Training in progress, epoch 1
Browse files- config.json +154 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Jan10_21-41-54_c6c8211e2688/events.out.tfevents.1704922938.c6c8211e2688.512.0 +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +61 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "MMG/mlm-spanish-roberta-base",
|
3 |
+
"add_prefix_space": true,
|
4 |
+
"architectures": [
|
5 |
+
"RobertaForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token": "<s>",
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"classifier_dropout": null,
|
11 |
+
"cls_token": "<s>",
|
12 |
+
"eos_token": "</s>",
|
13 |
+
"eos_token_id": 2,
|
14 |
+
"errors": "replace",
|
15 |
+
"gradient_checkpointing": false,
|
16 |
+
"hidden_act": "gelu",
|
17 |
+
"hidden_dropout_prob": 0.1,
|
18 |
+
"hidden_size": 768,
|
19 |
+
"id2label": {
|
20 |
+
"0": "B-GREET",
|
21 |
+
"1": "I-GREET",
|
22 |
+
"2": "B-APOLOGIZE",
|
23 |
+
"3": "I-APOLOGIZE",
|
24 |
+
"4": "B-EXPLAIN",
|
25 |
+
"5": "I-EXPLAIN",
|
26 |
+
"6": "B-CALM_USER",
|
27 |
+
"7": "I-CALM_USER",
|
28 |
+
"8": "B-VOICE_OPINION",
|
29 |
+
"9": "I-VOICE_OPINION",
|
30 |
+
"10": "B-CONFRONT",
|
31 |
+
"11": "I-CONFRONT",
|
32 |
+
"12": "B-EMPHATIZE",
|
33 |
+
"13": "I-EMPHATIZE",
|
34 |
+
"14": "B-MAKE_OFFER",
|
35 |
+
"15": "I-MAKE_OFFER",
|
36 |
+
"16": "B-AGREE",
|
37 |
+
"17": "I-AGREE",
|
38 |
+
"18": "B-EXPRESS_NEED",
|
39 |
+
"19": "I-EXPRESS_NEED",
|
40 |
+
"20": "B-COUNTER_OPINION",
|
41 |
+
"21": "I-COUNTER_OPINION",
|
42 |
+
"22": "B-ASK_FOR_OPINION",
|
43 |
+
"23": "I-ASK_FOR_OPINION",
|
44 |
+
"24": "B-REQUEST_PERSONAL_INFO",
|
45 |
+
"25": "I-REQUEST_PERSONAL_INFO",
|
46 |
+
"26": "B-ASK_QUESTION",
|
47 |
+
"27": "I-ASK_QUESTION",
|
48 |
+
"28": "B-GIVE_EVALUATION",
|
49 |
+
"29": "I-GIVE_EVALUATION",
|
50 |
+
"30": "B-NOTIFY_ACTION",
|
51 |
+
"31": "I-NOTIFY_ACTION",
|
52 |
+
"32": "B-EXPRESS_ENTHUSIASM",
|
53 |
+
"33": "I-EXPRESS_ENTHUSIASM",
|
54 |
+
"34": "B-ENCOURAGE",
|
55 |
+
"35": "I-ENCOURAGE",
|
56 |
+
"36": "B-EXPRESS_DOUBT",
|
57 |
+
"37": "I-EXPRESS_DOUBT",
|
58 |
+
"38": "B-STATE_USER_FACT",
|
59 |
+
"39": "I-STATE_USER_FACT",
|
60 |
+
"40": "B-STATE_ROBOT_FACT",
|
61 |
+
"41": "I-STATE_ROBOT_FACT",
|
62 |
+
"42": "B-STATE_THIRD_PARTY_FACT",
|
63 |
+
"43": "I-STATE_THIRD_PARTY_FACT",
|
64 |
+
"44": "B-OFFER_CHOICE",
|
65 |
+
"45": "I-OFFER_CHOICE",
|
66 |
+
"46": "B-REQUEST_ACTION",
|
67 |
+
"47": "I-REQUEST_ACTION",
|
68 |
+
"48": "B-SHOW_EMPATHY",
|
69 |
+
"49": "I-SHOW_EMPATHY",
|
70 |
+
"50": "B-CHANGE_TOPIC",
|
71 |
+
"51": "I-CHANGE_TOPIC",
|
72 |
+
"52": "B-THANK_USER",
|
73 |
+
"53": "I-THANK_USER",
|
74 |
+
"54": "B-REFUSE",
|
75 |
+
"55": "I-REFUSE"
|
76 |
+
},
|
77 |
+
"initializer_range": 0.02,
|
78 |
+
"intermediate_size": 3072,
|
79 |
+
"label2id": {
|
80 |
+
"B-AGREE": 16,
|
81 |
+
"B-APOLOGIZE": 2,
|
82 |
+
"B-ASK_FOR_OPINION": 22,
|
83 |
+
"B-ASK_QUESTION": 26,
|
84 |
+
"B-CALM_USER": 6,
|
85 |
+
"B-CHANGE_TOPIC": 50,
|
86 |
+
"B-CONFRONT": 10,
|
87 |
+
"B-COUNTER_OPINION": 20,
|
88 |
+
"B-EMPHATIZE": 12,
|
89 |
+
"B-ENCOURAGE": 34,
|
90 |
+
"B-EXPLAIN": 4,
|
91 |
+
"B-EXPRESS_DOUBT": 36,
|
92 |
+
"B-EXPRESS_ENTHUSIASM": 32,
|
93 |
+
"B-EXPRESS_NEED": 18,
|
94 |
+
"B-GIVE_EVALUATION": 28,
|
95 |
+
"B-GREET": 0,
|
96 |
+
"B-MAKE_OFFER": 14,
|
97 |
+
"B-NOTIFY_ACTION": 30,
|
98 |
+
"B-OFFER_CHOICE": 44,
|
99 |
+
"B-REFUSE": 54,
|
100 |
+
"B-REQUEST_ACTION": 46,
|
101 |
+
"B-REQUEST_PERSONAL_INFO": 24,
|
102 |
+
"B-SHOW_EMPATHY": 48,
|
103 |
+
"B-STATE_ROBOT_FACT": 40,
|
104 |
+
"B-STATE_THIRD_PARTY_FACT": 42,
|
105 |
+
"B-STATE_USER_FACT": 38,
|
106 |
+
"B-THANK_USER": 52,
|
107 |
+
"B-VOICE_OPINION": 8,
|
108 |
+
"I-AGREE": 17,
|
109 |
+
"I-APOLOGIZE": 3,
|
110 |
+
"I-ASK_FOR_OPINION": 23,
|
111 |
+
"I-ASK_QUESTION": 27,
|
112 |
+
"I-CALM_USER": 7,
|
113 |
+
"I-CHANGE_TOPIC": 51,
|
114 |
+
"I-CONFRONT": 11,
|
115 |
+
"I-COUNTER_OPINION": 21,
|
116 |
+
"I-EMPHATIZE": 13,
|
117 |
+
"I-ENCOURAGE": 35,
|
118 |
+
"I-EXPLAIN": 5,
|
119 |
+
"I-EXPRESS_DOUBT": 37,
|
120 |
+
"I-EXPRESS_ENTHUSIASM": 33,
|
121 |
+
"I-EXPRESS_NEED": 19,
|
122 |
+
"I-GIVE_EVALUATION": 29,
|
123 |
+
"I-GREET": 1,
|
124 |
+
"I-MAKE_OFFER": 15,
|
125 |
+
"I-NOTIFY_ACTION": 31,
|
126 |
+
"I-OFFER_CHOICE": 45,
|
127 |
+
"I-REFUSE": 55,
|
128 |
+
"I-REQUEST_ACTION": 47,
|
129 |
+
"I-REQUEST_PERSONAL_INFO": 25,
|
130 |
+
"I-SHOW_EMPATHY": 49,
|
131 |
+
"I-STATE_ROBOT_FACT": 41,
|
132 |
+
"I-STATE_THIRD_PARTY_FACT": 43,
|
133 |
+
"I-STATE_USER_FACT": 39,
|
134 |
+
"I-THANK_USER": 53,
|
135 |
+
"I-VOICE_OPINION": 9
|
136 |
+
},
|
137 |
+
"layer_norm_eps": 1e-12,
|
138 |
+
"mask_token": "<mask>",
|
139 |
+
"max_position_embeddings": 512,
|
140 |
+
"model_max_length": 512,
|
141 |
+
"model_type": "roberta",
|
142 |
+
"num_attention_heads": 12,
|
143 |
+
"num_hidden_layers": 12,
|
144 |
+
"pad_token": "<pad>",
|
145 |
+
"pad_token_id": 1,
|
146 |
+
"position_embedding_type": "absolute",
|
147 |
+
"sep_token": "</s>",
|
148 |
+
"torch_dtype": "float32",
|
149 |
+
"transformers_version": "4.35.2",
|
150 |
+
"type_vocab_size": 2,
|
151 |
+
"unk_token": "<unk>",
|
152 |
+
"use_cache": true,
|
153 |
+
"vocab_size": 52000
|
154 |
+
}
|
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 sha256:604402e7f7b47976b6d7a25aefcd85a9ccf456fe9825dad6d72a0922009c8912
|
3 |
+
size 501743200
|
runs/Jan10_21-41-54_c6c8211e2688/events.out.tfevents.1704922938.c6c8211e2688.512.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62cfd8676d790f0eb31d7ef5534f8cc754eef55a4da9165cdd465a5a25ed89f2
|
3 |
+
size 8244
|
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 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
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 |
+
"max_length": null,
|
52 |
+
"model_max_length": 1000000000000000019884624838656,
|
53 |
+
"pad_to_multiple_of": null,
|
54 |
+
"pad_token": "<pad>",
|
55 |
+
"pad_token_type_id": 0,
|
56 |
+
"padding_side": "right",
|
57 |
+
"sep_token": "</s>",
|
58 |
+
"tokenizer_class": "RobertaTokenizer",
|
59 |
+
"trim_offsets": true,
|
60 |
+
"unk_token": "<unk>"
|
61 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e693bf7857b7ed7319129537b58d3164c78277c54d3ab2e74f484532512d7251
|
3 |
+
size 4600
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|