RDCPP commited on
Commit
d861969
·
1 Parent(s): 213c310

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": "4.28.1",
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:ac29a86d02147bddb7b33823ca0dffad0023402529791c3eb60409e26adc2581
3
+ size 1625537293
runs/Apr24_07-17-49_gpusvr102003/1682320683.5340626/events.out.tfevents.1682320683.gpusvr102003.18732.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ac289383fccad5820aa5b6eda41bc7216fb192e0ec3d7616e7f56120a29b663
3
+ size 6119
runs/Apr24_07-17-49_gpusvr102003/events.out.tfevents.1682320683.gpusvr102003.18732.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a646a8b6b289b29a2f8c9dd52f4a527c5f5aaf934f92fd2f55add84107ff82b9
3
+ size 5090
runs/Apr24_07-19-38_gpusvr102003/1682320785.734338/events.out.tfevents.1682320785.gpusvr102003.18732.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4c0fa9ebb86c26e6ba715d9d6ae1fcf651ec24c7bfd03fead03d7f4bbc02d27
3
+ size 6119
runs/Apr24_07-19-38_gpusvr102003/events.out.tfevents.1682320785.gpusvr102003.18732.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:636222e970ee0c0a13e34fa7350a4f1e7be00ea2ea137b9ebef35f6b53477a07
3
+ size 5090
runs/Apr24_07-20-07_gpusvr102003/1682320814.5947163/events.out.tfevents.1682320814.gpusvr102003.18732.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e128fe2a880648780f7161b2e5d261e5206f8a9b1c5a71e4a2222b7701dd370
3
+ size 6119
runs/Apr24_07-20-07_gpusvr102003/events.out.tfevents.1682320814.gpusvr102003.18732.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf527b159499c6b68a1d3de8fee0b6ec7f026cdbacf0014a8abb7564cec72066
3
+ size 5090
runs/Apr24_07-21-59_gpusvr102003/1682320927.552789/events.out.tfevents.1682320927.gpusvr102003.18732.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfc03647dd8565c096df9ad6ca28cbb4a9b50415e5519bf87eb1aeae31715f5a
3
+ size 6119
runs/Apr24_07-21-59_gpusvr102003/events.out.tfevents.1682320927.gpusvr102003.18732.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:487fbd4293513761a8e7c9b3e120b0ce95048d00f30033818addff7d349e388a
3
+ size 4136
runs/Apr24_07-22-26_gpusvr102003/1682320954.3729467/events.out.tfevents.1682320954.gpusvr102003.18732.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57a04bbaefe20911ed05ba1cc42d582514183223d204b14627d687eb32aa3788
3
+ size 6119
runs/Apr24_07-22-26_gpusvr102003/events.out.tfevents.1682320954.gpusvr102003.18732.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c619cf661c33eaff2095ef3fe7f95fca82034a6d29983dd1a344aeafc6f620f2
3
+ size 4136
runs/Apr24_07-25-38_gpusvr102003/1682321148.3276746/events.out.tfevents.1682321148.gpusvr102003.21715.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b4e012e6a09cedc39ce05134691c1ddc29e5d273567b2c5ea89e868ed82e374
3
+ size 6119
runs/Apr24_07-25-38_gpusvr102003/events.out.tfevents.1682321148.gpusvr102003.21715.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8460983a58fc7986b24e44ea44575b5cd791c2f7bb8f1d2502c7727c4a8e5d7e
3
+ size 5247
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
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 1024,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
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:e7f262d9cc4041ce7ed5e4520e8e80d030e30871baaf72b9e42eab4912201ed0
3
+ size 3771
vocab.json ADDED
The diff for this file is too large to render. See raw diff