": true,
|
61 |
+
"rstrip": false,
|
62 |
+
"single_word": false
|
63 |
+
}
|
64 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b98a1dc042faf862e46d622e192eca6fad17ffbf8111f584f065ce91e413d14
|
3 |
+
size 4091
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|