Commit
•
0143798
1
Parent(s):
f9784fd
Training in progress, epoch 1
Browse files- .gitattributes +1 -0
- .gitignore +1 -0
- config.json +170 -0
- pytorch_model.bin +3 -0
- runs/Jun16_11-04-06_580c4d4a4d82/1655377453.0119276/events.out.tfevents.1655377453.580c4d4a4d82.82.1 +3 -0
- runs/Jun16_11-04-06_580c4d4a4d82/events.out.tfevents.1655377452.580c4d4a4d82.82.0 +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +3 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"EncoderDecoderModel"
|
4 |
+
],
|
5 |
+
"decoder": {
|
6 |
+
"_name_or_path": "xlm-roberta-base",
|
7 |
+
"add_cross_attention": true,
|
8 |
+
"architectures": [
|
9 |
+
"XLMRobertaForMaskedLM"
|
10 |
+
],
|
11 |
+
"attention_probs_dropout_prob": 0.1,
|
12 |
+
"bad_words_ids": null,
|
13 |
+
"bos_token_id": 0,
|
14 |
+
"chunk_size_feed_forward": 0,
|
15 |
+
"classifier_dropout": null,
|
16 |
+
"cross_attention_hidden_size": null,
|
17 |
+
"decoder_start_token_id": null,
|
18 |
+
"diversity_penalty": 0.0,
|
19 |
+
"do_sample": false,
|
20 |
+
"early_stopping": false,
|
21 |
+
"encoder_no_repeat_ngram_size": 0,
|
22 |
+
"eos_token_id": 2,
|
23 |
+
"exponential_decay_length_penalty": null,
|
24 |
+
"finetuning_task": null,
|
25 |
+
"forced_bos_token_id": null,
|
26 |
+
"forced_eos_token_id": null,
|
27 |
+
"hidden_act": "gelu",
|
28 |
+
"hidden_dropout_prob": 0.1,
|
29 |
+
"hidden_size": 768,
|
30 |
+
"id2label": {
|
31 |
+
"0": "LABEL_0",
|
32 |
+
"1": "LABEL_1"
|
33 |
+
},
|
34 |
+
"initializer_range": 0.02,
|
35 |
+
"intermediate_size": 3072,
|
36 |
+
"is_decoder": true,
|
37 |
+
"is_encoder_decoder": false,
|
38 |
+
"label2id": {
|
39 |
+
"LABEL_0": 0,
|
40 |
+
"LABEL_1": 1
|
41 |
+
},
|
42 |
+
"layer_norm_eps": 1e-05,
|
43 |
+
"length_penalty": 1.0,
|
44 |
+
"max_length": 20,
|
45 |
+
"max_position_embeddings": 514,
|
46 |
+
"min_length": 0,
|
47 |
+
"model_type": "xlm-roberta",
|
48 |
+
"no_repeat_ngram_size": 0,
|
49 |
+
"num_attention_heads": 12,
|
50 |
+
"num_beam_groups": 1,
|
51 |
+
"num_beams": 1,
|
52 |
+
"num_hidden_layers": 12,
|
53 |
+
"num_return_sequences": 1,
|
54 |
+
"output_attentions": false,
|
55 |
+
"output_hidden_states": false,
|
56 |
+
"output_past": true,
|
57 |
+
"output_scores": false,
|
58 |
+
"pad_token_id": 1,
|
59 |
+
"position_embedding_type": "absolute",
|
60 |
+
"prefix": null,
|
61 |
+
"problem_type": null,
|
62 |
+
"pruned_heads": {},
|
63 |
+
"remove_invalid_values": false,
|
64 |
+
"repetition_penalty": 1.0,
|
65 |
+
"return_dict": true,
|
66 |
+
"return_dict_in_generate": false,
|
67 |
+
"sep_token_id": null,
|
68 |
+
"task_specific_params": null,
|
69 |
+
"temperature": 1.0,
|
70 |
+
"tie_encoder_decoder": false,
|
71 |
+
"tie_word_embeddings": true,
|
72 |
+
"tokenizer_class": null,
|
73 |
+
"top_k": 50,
|
74 |
+
"top_p": 1.0,
|
75 |
+
"torch_dtype": null,
|
76 |
+
"torchscript": false,
|
77 |
+
"transformers_version": "4.19.4",
|
78 |
+
"type_vocab_size": 1,
|
79 |
+
"typical_p": 1.0,
|
80 |
+
"use_bfloat16": false,
|
81 |
+
"use_cache": true,
|
82 |
+
"vocab_size": 250002
|
83 |
+
},
|
84 |
+
"decoder_start_token_id": 0,
|
85 |
+
"encoder": {
|
86 |
+
"_name_or_path": "xlm-roberta-base",
|
87 |
+
"add_cross_attention": false,
|
88 |
+
"architectures": [
|
89 |
+
"XLMRobertaForMaskedLM"
|
90 |
+
],
|
91 |
+
"attention_probs_dropout_prob": 0.1,
|
92 |
+
"bad_words_ids": null,
|
93 |
+
"bos_token_id": 0,
|
94 |
+
"chunk_size_feed_forward": 0,
|
95 |
+
"classifier_dropout": null,
|
96 |
+
"cross_attention_hidden_size": null,
|
97 |
+
"decoder_start_token_id": null,
|
98 |
+
"diversity_penalty": 0.0,
|
99 |
+
"do_sample": false,
|
100 |
+
"early_stopping": false,
|
101 |
+
"encoder_no_repeat_ngram_size": 0,
|
102 |
+
"eos_token_id": 2,
|
103 |
+
"exponential_decay_length_penalty": null,
|
104 |
+
"finetuning_task": null,
|
105 |
+
"forced_bos_token_id": null,
|
106 |
+
"forced_eos_token_id": null,
|
107 |
+
"hidden_act": "gelu",
|
108 |
+
"hidden_dropout_prob": 0.1,
|
109 |
+
"hidden_size": 768,
|
110 |
+
"id2label": {
|
111 |
+
"0": "LABEL_0",
|
112 |
+
"1": "LABEL_1"
|
113 |
+
},
|
114 |
+
"initializer_range": 0.02,
|
115 |
+
"intermediate_size": 3072,
|
116 |
+
"is_decoder": false,
|
117 |
+
"is_encoder_decoder": false,
|
118 |
+
"label2id": {
|
119 |
+
"LABEL_0": 0,
|
120 |
+
"LABEL_1": 1
|
121 |
+
},
|
122 |
+
"layer_norm_eps": 1e-05,
|
123 |
+
"length_penalty": 1.0,
|
124 |
+
"max_length": 20,
|
125 |
+
"max_position_embeddings": 514,
|
126 |
+
"min_length": 0,
|
127 |
+
"model_type": "xlm-roberta",
|
128 |
+
"no_repeat_ngram_size": 0,
|
129 |
+
"num_attention_heads": 12,
|
130 |
+
"num_beam_groups": 1,
|
131 |
+
"num_beams": 1,
|
132 |
+
"num_hidden_layers": 12,
|
133 |
+
"num_return_sequences": 1,
|
134 |
+
"output_attentions": false,
|
135 |
+
"output_hidden_states": false,
|
136 |
+
"output_past": true,
|
137 |
+
"output_scores": false,
|
138 |
+
"pad_token_id": 1,
|
139 |
+
"position_embedding_type": "absolute",
|
140 |
+
"prefix": null,
|
141 |
+
"problem_type": null,
|
142 |
+
"pruned_heads": {},
|
143 |
+
"remove_invalid_values": false,
|
144 |
+
"repetition_penalty": 1.0,
|
145 |
+
"return_dict": true,
|
146 |
+
"return_dict_in_generate": false,
|
147 |
+
"sep_token_id": null,
|
148 |
+
"task_specific_params": null,
|
149 |
+
"temperature": 1.0,
|
150 |
+
"tie_encoder_decoder": false,
|
151 |
+
"tie_word_embeddings": true,
|
152 |
+
"tokenizer_class": null,
|
153 |
+
"top_k": 50,
|
154 |
+
"top_p": 1.0,
|
155 |
+
"torch_dtype": null,
|
156 |
+
"torchscript": false,
|
157 |
+
"transformers_version": "4.19.4",
|
158 |
+
"type_vocab_size": 1,
|
159 |
+
"typical_p": 1.0,
|
160 |
+
"use_bfloat16": false,
|
161 |
+
"use_cache": true,
|
162 |
+
"vocab_size": 250002
|
163 |
+
},
|
164 |
+
"is_encoder_decoder": true,
|
165 |
+
"model_type": "encoder-decoder",
|
166 |
+
"pad_token_id": 1,
|
167 |
+
"torch_dtype": "float32",
|
168 |
+
"transformers_version": null,
|
169 |
+
"vocab_size": 250002
|
170 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dbc24a5df815d713c656bb7870e1353f3874aabfc69a1ea7a178dcf132f5f69
|
3 |
+
size 2339011307
|
runs/Jun16_11-04-06_580c4d4a4d82/1655377453.0119276/events.out.tfevents.1655377453.580c4d4a4d82.82.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73c0a6b2672636b2f6cc225e7364d0fd20cf720a477ced6a0776be418857f09f
|
3 |
+
size 5426
|
runs/Jun16_11-04-06_580c4d4a4d82/events.out.tfevents.1655377452.580c4d4a4d82.82.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31d9ced8f129b98699e2670566872675705af9aacd80829d448a1c5c8da322c2
|
3 |
+
size 7673
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1edb0658cb47689db5cf78194ebe041bba3b6b775d1f1069fc9501b372d4acb0
|
3 |
+
size 17082758
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base", "tokenizer_class": "XLMRobertaTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8648cba0927000ae3e625844ba7e980cb689c826bc1b65a6ee2a6b134af30e7c
|
3 |
+
size 3311
|