alex2awesome commited on
Commit
9cbdadf
·
1 Parent(s): 5960f68

Training in progress, step 500

Browse files
Files changed (4) hide show
  1. .gitignore +1 -0
  2. config.json +138 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-large",
3
+ "architectures": [
4
+ "SentenceClassificationModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classification_head": {
9
+ "num_labels": 9,
10
+ "pooling_method": "attention"
11
+ },
12
+ "classifier_dropout": null,
13
+ "context_config": {
14
+ "_name_or_path": "roberta-large",
15
+ "add_cross_attention": false,
16
+ "architectures": [
17
+ "RobertaForMaskedLM"
18
+ ],
19
+ "attention_probs_dropout_prob": 0.1,
20
+ "bad_words_ids": null,
21
+ "begin_suppress_tokens": null,
22
+ "bos_token_id": 0,
23
+ "chunk_size_feed_forward": 0,
24
+ "classifier_dropout": null,
25
+ "cross_attention_hidden_size": null,
26
+ "decoder_start_token_id": null,
27
+ "diversity_penalty": 0.0,
28
+ "do_sample": false,
29
+ "early_stopping": false,
30
+ "encoder_no_repeat_ngram_size": 0,
31
+ "eos_token_id": 2,
32
+ "exponential_decay_length_penalty": null,
33
+ "finetuning_task": null,
34
+ "forced_bos_token_id": null,
35
+ "forced_eos_token_id": null,
36
+ "hidden_act": "gelu",
37
+ "hidden_dropout_prob": 0.1,
38
+ "hidden_size": 1024,
39
+ "id2label": {
40
+ "0": "LABEL_0",
41
+ "1": "LABEL_1"
42
+ },
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 4096,
45
+ "is_decoder": false,
46
+ "is_encoder_decoder": false,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1
50
+ },
51
+ "layer_norm_eps": 1e-05,
52
+ "length_penalty": 1.0,
53
+ "max_length": 20,
54
+ "max_position_embeddings": 120,
55
+ "min_length": 0,
56
+ "model_type": "roberta",
57
+ "no_repeat_ngram_size": 0,
58
+ "num_attention_heads": 2,
59
+ "num_beam_groups": 1,
60
+ "num_beams": 1,
61
+ "num_hidden_layers": 2,
62
+ "num_return_sequences": 1,
63
+ "output_attentions": false,
64
+ "output_hidden_states": false,
65
+ "output_scores": false,
66
+ "pad_token_id": 1,
67
+ "position_embedding_type": "absolute",
68
+ "prefix": null,
69
+ "problem_type": null,
70
+ "pruned_heads": {},
71
+ "remove_invalid_values": false,
72
+ "repetition_penalty": 1.0,
73
+ "return_dict": true,
74
+ "return_dict_in_generate": false,
75
+ "sep_token_id": null,
76
+ "suppress_tokens": null,
77
+ "task_specific_params": null,
78
+ "temperature": 1.0,
79
+ "tf_legacy_loss": false,
80
+ "tie_encoder_decoder": false,
81
+ "tie_word_embeddings": true,
82
+ "tokenizer_class": null,
83
+ "top_k": 50,
84
+ "top_p": 1.0,
85
+ "torch_dtype": null,
86
+ "torchscript": false,
87
+ "transformers_version": "4.30.2",
88
+ "type_vocab_size": 1,
89
+ "typical_p": 1.0,
90
+ "use_bfloat16": false,
91
+ "use_cache": true,
92
+ "vocab_size": 50265
93
+ },
94
+ "context_layer": "transformer",
95
+ "eos_token_id": 2,
96
+ "frozen_layers": [
97
+ 0,
98
+ 1,
99
+ 2,
100
+ 3,
101
+ 4,
102
+ 5,
103
+ 6,
104
+ 7,
105
+ 8,
106
+ 9,
107
+ 10,
108
+ 11,
109
+ 12,
110
+ 13,
111
+ 14,
112
+ 15,
113
+ 16,
114
+ 17,
115
+ 18,
116
+ 19,
117
+ 20,
118
+ 21,
119
+ 22
120
+ ],
121
+ "hidden_act": "gelu",
122
+ "hidden_dropout_prob": 0.1,
123
+ "hidden_size": 1024,
124
+ "initializer_range": 0.02,
125
+ "intermediate_size": 4096,
126
+ "layer_norm_eps": 1e-05,
127
+ "max_position_embeddings": 514,
128
+ "model_type": "roberta",
129
+ "num_attention_heads": 16,
130
+ "num_hidden_layers": 24,
131
+ "pad_token_id": 1,
132
+ "position_embedding_type": "absolute",
133
+ "torch_dtype": "float32",
134
+ "transformers_version": "4.30.2",
135
+ "type_vocab_size": 1,
136
+ "use_cache": true,
137
+ "vocab_size": 50265
138
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf7b63b6cd3124235fd2ba2d05111f37e07d03a0477fdf041f2300a8c9647dd4
3
+ size 1737192225
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:534be5c7347ae2e41b31dbcf31907444936f00d0a8bc4d93cbd7a69512c6f5f6
3
+ size 3899