chinhon commited on
Commit
fae3500
1 Parent(s): 877d82e

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large-cnn",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "force_bos_token_to_be_generated": true,
28
+ "forced_bos_token_id": 0,
29
+ "forced_eos_token_id": 2,
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": 2.0,
44
+ "max_length": 142,
45
+ "max_position_embeddings": 1024,
46
+ "min_length": 56,
47
+ "model_type": "bart",
48
+ "no_repeat_ngram_size": 3,
49
+ "normalize_before": false,
50
+ "num_beams": 4,
51
+ "num_hidden_layers": 12,
52
+ "output_past": true,
53
+ "pad_token_id": 1,
54
+ "prefix": " ",
55
+ "scale_embedding": false,
56
+ "task_specific_params": {
57
+ "summarization": {
58
+ "early_stopping": true,
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "no_repeat_ngram_size": 3,
63
+ "num_beams": 4
64
+ }
65
+ },
66
+ "torch_dtype": "float32",
67
+ "transformers_version": "4.12.3",
68
+ "use_cache": true,
69
+ "vocab_size": 50264
70
+ }
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 sha256:3b06a70df5fc0b06ad2308c740027e32d24353230c86f03bfc94aa4b93b9aa93
3
+ size 1625553217
runs/Nov07_13-51-43_d081b045dd4a/1636293127.40451/events.out.tfevents.1636293127.d081b045dd4a.114.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:351cacb3f5ccd67631c054c8398438659bbd410e5759b6d92e64e1bbca908f29
3
+ size 4778
runs/Nov07_13-51-43_d081b045dd4a/events.out.tfevents.1636293127.d081b045dd4a.114.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e6088d2b369eaf94278ac5b147834efc1c2d540fa515ecb55c18327cd28e024
3
+ size 4290
runs/Nov07_13-52-17_d081b045dd4a/1636293147.5709007/events.out.tfevents.1636293147.d081b045dd4a.114.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b82927c3809047a3079944775c14281c2d249f7298054f7a8d9f6dbb311d327d
3
+ size 4778
runs/Nov07_13-52-17_d081b045dd4a/1636293153.737922/events.out.tfevents.1636293153.d081b045dd4a.114.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad7b758311fddb102d33e94954ccf511329079ca00dbfdd685006f2248200af
3
+ size 4778
runs/Nov07_13-52-17_d081b045dd4a/1636293155.5875728/events.out.tfevents.1636293155.d081b045dd4a.114.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dd8aa1e5616638e8d5c6ef3cc0a49a0db4d39a5877af91aeedec92b54aa25a5
3
+ size 4778
runs/Nov07_13-52-17_d081b045dd4a/1636293157.467243/events.out.tfevents.1636293157.d081b045dd4a.114.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7485026c94e739b7dad2cddb45d87858fe35faa39ec89e5ff4ee888c28d9006a
3
+ size 4778
runs/Nov07_13-52-17_d081b045dd4a/events.out.tfevents.1636293147.d081b045dd4a.114.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ccfcb27f0524913093c242562b47ca985f8ab7ffb7edd417f9192b9e1689abe
3
+ size 17040
runs/Nov07_13-53-28_d081b045dd4a/1636293215.8372917/events.out.tfevents.1636293215.d081b045dd4a.114.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dacf8014a214a6fc694e4f0bc753008907b3b9270882b26af1ab7a063db74a6
3
+ size 4778
runs/Nov07_13-53-28_d081b045dd4a/events.out.tfevents.1636293215.d081b045dd4a.114.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62b1481d7e72454a69f0c5a3d48ad89353603083cb0e12dd82e0aec1ec04fd87
3
+ size 4447
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}}
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": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-large-cnn", "tokenizer_class": "BartTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10a62c1972d086b46d9e17b0f81b9e2f015254dd8f782e5bcfb65fd187d32298
3
+ size 2991
vocab.json ADDED
The diff for this file is too large to render. See raw diff