Xiaolihai commited on
Commit
c1ce0f8
1 Parent(s): f91f07e

Training in progress, step 600

Browse files
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "T5ForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_ff": 2048,
15
+ "d_kv": 64,
16
+ "d_model": 1024,
17
+ "decoder_attention_heads": 16,
18
+ "decoder_ffn_dim": 4096,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 12,
21
+ "decoder_start_token_id": 2,
22
+ "dense_act_fn": "relu",
23
+ "dropout": 0.1,
24
+ "dropout_rate": 0.1,
25
+ "early_stopping": true,
26
+ "encoder_attention_heads": 16,
27
+ "encoder_ffn_dim": 4096,
28
+ "encoder_layerdrop": 0.0,
29
+ "encoder_layers": 12,
30
+ "eos_token_id": 2,
31
+ "feed_forward_proj": "relu",
32
+ "force_bos_token_to_be_generated": true,
33
+ "forced_bos_token_id": 0,
34
+ "forced_eos_token_id": 2,
35
+ "gradient_checkpointing": false,
36
+ "id2label": {
37
+ "0": "LABEL_0",
38
+ "1": "LABEL_1",
39
+ "2": "LABEL_2"
40
+ },
41
+ "init_std": 0.02,
42
+ "initializer_factor": 1.0,
43
+ "is_encoder_decoder": true,
44
+ "is_gated_act": false,
45
+ "label2id": {
46
+ "LABEL_0": 0,
47
+ "LABEL_1": 1,
48
+ "LABEL_2": 2
49
+ },
50
+ "layer_norm_epsilon": 1e-06,
51
+ "length_penalty": 2.0,
52
+ "max_length": 142,
53
+ "max_position_embeddings": 1024,
54
+ "min_length": 56,
55
+ "model_type": "t5",
56
+ "no_repeat_ngram_size": 3,
57
+ "normalize_before": false,
58
+ "num_beams": 4,
59
+ "num_decoder_layers": 6,
60
+ "num_heads": 8,
61
+ "num_layers": 12,
62
+ "output_past": true,
63
+ "pad_token_id": 1,
64
+ "prefix": " ",
65
+ "relative_attention_max_distance": 128,
66
+ "relative_attention_num_buckets": 32,
67
+ "scale_embedding": false,
68
+ "task_specific_params": {
69
+ "summarization": {
70
+ "early_stopping": true,
71
+ "length_penalty": 2.0,
72
+ "max_length": 142,
73
+ "min_length": 56,
74
+ "no_repeat_ngram_size": 3,
75
+ "num_beams": 4
76
+ }
77
+ },
78
+ "torch_dtype": "float32",
79
+ "transformers_version": "4.39.3",
80
+ "use_cache": true,
81
+ "vocab_size": 50264
82
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f58d544ec8fefcfdbb4e6e1cb62ad202b395e1fbb0bfb5858b0b97e8f43898f2
3
+ size 1327045800
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": true,
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 1024,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "BartTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4508346644d067001cee5d3359d7c56df964a47cef8d7c6313abc97bc497145c
3
+ size 6331
vocab.json ADDED
The diff for this file is too large to render. See raw diff