qBob commited on
Commit
e634c07
·
1 Parent(s): 6c4a851

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ainize/bart-base-cnn",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 2,
27
+ "forced_eos_token_id": 2,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1",
31
+ "2": "LABEL_2"
32
+ },
33
+ "init_std": 0.02,
34
+ "is_encoder_decoder": true,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1,
38
+ "LABEL_2": 2
39
+ },
40
+ "max_position_embeddings": 1024,
41
+ "model_type": "bart",
42
+ "no_repeat_ngram_size": 3,
43
+ "normalize_before": false,
44
+ "normalize_embedding": true,
45
+ "num_beams": 4,
46
+ "num_hidden_layers": 6,
47
+ "pad_token_id": 1,
48
+ "scale_embedding": false,
49
+ "task_specific_params": {
50
+ "summarization": {
51
+ "length_penalty": 1.0,
52
+ "max_length": 128,
53
+ "min_length": 12,
54
+ "num_beams": 4
55
+ },
56
+ "summarization_cnn": {
57
+ "length_penalty": 2.0,
58
+ "max_length": 142,
59
+ "min_length": 56,
60
+ "num_beams": 4
61
+ },
62
+ "summarization_xsum": {
63
+ "length_penalty": 1.0,
64
+ "max_length": 62,
65
+ "min_length": 11,
66
+ "num_beams": 6
67
+ }
68
+ },
69
+ "torch_dtype": "float32",
70
+ "transformers_version": "4.21.1",
71
+ "use_cache": true,
72
+ "vocab_size": 50265
73
+ }
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:d5bc38caa34468f622ecca1287da706ab90520fa72beb90376ad27300801aea2
3
+ size 557969145
runs/Aug12_14-22-27_0bc12166e05f/1660314166.70042/events.out.tfevents.1660314166.0bc12166e05f.71.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f512f42f756b1fa51a6745616fc179aba0c538c881e77091eb61a4941766734b
3
+ size 5636
runs/Aug12_14-22-27_0bc12166e05f/1660314220.1546767/events.out.tfevents.1660314220.0bc12166e05f.71.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4ec9e1c7440f66dc923f5632b0986cebde5d2645c8a6805e276f25a4a53862e
3
+ size 5636
runs/Aug12_14-22-27_0bc12166e05f/1660314269.161092/events.out.tfevents.1660314269.0bc12166e05f.71.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50f2b87f406ca0548cbeea1195f7ab636b30559f202b0febfa3d72248f4999aa
3
+ size 5636
runs/Aug12_14-22-27_0bc12166e05f/events.out.tfevents.1660314166.0bc12166e05f.71.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e291c15ded279eb6e7d8d7afdb7cd187982ac49560c9f46a621623b23d3dbf58
3
+ size 4830
runs/Aug12_14-22-27_0bc12166e05f/events.out.tfevents.1660314220.0bc12166e05f.71.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65cfcc58ae6d9b4f1cfa812c971e41ddfbe9ee86897c9003bb975ca790e17dd7
3
+ size 9620
runs/Aug12_14-25-05_0bc12166e05f/1660314317.9250102/events.out.tfevents.1660314317.0bc12166e05f.71.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8059107216cb14863fa98d5418707e1f72846fcd9b1c8f84d7801bd3f87ddda2
3
+ size 5636
runs/Aug12_14-25-05_0bc12166e05f/events.out.tfevents.1660314317.0bc12166e05f.71.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1078e58220e03a5c362c82f69199965a83b81add45770ee0e58e049779f83f9b
3
+ size 4828
runs/Aug12_14-25-28_0bc12166e05f/1660314336.1879272/events.out.tfevents.1660314336.0bc12166e05f.71.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:973d6f42b98001a5745c754f865adc03bb24854b2cfec34fdcd88769c575a4d0
3
+ size 5636
runs/Aug12_14-25-28_0bc12166e05f/events.out.tfevents.1660314336.0bc12166e05f.71.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89ca6f525b8afd5e58f0909cf659d95e2d4918451dbe17338452da1dfebbbbb8
3
+ size 4828
runs/Aug12_14-34-43_0bc12166e05f/1660314970.2197053/events.out.tfevents.1660314970.0bc12166e05f.1480.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24cfb736cf679319def46fbe3660618598a4236f5e11bbe9a1b819aa11a6d756
3
+ size 5636
runs/Aug12_14-34-43_0bc12166e05f/events.out.tfevents.1660314970.0bc12166e05f.1480.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e233c20a8727a99b2577439a0103a941a3f2faa6f6d95fd62960f1f5b387266
3
+ size 4985
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "name_or_path": "ainize/bart-base-cnn",
9
+ "pad_token": "<pad>",
10
+ "sep_token": "</s>",
11
+ "special_tokens_map_file": null,
12
+ "tokenizer_class": "BartTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d65cb3bd2a90ccfb208b2044408ca72e543b75ffaac106990c5de5fde9c8e1b5
3
+ size 3439
vocab.json ADDED
The diff for this file is too large to render. See raw diff