Training in progress, epoch 1
Browse files- config.json +45 -0
- model.safetensors +3 -0
- runs/Sep04_12-11-59_e2e-68-229/events.out.tfevents.1725466430.e2e-68-229 +3 -0
- runs/Sep04_12-15-56_e2e-68-229/events.out.tfevents.1725466563.e2e-68-229 +3 -0
- runs/Sep04_12-16-53_e2e-68-229/events.out.tfevents.1725466621.e2e-68-229 +3 -0
- runs/Sep04_12-19-17_e2e-68-229/events.out.tfevents.1725466766.e2e-68-229 +3 -0
- runs/Sep04_12-23-16_e2e-68-229/events.out.tfevents.1725467105.e2e-68-229 +3 -0
- runs/Sep04_15-07-03_e2e-68-229/events.out.tfevents.1725476869.e2e-68-229 +3 -0
- special_tokens_map.json +78 -0
- tokenizer.json +0 -0
- tokenizer_config.json +287 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "danasone/bart-small-ru-en",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"BartForConditionalGeneration"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"classifier_dropout": 0.0,
|
11 |
+
"d_model": 512,
|
12 |
+
"decoder_attention_heads": 4,
|
13 |
+
"decoder_ffn_dim": 2048,
|
14 |
+
"decoder_layerdrop": 0.0,
|
15 |
+
"decoder_layers": 2,
|
16 |
+
"decoder_start_token_id": 2,
|
17 |
+
"dropout": 0.1,
|
18 |
+
"encoder_attention_heads": 4,
|
19 |
+
"encoder_ffn_dim": 2048,
|
20 |
+
"encoder_layerdrop": 0.0,
|
21 |
+
"encoder_layers": 2,
|
22 |
+
"eos_token_id": 2,
|
23 |
+
"forced_eos_token_id": 2,
|
24 |
+
"id2label": {
|
25 |
+
"0": "LABEL_0",
|
26 |
+
"1": "LABEL_1",
|
27 |
+
"2": "LABEL_2"
|
28 |
+
},
|
29 |
+
"init_std": 0.02,
|
30 |
+
"is_encoder_decoder": true,
|
31 |
+
"label2id": {
|
32 |
+
"LABEL_0": 0,
|
33 |
+
"LABEL_1": 1,
|
34 |
+
"LABEL_2": 2
|
35 |
+
},
|
36 |
+
"max_position_embeddings": 1024,
|
37 |
+
"model_type": "bart",
|
38 |
+
"num_hidden_layers": 2,
|
39 |
+
"pad_token_id": 1,
|
40 |
+
"scale_embedding": false,
|
41 |
+
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.45.0.dev0",
|
43 |
+
"use_cache": true,
|
44 |
+
"vocab_size": 65561
|
45 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db91a420a92541310b1cd861d3a91ba70981faad406efd20526210d58eab0d7d
|
3 |
+
size 197603580
|
runs/Sep04_12-11-59_e2e-68-229/events.out.tfevents.1725466430.e2e-68-229
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a0ab82328adafeb7bb4521d9fc135578dcc08b65b2c76dc4231b43d910e8260
|
3 |
+
size 5398
|
runs/Sep04_12-15-56_e2e-68-229/events.out.tfevents.1725466563.e2e-68-229
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4bd495b6d830a477ca528769657d21361cf085b1bd92541c18f474e4c6d84e6
|
3 |
+
size 5398
|
runs/Sep04_12-16-53_e2e-68-229/events.out.tfevents.1725466621.e2e-68-229
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22348eeecdce5bd45e0b631322da2630ef659388d5ff1263a452b3c1372e4ff5
|
3 |
+
size 7468
|
runs/Sep04_12-19-17_e2e-68-229/events.out.tfevents.1725466766.e2e-68-229
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7216bc856b7666a9501f3958c505331e6a1e9b815bd95b63bdadd6b555875812
|
3 |
+
size 9992
|
runs/Sep04_12-23-16_e2e-68-229/events.out.tfevents.1725467105.e2e-68-229
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e60a87e9c1d7a8920cba93a8836db4c6dbec1997e7493d469ad134e5bb5f4d1
|
3 |
+
size 238453
|
runs/Sep04_15-07-03_e2e-68-229/events.out.tfevents.1725476869.e2e-68-229
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eceeb66c07dd83bc50bb5df8f71f543c533c3182077c0a961b7e46bb74e9796e
|
3 |
+
size 179637
|
special_tokens_map.json
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"ar_AR",
|
4 |
+
"cs_CZ",
|
5 |
+
"de_DE",
|
6 |
+
"en_XX",
|
7 |
+
"es_XX",
|
8 |
+
"et_EE",
|
9 |
+
"fi_FI",
|
10 |
+
"fr_XX",
|
11 |
+
"gu_IN",
|
12 |
+
"hi_IN",
|
13 |
+
"it_IT",
|
14 |
+
"ja_XX",
|
15 |
+
"kk_KZ",
|
16 |
+
"ko_KR",
|
17 |
+
"lt_LT",
|
18 |
+
"lv_LV",
|
19 |
+
"my_MM",
|
20 |
+
"ne_NP",
|
21 |
+
"nl_XX",
|
22 |
+
"ro_RO",
|
23 |
+
"ru_RU",
|
24 |
+
"si_LK",
|
25 |
+
"tr_TR",
|
26 |
+
"vi_VN",
|
27 |
+
"zh_CN"
|
28 |
+
],
|
29 |
+
"bos_token": {
|
30 |
+
"content": "<s>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
},
|
36 |
+
"cls_token": {
|
37 |
+
"content": "<s>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false
|
42 |
+
},
|
43 |
+
"eos_token": {
|
44 |
+
"content": "</s>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false
|
49 |
+
},
|
50 |
+
"mask_token": {
|
51 |
+
"content": "<mask>",
|
52 |
+
"lstrip": true,
|
53 |
+
"normalized": true,
|
54 |
+
"rstrip": false,
|
55 |
+
"single_word": false
|
56 |
+
},
|
57 |
+
"pad_token": {
|
58 |
+
"content": "<pad>",
|
59 |
+
"lstrip": false,
|
60 |
+
"normalized": true,
|
61 |
+
"rstrip": false,
|
62 |
+
"single_word": false
|
63 |
+
},
|
64 |
+
"sep_token": {
|
65 |
+
"content": "</s>",
|
66 |
+
"lstrip": false,
|
67 |
+
"normalized": true,
|
68 |
+
"rstrip": false,
|
69 |
+
"single_word": false
|
70 |
+
},
|
71 |
+
"unk_token": {
|
72 |
+
"content": "<unk>",
|
73 |
+
"lstrip": false,
|
74 |
+
"normalized": true,
|
75 |
+
"rstrip": false,
|
76 |
+
"single_word": false
|
77 |
+
}
|
78 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,287 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"4": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"65536": {
|
45 |
+
"content": "ar_AR",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"65537": {
|
53 |
+
"content": "cs_CZ",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"65538": {
|
61 |
+
"content": "de_DE",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"65539": {
|
69 |
+
"content": "en_XX",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"65540": {
|
77 |
+
"content": "es_XX",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"65541": {
|
85 |
+
"content": "et_EE",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"65542": {
|
93 |
+
"content": "fi_FI",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"65543": {
|
101 |
+
"content": "fr_XX",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"65544": {
|
109 |
+
"content": "gu_IN",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"65545": {
|
117 |
+
"content": "hi_IN",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": true
|
123 |
+
},
|
124 |
+
"65546": {
|
125 |
+
"content": "it_IT",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
"65547": {
|
133 |
+
"content": "ja_XX",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": true
|
139 |
+
},
|
140 |
+
"65548": {
|
141 |
+
"content": "kk_KZ",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": true
|
147 |
+
},
|
148 |
+
"65549": {
|
149 |
+
"content": "ko_KR",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": false,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": true
|
155 |
+
},
|
156 |
+
"65550": {
|
157 |
+
"content": "lt_LT",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": false,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": true
|
163 |
+
},
|
164 |
+
"65551": {
|
165 |
+
"content": "lv_LV",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": true
|
171 |
+
},
|
172 |
+
"65552": {
|
173 |
+
"content": "my_MM",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": false,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": true
|
179 |
+
},
|
180 |
+
"65553": {
|
181 |
+
"content": "ne_NP",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": false,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": true
|
187 |
+
},
|
188 |
+
"65554": {
|
189 |
+
"content": "nl_XX",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": false,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": true
|
195 |
+
},
|
196 |
+
"65555": {
|
197 |
+
"content": "ro_RO",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": false,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": true
|
203 |
+
},
|
204 |
+
"65556": {
|
205 |
+
"content": "ru_RU",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": false,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": true
|
211 |
+
},
|
212 |
+
"65557": {
|
213 |
+
"content": "si_LK",
|
214 |
+
"lstrip": false,
|
215 |
+
"normalized": false,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": true
|
219 |
+
},
|
220 |
+
"65558": {
|
221 |
+
"content": "tr_TR",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": true
|
227 |
+
},
|
228 |
+
"65559": {
|
229 |
+
"content": "vi_VN",
|
230 |
+
"lstrip": false,
|
231 |
+
"normalized": false,
|
232 |
+
"rstrip": false,
|
233 |
+
"single_word": false,
|
234 |
+
"special": true
|
235 |
+
},
|
236 |
+
"65560": {
|
237 |
+
"content": "zh_CN",
|
238 |
+
"lstrip": false,
|
239 |
+
"normalized": false,
|
240 |
+
"rstrip": false,
|
241 |
+
"single_word": false,
|
242 |
+
"special": true
|
243 |
+
}
|
244 |
+
},
|
245 |
+
"additional_special_tokens": [
|
246 |
+
"ar_AR",
|
247 |
+
"cs_CZ",
|
248 |
+
"de_DE",
|
249 |
+
"en_XX",
|
250 |
+
"es_XX",
|
251 |
+
"et_EE",
|
252 |
+
"fi_FI",
|
253 |
+
"fr_XX",
|
254 |
+
"gu_IN",
|
255 |
+
"hi_IN",
|
256 |
+
"it_IT",
|
257 |
+
"ja_XX",
|
258 |
+
"kk_KZ",
|
259 |
+
"ko_KR",
|
260 |
+
"lt_LT",
|
261 |
+
"lv_LV",
|
262 |
+
"my_MM",
|
263 |
+
"ne_NP",
|
264 |
+
"nl_XX",
|
265 |
+
"ro_RO",
|
266 |
+
"ru_RU",
|
267 |
+
"si_LK",
|
268 |
+
"tr_TR",
|
269 |
+
"vi_VN",
|
270 |
+
"zh_CN"
|
271 |
+
],
|
272 |
+
"bos_token": "<s>",
|
273 |
+
"clean_up_tokenization_spaces": true,
|
274 |
+
"cls_token": "<s>",
|
275 |
+
"eos_token": "</s>",
|
276 |
+
"errors": "replace",
|
277 |
+
"mask_token": "<mask>",
|
278 |
+
"max_len": 512,
|
279 |
+
"model_max_length": 1024,
|
280 |
+
"pad_token": "<pad>",
|
281 |
+
"sep_token": "</s>",
|
282 |
+
"src_lang": "en_XX",
|
283 |
+
"tgt_lang": "en_XX",
|
284 |
+
"tokenizer_class": "MBartTokenizer",
|
285 |
+
"trim_offsets": true,
|
286 |
+
"unk_token": "<unk>"
|
287 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbdbe63770a0078c74d73b2ee9fd952c93d61264eb11640e25a5dc3edaa4e2fe
|
3 |
+
size 5368
|