Le Duc Anh
commited on
Commit
•
1bc71c6
1
Parent(s):
bd13e0e
Upload folder using huggingface_hub
Browse files- config.json +69 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +753 -0
- tokenizer.json +0 -0
- tokenizer_config.json +959 -0
- trainer_state.json +1873 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Salesforce/codet5-base",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"classifier_dropout": 0.0,
|
8 |
+
"d_ff": 3072,
|
9 |
+
"d_kv": 64,
|
10 |
+
"d_model": 768,
|
11 |
+
"decoder_start_token_id": 0,
|
12 |
+
"dense_act_fn": "relu",
|
13 |
+
"dropout_rate": 0.1,
|
14 |
+
"eos_token_id": 2,
|
15 |
+
"feed_forward_proj": "relu",
|
16 |
+
"gradient_checkpointing": false,
|
17 |
+
"id2label": {
|
18 |
+
"0": "LABEL_0"
|
19 |
+
},
|
20 |
+
"initializer_factor": 1.0,
|
21 |
+
"is_encoder_decoder": true,
|
22 |
+
"is_gated_act": false,
|
23 |
+
"label2id": {
|
24 |
+
"LABEL_0": 0
|
25 |
+
},
|
26 |
+
"layer_norm_epsilon": 1e-06,
|
27 |
+
"model_type": "t5",
|
28 |
+
"n_positions": 512,
|
29 |
+
"num_decoder_layers": 12,
|
30 |
+
"num_heads": 12,
|
31 |
+
"num_layers": 12,
|
32 |
+
"output_past": true,
|
33 |
+
"pad_token_id": 0,
|
34 |
+
"relative_attention_max_distance": 128,
|
35 |
+
"relative_attention_num_buckets": 32,
|
36 |
+
"task_specific_params": {
|
37 |
+
"summarization": {
|
38 |
+
"early_stopping": true,
|
39 |
+
"length_penalty": 2.0,
|
40 |
+
"max_length": 200,
|
41 |
+
"min_length": 30,
|
42 |
+
"no_repeat_ngram_size": 3,
|
43 |
+
"num_beams": 4,
|
44 |
+
"prefix": "summarize: "
|
45 |
+
},
|
46 |
+
"translation_en_to_de": {
|
47 |
+
"early_stopping": true,
|
48 |
+
"max_length": 300,
|
49 |
+
"num_beams": 4,
|
50 |
+
"prefix": "translate English to German: "
|
51 |
+
},
|
52 |
+
"translation_en_to_fr": {
|
53 |
+
"early_stopping": true,
|
54 |
+
"max_length": 300,
|
55 |
+
"num_beams": 4,
|
56 |
+
"prefix": "translate English to French: "
|
57 |
+
},
|
58 |
+
"translation_en_to_ro": {
|
59 |
+
"early_stopping": true,
|
60 |
+
"max_length": 300,
|
61 |
+
"num_beams": 4,
|
62 |
+
"prefix": "translate English to Romanian: "
|
63 |
+
}
|
64 |
+
},
|
65 |
+
"torch_dtype": "float32",
|
66 |
+
"transformers_version": "4.36.0",
|
67 |
+
"use_cache": true,
|
68 |
+
"vocab_size": 32100
|
69 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 1,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.36.0"
|
7 |
+
}
|
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:a6b872719bb065112de653a5c29aad1cf8bb32edf585c51beed98a517ec297a4
|
3 |
+
size 891558696
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b05e14eb3edea60c7e775cd5e7fa089e33285227ad71ed45afc15d1fd31fb2f6
|
3 |
+
size 1783272762
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8407802bcbd749ee903beba6b6c5ec0a5b65d90ff8f369f5b6fb79a7455dc59b
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e38662b51991b35fd3869725e8e6e2aa66f8d6ab68a03fab9b3bafd27365bf71
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,753 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<extra_id_99>",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "<extra_id_98>",
|
12 |
+
"lstrip": true,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"content": "<extra_id_97>",
|
19 |
+
"lstrip": true,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"content": "<extra_id_96>",
|
26 |
+
"lstrip": true,
|
27 |
+
"normalized": true,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"content": "<extra_id_95>",
|
33 |
+
"lstrip": true,
|
34 |
+
"normalized": true,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"content": "<extra_id_94>",
|
40 |
+
"lstrip": true,
|
41 |
+
"normalized": true,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"content": "<extra_id_93>",
|
47 |
+
"lstrip": true,
|
48 |
+
"normalized": true,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"content": "<extra_id_92>",
|
54 |
+
"lstrip": true,
|
55 |
+
"normalized": true,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"content": "<extra_id_91>",
|
61 |
+
"lstrip": true,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"content": "<extra_id_90>",
|
68 |
+
"lstrip": true,
|
69 |
+
"normalized": true,
|
70 |
+
"rstrip": false,
|
71 |
+
"single_word": false
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"content": "<extra_id_89>",
|
75 |
+
"lstrip": true,
|
76 |
+
"normalized": true,
|
77 |
+
"rstrip": false,
|
78 |
+
"single_word": false
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"content": "<extra_id_88>",
|
82 |
+
"lstrip": true,
|
83 |
+
"normalized": true,
|
84 |
+
"rstrip": false,
|
85 |
+
"single_word": false
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"content": "<extra_id_87>",
|
89 |
+
"lstrip": true,
|
90 |
+
"normalized": true,
|
91 |
+
"rstrip": false,
|
92 |
+
"single_word": false
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"content": "<extra_id_86>",
|
96 |
+
"lstrip": true,
|
97 |
+
"normalized": true,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"content": "<extra_id_85>",
|
103 |
+
"lstrip": true,
|
104 |
+
"normalized": true,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"content": "<extra_id_84>",
|
110 |
+
"lstrip": true,
|
111 |
+
"normalized": true,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"content": "<extra_id_83>",
|
117 |
+
"lstrip": true,
|
118 |
+
"normalized": true,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"content": "<extra_id_82>",
|
124 |
+
"lstrip": true,
|
125 |
+
"normalized": true,
|
126 |
+
"rstrip": false,
|
127 |
+
"single_word": false
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"content": "<extra_id_81>",
|
131 |
+
"lstrip": true,
|
132 |
+
"normalized": true,
|
133 |
+
"rstrip": false,
|
134 |
+
"single_word": false
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"content": "<extra_id_80>",
|
138 |
+
"lstrip": true,
|
139 |
+
"normalized": true,
|
140 |
+
"rstrip": false,
|
141 |
+
"single_word": false
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"content": "<extra_id_79>",
|
145 |
+
"lstrip": true,
|
146 |
+
"normalized": true,
|
147 |
+
"rstrip": false,
|
148 |
+
"single_word": false
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"content": "<extra_id_78>",
|
152 |
+
"lstrip": true,
|
153 |
+
"normalized": true,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"content": "<extra_id_77>",
|
159 |
+
"lstrip": true,
|
160 |
+
"normalized": true,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"content": "<extra_id_76>",
|
166 |
+
"lstrip": true,
|
167 |
+
"normalized": true,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"content": "<extra_id_75>",
|
173 |
+
"lstrip": true,
|
174 |
+
"normalized": true,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"content": "<extra_id_74>",
|
180 |
+
"lstrip": true,
|
181 |
+
"normalized": true,
|
182 |
+
"rstrip": false,
|
183 |
+
"single_word": false
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"content": "<extra_id_73>",
|
187 |
+
"lstrip": true,
|
188 |
+
"normalized": true,
|
189 |
+
"rstrip": false,
|
190 |
+
"single_word": false
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"content": "<extra_id_72>",
|
194 |
+
"lstrip": true,
|
195 |
+
"normalized": true,
|
196 |
+
"rstrip": false,
|
197 |
+
"single_word": false
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"content": "<extra_id_71>",
|
201 |
+
"lstrip": true,
|
202 |
+
"normalized": true,
|
203 |
+
"rstrip": false,
|
204 |
+
"single_word": false
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"content": "<extra_id_70>",
|
208 |
+
"lstrip": true,
|
209 |
+
"normalized": true,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"content": "<extra_id_69>",
|
215 |
+
"lstrip": true,
|
216 |
+
"normalized": true,
|
217 |
+
"rstrip": false,
|
218 |
+
"single_word": false
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"content": "<extra_id_68>",
|
222 |
+
"lstrip": true,
|
223 |
+
"normalized": true,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"content": "<extra_id_67>",
|
229 |
+
"lstrip": true,
|
230 |
+
"normalized": true,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"content": "<extra_id_66>",
|
236 |
+
"lstrip": true,
|
237 |
+
"normalized": true,
|
238 |
+
"rstrip": false,
|
239 |
+
"single_word": false
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"content": "<extra_id_65>",
|
243 |
+
"lstrip": true,
|
244 |
+
"normalized": true,
|
245 |
+
"rstrip": false,
|
246 |
+
"single_word": false
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"content": "<extra_id_64>",
|
250 |
+
"lstrip": true,
|
251 |
+
"normalized": true,
|
252 |
+
"rstrip": false,
|
253 |
+
"single_word": false
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"content": "<extra_id_63>",
|
257 |
+
"lstrip": true,
|
258 |
+
"normalized": true,
|
259 |
+
"rstrip": false,
|
260 |
+
"single_word": false
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"content": "<extra_id_62>",
|
264 |
+
"lstrip": true,
|
265 |
+
"normalized": true,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"content": "<extra_id_61>",
|
271 |
+
"lstrip": true,
|
272 |
+
"normalized": true,
|
273 |
+
"rstrip": false,
|
274 |
+
"single_word": false
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"content": "<extra_id_60>",
|
278 |
+
"lstrip": true,
|
279 |
+
"normalized": true,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"content": "<extra_id_59>",
|
285 |
+
"lstrip": true,
|
286 |
+
"normalized": true,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"content": "<extra_id_58>",
|
292 |
+
"lstrip": true,
|
293 |
+
"normalized": true,
|
294 |
+
"rstrip": false,
|
295 |
+
"single_word": false
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"content": "<extra_id_57>",
|
299 |
+
"lstrip": true,
|
300 |
+
"normalized": true,
|
301 |
+
"rstrip": false,
|
302 |
+
"single_word": false
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"content": "<extra_id_56>",
|
306 |
+
"lstrip": true,
|
307 |
+
"normalized": true,
|
308 |
+
"rstrip": false,
|
309 |
+
"single_word": false
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"content": "<extra_id_55>",
|
313 |
+
"lstrip": true,
|
314 |
+
"normalized": true,
|
315 |
+
"rstrip": false,
|
316 |
+
"single_word": false
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"content": "<extra_id_54>",
|
320 |
+
"lstrip": true,
|
321 |
+
"normalized": true,
|
322 |
+
"rstrip": false,
|
323 |
+
"single_word": false
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"content": "<extra_id_53>",
|
327 |
+
"lstrip": true,
|
328 |
+
"normalized": true,
|
329 |
+
"rstrip": false,
|
330 |
+
"single_word": false
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"content": "<extra_id_52>",
|
334 |
+
"lstrip": true,
|
335 |
+
"normalized": true,
|
336 |
+
"rstrip": false,
|
337 |
+
"single_word": false
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"content": "<extra_id_51>",
|
341 |
+
"lstrip": true,
|
342 |
+
"normalized": true,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"content": "<extra_id_50>",
|
348 |
+
"lstrip": true,
|
349 |
+
"normalized": true,
|
350 |
+
"rstrip": false,
|
351 |
+
"single_word": false
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"content": "<extra_id_49>",
|
355 |
+
"lstrip": true,
|
356 |
+
"normalized": true,
|
357 |
+
"rstrip": false,
|
358 |
+
"single_word": false
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"content": "<extra_id_48>",
|
362 |
+
"lstrip": true,
|
363 |
+
"normalized": true,
|
364 |
+
"rstrip": false,
|
365 |
+
"single_word": false
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"content": "<extra_id_47>",
|
369 |
+
"lstrip": true,
|
370 |
+
"normalized": true,
|
371 |
+
"rstrip": false,
|
372 |
+
"single_word": false
|
373 |
+
},
|
374 |
+
{
|
375 |
+
"content": "<extra_id_46>",
|
376 |
+
"lstrip": true,
|
377 |
+
"normalized": true,
|
378 |
+
"rstrip": false,
|
379 |
+
"single_word": false
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"content": "<extra_id_45>",
|
383 |
+
"lstrip": true,
|
384 |
+
"normalized": true,
|
385 |
+
"rstrip": false,
|
386 |
+
"single_word": false
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"content": "<extra_id_44>",
|
390 |
+
"lstrip": true,
|
391 |
+
"normalized": true,
|
392 |
+
"rstrip": false,
|
393 |
+
"single_word": false
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"content": "<extra_id_43>",
|
397 |
+
"lstrip": true,
|
398 |
+
"normalized": true,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"content": "<extra_id_42>",
|
404 |
+
"lstrip": true,
|
405 |
+
"normalized": true,
|
406 |
+
"rstrip": false,
|
407 |
+
"single_word": false
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"content": "<extra_id_41>",
|
411 |
+
"lstrip": true,
|
412 |
+
"normalized": true,
|
413 |
+
"rstrip": false,
|
414 |
+
"single_word": false
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"content": "<extra_id_40>",
|
418 |
+
"lstrip": true,
|
419 |
+
"normalized": true,
|
420 |
+
"rstrip": false,
|
421 |
+
"single_word": false
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"content": "<extra_id_39>",
|
425 |
+
"lstrip": true,
|
426 |
+
"normalized": true,
|
427 |
+
"rstrip": false,
|
428 |
+
"single_word": false
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"content": "<extra_id_38>",
|
432 |
+
"lstrip": true,
|
433 |
+
"normalized": true,
|
434 |
+
"rstrip": false,
|
435 |
+
"single_word": false
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"content": "<extra_id_37>",
|
439 |
+
"lstrip": true,
|
440 |
+
"normalized": true,
|
441 |
+
"rstrip": false,
|
442 |
+
"single_word": false
|
443 |
+
},
|
444 |
+
{
|
445 |
+
"content": "<extra_id_36>",
|
446 |
+
"lstrip": true,
|
447 |
+
"normalized": true,
|
448 |
+
"rstrip": false,
|
449 |
+
"single_word": false
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"content": "<extra_id_35>",
|
453 |
+
"lstrip": true,
|
454 |
+
"normalized": true,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"content": "<extra_id_34>",
|
460 |
+
"lstrip": true,
|
461 |
+
"normalized": true,
|
462 |
+
"rstrip": false,
|
463 |
+
"single_word": false
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"content": "<extra_id_33>",
|
467 |
+
"lstrip": true,
|
468 |
+
"normalized": true,
|
469 |
+
"rstrip": false,
|
470 |
+
"single_word": false
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"content": "<extra_id_32>",
|
474 |
+
"lstrip": true,
|
475 |
+
"normalized": true,
|
476 |
+
"rstrip": false,
|
477 |
+
"single_word": false
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"content": "<extra_id_31>",
|
481 |
+
"lstrip": true,
|
482 |
+
"normalized": true,
|
483 |
+
"rstrip": false,
|
484 |
+
"single_word": false
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"content": "<extra_id_30>",
|
488 |
+
"lstrip": true,
|
489 |
+
"normalized": true,
|
490 |
+
"rstrip": false,
|
491 |
+
"single_word": false
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"content": "<extra_id_29>",
|
495 |
+
"lstrip": true,
|
496 |
+
"normalized": true,
|
497 |
+
"rstrip": false,
|
498 |
+
"single_word": false
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"content": "<extra_id_28>",
|
502 |
+
"lstrip": true,
|
503 |
+
"normalized": true,
|
504 |
+
"rstrip": false,
|
505 |
+
"single_word": false
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"content": "<extra_id_27>",
|
509 |
+
"lstrip": true,
|
510 |
+
"normalized": true,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"content": "<extra_id_26>",
|
516 |
+
"lstrip": true,
|
517 |
+
"normalized": true,
|
518 |
+
"rstrip": false,
|
519 |
+
"single_word": false
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"content": "<extra_id_25>",
|
523 |
+
"lstrip": true,
|
524 |
+
"normalized": true,
|
525 |
+
"rstrip": false,
|
526 |
+
"single_word": false
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"content": "<extra_id_24>",
|
530 |
+
"lstrip": true,
|
531 |
+
"normalized": true,
|
532 |
+
"rstrip": false,
|
533 |
+
"single_word": false
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"content": "<extra_id_23>",
|
537 |
+
"lstrip": true,
|
538 |
+
"normalized": true,
|
539 |
+
"rstrip": false,
|
540 |
+
"single_word": false
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"content": "<extra_id_22>",
|
544 |
+
"lstrip": true,
|
545 |
+
"normalized": true,
|
546 |
+
"rstrip": false,
|
547 |
+
"single_word": false
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"content": "<extra_id_21>",
|
551 |
+
"lstrip": true,
|
552 |
+
"normalized": true,
|
553 |
+
"rstrip": false,
|
554 |
+
"single_word": false
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"content": "<extra_id_20>",
|
558 |
+
"lstrip": true,
|
559 |
+
"normalized": true,
|
560 |
+
"rstrip": false,
|
561 |
+
"single_word": false
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"content": "<extra_id_19>",
|
565 |
+
"lstrip": true,
|
566 |
+
"normalized": true,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"content": "<extra_id_18>",
|
572 |
+
"lstrip": true,
|
573 |
+
"normalized": true,
|
574 |
+
"rstrip": false,
|
575 |
+
"single_word": false
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"content": "<extra_id_17>",
|
579 |
+
"lstrip": true,
|
580 |
+
"normalized": true,
|
581 |
+
"rstrip": false,
|
582 |
+
"single_word": false
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"content": "<extra_id_16>",
|
586 |
+
"lstrip": true,
|
587 |
+
"normalized": true,
|
588 |
+
"rstrip": false,
|
589 |
+
"single_word": false
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"content": "<extra_id_15>",
|
593 |
+
"lstrip": true,
|
594 |
+
"normalized": true,
|
595 |
+
"rstrip": false,
|
596 |
+
"single_word": false
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"content": "<extra_id_14>",
|
600 |
+
"lstrip": true,
|
601 |
+
"normalized": true,
|
602 |
+
"rstrip": false,
|
603 |
+
"single_word": false
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"content": "<extra_id_13>",
|
607 |
+
"lstrip": true,
|
608 |
+
"normalized": true,
|
609 |
+
"rstrip": false,
|
610 |
+
"single_word": false
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"content": "<extra_id_12>",
|
614 |
+
"lstrip": true,
|
615 |
+
"normalized": true,
|
616 |
+
"rstrip": false,
|
617 |
+
"single_word": false
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"content": "<extra_id_11>",
|
621 |
+
"lstrip": true,
|
622 |
+
"normalized": true,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"content": "<extra_id_10>",
|
628 |
+
"lstrip": true,
|
629 |
+
"normalized": true,
|
630 |
+
"rstrip": false,
|
631 |
+
"single_word": false
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"content": "<extra_id_9>",
|
635 |
+
"lstrip": true,
|
636 |
+
"normalized": true,
|
637 |
+
"rstrip": false,
|
638 |
+
"single_word": false
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"content": "<extra_id_8>",
|
642 |
+
"lstrip": true,
|
643 |
+
"normalized": true,
|
644 |
+
"rstrip": false,
|
645 |
+
"single_word": false
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"content": "<extra_id_7>",
|
649 |
+
"lstrip": true,
|
650 |
+
"normalized": true,
|
651 |
+
"rstrip": false,
|
652 |
+
"single_word": false
|
653 |
+
},
|
654 |
+
{
|
655 |
+
"content": "<extra_id_6>",
|
656 |
+
"lstrip": true,
|
657 |
+
"normalized": true,
|
658 |
+
"rstrip": false,
|
659 |
+
"single_word": false
|
660 |
+
},
|
661 |
+
{
|
662 |
+
"content": "<extra_id_5>",
|
663 |
+
"lstrip": true,
|
664 |
+
"normalized": true,
|
665 |
+
"rstrip": false,
|
666 |
+
"single_word": false
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"content": "<extra_id_4>",
|
670 |
+
"lstrip": true,
|
671 |
+
"normalized": true,
|
672 |
+
"rstrip": false,
|
673 |
+
"single_word": false
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"content": "<extra_id_3>",
|
677 |
+
"lstrip": true,
|
678 |
+
"normalized": true,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"content": "<extra_id_2>",
|
684 |
+
"lstrip": true,
|
685 |
+
"normalized": true,
|
686 |
+
"rstrip": false,
|
687 |
+
"single_word": false
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"content": "<extra_id_1>",
|
691 |
+
"lstrip": true,
|
692 |
+
"normalized": true,
|
693 |
+
"rstrip": false,
|
694 |
+
"single_word": false
|
695 |
+
},
|
696 |
+
{
|
697 |
+
"content": "<extra_id_0>",
|
698 |
+
"lstrip": true,
|
699 |
+
"normalized": true,
|
700 |
+
"rstrip": false,
|
701 |
+
"single_word": false
|
702 |
+
}
|
703 |
+
],
|
704 |
+
"bos_token": {
|
705 |
+
"content": "<s>",
|
706 |
+
"lstrip": false,
|
707 |
+
"normalized": true,
|
708 |
+
"rstrip": false,
|
709 |
+
"single_word": false
|
710 |
+
},
|
711 |
+
"cls_token": {
|
712 |
+
"content": "<s>",
|
713 |
+
"lstrip": false,
|
714 |
+
"normalized": true,
|
715 |
+
"rstrip": false,
|
716 |
+
"single_word": false
|
717 |
+
},
|
718 |
+
"eos_token": {
|
719 |
+
"content": "</s>",
|
720 |
+
"lstrip": false,
|
721 |
+
"normalized": true,
|
722 |
+
"rstrip": false,
|
723 |
+
"single_word": false
|
724 |
+
},
|
725 |
+
"mask_token": {
|
726 |
+
"content": "<mask>",
|
727 |
+
"lstrip": true,
|
728 |
+
"normalized": true,
|
729 |
+
"rstrip": false,
|
730 |
+
"single_word": false
|
731 |
+
},
|
732 |
+
"pad_token": {
|
733 |
+
"content": "<pad>",
|
734 |
+
"lstrip": false,
|
735 |
+
"normalized": true,
|
736 |
+
"rstrip": false,
|
737 |
+
"single_word": false
|
738 |
+
},
|
739 |
+
"sep_token": {
|
740 |
+
"content": "</s>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": true,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false
|
745 |
+
},
|
746 |
+
"unk_token": {
|
747 |
+
"content": "<unk>",
|
748 |
+
"lstrip": false,
|
749 |
+
"normalized": true,
|
750 |
+
"rstrip": false,
|
751 |
+
"single_word": false
|
752 |
+
}
|
753 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,959 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<pad>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<s>",
|
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 |
+
"32000": {
|
45 |
+
"content": "<extra_id_99>",
|
46 |
+
"lstrip": true,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"32001": {
|
53 |
+
"content": "<extra_id_98>",
|
54 |
+
"lstrip": true,
|
55 |
+
"normalized": true,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"32002": {
|
61 |
+
"content": "<extra_id_97>",
|
62 |
+
"lstrip": true,
|
63 |
+
"normalized": true,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"32003": {
|
69 |
+
"content": "<extra_id_96>",
|
70 |
+
"lstrip": true,
|
71 |
+
"normalized": true,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"32004": {
|
77 |
+
"content": "<extra_id_95>",
|
78 |
+
"lstrip": true,
|
79 |
+
"normalized": true,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"32005": {
|
85 |
+
"content": "<extra_id_94>",
|
86 |
+
"lstrip": true,
|
87 |
+
"normalized": true,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"32006": {
|
93 |
+
"content": "<extra_id_93>",
|
94 |
+
"lstrip": true,
|
95 |
+
"normalized": true,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"32007": {
|
101 |
+
"content": "<extra_id_92>",
|
102 |
+
"lstrip": true,
|
103 |
+
"normalized": true,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"32008": {
|
109 |
+
"content": "<extra_id_91>",
|
110 |
+
"lstrip": true,
|
111 |
+
"normalized": true,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"32009": {
|
117 |
+
"content": "<extra_id_90>",
|
118 |
+
"lstrip": true,
|
119 |
+
"normalized": true,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": true
|
123 |
+
},
|
124 |
+
"32010": {
|
125 |
+
"content": "<extra_id_89>",
|
126 |
+
"lstrip": true,
|
127 |
+
"normalized": true,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
"32011": {
|
133 |
+
"content": "<extra_id_88>",
|
134 |
+
"lstrip": true,
|
135 |
+
"normalized": true,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": true
|
139 |
+
},
|
140 |
+
"32012": {
|
141 |
+
"content": "<extra_id_87>",
|
142 |
+
"lstrip": true,
|
143 |
+
"normalized": true,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": true
|
147 |
+
},
|
148 |
+
"32013": {
|
149 |
+
"content": "<extra_id_86>",
|
150 |
+
"lstrip": true,
|
151 |
+
"normalized": true,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": true
|
155 |
+
},
|
156 |
+
"32014": {
|
157 |
+
"content": "<extra_id_85>",
|
158 |
+
"lstrip": true,
|
159 |
+
"normalized": true,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": true
|
163 |
+
},
|
164 |
+
"32015": {
|
165 |
+
"content": "<extra_id_84>",
|
166 |
+
"lstrip": true,
|
167 |
+
"normalized": true,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": true
|
171 |
+
},
|
172 |
+
"32016": {
|
173 |
+
"content": "<extra_id_83>",
|
174 |
+
"lstrip": true,
|
175 |
+
"normalized": true,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": true
|
179 |
+
},
|
180 |
+
"32017": {
|
181 |
+
"content": "<extra_id_82>",
|
182 |
+
"lstrip": true,
|
183 |
+
"normalized": true,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": true
|
187 |
+
},
|
188 |
+
"32018": {
|
189 |
+
"content": "<extra_id_81>",
|
190 |
+
"lstrip": true,
|
191 |
+
"normalized": true,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": true
|
195 |
+
},
|
196 |
+
"32019": {
|
197 |
+
"content": "<extra_id_80>",
|
198 |
+
"lstrip": true,
|
199 |
+
"normalized": true,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": true
|
203 |
+
},
|
204 |
+
"32020": {
|
205 |
+
"content": "<extra_id_79>",
|
206 |
+
"lstrip": true,
|
207 |
+
"normalized": true,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": true
|
211 |
+
},
|
212 |
+
"32021": {
|
213 |
+
"content": "<extra_id_78>",
|
214 |
+
"lstrip": true,
|
215 |
+
"normalized": true,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": true
|
219 |
+
},
|
220 |
+
"32022": {
|
221 |
+
"content": "<extra_id_77>",
|
222 |
+
"lstrip": true,
|
223 |
+
"normalized": true,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": true
|
227 |
+
},
|
228 |
+
"32023": {
|
229 |
+
"content": "<extra_id_76>",
|
230 |
+
"lstrip": true,
|
231 |
+
"normalized": true,
|
232 |
+
"rstrip": false,
|
233 |
+
"single_word": false,
|
234 |
+
"special": true
|
235 |
+
},
|
236 |
+
"32024": {
|
237 |
+
"content": "<extra_id_75>",
|
238 |
+
"lstrip": true,
|
239 |
+
"normalized": true,
|
240 |
+
"rstrip": false,
|
241 |
+
"single_word": false,
|
242 |
+
"special": true
|
243 |
+
},
|
244 |
+
"32025": {
|
245 |
+
"content": "<extra_id_74>",
|
246 |
+
"lstrip": true,
|
247 |
+
"normalized": true,
|
248 |
+
"rstrip": false,
|
249 |
+
"single_word": false,
|
250 |
+
"special": true
|
251 |
+
},
|
252 |
+
"32026": {
|
253 |
+
"content": "<extra_id_73>",
|
254 |
+
"lstrip": true,
|
255 |
+
"normalized": true,
|
256 |
+
"rstrip": false,
|
257 |
+
"single_word": false,
|
258 |
+
"special": true
|
259 |
+
},
|
260 |
+
"32027": {
|
261 |
+
"content": "<extra_id_72>",
|
262 |
+
"lstrip": true,
|
263 |
+
"normalized": true,
|
264 |
+
"rstrip": false,
|
265 |
+
"single_word": false,
|
266 |
+
"special": true
|
267 |
+
},
|
268 |
+
"32028": {
|
269 |
+
"content": "<extra_id_71>",
|
270 |
+
"lstrip": true,
|
271 |
+
"normalized": true,
|
272 |
+
"rstrip": false,
|
273 |
+
"single_word": false,
|
274 |
+
"special": true
|
275 |
+
},
|
276 |
+
"32029": {
|
277 |
+
"content": "<extra_id_70>",
|
278 |
+
"lstrip": true,
|
279 |
+
"normalized": true,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false,
|
282 |
+
"special": true
|
283 |
+
},
|
284 |
+
"32030": {
|
285 |
+
"content": "<extra_id_69>",
|
286 |
+
"lstrip": true,
|
287 |
+
"normalized": true,
|
288 |
+
"rstrip": false,
|
289 |
+
"single_word": false,
|
290 |
+
"special": true
|
291 |
+
},
|
292 |
+
"32031": {
|
293 |
+
"content": "<extra_id_68>",
|
294 |
+
"lstrip": true,
|
295 |
+
"normalized": true,
|
296 |
+
"rstrip": false,
|
297 |
+
"single_word": false,
|
298 |
+
"special": true
|
299 |
+
},
|
300 |
+
"32032": {
|
301 |
+
"content": "<extra_id_67>",
|
302 |
+
"lstrip": true,
|
303 |
+
"normalized": true,
|
304 |
+
"rstrip": false,
|
305 |
+
"single_word": false,
|
306 |
+
"special": true
|
307 |
+
},
|
308 |
+
"32033": {
|
309 |
+
"content": "<extra_id_66>",
|
310 |
+
"lstrip": true,
|
311 |
+
"normalized": true,
|
312 |
+
"rstrip": false,
|
313 |
+
"single_word": false,
|
314 |
+
"special": true
|
315 |
+
},
|
316 |
+
"32034": {
|
317 |
+
"content": "<extra_id_65>",
|
318 |
+
"lstrip": true,
|
319 |
+
"normalized": true,
|
320 |
+
"rstrip": false,
|
321 |
+
"single_word": false,
|
322 |
+
"special": true
|
323 |
+
},
|
324 |
+
"32035": {
|
325 |
+
"content": "<extra_id_64>",
|
326 |
+
"lstrip": true,
|
327 |
+
"normalized": true,
|
328 |
+
"rstrip": false,
|
329 |
+
"single_word": false,
|
330 |
+
"special": true
|
331 |
+
},
|
332 |
+
"32036": {
|
333 |
+
"content": "<extra_id_63>",
|
334 |
+
"lstrip": true,
|
335 |
+
"normalized": true,
|
336 |
+
"rstrip": false,
|
337 |
+
"single_word": false,
|
338 |
+
"special": true
|
339 |
+
},
|
340 |
+
"32037": {
|
341 |
+
"content": "<extra_id_62>",
|
342 |
+
"lstrip": true,
|
343 |
+
"normalized": true,
|
344 |
+
"rstrip": false,
|
345 |
+
"single_word": false,
|
346 |
+
"special": true
|
347 |
+
},
|
348 |
+
"32038": {
|
349 |
+
"content": "<extra_id_61>",
|
350 |
+
"lstrip": true,
|
351 |
+
"normalized": true,
|
352 |
+
"rstrip": false,
|
353 |
+
"single_word": false,
|
354 |
+
"special": true
|
355 |
+
},
|
356 |
+
"32039": {
|
357 |
+
"content": "<extra_id_60>",
|
358 |
+
"lstrip": true,
|
359 |
+
"normalized": true,
|
360 |
+
"rstrip": false,
|
361 |
+
"single_word": false,
|
362 |
+
"special": true
|
363 |
+
},
|
364 |
+
"32040": {
|
365 |
+
"content": "<extra_id_59>",
|
366 |
+
"lstrip": true,
|
367 |
+
"normalized": true,
|
368 |
+
"rstrip": false,
|
369 |
+
"single_word": false,
|
370 |
+
"special": true
|
371 |
+
},
|
372 |
+
"32041": {
|
373 |
+
"content": "<extra_id_58>",
|
374 |
+
"lstrip": true,
|
375 |
+
"normalized": true,
|
376 |
+
"rstrip": false,
|
377 |
+
"single_word": false,
|
378 |
+
"special": true
|
379 |
+
},
|
380 |
+
"32042": {
|
381 |
+
"content": "<extra_id_57>",
|
382 |
+
"lstrip": true,
|
383 |
+
"normalized": true,
|
384 |
+
"rstrip": false,
|
385 |
+
"single_word": false,
|
386 |
+
"special": true
|
387 |
+
},
|
388 |
+
"32043": {
|
389 |
+
"content": "<extra_id_56>",
|
390 |
+
"lstrip": true,
|
391 |
+
"normalized": true,
|
392 |
+
"rstrip": false,
|
393 |
+
"single_word": false,
|
394 |
+
"special": true
|
395 |
+
},
|
396 |
+
"32044": {
|
397 |
+
"content": "<extra_id_55>",
|
398 |
+
"lstrip": true,
|
399 |
+
"normalized": true,
|
400 |
+
"rstrip": false,
|
401 |
+
"single_word": false,
|
402 |
+
"special": true
|
403 |
+
},
|
404 |
+
"32045": {
|
405 |
+
"content": "<extra_id_54>",
|
406 |
+
"lstrip": true,
|
407 |
+
"normalized": true,
|
408 |
+
"rstrip": false,
|
409 |
+
"single_word": false,
|
410 |
+
"special": true
|
411 |
+
},
|
412 |
+
"32046": {
|
413 |
+
"content": "<extra_id_53>",
|
414 |
+
"lstrip": true,
|
415 |
+
"normalized": true,
|
416 |
+
"rstrip": false,
|
417 |
+
"single_word": false,
|
418 |
+
"special": true
|
419 |
+
},
|
420 |
+
"32047": {
|
421 |
+
"content": "<extra_id_52>",
|
422 |
+
"lstrip": true,
|
423 |
+
"normalized": true,
|
424 |
+
"rstrip": false,
|
425 |
+
"single_word": false,
|
426 |
+
"special": true
|
427 |
+
},
|
428 |
+
"32048": {
|
429 |
+
"content": "<extra_id_51>",
|
430 |
+
"lstrip": true,
|
431 |
+
"normalized": true,
|
432 |
+
"rstrip": false,
|
433 |
+
"single_word": false,
|
434 |
+
"special": true
|
435 |
+
},
|
436 |
+
"32049": {
|
437 |
+
"content": "<extra_id_50>",
|
438 |
+
"lstrip": true,
|
439 |
+
"normalized": true,
|
440 |
+
"rstrip": false,
|
441 |
+
"single_word": false,
|
442 |
+
"special": true
|
443 |
+
},
|
444 |
+
"32050": {
|
445 |
+
"content": "<extra_id_49>",
|
446 |
+
"lstrip": true,
|
447 |
+
"normalized": true,
|
448 |
+
"rstrip": false,
|
449 |
+
"single_word": false,
|
450 |
+
"special": true
|
451 |
+
},
|
452 |
+
"32051": {
|
453 |
+
"content": "<extra_id_48>",
|
454 |
+
"lstrip": true,
|
455 |
+
"normalized": true,
|
456 |
+
"rstrip": false,
|
457 |
+
"single_word": false,
|
458 |
+
"special": true
|
459 |
+
},
|
460 |
+
"32052": {
|
461 |
+
"content": "<extra_id_47>",
|
462 |
+
"lstrip": true,
|
463 |
+
"normalized": true,
|
464 |
+
"rstrip": false,
|
465 |
+
"single_word": false,
|
466 |
+
"special": true
|
467 |
+
},
|
468 |
+
"32053": {
|
469 |
+
"content": "<extra_id_46>",
|
470 |
+
"lstrip": true,
|
471 |
+
"normalized": true,
|
472 |
+
"rstrip": false,
|
473 |
+
"single_word": false,
|
474 |
+
"special": true
|
475 |
+
},
|
476 |
+
"32054": {
|
477 |
+
"content": "<extra_id_45>",
|
478 |
+
"lstrip": true,
|
479 |
+
"normalized": true,
|
480 |
+
"rstrip": false,
|
481 |
+
"single_word": false,
|
482 |
+
"special": true
|
483 |
+
},
|
484 |
+
"32055": {
|
485 |
+
"content": "<extra_id_44>",
|
486 |
+
"lstrip": true,
|
487 |
+
"normalized": true,
|
488 |
+
"rstrip": false,
|
489 |
+
"single_word": false,
|
490 |
+
"special": true
|
491 |
+
},
|
492 |
+
"32056": {
|
493 |
+
"content": "<extra_id_43>",
|
494 |
+
"lstrip": true,
|
495 |
+
"normalized": true,
|
496 |
+
"rstrip": false,
|
497 |
+
"single_word": false,
|
498 |
+
"special": true
|
499 |
+
},
|
500 |
+
"32057": {
|
501 |
+
"content": "<extra_id_42>",
|
502 |
+
"lstrip": true,
|
503 |
+
"normalized": true,
|
504 |
+
"rstrip": false,
|
505 |
+
"single_word": false,
|
506 |
+
"special": true
|
507 |
+
},
|
508 |
+
"32058": {
|
509 |
+
"content": "<extra_id_41>",
|
510 |
+
"lstrip": true,
|
511 |
+
"normalized": true,
|
512 |
+
"rstrip": false,
|
513 |
+
"single_word": false,
|
514 |
+
"special": true
|
515 |
+
},
|
516 |
+
"32059": {
|
517 |
+
"content": "<extra_id_40>",
|
518 |
+
"lstrip": true,
|
519 |
+
"normalized": true,
|
520 |
+
"rstrip": false,
|
521 |
+
"single_word": false,
|
522 |
+
"special": true
|
523 |
+
},
|
524 |
+
"32060": {
|
525 |
+
"content": "<extra_id_39>",
|
526 |
+
"lstrip": true,
|
527 |
+
"normalized": true,
|
528 |
+
"rstrip": false,
|
529 |
+
"single_word": false,
|
530 |
+
"special": true
|
531 |
+
},
|
532 |
+
"32061": {
|
533 |
+
"content": "<extra_id_38>",
|
534 |
+
"lstrip": true,
|
535 |
+
"normalized": true,
|
536 |
+
"rstrip": false,
|
537 |
+
"single_word": false,
|
538 |
+
"special": true
|
539 |
+
},
|
540 |
+
"32062": {
|
541 |
+
"content": "<extra_id_37>",
|
542 |
+
"lstrip": true,
|
543 |
+
"normalized": true,
|
544 |
+
"rstrip": false,
|
545 |
+
"single_word": false,
|
546 |
+
"special": true
|
547 |
+
},
|
548 |
+
"32063": {
|
549 |
+
"content": "<extra_id_36>",
|
550 |
+
"lstrip": true,
|
551 |
+
"normalized": true,
|
552 |
+
"rstrip": false,
|
553 |
+
"single_word": false,
|
554 |
+
"special": true
|
555 |
+
},
|
556 |
+
"32064": {
|
557 |
+
"content": "<extra_id_35>",
|
558 |
+
"lstrip": true,
|
559 |
+
"normalized": true,
|
560 |
+
"rstrip": false,
|
561 |
+
"single_word": false,
|
562 |
+
"special": true
|
563 |
+
},
|
564 |
+
"32065": {
|
565 |
+
"content": "<extra_id_34>",
|
566 |
+
"lstrip": true,
|
567 |
+
"normalized": true,
|
568 |
+
"rstrip": false,
|
569 |
+
"single_word": false,
|
570 |
+
"special": true
|
571 |
+
},
|
572 |
+
"32066": {
|
573 |
+
"content": "<extra_id_33>",
|
574 |
+
"lstrip": true,
|
575 |
+
"normalized": true,
|
576 |
+
"rstrip": false,
|
577 |
+
"single_word": false,
|
578 |
+
"special": true
|
579 |
+
},
|
580 |
+
"32067": {
|
581 |
+
"content": "<extra_id_32>",
|
582 |
+
"lstrip": true,
|
583 |
+
"normalized": true,
|
584 |
+
"rstrip": false,
|
585 |
+
"single_word": false,
|
586 |
+
"special": true
|
587 |
+
},
|
588 |
+
"32068": {
|
589 |
+
"content": "<extra_id_31>",
|
590 |
+
"lstrip": true,
|
591 |
+
"normalized": true,
|
592 |
+
"rstrip": false,
|
593 |
+
"single_word": false,
|
594 |
+
"special": true
|
595 |
+
},
|
596 |
+
"32069": {
|
597 |
+
"content": "<extra_id_30>",
|
598 |
+
"lstrip": true,
|
599 |
+
"normalized": true,
|
600 |
+
"rstrip": false,
|
601 |
+
"single_word": false,
|
602 |
+
"special": true
|
603 |
+
},
|
604 |
+
"32070": {
|
605 |
+
"content": "<extra_id_29>",
|
606 |
+
"lstrip": true,
|
607 |
+
"normalized": true,
|
608 |
+
"rstrip": false,
|
609 |
+
"single_word": false,
|
610 |
+
"special": true
|
611 |
+
},
|
612 |
+
"32071": {
|
613 |
+
"content": "<extra_id_28>",
|
614 |
+
"lstrip": true,
|
615 |
+
"normalized": true,
|
616 |
+
"rstrip": false,
|
617 |
+
"single_word": false,
|
618 |
+
"special": true
|
619 |
+
},
|
620 |
+
"32072": {
|
621 |
+
"content": "<extra_id_27>",
|
622 |
+
"lstrip": true,
|
623 |
+
"normalized": true,
|
624 |
+
"rstrip": false,
|
625 |
+
"single_word": false,
|
626 |
+
"special": true
|
627 |
+
},
|
628 |
+
"32073": {
|
629 |
+
"content": "<extra_id_26>",
|
630 |
+
"lstrip": true,
|
631 |
+
"normalized": true,
|
632 |
+
"rstrip": false,
|
633 |
+
"single_word": false,
|
634 |
+
"special": true
|
635 |
+
},
|
636 |
+
"32074": {
|
637 |
+
"content": "<extra_id_25>",
|
638 |
+
"lstrip": true,
|
639 |
+
"normalized": true,
|
640 |
+
"rstrip": false,
|
641 |
+
"single_word": false,
|
642 |
+
"special": true
|
643 |
+
},
|
644 |
+
"32075": {
|
645 |
+
"content": "<extra_id_24>",
|
646 |
+
"lstrip": true,
|
647 |
+
"normalized": true,
|
648 |
+
"rstrip": false,
|
649 |
+
"single_word": false,
|
650 |
+
"special": true
|
651 |
+
},
|
652 |
+
"32076": {
|
653 |
+
"content": "<extra_id_23>",
|
654 |
+
"lstrip": true,
|
655 |
+
"normalized": true,
|
656 |
+
"rstrip": false,
|
657 |
+
"single_word": false,
|
658 |
+
"special": true
|
659 |
+
},
|
660 |
+
"32077": {
|
661 |
+
"content": "<extra_id_22>",
|
662 |
+
"lstrip": true,
|
663 |
+
"normalized": true,
|
664 |
+
"rstrip": false,
|
665 |
+
"single_word": false,
|
666 |
+
"special": true
|
667 |
+
},
|
668 |
+
"32078": {
|
669 |
+
"content": "<extra_id_21>",
|
670 |
+
"lstrip": true,
|
671 |
+
"normalized": true,
|
672 |
+
"rstrip": false,
|
673 |
+
"single_word": false,
|
674 |
+
"special": true
|
675 |
+
},
|
676 |
+
"32079": {
|
677 |
+
"content": "<extra_id_20>",
|
678 |
+
"lstrip": true,
|
679 |
+
"normalized": true,
|
680 |
+
"rstrip": false,
|
681 |
+
"single_word": false,
|
682 |
+
"special": true
|
683 |
+
},
|
684 |
+
"32080": {
|
685 |
+
"content": "<extra_id_19>",
|
686 |
+
"lstrip": true,
|
687 |
+
"normalized": true,
|
688 |
+
"rstrip": false,
|
689 |
+
"single_word": false,
|
690 |
+
"special": true
|
691 |
+
},
|
692 |
+
"32081": {
|
693 |
+
"content": "<extra_id_18>",
|
694 |
+
"lstrip": true,
|
695 |
+
"normalized": true,
|
696 |
+
"rstrip": false,
|
697 |
+
"single_word": false,
|
698 |
+
"special": true
|
699 |
+
},
|
700 |
+
"32082": {
|
701 |
+
"content": "<extra_id_17>",
|
702 |
+
"lstrip": true,
|
703 |
+
"normalized": true,
|
704 |
+
"rstrip": false,
|
705 |
+
"single_word": false,
|
706 |
+
"special": true
|
707 |
+
},
|
708 |
+
"32083": {
|
709 |
+
"content": "<extra_id_16>",
|
710 |
+
"lstrip": true,
|
711 |
+
"normalized": true,
|
712 |
+
"rstrip": false,
|
713 |
+
"single_word": false,
|
714 |
+
"special": true
|
715 |
+
},
|
716 |
+
"32084": {
|
717 |
+
"content": "<extra_id_15>",
|
718 |
+
"lstrip": true,
|
719 |
+
"normalized": true,
|
720 |
+
"rstrip": false,
|
721 |
+
"single_word": false,
|
722 |
+
"special": true
|
723 |
+
},
|
724 |
+
"32085": {
|
725 |
+
"content": "<extra_id_14>",
|
726 |
+
"lstrip": true,
|
727 |
+
"normalized": true,
|
728 |
+
"rstrip": false,
|
729 |
+
"single_word": false,
|
730 |
+
"special": true
|
731 |
+
},
|
732 |
+
"32086": {
|
733 |
+
"content": "<extra_id_13>",
|
734 |
+
"lstrip": true,
|
735 |
+
"normalized": true,
|
736 |
+
"rstrip": false,
|
737 |
+
"single_word": false,
|
738 |
+
"special": true
|
739 |
+
},
|
740 |
+
"32087": {
|
741 |
+
"content": "<extra_id_12>",
|
742 |
+
"lstrip": true,
|
743 |
+
"normalized": true,
|
744 |
+
"rstrip": false,
|
745 |
+
"single_word": false,
|
746 |
+
"special": true
|
747 |
+
},
|
748 |
+
"32088": {
|
749 |
+
"content": "<extra_id_11>",
|
750 |
+
"lstrip": true,
|
751 |
+
"normalized": true,
|
752 |
+
"rstrip": false,
|
753 |
+
"single_word": false,
|
754 |
+
"special": true
|
755 |
+
},
|
756 |
+
"32089": {
|
757 |
+
"content": "<extra_id_10>",
|
758 |
+
"lstrip": true,
|
759 |
+
"normalized": true,
|
760 |
+
"rstrip": false,
|
761 |
+
"single_word": false,
|
762 |
+
"special": true
|
763 |
+
},
|
764 |
+
"32090": {
|
765 |
+
"content": "<extra_id_9>",
|
766 |
+
"lstrip": true,
|
767 |
+
"normalized": true,
|
768 |
+
"rstrip": false,
|
769 |
+
"single_word": false,
|
770 |
+
"special": true
|
771 |
+
},
|
772 |
+
"32091": {
|
773 |
+
"content": "<extra_id_8>",
|
774 |
+
"lstrip": true,
|
775 |
+
"normalized": true,
|
776 |
+
"rstrip": false,
|
777 |
+
"single_word": false,
|
778 |
+
"special": true
|
779 |
+
},
|
780 |
+
"32092": {
|
781 |
+
"content": "<extra_id_7>",
|
782 |
+
"lstrip": true,
|
783 |
+
"normalized": true,
|
784 |
+
"rstrip": false,
|
785 |
+
"single_word": false,
|
786 |
+
"special": true
|
787 |
+
},
|
788 |
+
"32093": {
|
789 |
+
"content": "<extra_id_6>",
|
790 |
+
"lstrip": true,
|
791 |
+
"normalized": true,
|
792 |
+
"rstrip": false,
|
793 |
+
"single_word": false,
|
794 |
+
"special": true
|
795 |
+
},
|
796 |
+
"32094": {
|
797 |
+
"content": "<extra_id_5>",
|
798 |
+
"lstrip": true,
|
799 |
+
"normalized": true,
|
800 |
+
"rstrip": false,
|
801 |
+
"single_word": false,
|
802 |
+
"special": true
|
803 |
+
},
|
804 |
+
"32095": {
|
805 |
+
"content": "<extra_id_4>",
|
806 |
+
"lstrip": true,
|
807 |
+
"normalized": true,
|
808 |
+
"rstrip": false,
|
809 |
+
"single_word": false,
|
810 |
+
"special": true
|
811 |
+
},
|
812 |
+
"32096": {
|
813 |
+
"content": "<extra_id_3>",
|
814 |
+
"lstrip": true,
|
815 |
+
"normalized": true,
|
816 |
+
"rstrip": false,
|
817 |
+
"single_word": false,
|
818 |
+
"special": true
|
819 |
+
},
|
820 |
+
"32097": {
|
821 |
+
"content": "<extra_id_2>",
|
822 |
+
"lstrip": true,
|
823 |
+
"normalized": true,
|
824 |
+
"rstrip": false,
|
825 |
+
"single_word": false,
|
826 |
+
"special": true
|
827 |
+
},
|
828 |
+
"32098": {
|
829 |
+
"content": "<extra_id_1>",
|
830 |
+
"lstrip": true,
|
831 |
+
"normalized": true,
|
832 |
+
"rstrip": false,
|
833 |
+
"single_word": false,
|
834 |
+
"special": true
|
835 |
+
},
|
836 |
+
"32099": {
|
837 |
+
"content": "<extra_id_0>",
|
838 |
+
"lstrip": true,
|
839 |
+
"normalized": true,
|
840 |
+
"rstrip": false,
|
841 |
+
"single_word": false,
|
842 |
+
"special": true
|
843 |
+
}
|
844 |
+
},
|
845 |
+
"additional_special_tokens": [
|
846 |
+
"<extra_id_99>",
|
847 |
+
"<extra_id_98>",
|
848 |
+
"<extra_id_97>",
|
849 |
+
"<extra_id_96>",
|
850 |
+
"<extra_id_95>",
|
851 |
+
"<extra_id_94>",
|
852 |
+
"<extra_id_93>",
|
853 |
+
"<extra_id_92>",
|
854 |
+
"<extra_id_91>",
|
855 |
+
"<extra_id_90>",
|
856 |
+
"<extra_id_89>",
|
857 |
+
"<extra_id_88>",
|
858 |
+
"<extra_id_87>",
|
859 |
+
"<extra_id_86>",
|
860 |
+
"<extra_id_85>",
|
861 |
+
"<extra_id_84>",
|
862 |
+
"<extra_id_83>",
|
863 |
+
"<extra_id_82>",
|
864 |
+
"<extra_id_81>",
|
865 |
+
"<extra_id_80>",
|
866 |
+
"<extra_id_79>",
|
867 |
+
"<extra_id_78>",
|
868 |
+
"<extra_id_77>",
|
869 |
+
"<extra_id_76>",
|
870 |
+
"<extra_id_75>",
|
871 |
+
"<extra_id_74>",
|
872 |
+
"<extra_id_73>",
|
873 |
+
"<extra_id_72>",
|
874 |
+
"<extra_id_71>",
|
875 |
+
"<extra_id_70>",
|
876 |
+
"<extra_id_69>",
|
877 |
+
"<extra_id_68>",
|
878 |
+
"<extra_id_67>",
|
879 |
+
"<extra_id_66>",
|
880 |
+
"<extra_id_65>",
|
881 |
+
"<extra_id_64>",
|
882 |
+
"<extra_id_63>",
|
883 |
+
"<extra_id_62>",
|
884 |
+
"<extra_id_61>",
|
885 |
+
"<extra_id_60>",
|
886 |
+
"<extra_id_59>",
|
887 |
+
"<extra_id_58>",
|
888 |
+
"<extra_id_57>",
|
889 |
+
"<extra_id_56>",
|
890 |
+
"<extra_id_55>",
|
891 |
+
"<extra_id_54>",
|
892 |
+
"<extra_id_53>",
|
893 |
+
"<extra_id_52>",
|
894 |
+
"<extra_id_51>",
|
895 |
+
"<extra_id_50>",
|
896 |
+
"<extra_id_49>",
|
897 |
+
"<extra_id_48>",
|
898 |
+
"<extra_id_47>",
|
899 |
+
"<extra_id_46>",
|
900 |
+
"<extra_id_45>",
|
901 |
+
"<extra_id_44>",
|
902 |
+
"<extra_id_43>",
|
903 |
+
"<extra_id_42>",
|
904 |
+
"<extra_id_41>",
|
905 |
+
"<extra_id_40>",
|
906 |
+
"<extra_id_39>",
|
907 |
+
"<extra_id_38>",
|
908 |
+
"<extra_id_37>",
|
909 |
+
"<extra_id_36>",
|
910 |
+
"<extra_id_35>",
|
911 |
+
"<extra_id_34>",
|
912 |
+
"<extra_id_33>",
|
913 |
+
"<extra_id_32>",
|
914 |
+
"<extra_id_31>",
|
915 |
+
"<extra_id_30>",
|
916 |
+
"<extra_id_29>",
|
917 |
+
"<extra_id_28>",
|
918 |
+
"<extra_id_27>",
|
919 |
+
"<extra_id_26>",
|
920 |
+
"<extra_id_25>",
|
921 |
+
"<extra_id_24>",
|
922 |
+
"<extra_id_23>",
|
923 |
+
"<extra_id_22>",
|
924 |
+
"<extra_id_21>",
|
925 |
+
"<extra_id_20>",
|
926 |
+
"<extra_id_19>",
|
927 |
+
"<extra_id_18>",
|
928 |
+
"<extra_id_17>",
|
929 |
+
"<extra_id_16>",
|
930 |
+
"<extra_id_15>",
|
931 |
+
"<extra_id_14>",
|
932 |
+
"<extra_id_13>",
|
933 |
+
"<extra_id_12>",
|
934 |
+
"<extra_id_11>",
|
935 |
+
"<extra_id_10>",
|
936 |
+
"<extra_id_9>",
|
937 |
+
"<extra_id_8>",
|
938 |
+
"<extra_id_7>",
|
939 |
+
"<extra_id_6>",
|
940 |
+
"<extra_id_5>",
|
941 |
+
"<extra_id_4>",
|
942 |
+
"<extra_id_3>",
|
943 |
+
"<extra_id_2>",
|
944 |
+
"<extra_id_1>",
|
945 |
+
"<extra_id_0>"
|
946 |
+
],
|
947 |
+
"bos_token": "<s>",
|
948 |
+
"clean_up_tokenization_spaces": true,
|
949 |
+
"cls_token": "<s>",
|
950 |
+
"eos_token": "</s>",
|
951 |
+
"errors": "replace",
|
952 |
+
"mask_token": "<mask>",
|
953 |
+
"model_max_length": 512,
|
954 |
+
"pad_token": "<pad>",
|
955 |
+
"sep_token": "</s>",
|
956 |
+
"tokenizer_class": "RobertaTokenizer",
|
957 |
+
"trim_offsets": true,
|
958 |
+
"unk_token": "<unk>"
|
959 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1873 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 60000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01,
|
13 |
+
"learning_rate": 4.991666666666667e-05,
|
14 |
+
"loss": 2.8022,
|
15 |
+
"step": 200
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.03,
|
19 |
+
"learning_rate": 4.9833333333333336e-05,
|
20 |
+
"loss": 2.516,
|
21 |
+
"step": 400
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.04,
|
25 |
+
"learning_rate": 4.975e-05,
|
26 |
+
"loss": 2.4557,
|
27 |
+
"step": 600
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.05,
|
31 |
+
"learning_rate": 4.966666666666667e-05,
|
32 |
+
"loss": 2.4088,
|
33 |
+
"step": 800
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.07,
|
37 |
+
"learning_rate": 4.958333333333334e-05,
|
38 |
+
"loss": 2.3729,
|
39 |
+
"step": 1000
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.08,
|
43 |
+
"learning_rate": 4.9500000000000004e-05,
|
44 |
+
"loss": 2.3784,
|
45 |
+
"step": 1200
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.09,
|
49 |
+
"learning_rate": 4.9416666666666664e-05,
|
50 |
+
"loss": 2.3573,
|
51 |
+
"step": 1400
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.11,
|
55 |
+
"learning_rate": 4.933333333333334e-05,
|
56 |
+
"loss": 2.3411,
|
57 |
+
"step": 1600
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.12,
|
61 |
+
"learning_rate": 4.9250000000000004e-05,
|
62 |
+
"loss": 2.2949,
|
63 |
+
"step": 1800
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.13,
|
67 |
+
"learning_rate": 4.9166666666666665e-05,
|
68 |
+
"loss": 2.2912,
|
69 |
+
"step": 2000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.15,
|
73 |
+
"learning_rate": 4.908333333333334e-05,
|
74 |
+
"loss": 2.2367,
|
75 |
+
"step": 2200
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.16,
|
79 |
+
"learning_rate": 4.9e-05,
|
80 |
+
"loss": 2.2421,
|
81 |
+
"step": 2400
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.17,
|
85 |
+
"learning_rate": 4.891666666666667e-05,
|
86 |
+
"loss": 2.2875,
|
87 |
+
"step": 2600
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.19,
|
91 |
+
"learning_rate": 4.883333333333334e-05,
|
92 |
+
"loss": 2.259,
|
93 |
+
"step": 2800
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.2,
|
97 |
+
"learning_rate": 4.875e-05,
|
98 |
+
"loss": 2.2614,
|
99 |
+
"step": 3000
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.21,
|
103 |
+
"learning_rate": 4.866666666666667e-05,
|
104 |
+
"loss": 2.2481,
|
105 |
+
"step": 3200
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.23,
|
109 |
+
"learning_rate": 4.858333333333333e-05,
|
110 |
+
"loss": 2.2769,
|
111 |
+
"step": 3400
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.24,
|
115 |
+
"learning_rate": 4.85e-05,
|
116 |
+
"loss": 2.2317,
|
117 |
+
"step": 3600
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.25,
|
121 |
+
"learning_rate": 4.8416666666666673e-05,
|
122 |
+
"loss": 2.2472,
|
123 |
+
"step": 3800
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.27,
|
127 |
+
"learning_rate": 4.8333333333333334e-05,
|
128 |
+
"loss": 2.209,
|
129 |
+
"step": 4000
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.28,
|
133 |
+
"learning_rate": 4.825e-05,
|
134 |
+
"loss": 2.225,
|
135 |
+
"step": 4200
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.29,
|
139 |
+
"learning_rate": 4.8166666666666674e-05,
|
140 |
+
"loss": 2.2069,
|
141 |
+
"step": 4400
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.31,
|
145 |
+
"learning_rate": 4.8083333333333334e-05,
|
146 |
+
"loss": 2.1974,
|
147 |
+
"step": 4600
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.32,
|
151 |
+
"learning_rate": 4.8e-05,
|
152 |
+
"loss": 2.1778,
|
153 |
+
"step": 4800
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.33,
|
157 |
+
"learning_rate": 4.791666666666667e-05,
|
158 |
+
"loss": 2.187,
|
159 |
+
"step": 5000
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.35,
|
163 |
+
"learning_rate": 4.7833333333333335e-05,
|
164 |
+
"loss": 2.1872,
|
165 |
+
"step": 5200
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.36,
|
169 |
+
"learning_rate": 4.775e-05,
|
170 |
+
"loss": 2.16,
|
171 |
+
"step": 5400
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.37,
|
175 |
+
"learning_rate": 4.766666666666667e-05,
|
176 |
+
"loss": 2.1913,
|
177 |
+
"step": 5600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.39,
|
181 |
+
"learning_rate": 4.7583333333333336e-05,
|
182 |
+
"loss": 2.1698,
|
183 |
+
"step": 5800
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.4,
|
187 |
+
"learning_rate": 4.75e-05,
|
188 |
+
"loss": 2.1768,
|
189 |
+
"step": 6000
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.41,
|
193 |
+
"learning_rate": 4.741666666666667e-05,
|
194 |
+
"loss": 2.1703,
|
195 |
+
"step": 6200
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.43,
|
199 |
+
"learning_rate": 4.7333333333333336e-05,
|
200 |
+
"loss": 2.1733,
|
201 |
+
"step": 6400
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.44,
|
205 |
+
"learning_rate": 4.7249999999999997e-05,
|
206 |
+
"loss": 2.1701,
|
207 |
+
"step": 6600
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.45,
|
211 |
+
"learning_rate": 4.716666666666667e-05,
|
212 |
+
"loss": 2.17,
|
213 |
+
"step": 6800
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.47,
|
217 |
+
"learning_rate": 4.708333333333334e-05,
|
218 |
+
"loss": 2.1496,
|
219 |
+
"step": 7000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.48,
|
223 |
+
"learning_rate": 4.7e-05,
|
224 |
+
"loss": 2.1431,
|
225 |
+
"step": 7200
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.49,
|
229 |
+
"learning_rate": 4.691666666666667e-05,
|
230 |
+
"loss": 2.1408,
|
231 |
+
"step": 7400
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.51,
|
235 |
+
"learning_rate": 4.683333333333334e-05,
|
236 |
+
"loss": 2.1732,
|
237 |
+
"step": 7600
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.52,
|
241 |
+
"learning_rate": 4.6750000000000005e-05,
|
242 |
+
"loss": 2.1479,
|
243 |
+
"step": 7800
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.53,
|
247 |
+
"learning_rate": 4.666666666666667e-05,
|
248 |
+
"loss": 2.1516,
|
249 |
+
"step": 8000
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.55,
|
253 |
+
"learning_rate": 4.658333333333333e-05,
|
254 |
+
"loss": 2.1328,
|
255 |
+
"step": 8200
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.56,
|
259 |
+
"learning_rate": 4.6500000000000005e-05,
|
260 |
+
"loss": 2.153,
|
261 |
+
"step": 8400
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.57,
|
265 |
+
"learning_rate": 4.641666666666667e-05,
|
266 |
+
"loss": 2.1496,
|
267 |
+
"step": 8600
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.59,
|
271 |
+
"learning_rate": 4.633333333333333e-05,
|
272 |
+
"loss": 2.1161,
|
273 |
+
"step": 8800
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.6,
|
277 |
+
"learning_rate": 4.6250000000000006e-05,
|
278 |
+
"loss": 2.1054,
|
279 |
+
"step": 9000
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.61,
|
283 |
+
"learning_rate": 4.6166666666666666e-05,
|
284 |
+
"loss": 2.1412,
|
285 |
+
"step": 9200
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.63,
|
289 |
+
"learning_rate": 4.608333333333333e-05,
|
290 |
+
"loss": 2.1059,
|
291 |
+
"step": 9400
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.64,
|
295 |
+
"learning_rate": 4.600000000000001e-05,
|
296 |
+
"loss": 2.1262,
|
297 |
+
"step": 9600
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.65,
|
301 |
+
"learning_rate": 4.591666666666667e-05,
|
302 |
+
"loss": 2.1024,
|
303 |
+
"step": 9800
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.67,
|
307 |
+
"learning_rate": 4.5833333333333334e-05,
|
308 |
+
"loss": 2.1258,
|
309 |
+
"step": 10000
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.68,
|
313 |
+
"learning_rate": 4.575e-05,
|
314 |
+
"loss": 2.0999,
|
315 |
+
"step": 10200
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.69,
|
319 |
+
"learning_rate": 4.566666666666667e-05,
|
320 |
+
"loss": 2.1237,
|
321 |
+
"step": 10400
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.71,
|
325 |
+
"learning_rate": 4.5583333333333335e-05,
|
326 |
+
"loss": 2.1142,
|
327 |
+
"step": 10600
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.72,
|
331 |
+
"learning_rate": 4.55e-05,
|
332 |
+
"loss": 2.0747,
|
333 |
+
"step": 10800
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.73,
|
337 |
+
"learning_rate": 4.541666666666667e-05,
|
338 |
+
"loss": 2.0865,
|
339 |
+
"step": 11000
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.75,
|
343 |
+
"learning_rate": 4.5333333333333335e-05,
|
344 |
+
"loss": 2.1271,
|
345 |
+
"step": 11200
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.76,
|
349 |
+
"learning_rate": 4.525e-05,
|
350 |
+
"loss": 2.0835,
|
351 |
+
"step": 11400
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.77,
|
355 |
+
"learning_rate": 4.516666666666667e-05,
|
356 |
+
"loss": 2.0794,
|
357 |
+
"step": 11600
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.79,
|
361 |
+
"learning_rate": 4.5083333333333336e-05,
|
362 |
+
"loss": 2.1096,
|
363 |
+
"step": 11800
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.8,
|
367 |
+
"learning_rate": 4.5e-05,
|
368 |
+
"loss": 2.1244,
|
369 |
+
"step": 12000
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.81,
|
373 |
+
"learning_rate": 4.491666666666667e-05,
|
374 |
+
"loss": 2.0884,
|
375 |
+
"step": 12200
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.83,
|
379 |
+
"learning_rate": 4.483333333333333e-05,
|
380 |
+
"loss": 2.0929,
|
381 |
+
"step": 12400
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.84,
|
385 |
+
"learning_rate": 4.4750000000000004e-05,
|
386 |
+
"loss": 2.0652,
|
387 |
+
"step": 12600
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.85,
|
391 |
+
"learning_rate": 4.466666666666667e-05,
|
392 |
+
"loss": 2.0935,
|
393 |
+
"step": 12800
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.87,
|
397 |
+
"learning_rate": 4.458333333333334e-05,
|
398 |
+
"loss": 2.0906,
|
399 |
+
"step": 13000
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.88,
|
403 |
+
"learning_rate": 4.4500000000000004e-05,
|
404 |
+
"loss": 2.0801,
|
405 |
+
"step": 13200
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.89,
|
409 |
+
"learning_rate": 4.4416666666666664e-05,
|
410 |
+
"loss": 2.0671,
|
411 |
+
"step": 13400
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.91,
|
415 |
+
"learning_rate": 4.433333333333334e-05,
|
416 |
+
"loss": 2.1327,
|
417 |
+
"step": 13600
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.92,
|
421 |
+
"learning_rate": 4.4250000000000005e-05,
|
422 |
+
"loss": 2.0867,
|
423 |
+
"step": 13800
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.93,
|
427 |
+
"learning_rate": 4.4166666666666665e-05,
|
428 |
+
"loss": 2.075,
|
429 |
+
"step": 14000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.95,
|
433 |
+
"learning_rate": 4.408333333333334e-05,
|
434 |
+
"loss": 2.1014,
|
435 |
+
"step": 14200
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.96,
|
439 |
+
"learning_rate": 4.4000000000000006e-05,
|
440 |
+
"loss": 2.0797,
|
441 |
+
"step": 14400
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.97,
|
445 |
+
"learning_rate": 4.3916666666666666e-05,
|
446 |
+
"loss": 2.0455,
|
447 |
+
"step": 14600
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.99,
|
451 |
+
"learning_rate": 4.383333333333334e-05,
|
452 |
+
"loss": 2.0765,
|
453 |
+
"step": 14800
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 1.0,
|
457 |
+
"learning_rate": 4.375e-05,
|
458 |
+
"loss": 2.0806,
|
459 |
+
"step": 15000
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 1.0,
|
463 |
+
"eval_gen_len": 15.620051033006831,
|
464 |
+
"eval_loss": 2.459954023361206,
|
465 |
+
"eval_rouge1": 34.4464,
|
466 |
+
"eval_rouge2": 13.8945,
|
467 |
+
"eval_rougeL": 30.5475,
|
468 |
+
"eval_rougeLsum": 30.6085,
|
469 |
+
"eval_runtime": 2863.3613,
|
470 |
+
"eval_samples_per_second": 8.486,
|
471 |
+
"eval_steps_per_second": 2.122,
|
472 |
+
"step": 15000
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 1.01,
|
476 |
+
"learning_rate": 4.3666666666666666e-05,
|
477 |
+
"loss": 1.9174,
|
478 |
+
"step": 15200
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 1.03,
|
482 |
+
"learning_rate": 4.358333333333334e-05,
|
483 |
+
"loss": 1.9011,
|
484 |
+
"step": 15400
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 1.04,
|
488 |
+
"learning_rate": 4.35e-05,
|
489 |
+
"loss": 1.8711,
|
490 |
+
"step": 15600
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 1.05,
|
494 |
+
"learning_rate": 4.341666666666667e-05,
|
495 |
+
"loss": 1.8958,
|
496 |
+
"step": 15800
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 1.07,
|
500 |
+
"learning_rate": 4.3333333333333334e-05,
|
501 |
+
"loss": 1.8875,
|
502 |
+
"step": 16000
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 1.08,
|
506 |
+
"learning_rate": 4.325e-05,
|
507 |
+
"loss": 1.897,
|
508 |
+
"step": 16200
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 1.09,
|
512 |
+
"learning_rate": 4.316666666666667e-05,
|
513 |
+
"loss": 1.8898,
|
514 |
+
"step": 16400
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 1.11,
|
518 |
+
"learning_rate": 4.3083333333333335e-05,
|
519 |
+
"loss": 1.8787,
|
520 |
+
"step": 16600
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 1.12,
|
524 |
+
"learning_rate": 4.3e-05,
|
525 |
+
"loss": 1.917,
|
526 |
+
"step": 16800
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 1.13,
|
530 |
+
"learning_rate": 4.291666666666667e-05,
|
531 |
+
"loss": 1.8803,
|
532 |
+
"step": 17000
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"epoch": 1.15,
|
536 |
+
"learning_rate": 4.2833333333333335e-05,
|
537 |
+
"loss": 1.8789,
|
538 |
+
"step": 17200
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 1.16,
|
542 |
+
"learning_rate": 4.275e-05,
|
543 |
+
"loss": 1.8935,
|
544 |
+
"step": 17400
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 1.17,
|
548 |
+
"learning_rate": 4.266666666666667e-05,
|
549 |
+
"loss": 1.907,
|
550 |
+
"step": 17600
|
551 |
+
},
|
552 |
+
{
|
553 |
+
"epoch": 1.19,
|
554 |
+
"learning_rate": 4.2583333333333336e-05,
|
555 |
+
"loss": 1.9027,
|
556 |
+
"step": 17800
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 1.2,
|
560 |
+
"learning_rate": 4.25e-05,
|
561 |
+
"loss": 1.8984,
|
562 |
+
"step": 18000
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 1.21,
|
566 |
+
"learning_rate": 4.241666666666667e-05,
|
567 |
+
"loss": 1.9044,
|
568 |
+
"step": 18200
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 1.23,
|
572 |
+
"learning_rate": 4.233333333333334e-05,
|
573 |
+
"loss": 1.8847,
|
574 |
+
"step": 18400
|
575 |
+
},
|
576 |
+
{
|
577 |
+
"epoch": 1.24,
|
578 |
+
"learning_rate": 4.2250000000000004e-05,
|
579 |
+
"loss": 1.9184,
|
580 |
+
"step": 18600
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 1.25,
|
584 |
+
"learning_rate": 4.216666666666667e-05,
|
585 |
+
"loss": 1.8882,
|
586 |
+
"step": 18800
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 1.27,
|
590 |
+
"learning_rate": 4.208333333333334e-05,
|
591 |
+
"loss": 1.9256,
|
592 |
+
"step": 19000
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 1.28,
|
596 |
+
"learning_rate": 4.2e-05,
|
597 |
+
"loss": 1.9158,
|
598 |
+
"step": 19200
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 1.29,
|
602 |
+
"learning_rate": 4.191666666666667e-05,
|
603 |
+
"loss": 1.9068,
|
604 |
+
"step": 19400
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 1.31,
|
608 |
+
"learning_rate": 4.183333333333334e-05,
|
609 |
+
"loss": 1.8879,
|
610 |
+
"step": 19600
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 1.32,
|
614 |
+
"learning_rate": 4.175e-05,
|
615 |
+
"loss": 1.8831,
|
616 |
+
"step": 19800
|
617 |
+
},
|
618 |
+
{
|
619 |
+
"epoch": 1.33,
|
620 |
+
"learning_rate": 4.166666666666667e-05,
|
621 |
+
"loss": 1.9087,
|
622 |
+
"step": 20000
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"epoch": 1.35,
|
626 |
+
"learning_rate": 4.158333333333333e-05,
|
627 |
+
"loss": 1.9149,
|
628 |
+
"step": 20200
|
629 |
+
},
|
630 |
+
{
|
631 |
+
"epoch": 1.36,
|
632 |
+
"learning_rate": 4.15e-05,
|
633 |
+
"loss": 1.9074,
|
634 |
+
"step": 20400
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 1.37,
|
638 |
+
"learning_rate": 4.141666666666667e-05,
|
639 |
+
"loss": 1.8769,
|
640 |
+
"step": 20600
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 1.39,
|
644 |
+
"learning_rate": 4.133333333333333e-05,
|
645 |
+
"loss": 1.8743,
|
646 |
+
"step": 20800
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 1.4,
|
650 |
+
"learning_rate": 4.125e-05,
|
651 |
+
"loss": 1.9055,
|
652 |
+
"step": 21000
|
653 |
+
},
|
654 |
+
{
|
655 |
+
"epoch": 1.41,
|
656 |
+
"learning_rate": 4.116666666666667e-05,
|
657 |
+
"loss": 1.8867,
|
658 |
+
"step": 21200
|
659 |
+
},
|
660 |
+
{
|
661 |
+
"epoch": 1.43,
|
662 |
+
"learning_rate": 4.1083333333333334e-05,
|
663 |
+
"loss": 1.893,
|
664 |
+
"step": 21400
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 1.44,
|
668 |
+
"learning_rate": 4.1e-05,
|
669 |
+
"loss": 1.8874,
|
670 |
+
"step": 21600
|
671 |
+
},
|
672 |
+
{
|
673 |
+
"epoch": 1.45,
|
674 |
+
"learning_rate": 4.091666666666667e-05,
|
675 |
+
"loss": 1.9026,
|
676 |
+
"step": 21800
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 1.47,
|
680 |
+
"learning_rate": 4.0833333333333334e-05,
|
681 |
+
"loss": 1.8764,
|
682 |
+
"step": 22000
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 1.48,
|
686 |
+
"learning_rate": 4.075e-05,
|
687 |
+
"loss": 1.9112,
|
688 |
+
"step": 22200
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 1.49,
|
692 |
+
"learning_rate": 4.066666666666667e-05,
|
693 |
+
"loss": 1.9089,
|
694 |
+
"step": 22400
|
695 |
+
},
|
696 |
+
{
|
697 |
+
"epoch": 1.51,
|
698 |
+
"learning_rate": 4.0583333333333335e-05,
|
699 |
+
"loss": 1.8853,
|
700 |
+
"step": 22600
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"epoch": 1.52,
|
704 |
+
"learning_rate": 4.05e-05,
|
705 |
+
"loss": 1.8859,
|
706 |
+
"step": 22800
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 1.53,
|
710 |
+
"learning_rate": 4.041666666666667e-05,
|
711 |
+
"loss": 1.9075,
|
712 |
+
"step": 23000
|
713 |
+
},
|
714 |
+
{
|
715 |
+
"epoch": 1.55,
|
716 |
+
"learning_rate": 4.0333333333333336e-05,
|
717 |
+
"loss": 1.8879,
|
718 |
+
"step": 23200
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 1.56,
|
722 |
+
"learning_rate": 4.025e-05,
|
723 |
+
"loss": 1.8611,
|
724 |
+
"step": 23400
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 1.57,
|
728 |
+
"learning_rate": 4.016666666666667e-05,
|
729 |
+
"loss": 1.8982,
|
730 |
+
"step": 23600
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 1.59,
|
734 |
+
"learning_rate": 4.0083333333333336e-05,
|
735 |
+
"loss": 1.9351,
|
736 |
+
"step": 23800
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"epoch": 1.6,
|
740 |
+
"learning_rate": 4e-05,
|
741 |
+
"loss": 1.916,
|
742 |
+
"step": 24000
|
743 |
+
},
|
744 |
+
{
|
745 |
+
"epoch": 1.61,
|
746 |
+
"learning_rate": 3.991666666666667e-05,
|
747 |
+
"loss": 1.9065,
|
748 |
+
"step": 24200
|
749 |
+
},
|
750 |
+
{
|
751 |
+
"epoch": 1.63,
|
752 |
+
"learning_rate": 3.983333333333333e-05,
|
753 |
+
"loss": 1.8713,
|
754 |
+
"step": 24400
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 1.64,
|
758 |
+
"learning_rate": 3.9750000000000004e-05,
|
759 |
+
"loss": 1.8929,
|
760 |
+
"step": 24600
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 1.65,
|
764 |
+
"learning_rate": 3.966666666666667e-05,
|
765 |
+
"loss": 1.8875,
|
766 |
+
"step": 24800
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 1.67,
|
770 |
+
"learning_rate": 3.958333333333333e-05,
|
771 |
+
"loss": 1.9038,
|
772 |
+
"step": 25000
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 1.68,
|
776 |
+
"learning_rate": 3.9500000000000005e-05,
|
777 |
+
"loss": 1.9052,
|
778 |
+
"step": 25200
|
779 |
+
},
|
780 |
+
{
|
781 |
+
"epoch": 1.69,
|
782 |
+
"learning_rate": 3.941666666666667e-05,
|
783 |
+
"loss": 1.8826,
|
784 |
+
"step": 25400
|
785 |
+
},
|
786 |
+
{
|
787 |
+
"epoch": 1.71,
|
788 |
+
"learning_rate": 3.933333333333333e-05,
|
789 |
+
"loss": 1.9191,
|
790 |
+
"step": 25600
|
791 |
+
},
|
792 |
+
{
|
793 |
+
"epoch": 1.72,
|
794 |
+
"learning_rate": 3.9250000000000005e-05,
|
795 |
+
"loss": 1.8977,
|
796 |
+
"step": 25800
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 1.73,
|
800 |
+
"learning_rate": 3.9166666666666665e-05,
|
801 |
+
"loss": 1.8694,
|
802 |
+
"step": 26000
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 1.75,
|
806 |
+
"learning_rate": 3.908333333333333e-05,
|
807 |
+
"loss": 1.9068,
|
808 |
+
"step": 26200
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 1.76,
|
812 |
+
"learning_rate": 3.9000000000000006e-05,
|
813 |
+
"loss": 1.8862,
|
814 |
+
"step": 26400
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 1.77,
|
818 |
+
"learning_rate": 3.8916666666666666e-05,
|
819 |
+
"loss": 1.8971,
|
820 |
+
"step": 26600
|
821 |
+
},
|
822 |
+
{
|
823 |
+
"epoch": 1.79,
|
824 |
+
"learning_rate": 3.883333333333333e-05,
|
825 |
+
"loss": 1.8722,
|
826 |
+
"step": 26800
|
827 |
+
},
|
828 |
+
{
|
829 |
+
"epoch": 1.8,
|
830 |
+
"learning_rate": 3.875e-05,
|
831 |
+
"loss": 1.8848,
|
832 |
+
"step": 27000
|
833 |
+
},
|
834 |
+
{
|
835 |
+
"epoch": 1.81,
|
836 |
+
"learning_rate": 3.866666666666667e-05,
|
837 |
+
"loss": 1.9101,
|
838 |
+
"step": 27200
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 1.83,
|
842 |
+
"learning_rate": 3.8583333333333334e-05,
|
843 |
+
"loss": 1.8644,
|
844 |
+
"step": 27400
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 1.84,
|
848 |
+
"learning_rate": 3.85e-05,
|
849 |
+
"loss": 1.8813,
|
850 |
+
"step": 27600
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 1.85,
|
854 |
+
"learning_rate": 3.841666666666667e-05,
|
855 |
+
"loss": 1.8664,
|
856 |
+
"step": 27800
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 1.87,
|
860 |
+
"learning_rate": 3.8333333333333334e-05,
|
861 |
+
"loss": 1.8755,
|
862 |
+
"step": 28000
|
863 |
+
},
|
864 |
+
{
|
865 |
+
"epoch": 1.88,
|
866 |
+
"learning_rate": 3.825e-05,
|
867 |
+
"loss": 1.8921,
|
868 |
+
"step": 28200
|
869 |
+
},
|
870 |
+
{
|
871 |
+
"epoch": 1.89,
|
872 |
+
"learning_rate": 3.816666666666667e-05,
|
873 |
+
"loss": 1.8937,
|
874 |
+
"step": 28400
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 1.91,
|
878 |
+
"learning_rate": 3.8083333333333335e-05,
|
879 |
+
"loss": 1.8644,
|
880 |
+
"step": 28600
|
881 |
+
},
|
882 |
+
{
|
883 |
+
"epoch": 1.92,
|
884 |
+
"learning_rate": 3.8e-05,
|
885 |
+
"loss": 1.8972,
|
886 |
+
"step": 28800
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 1.93,
|
890 |
+
"learning_rate": 3.791666666666667e-05,
|
891 |
+
"loss": 1.8875,
|
892 |
+
"step": 29000
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 1.95,
|
896 |
+
"learning_rate": 3.7833333333333336e-05,
|
897 |
+
"loss": 1.8615,
|
898 |
+
"step": 29200
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 1.96,
|
902 |
+
"learning_rate": 3.775e-05,
|
903 |
+
"loss": 1.9172,
|
904 |
+
"step": 29400
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 1.97,
|
908 |
+
"learning_rate": 3.766666666666667e-05,
|
909 |
+
"loss": 1.8913,
|
910 |
+
"step": 29600
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"epoch": 1.99,
|
914 |
+
"learning_rate": 3.7583333333333337e-05,
|
915 |
+
"loss": 1.8904,
|
916 |
+
"step": 29800
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 2.0,
|
920 |
+
"learning_rate": 3.7500000000000003e-05,
|
921 |
+
"loss": 1.9154,
|
922 |
+
"step": 30000
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 2.0,
|
926 |
+
"eval_gen_len": 16.043007654951026,
|
927 |
+
"eval_loss": 2.419179677963257,
|
928 |
+
"eval_rouge1": 34.5156,
|
929 |
+
"eval_rouge2": 14.0265,
|
930 |
+
"eval_rougeL": 30.6272,
|
931 |
+
"eval_rougeLsum": 30.6921,
|
932 |
+
"eval_runtime": 2912.5692,
|
933 |
+
"eval_samples_per_second": 8.342,
|
934 |
+
"eval_steps_per_second": 2.086,
|
935 |
+
"step": 30000
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 2.01,
|
939 |
+
"learning_rate": 3.7416666666666664e-05,
|
940 |
+
"loss": 1.6859,
|
941 |
+
"step": 30200
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 2.03,
|
945 |
+
"learning_rate": 3.733333333333334e-05,
|
946 |
+
"loss": 1.714,
|
947 |
+
"step": 30400
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 2.04,
|
951 |
+
"learning_rate": 3.7250000000000004e-05,
|
952 |
+
"loss": 1.7231,
|
953 |
+
"step": 30600
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 2.05,
|
957 |
+
"learning_rate": 3.7166666666666664e-05,
|
958 |
+
"loss": 1.7206,
|
959 |
+
"step": 30800
|
960 |
+
},
|
961 |
+
{
|
962 |
+
"epoch": 2.07,
|
963 |
+
"learning_rate": 3.708333333333334e-05,
|
964 |
+
"loss": 1.6844,
|
965 |
+
"step": 31000
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 2.08,
|
969 |
+
"learning_rate": 3.7e-05,
|
970 |
+
"loss": 1.7092,
|
971 |
+
"step": 31200
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 2.09,
|
975 |
+
"learning_rate": 3.6916666666666665e-05,
|
976 |
+
"loss": 1.7228,
|
977 |
+
"step": 31400
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 2.11,
|
981 |
+
"learning_rate": 3.683333333333334e-05,
|
982 |
+
"loss": 1.6913,
|
983 |
+
"step": 31600
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 2.12,
|
987 |
+
"learning_rate": 3.675e-05,
|
988 |
+
"loss": 1.7009,
|
989 |
+
"step": 31800
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 2.13,
|
993 |
+
"learning_rate": 3.6666666666666666e-05,
|
994 |
+
"loss": 1.7045,
|
995 |
+
"step": 32000
|
996 |
+
},
|
997 |
+
{
|
998 |
+
"epoch": 2.15,
|
999 |
+
"learning_rate": 3.658333333333334e-05,
|
1000 |
+
"loss": 1.7111,
|
1001 |
+
"step": 32200
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"epoch": 2.16,
|
1005 |
+
"learning_rate": 3.65e-05,
|
1006 |
+
"loss": 1.7166,
|
1007 |
+
"step": 32400
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"epoch": 2.17,
|
1011 |
+
"learning_rate": 3.641666666666667e-05,
|
1012 |
+
"loss": 1.7458,
|
1013 |
+
"step": 32600
|
1014 |
+
},
|
1015 |
+
{
|
1016 |
+
"epoch": 2.19,
|
1017 |
+
"learning_rate": 3.633333333333333e-05,
|
1018 |
+
"loss": 1.7357,
|
1019 |
+
"step": 32800
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 2.2,
|
1023 |
+
"learning_rate": 3.625e-05,
|
1024 |
+
"loss": 1.7032,
|
1025 |
+
"step": 33000
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 2.21,
|
1029 |
+
"learning_rate": 3.6166666666666674e-05,
|
1030 |
+
"loss": 1.7072,
|
1031 |
+
"step": 33200
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 2.23,
|
1035 |
+
"learning_rate": 3.6083333333333334e-05,
|
1036 |
+
"loss": 1.6994,
|
1037 |
+
"step": 33400
|
1038 |
+
},
|
1039 |
+
{
|
1040 |
+
"epoch": 2.24,
|
1041 |
+
"learning_rate": 3.6e-05,
|
1042 |
+
"loss": 1.6992,
|
1043 |
+
"step": 33600
|
1044 |
+
},
|
1045 |
+
{
|
1046 |
+
"epoch": 2.25,
|
1047 |
+
"learning_rate": 3.591666666666667e-05,
|
1048 |
+
"loss": 1.7208,
|
1049 |
+
"step": 33800
|
1050 |
+
},
|
1051 |
+
{
|
1052 |
+
"epoch": 2.27,
|
1053 |
+
"learning_rate": 3.5833333333333335e-05,
|
1054 |
+
"loss": 1.7011,
|
1055 |
+
"step": 34000
|
1056 |
+
},
|
1057 |
+
{
|
1058 |
+
"epoch": 2.28,
|
1059 |
+
"learning_rate": 3.575e-05,
|
1060 |
+
"loss": 1.7278,
|
1061 |
+
"step": 34200
|
1062 |
+
},
|
1063 |
+
{
|
1064 |
+
"epoch": 2.29,
|
1065 |
+
"learning_rate": 3.566666666666667e-05,
|
1066 |
+
"loss": 1.7246,
|
1067 |
+
"step": 34400
|
1068 |
+
},
|
1069 |
+
{
|
1070 |
+
"epoch": 2.31,
|
1071 |
+
"learning_rate": 3.5583333333333335e-05,
|
1072 |
+
"loss": 1.7248,
|
1073 |
+
"step": 34600
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 2.32,
|
1077 |
+
"learning_rate": 3.55e-05,
|
1078 |
+
"loss": 1.7244,
|
1079 |
+
"step": 34800
|
1080 |
+
},
|
1081 |
+
{
|
1082 |
+
"epoch": 2.33,
|
1083 |
+
"learning_rate": 3.541666666666667e-05,
|
1084 |
+
"loss": 1.7531,
|
1085 |
+
"step": 35000
|
1086 |
+
},
|
1087 |
+
{
|
1088 |
+
"epoch": 2.35,
|
1089 |
+
"learning_rate": 3.5333333333333336e-05,
|
1090 |
+
"loss": 1.755,
|
1091 |
+
"step": 35200
|
1092 |
+
},
|
1093 |
+
{
|
1094 |
+
"epoch": 2.36,
|
1095 |
+
"learning_rate": 3.525e-05,
|
1096 |
+
"loss": 1.7275,
|
1097 |
+
"step": 35400
|
1098 |
+
},
|
1099 |
+
{
|
1100 |
+
"epoch": 2.37,
|
1101 |
+
"learning_rate": 3.516666666666667e-05,
|
1102 |
+
"loss": 1.7237,
|
1103 |
+
"step": 35600
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 2.39,
|
1107 |
+
"learning_rate": 3.508333333333334e-05,
|
1108 |
+
"loss": 1.7379,
|
1109 |
+
"step": 35800
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 2.4,
|
1113 |
+
"learning_rate": 3.5e-05,
|
1114 |
+
"loss": 1.7157,
|
1115 |
+
"step": 36000
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 2.41,
|
1119 |
+
"learning_rate": 3.491666666666667e-05,
|
1120 |
+
"loss": 1.7413,
|
1121 |
+
"step": 36200
|
1122 |
+
},
|
1123 |
+
{
|
1124 |
+
"epoch": 2.43,
|
1125 |
+
"learning_rate": 3.483333333333334e-05,
|
1126 |
+
"loss": 1.723,
|
1127 |
+
"step": 36400
|
1128 |
+
},
|
1129 |
+
{
|
1130 |
+
"epoch": 2.44,
|
1131 |
+
"learning_rate": 3.475e-05,
|
1132 |
+
"loss": 1.7213,
|
1133 |
+
"step": 36600
|
1134 |
+
},
|
1135 |
+
{
|
1136 |
+
"epoch": 2.45,
|
1137 |
+
"learning_rate": 3.466666666666667e-05,
|
1138 |
+
"loss": 1.7213,
|
1139 |
+
"step": 36800
|
1140 |
+
},
|
1141 |
+
{
|
1142 |
+
"epoch": 2.47,
|
1143 |
+
"learning_rate": 3.458333333333333e-05,
|
1144 |
+
"loss": 1.6957,
|
1145 |
+
"step": 37000
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 2.48,
|
1149 |
+
"learning_rate": 3.45e-05,
|
1150 |
+
"loss": 1.7003,
|
1151 |
+
"step": 37200
|
1152 |
+
},
|
1153 |
+
{
|
1154 |
+
"epoch": 2.49,
|
1155 |
+
"learning_rate": 3.441666666666667e-05,
|
1156 |
+
"loss": 1.7397,
|
1157 |
+
"step": 37400
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 2.51,
|
1161 |
+
"learning_rate": 3.433333333333333e-05,
|
1162 |
+
"loss": 1.693,
|
1163 |
+
"step": 37600
|
1164 |
+
},
|
1165 |
+
{
|
1166 |
+
"epoch": 2.52,
|
1167 |
+
"learning_rate": 3.4250000000000006e-05,
|
1168 |
+
"loss": 1.7026,
|
1169 |
+
"step": 37800
|
1170 |
+
},
|
1171 |
+
{
|
1172 |
+
"epoch": 2.53,
|
1173 |
+
"learning_rate": 3.4166666666666666e-05,
|
1174 |
+
"loss": 1.7449,
|
1175 |
+
"step": 38000
|
1176 |
+
},
|
1177 |
+
{
|
1178 |
+
"epoch": 2.55,
|
1179 |
+
"learning_rate": 3.408333333333333e-05,
|
1180 |
+
"loss": 1.7425,
|
1181 |
+
"step": 38200
|
1182 |
+
},
|
1183 |
+
{
|
1184 |
+
"epoch": 2.56,
|
1185 |
+
"learning_rate": 3.4000000000000007e-05,
|
1186 |
+
"loss": 1.7533,
|
1187 |
+
"step": 38400
|
1188 |
+
},
|
1189 |
+
{
|
1190 |
+
"epoch": 2.57,
|
1191 |
+
"learning_rate": 3.391666666666667e-05,
|
1192 |
+
"loss": 1.7184,
|
1193 |
+
"step": 38600
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 2.59,
|
1197 |
+
"learning_rate": 3.3833333333333334e-05,
|
1198 |
+
"loss": 1.7301,
|
1199 |
+
"step": 38800
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 2.6,
|
1203 |
+
"learning_rate": 3.375000000000001e-05,
|
1204 |
+
"loss": 1.7336,
|
1205 |
+
"step": 39000
|
1206 |
+
},
|
1207 |
+
{
|
1208 |
+
"epoch": 2.61,
|
1209 |
+
"learning_rate": 3.366666666666667e-05,
|
1210 |
+
"loss": 1.7344,
|
1211 |
+
"step": 39200
|
1212 |
+
},
|
1213 |
+
{
|
1214 |
+
"epoch": 2.63,
|
1215 |
+
"learning_rate": 3.3583333333333334e-05,
|
1216 |
+
"loss": 1.7127,
|
1217 |
+
"step": 39400
|
1218 |
+
},
|
1219 |
+
{
|
1220 |
+
"epoch": 2.64,
|
1221 |
+
"learning_rate": 3.35e-05,
|
1222 |
+
"loss": 1.7291,
|
1223 |
+
"step": 39600
|
1224 |
+
},
|
1225 |
+
{
|
1226 |
+
"epoch": 2.65,
|
1227 |
+
"learning_rate": 3.341666666666667e-05,
|
1228 |
+
"loss": 1.7096,
|
1229 |
+
"step": 39800
|
1230 |
+
},
|
1231 |
+
{
|
1232 |
+
"epoch": 2.67,
|
1233 |
+
"learning_rate": 3.3333333333333335e-05,
|
1234 |
+
"loss": 1.7135,
|
1235 |
+
"step": 40000
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 2.68,
|
1239 |
+
"learning_rate": 3.325e-05,
|
1240 |
+
"loss": 1.7156,
|
1241 |
+
"step": 40200
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 2.69,
|
1245 |
+
"learning_rate": 3.316666666666667e-05,
|
1246 |
+
"loss": 1.7434,
|
1247 |
+
"step": 40400
|
1248 |
+
},
|
1249 |
+
{
|
1250 |
+
"epoch": 2.71,
|
1251 |
+
"learning_rate": 3.3083333333333336e-05,
|
1252 |
+
"loss": 1.7479,
|
1253 |
+
"step": 40600
|
1254 |
+
},
|
1255 |
+
{
|
1256 |
+
"epoch": 2.72,
|
1257 |
+
"learning_rate": 3.3e-05,
|
1258 |
+
"loss": 1.7172,
|
1259 |
+
"step": 40800
|
1260 |
+
},
|
1261 |
+
{
|
1262 |
+
"epoch": 2.73,
|
1263 |
+
"learning_rate": 3.291666666666667e-05,
|
1264 |
+
"loss": 1.7347,
|
1265 |
+
"step": 41000
|
1266 |
+
},
|
1267 |
+
{
|
1268 |
+
"epoch": 2.75,
|
1269 |
+
"learning_rate": 3.283333333333333e-05,
|
1270 |
+
"loss": 1.7063,
|
1271 |
+
"step": 41200
|
1272 |
+
},
|
1273 |
+
{
|
1274 |
+
"epoch": 2.76,
|
1275 |
+
"learning_rate": 3.275e-05,
|
1276 |
+
"loss": 1.736,
|
1277 |
+
"step": 41400
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 2.77,
|
1281 |
+
"learning_rate": 3.266666666666667e-05,
|
1282 |
+
"loss": 1.7389,
|
1283 |
+
"step": 41600
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 2.79,
|
1287 |
+
"learning_rate": 3.258333333333333e-05,
|
1288 |
+
"loss": 1.7315,
|
1289 |
+
"step": 41800
|
1290 |
+
},
|
1291 |
+
{
|
1292 |
+
"epoch": 2.8,
|
1293 |
+
"learning_rate": 3.2500000000000004e-05,
|
1294 |
+
"loss": 1.7162,
|
1295 |
+
"step": 42000
|
1296 |
+
},
|
1297 |
+
{
|
1298 |
+
"epoch": 2.81,
|
1299 |
+
"learning_rate": 3.2416666666666664e-05,
|
1300 |
+
"loss": 1.7181,
|
1301 |
+
"step": 42200
|
1302 |
+
},
|
1303 |
+
{
|
1304 |
+
"epoch": 2.83,
|
1305 |
+
"learning_rate": 3.233333333333333e-05,
|
1306 |
+
"loss": 1.7168,
|
1307 |
+
"step": 42400
|
1308 |
+
},
|
1309 |
+
{
|
1310 |
+
"epoch": 2.84,
|
1311 |
+
"learning_rate": 3.2250000000000005e-05,
|
1312 |
+
"loss": 1.7243,
|
1313 |
+
"step": 42600
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 2.85,
|
1317 |
+
"learning_rate": 3.2166666666666665e-05,
|
1318 |
+
"loss": 1.7113,
|
1319 |
+
"step": 42800
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 2.87,
|
1323 |
+
"learning_rate": 3.208333333333334e-05,
|
1324 |
+
"loss": 1.7294,
|
1325 |
+
"step": 43000
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 2.88,
|
1329 |
+
"learning_rate": 3.2000000000000005e-05,
|
1330 |
+
"loss": 1.7033,
|
1331 |
+
"step": 43200
|
1332 |
+
},
|
1333 |
+
{
|
1334 |
+
"epoch": 2.89,
|
1335 |
+
"learning_rate": 3.1916666666666665e-05,
|
1336 |
+
"loss": 1.7622,
|
1337 |
+
"step": 43400
|
1338 |
+
},
|
1339 |
+
{
|
1340 |
+
"epoch": 2.91,
|
1341 |
+
"learning_rate": 3.183333333333334e-05,
|
1342 |
+
"loss": 1.7233,
|
1343 |
+
"step": 43600
|
1344 |
+
},
|
1345 |
+
{
|
1346 |
+
"epoch": 2.92,
|
1347 |
+
"learning_rate": 3.175e-05,
|
1348 |
+
"loss": 1.7479,
|
1349 |
+
"step": 43800
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"epoch": 2.93,
|
1353 |
+
"learning_rate": 3.1666666666666666e-05,
|
1354 |
+
"loss": 1.7312,
|
1355 |
+
"step": 44000
|
1356 |
+
},
|
1357 |
+
{
|
1358 |
+
"epoch": 2.95,
|
1359 |
+
"learning_rate": 3.158333333333334e-05,
|
1360 |
+
"loss": 1.7526,
|
1361 |
+
"step": 44200
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 2.96,
|
1365 |
+
"learning_rate": 3.15e-05,
|
1366 |
+
"loss": 1.7419,
|
1367 |
+
"step": 44400
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 2.97,
|
1371 |
+
"learning_rate": 3.141666666666667e-05,
|
1372 |
+
"loss": 1.7287,
|
1373 |
+
"step": 44600
|
1374 |
+
},
|
1375 |
+
{
|
1376 |
+
"epoch": 2.99,
|
1377 |
+
"learning_rate": 3.1333333333333334e-05,
|
1378 |
+
"loss": 1.7304,
|
1379 |
+
"step": 44800
|
1380 |
+
},
|
1381 |
+
{
|
1382 |
+
"epoch": 3.0,
|
1383 |
+
"learning_rate": 3.125e-05,
|
1384 |
+
"loss": 1.7863,
|
1385 |
+
"step": 45000
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 3.0,
|
1389 |
+
"eval_gen_len": 15.681784509013088,
|
1390 |
+
"eval_loss": 2.4119651317596436,
|
1391 |
+
"eval_rouge1": 35.0684,
|
1392 |
+
"eval_rouge2": 14.2092,
|
1393 |
+
"eval_rougeL": 31.0091,
|
1394 |
+
"eval_rougeLsum": 31.0765,
|
1395 |
+
"eval_runtime": 2851.736,
|
1396 |
+
"eval_samples_per_second": 8.52,
|
1397 |
+
"eval_steps_per_second": 2.13,
|
1398 |
+
"step": 45000
|
1399 |
+
},
|
1400 |
+
{
|
1401 |
+
"epoch": 3.01,
|
1402 |
+
"learning_rate": 3.116666666666667e-05,
|
1403 |
+
"loss": 1.555,
|
1404 |
+
"step": 45200
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 3.03,
|
1408 |
+
"learning_rate": 3.1083333333333334e-05,
|
1409 |
+
"loss": 1.5511,
|
1410 |
+
"step": 45400
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 3.04,
|
1414 |
+
"learning_rate": 3.1e-05,
|
1415 |
+
"loss": 1.5533,
|
1416 |
+
"step": 45600
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 3.05,
|
1420 |
+
"learning_rate": 3.091666666666667e-05,
|
1421 |
+
"loss": 1.5438,
|
1422 |
+
"step": 45800
|
1423 |
+
},
|
1424 |
+
{
|
1425 |
+
"epoch": 3.07,
|
1426 |
+
"learning_rate": 3.0833333333333335e-05,
|
1427 |
+
"loss": 1.5714,
|
1428 |
+
"step": 46000
|
1429 |
+
},
|
1430 |
+
{
|
1431 |
+
"epoch": 3.08,
|
1432 |
+
"learning_rate": 3.075e-05,
|
1433 |
+
"loss": 1.5633,
|
1434 |
+
"step": 46200
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 3.09,
|
1438 |
+
"learning_rate": 3.066666666666667e-05,
|
1439 |
+
"loss": 1.574,
|
1440 |
+
"step": 46400
|
1441 |
+
},
|
1442 |
+
{
|
1443 |
+
"epoch": 3.11,
|
1444 |
+
"learning_rate": 3.0583333333333336e-05,
|
1445 |
+
"loss": 1.5698,
|
1446 |
+
"step": 46600
|
1447 |
+
},
|
1448 |
+
{
|
1449 |
+
"epoch": 3.12,
|
1450 |
+
"learning_rate": 3.05e-05,
|
1451 |
+
"loss": 1.5819,
|
1452 |
+
"step": 46800
|
1453 |
+
},
|
1454 |
+
{
|
1455 |
+
"epoch": 3.13,
|
1456 |
+
"learning_rate": 3.0416666666666666e-05,
|
1457 |
+
"loss": 1.5745,
|
1458 |
+
"step": 47000
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 3.15,
|
1462 |
+
"learning_rate": 3.0333333333333337e-05,
|
1463 |
+
"loss": 1.5622,
|
1464 |
+
"step": 47200
|
1465 |
+
},
|
1466 |
+
{
|
1467 |
+
"epoch": 3.16,
|
1468 |
+
"learning_rate": 3.025e-05,
|
1469 |
+
"loss": 1.5747,
|
1470 |
+
"step": 47400
|
1471 |
+
},
|
1472 |
+
{
|
1473 |
+
"epoch": 3.17,
|
1474 |
+
"learning_rate": 3.016666666666667e-05,
|
1475 |
+
"loss": 1.5793,
|
1476 |
+
"step": 47600
|
1477 |
+
},
|
1478 |
+
{
|
1479 |
+
"epoch": 3.19,
|
1480 |
+
"learning_rate": 3.0083333333333337e-05,
|
1481 |
+
"loss": 1.5884,
|
1482 |
+
"step": 47800
|
1483 |
+
},
|
1484 |
+
{
|
1485 |
+
"epoch": 3.2,
|
1486 |
+
"learning_rate": 3e-05,
|
1487 |
+
"loss": 1.5729,
|
1488 |
+
"step": 48000
|
1489 |
+
},
|
1490 |
+
{
|
1491 |
+
"epoch": 3.21,
|
1492 |
+
"learning_rate": 2.991666666666667e-05,
|
1493 |
+
"loss": 1.5944,
|
1494 |
+
"step": 48200
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 3.23,
|
1498 |
+
"learning_rate": 2.9833333333333335e-05,
|
1499 |
+
"loss": 1.5829,
|
1500 |
+
"step": 48400
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 3.24,
|
1504 |
+
"learning_rate": 2.975e-05,
|
1505 |
+
"loss": 1.588,
|
1506 |
+
"step": 48600
|
1507 |
+
},
|
1508 |
+
{
|
1509 |
+
"epoch": 3.25,
|
1510 |
+
"learning_rate": 2.9666666666666672e-05,
|
1511 |
+
"loss": 1.5519,
|
1512 |
+
"step": 48800
|
1513 |
+
},
|
1514 |
+
{
|
1515 |
+
"epoch": 3.27,
|
1516 |
+
"learning_rate": 2.9583333333333335e-05,
|
1517 |
+
"loss": 1.6017,
|
1518 |
+
"step": 49000
|
1519 |
+
},
|
1520 |
+
{
|
1521 |
+
"epoch": 3.28,
|
1522 |
+
"learning_rate": 2.95e-05,
|
1523 |
+
"loss": 1.5851,
|
1524 |
+
"step": 49200
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 3.29,
|
1528 |
+
"learning_rate": 2.941666666666667e-05,
|
1529 |
+
"loss": 1.5738,
|
1530 |
+
"step": 49400
|
1531 |
+
},
|
1532 |
+
{
|
1533 |
+
"epoch": 3.31,
|
1534 |
+
"learning_rate": 2.9333333333333336e-05,
|
1535 |
+
"loss": 1.5922,
|
1536 |
+
"step": 49600
|
1537 |
+
},
|
1538 |
+
{
|
1539 |
+
"epoch": 3.32,
|
1540 |
+
"learning_rate": 2.925e-05,
|
1541 |
+
"loss": 1.5425,
|
1542 |
+
"step": 49800
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 3.33,
|
1546 |
+
"learning_rate": 2.916666666666667e-05,
|
1547 |
+
"loss": 1.5725,
|
1548 |
+
"step": 50000
|
1549 |
+
},
|
1550 |
+
{
|
1551 |
+
"epoch": 3.35,
|
1552 |
+
"learning_rate": 2.9083333333333333e-05,
|
1553 |
+
"loss": 1.5734,
|
1554 |
+
"step": 50200
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 3.36,
|
1558 |
+
"learning_rate": 2.9e-05,
|
1559 |
+
"loss": 1.5821,
|
1560 |
+
"step": 50400
|
1561 |
+
},
|
1562 |
+
{
|
1563 |
+
"epoch": 3.37,
|
1564 |
+
"learning_rate": 2.891666666666667e-05,
|
1565 |
+
"loss": 1.5822,
|
1566 |
+
"step": 50600
|
1567 |
+
},
|
1568 |
+
{
|
1569 |
+
"epoch": 3.39,
|
1570 |
+
"learning_rate": 2.8833333333333334e-05,
|
1571 |
+
"loss": 1.5777,
|
1572 |
+
"step": 50800
|
1573 |
+
},
|
1574 |
+
{
|
1575 |
+
"epoch": 3.4,
|
1576 |
+
"learning_rate": 2.8749999999999997e-05,
|
1577 |
+
"loss": 1.6048,
|
1578 |
+
"step": 51000
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 3.41,
|
1582 |
+
"learning_rate": 2.8666666666666668e-05,
|
1583 |
+
"loss": 1.5623,
|
1584 |
+
"step": 51200
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 3.43,
|
1588 |
+
"learning_rate": 2.8583333333333335e-05,
|
1589 |
+
"loss": 1.6099,
|
1590 |
+
"step": 51400
|
1591 |
+
},
|
1592 |
+
{
|
1593 |
+
"epoch": 3.44,
|
1594 |
+
"learning_rate": 2.8499999999999998e-05,
|
1595 |
+
"loss": 1.5932,
|
1596 |
+
"step": 51600
|
1597 |
+
},
|
1598 |
+
{
|
1599 |
+
"epoch": 3.45,
|
1600 |
+
"learning_rate": 2.841666666666667e-05,
|
1601 |
+
"loss": 1.5597,
|
1602 |
+
"step": 51800
|
1603 |
+
},
|
1604 |
+
{
|
1605 |
+
"epoch": 3.47,
|
1606 |
+
"learning_rate": 2.8333333333333335e-05,
|
1607 |
+
"loss": 1.583,
|
1608 |
+
"step": 52000
|
1609 |
+
},
|
1610 |
+
{
|
1611 |
+
"epoch": 3.48,
|
1612 |
+
"learning_rate": 2.825e-05,
|
1613 |
+
"loss": 1.5846,
|
1614 |
+
"step": 52200
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"epoch": 3.49,
|
1618 |
+
"learning_rate": 2.816666666666667e-05,
|
1619 |
+
"loss": 1.5996,
|
1620 |
+
"step": 52400
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 3.51,
|
1624 |
+
"learning_rate": 2.8083333333333333e-05,
|
1625 |
+
"loss": 1.5999,
|
1626 |
+
"step": 52600
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 3.52,
|
1630 |
+
"learning_rate": 2.8000000000000003e-05,
|
1631 |
+
"loss": 1.605,
|
1632 |
+
"step": 52800
|
1633 |
+
},
|
1634 |
+
{
|
1635 |
+
"epoch": 3.53,
|
1636 |
+
"learning_rate": 2.791666666666667e-05,
|
1637 |
+
"loss": 1.5995,
|
1638 |
+
"step": 53000
|
1639 |
+
},
|
1640 |
+
{
|
1641 |
+
"epoch": 3.55,
|
1642 |
+
"learning_rate": 2.7833333333333333e-05,
|
1643 |
+
"loss": 1.6058,
|
1644 |
+
"step": 53200
|
1645 |
+
},
|
1646 |
+
{
|
1647 |
+
"epoch": 3.56,
|
1648 |
+
"learning_rate": 2.7750000000000004e-05,
|
1649 |
+
"loss": 1.59,
|
1650 |
+
"step": 53400
|
1651 |
+
},
|
1652 |
+
{
|
1653 |
+
"epoch": 3.57,
|
1654 |
+
"learning_rate": 2.7666666666666667e-05,
|
1655 |
+
"loss": 1.5918,
|
1656 |
+
"step": 53600
|
1657 |
+
},
|
1658 |
+
{
|
1659 |
+
"epoch": 3.59,
|
1660 |
+
"learning_rate": 2.7583333333333334e-05,
|
1661 |
+
"loss": 1.5833,
|
1662 |
+
"step": 53800
|
1663 |
+
},
|
1664 |
+
{
|
1665 |
+
"epoch": 3.6,
|
1666 |
+
"learning_rate": 2.7500000000000004e-05,
|
1667 |
+
"loss": 1.6004,
|
1668 |
+
"step": 54000
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 3.61,
|
1672 |
+
"learning_rate": 2.7416666666666668e-05,
|
1673 |
+
"loss": 1.5726,
|
1674 |
+
"step": 54200
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 3.63,
|
1678 |
+
"learning_rate": 2.733333333333333e-05,
|
1679 |
+
"loss": 1.6005,
|
1680 |
+
"step": 54400
|
1681 |
+
},
|
1682 |
+
{
|
1683 |
+
"epoch": 3.64,
|
1684 |
+
"learning_rate": 2.725e-05,
|
1685 |
+
"loss": 1.5796,
|
1686 |
+
"step": 54600
|
1687 |
+
},
|
1688 |
+
{
|
1689 |
+
"epoch": 3.65,
|
1690 |
+
"learning_rate": 2.716666666666667e-05,
|
1691 |
+
"loss": 1.5759,
|
1692 |
+
"step": 54800
|
1693 |
+
},
|
1694 |
+
{
|
1695 |
+
"epoch": 3.67,
|
1696 |
+
"learning_rate": 2.7083333333333332e-05,
|
1697 |
+
"loss": 1.5836,
|
1698 |
+
"step": 55000
|
1699 |
+
},
|
1700 |
+
{
|
1701 |
+
"epoch": 3.68,
|
1702 |
+
"learning_rate": 2.7000000000000002e-05,
|
1703 |
+
"loss": 1.614,
|
1704 |
+
"step": 55200
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 3.69,
|
1708 |
+
"learning_rate": 2.691666666666667e-05,
|
1709 |
+
"loss": 1.5921,
|
1710 |
+
"step": 55400
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 3.71,
|
1714 |
+
"learning_rate": 2.6833333333333333e-05,
|
1715 |
+
"loss": 1.5859,
|
1716 |
+
"step": 55600
|
1717 |
+
},
|
1718 |
+
{
|
1719 |
+
"epoch": 3.72,
|
1720 |
+
"learning_rate": 2.6750000000000003e-05,
|
1721 |
+
"loss": 1.5914,
|
1722 |
+
"step": 55800
|
1723 |
+
},
|
1724 |
+
{
|
1725 |
+
"epoch": 3.73,
|
1726 |
+
"learning_rate": 2.6666666666666667e-05,
|
1727 |
+
"loss": 1.5979,
|
1728 |
+
"step": 56000
|
1729 |
+
},
|
1730 |
+
{
|
1731 |
+
"epoch": 3.75,
|
1732 |
+
"learning_rate": 2.6583333333333333e-05,
|
1733 |
+
"loss": 1.6103,
|
1734 |
+
"step": 56200
|
1735 |
+
},
|
1736 |
+
{
|
1737 |
+
"epoch": 3.76,
|
1738 |
+
"learning_rate": 2.6500000000000004e-05,
|
1739 |
+
"loss": 1.5848,
|
1740 |
+
"step": 56400
|
1741 |
+
},
|
1742 |
+
{
|
1743 |
+
"epoch": 3.77,
|
1744 |
+
"learning_rate": 2.6416666666666667e-05,
|
1745 |
+
"loss": 1.583,
|
1746 |
+
"step": 56600
|
1747 |
+
},
|
1748 |
+
{
|
1749 |
+
"epoch": 3.79,
|
1750 |
+
"learning_rate": 2.633333333333333e-05,
|
1751 |
+
"loss": 1.6103,
|
1752 |
+
"step": 56800
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 3.8,
|
1756 |
+
"learning_rate": 2.625e-05,
|
1757 |
+
"loss": 1.5873,
|
1758 |
+
"step": 57000
|
1759 |
+
},
|
1760 |
+
{
|
1761 |
+
"epoch": 3.81,
|
1762 |
+
"learning_rate": 2.6166666666666668e-05,
|
1763 |
+
"loss": 1.5808,
|
1764 |
+
"step": 57200
|
1765 |
+
},
|
1766 |
+
{
|
1767 |
+
"epoch": 3.83,
|
1768 |
+
"learning_rate": 2.608333333333333e-05,
|
1769 |
+
"loss": 1.5985,
|
1770 |
+
"step": 57400
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"epoch": 3.84,
|
1774 |
+
"learning_rate": 2.6000000000000002e-05,
|
1775 |
+
"loss": 1.6133,
|
1776 |
+
"step": 57600
|
1777 |
+
},
|
1778 |
+
{
|
1779 |
+
"epoch": 3.85,
|
1780 |
+
"learning_rate": 2.5916666666666665e-05,
|
1781 |
+
"loss": 1.5778,
|
1782 |
+
"step": 57800
|
1783 |
+
},
|
1784 |
+
{
|
1785 |
+
"epoch": 3.87,
|
1786 |
+
"learning_rate": 2.5833333333333336e-05,
|
1787 |
+
"loss": 1.5961,
|
1788 |
+
"step": 58000
|
1789 |
+
},
|
1790 |
+
{
|
1791 |
+
"epoch": 3.88,
|
1792 |
+
"learning_rate": 2.5750000000000002e-05,
|
1793 |
+
"loss": 1.5924,
|
1794 |
+
"step": 58200
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 3.89,
|
1798 |
+
"learning_rate": 2.5666666666666666e-05,
|
1799 |
+
"loss": 1.5834,
|
1800 |
+
"step": 58400
|
1801 |
+
},
|
1802 |
+
{
|
1803 |
+
"epoch": 3.91,
|
1804 |
+
"learning_rate": 2.5583333333333336e-05,
|
1805 |
+
"loss": 1.5845,
|
1806 |
+
"step": 58600
|
1807 |
+
},
|
1808 |
+
{
|
1809 |
+
"epoch": 3.92,
|
1810 |
+
"learning_rate": 2.5500000000000003e-05,
|
1811 |
+
"loss": 1.6207,
|
1812 |
+
"step": 58800
|
1813 |
+
},
|
1814 |
+
{
|
1815 |
+
"epoch": 3.93,
|
1816 |
+
"learning_rate": 2.5416666666666667e-05,
|
1817 |
+
"loss": 1.5935,
|
1818 |
+
"step": 59000
|
1819 |
+
},
|
1820 |
+
{
|
1821 |
+
"epoch": 3.95,
|
1822 |
+
"learning_rate": 2.5333333333333337e-05,
|
1823 |
+
"loss": 1.5847,
|
1824 |
+
"step": 59200
|
1825 |
+
},
|
1826 |
+
{
|
1827 |
+
"epoch": 3.96,
|
1828 |
+
"learning_rate": 2.525e-05,
|
1829 |
+
"loss": 1.5708,
|
1830 |
+
"step": 59400
|
1831 |
+
},
|
1832 |
+
{
|
1833 |
+
"epoch": 3.97,
|
1834 |
+
"learning_rate": 2.5166666666666667e-05,
|
1835 |
+
"loss": 1.582,
|
1836 |
+
"step": 59600
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 3.99,
|
1840 |
+
"learning_rate": 2.5083333333333338e-05,
|
1841 |
+
"loss": 1.6068,
|
1842 |
+
"step": 59800
|
1843 |
+
},
|
1844 |
+
{
|
1845 |
+
"epoch": 4.0,
|
1846 |
+
"learning_rate": 2.5e-05,
|
1847 |
+
"loss": 1.5749,
|
1848 |
+
"step": 60000
|
1849 |
+
},
|
1850 |
+
{
|
1851 |
+
"epoch": 4.0,
|
1852 |
+
"eval_gen_len": 15.67746316569265,
|
1853 |
+
"eval_loss": 2.43806529045105,
|
1854 |
+
"eval_rouge1": 35.3459,
|
1855 |
+
"eval_rouge2": 14.4892,
|
1856 |
+
"eval_rougeL": 31.2887,
|
1857 |
+
"eval_rougeLsum": 31.3513,
|
1858 |
+
"eval_runtime": 3189.3267,
|
1859 |
+
"eval_samples_per_second": 7.619,
|
1860 |
+
"eval_steps_per_second": 1.905,
|
1861 |
+
"step": 60000
|
1862 |
+
}
|
1863 |
+
],
|
1864 |
+
"logging_steps": 200,
|
1865 |
+
"max_steps": 120000,
|
1866 |
+
"num_input_tokens_seen": 0,
|
1867 |
+
"num_train_epochs": 8,
|
1868 |
+
"save_steps": 500,
|
1869 |
+
"total_flos": 5.064159661468877e+17,
|
1870 |
+
"train_batch_size": 4,
|
1871 |
+
"trial_name": null,
|
1872 |
+
"trial_params": null
|
1873 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84273cdfd2d56f6ef0ba0c7d150d206c4a2a3d6786b3290150487b1740091b68
|
3 |
+
size 4856
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|