Add model
Browse files- config.gin +149 -0
- config.json +31 -0
- flax_model.msgpack +3 -0
- model-info.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +107 -0
- spiece.model +3 -0
- spiece.vocab +0 -0
- tokenizer_config.json +113 -0
- train/events.out.tfevents.1670764801.t1v-n-82e561a1-w-0.1168530.0.v2 +3 -0
- train/events.out.tfevents.1671135229.t1v-n-82e561a1-w-0.1383256.0.v2 +3 -0
- train/events.out.tfevents.1671186857.t1v-n-7fd9879f-w-0.50950.0.v2 +3 -0
- training_eval/mc4_nedd_wiki_news_mix_1/events.out.tfevents.1670764801.t1v-n-82e561a1-w-0.1168530.2.v2 +3 -0
- training_eval/mc4_nedd_wiki_news_mix_1/events.out.tfevents.1671135229.t1v-n-82e561a1-w-0.1383256.2.v2 +3 -0
- training_eval/mc4_nedd_wiki_news_mix_1/events.out.tfevents.1671186857.t1v-n-7fd9879f-w-0.50950.2.v2 +3 -0
- training_eval/mc4_nl_span_corruption/events.out.tfevents.1670764801.t1v-n-82e561a1-w-0.1168530.1.v2 +3 -0
- training_eval/mc4_nl_span_corruption/events.out.tfevents.1671135229.t1v-n-82e561a1-w-0.1383256.1.v2 +3 -0
- training_eval/mc4_nl_span_corruption/events.out.tfevents.1671186857.t1v-n-7fd9879f-w-0.50950.1.v2 +3 -0
config.gin
ADDED
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from __gin__ import dynamic_registration
|
2 |
+
import __main__ as train_script
|
3 |
+
import seqio
|
4 |
+
import t5.data.mixtures
|
5 |
+
from t5x import adafactor
|
6 |
+
from t5x.examples.t5 import network
|
7 |
+
from t5x import gin_utils
|
8 |
+
from t5x import models
|
9 |
+
from t5x import partitioning
|
10 |
+
from t5x import trainer
|
11 |
+
from t5x import utils
|
12 |
+
import tasks.nedd_tasks
|
13 |
+
|
14 |
+
# Macros:
|
15 |
+
# ==============================================================================
|
16 |
+
BATCH_SIZE = 128
|
17 |
+
DROPOUT_RATE = 0.0
|
18 |
+
LABEL_SMOOTHING = 0.0
|
19 |
+
LOSS_NORMALIZING_FACTOR = None
|
20 |
+
MIXTURE_OR_TASK_MODULE = None
|
21 |
+
MIXTURE_OR_TASK_NAME = 'mc4_nedd_wiki_news_mix_1'
|
22 |
+
MODEL = @models.EncoderDecoderModel()
|
23 |
+
MODEL_DIR = 't5_1_1_base_nl36_mc4_nedd_wiki_news_nl'
|
24 |
+
OPTIMIZER = @adafactor.Adafactor()
|
25 |
+
RANDOM_SEED = None
|
26 |
+
SHUFFLE_TRAIN_EXAMPLES = True
|
27 |
+
TASK_FEATURE_LENGTHS = {'inputs': 512, 'targets': 114}
|
28 |
+
TRAIN_STEPS = 1000000
|
29 |
+
USE_CACHED_TASKS = False
|
30 |
+
USE_HARDWARE_RNG = False
|
31 |
+
VOCABULARY = @seqio.SentencePieceVocabulary()
|
32 |
+
Z_LOSS = 0.0001
|
33 |
+
|
34 |
+
# Parameters for adafactor.Adafactor:
|
35 |
+
# ==============================================================================
|
36 |
+
adafactor.Adafactor.decay_rate = 0.8
|
37 |
+
adafactor.Adafactor.logical_factor_rules = \
|
38 |
+
@adafactor.standard_logical_factor_rules()
|
39 |
+
adafactor.Adafactor.step_offset = 0
|
40 |
+
|
41 |
+
# Parameters for utils.CheckpointConfig:
|
42 |
+
# ==============================================================================
|
43 |
+
utils.CheckpointConfig.restore = @utils.RestoreCheckpointConfig()
|
44 |
+
utils.CheckpointConfig.save = @utils.SaveCheckpointConfig()
|
45 |
+
|
46 |
+
# Parameters for utils.create_learning_rate_scheduler:
|
47 |
+
# ==============================================================================
|
48 |
+
utils.create_learning_rate_scheduler.base_learning_rate = 1.0
|
49 |
+
utils.create_learning_rate_scheduler.factors = 'constant * rsqrt_decay'
|
50 |
+
utils.create_learning_rate_scheduler.warmup_steps = 10000
|
51 |
+
|
52 |
+
# Parameters for train/utils.DatasetConfig:
|
53 |
+
# ==============================================================================
|
54 |
+
train/utils.DatasetConfig.batch_size = %BATCH_SIZE
|
55 |
+
train/utils.DatasetConfig.mixture_or_task_name = %MIXTURE_OR_TASK_NAME
|
56 |
+
train/utils.DatasetConfig.module = %MIXTURE_OR_TASK_MODULE
|
57 |
+
train/utils.DatasetConfig.pack = True
|
58 |
+
train/utils.DatasetConfig.seed = None
|
59 |
+
train/utils.DatasetConfig.shuffle = %SHUFFLE_TRAIN_EXAMPLES
|
60 |
+
train/utils.DatasetConfig.split = 'train'
|
61 |
+
train/utils.DatasetConfig.task_feature_lengths = %TASK_FEATURE_LENGTHS
|
62 |
+
train/utils.DatasetConfig.use_cached = %USE_CACHED_TASKS
|
63 |
+
|
64 |
+
# Parameters for train_eval/utils.DatasetConfig:
|
65 |
+
# ==============================================================================
|
66 |
+
train_eval/utils.DatasetConfig.batch_size = %BATCH_SIZE
|
67 |
+
train_eval/utils.DatasetConfig.mixture_or_task_name = %MIXTURE_OR_TASK_NAME
|
68 |
+
train_eval/utils.DatasetConfig.module = %MIXTURE_OR_TASK_MODULE
|
69 |
+
train_eval/utils.DatasetConfig.pack = True
|
70 |
+
train_eval/utils.DatasetConfig.seed = 42
|
71 |
+
train_eval/utils.DatasetConfig.shuffle = False
|
72 |
+
train_eval/utils.DatasetConfig.split = 'validation'
|
73 |
+
train_eval/utils.DatasetConfig.task_feature_lengths = %TASK_FEATURE_LENGTHS
|
74 |
+
train_eval/utils.DatasetConfig.use_cached = %USE_CACHED_TASKS
|
75 |
+
|
76 |
+
# Parameters for models.EncoderDecoderModel:
|
77 |
+
# ==============================================================================
|
78 |
+
models.EncoderDecoderModel.input_vocabulary = %VOCABULARY
|
79 |
+
models.EncoderDecoderModel.label_smoothing = %LABEL_SMOOTHING
|
80 |
+
models.EncoderDecoderModel.loss_normalizing_factor = %LOSS_NORMALIZING_FACTOR
|
81 |
+
models.EncoderDecoderModel.module = @network.Transformer()
|
82 |
+
models.EncoderDecoderModel.optimizer_def = %OPTIMIZER
|
83 |
+
models.EncoderDecoderModel.output_vocabulary = %VOCABULARY
|
84 |
+
models.EncoderDecoderModel.z_loss = %Z_LOSS
|
85 |
+
|
86 |
+
# Parameters for partitioning.PjitPartitioner:
|
87 |
+
# ==============================================================================
|
88 |
+
partitioning.PjitPartitioner.logical_axis_rules = \
|
89 |
+
@partitioning.standard_logical_axis_rules()
|
90 |
+
partitioning.PjitPartitioner.model_parallel_submesh = None
|
91 |
+
partitioning.PjitPartitioner.num_partitions = 1
|
92 |
+
|
93 |
+
# Parameters for utils.RestoreCheckpointConfig:
|
94 |
+
# ==============================================================================
|
95 |
+
utils.RestoreCheckpointConfig.path = []
|
96 |
+
|
97 |
+
# Parameters for utils.SaveCheckpointConfig:
|
98 |
+
# ==============================================================================
|
99 |
+
utils.SaveCheckpointConfig.dtype = 'float32'
|
100 |
+
utils.SaveCheckpointConfig.keep = 4
|
101 |
+
utils.SaveCheckpointConfig.period = 50000
|
102 |
+
utils.SaveCheckpointConfig.save_dataset = False
|
103 |
+
utils.SaveCheckpointConfig.use_gda = False
|
104 |
+
|
105 |
+
# Parameters for seqio.SentencePieceVocabulary:
|
106 |
+
# ==============================================================================
|
107 |
+
seqio.SentencePieceVocabulary.sentencepiece_model_file = \
|
108 |
+
'gs://t5-dutch-english/vocabs/nedd.32000.100extra/spiece.model'
|
109 |
+
|
110 |
+
# Parameters for network.T5Config:
|
111 |
+
# ==============================================================================
|
112 |
+
network.T5Config.dropout_rate = %DROPOUT_RATE
|
113 |
+
network.T5Config.dtype = 'bfloat16'
|
114 |
+
network.T5Config.emb_dim = 768
|
115 |
+
network.T5Config.head_dim = 64
|
116 |
+
network.T5Config.logits_via_embedding = False
|
117 |
+
network.T5Config.mlp_activations = ('gelu', 'linear')
|
118 |
+
network.T5Config.mlp_dim = 3072
|
119 |
+
network.T5Config.num_decoder_layers = 36
|
120 |
+
network.T5Config.num_encoder_layers = 36
|
121 |
+
network.T5Config.num_heads = 12
|
122 |
+
network.T5Config.vocab_size = 32128
|
123 |
+
|
124 |
+
# Parameters for train_script.train:
|
125 |
+
# ==============================================================================
|
126 |
+
train_script.train.checkpoint_cfg = @utils.CheckpointConfig()
|
127 |
+
train_script.train.eval_period = 2000
|
128 |
+
train_script.train.eval_steps = 20
|
129 |
+
train_script.train.infer_eval_dataset_cfg = None
|
130 |
+
train_script.train.model = %MODEL
|
131 |
+
train_script.train.model_dir = %MODEL_DIR
|
132 |
+
train_script.train.partitioner = @partitioning.PjitPartitioner()
|
133 |
+
train_script.train.random_seed = %RANDOM_SEED
|
134 |
+
train_script.train.stats_period = 100
|
135 |
+
train_script.train.summarize_config_fn = @gin_utils.summarize_gin_config
|
136 |
+
train_script.train.total_steps = %TRAIN_STEPS
|
137 |
+
train_script.train.train_dataset_cfg = @train/utils.DatasetConfig()
|
138 |
+
train_script.train.train_eval_dataset_cfg = @train_eval/utils.DatasetConfig()
|
139 |
+
train_script.train.trainer_cls = @trainer.Trainer
|
140 |
+
train_script.train.use_hardware_rng = %USE_HARDWARE_RNG
|
141 |
+
|
142 |
+
# Parameters for trainer.Trainer:
|
143 |
+
# ==============================================================================
|
144 |
+
trainer.Trainer.learning_rate_fn = @utils.create_learning_rate_scheduler()
|
145 |
+
trainer.Trainer.num_microbatches = None
|
146 |
+
|
147 |
+
# Parameters for network.Transformer:
|
148 |
+
# ==============================================================================
|
149 |
+
network.Transformer.config = @network.T5Config()
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "hf/t5_1_1-base-nl36-dutch",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 3072,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 768,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dense_act_fn": "gelu_new",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "gated-gelu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": true,
|
17 |
+
"layer_norm_epsilon": 1e-06,
|
18 |
+
"model_type": "t5",
|
19 |
+
"num_decoder_layers": 36,
|
20 |
+
"num_heads": 12,
|
21 |
+
"num_layers": 36,
|
22 |
+
"output_past": true,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"relative_attention_max_distance": 128,
|
25 |
+
"relative_attention_num_buckets": 32,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.24.0",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 32128
|
31 |
+
}
|
flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca1339806e388332eb5ce9036e9bd11f934f0605ea493a3c5347bc3c83b0def3
|
3 |
+
size 1677466902
|
model-info.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15c1631d525672979aa4e35f3fdc4af5780c56f8ffad2aa42ffb9190330ee3f8
|
3 |
+
size 3255881749
|
special_tokens_map.json
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"eos_token": "</s>",
|
105 |
+
"pad_token": "<pad>",
|
106 |
+
"unk_token": "<unk>"
|
107 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caa6e2f21aeec181276ab80273e3f869ce303ccb8602d68e0524783c3581092d
|
3 |
+
size 800223
|
spiece.vocab
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"eos_token": "</s>",
|
105 |
+
"extra_ids": 100,
|
106 |
+
"name_or_path": "yhavinga/ul2-base-en-nl",
|
107 |
+
"pad_token": "<pad>",
|
108 |
+
"sp_model_kwargs": {},
|
109 |
+
"special_tokens_map_file": null,
|
110 |
+
"tokenizer_class": "T5Tokenizer",
|
111 |
+
"unk_token": "<unk>",
|
112 |
+
"use_fast_tokenizer": false
|
113 |
+
}
|
train/events.out.tfevents.1670764801.t1v-n-82e561a1-w-0.1168530.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3227e48b338fa4e4361512b196dc44f0f72dab6eda1baae5114670c7feb9f5cb
|
3 |
+
size 7948873
|
train/events.out.tfevents.1671135229.t1v-n-82e561a1-w-0.1383256.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9617b7c1ccc9cfd1b9525c23a57546f40f549249f405592f487aa4f61c71a92a
|
3 |
+
size 274265
|
train/events.out.tfevents.1671186857.t1v-n-7fd9879f-w-0.50950.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ec26657ab86b74d0b8d77541ab44ccb6219625edde502711195a2a792b41e87
|
3 |
+
size 11923175
|
training_eval/mc4_nedd_wiki_news_mix_1/events.out.tfevents.1670764801.t1v-n-82e561a1-w-0.1168530.2.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06c17479056cba2bc1a97dc5a65ee9cfb75f84e67bf0aed4fa08871d36261f99
|
3 |
+
size 351757
|
training_eval/mc4_nedd_wiki_news_mix_1/events.out.tfevents.1671135229.t1v-n-82e561a1-w-0.1383256.2.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efc3e139b311b16c96db3591316053ffdfec7b904656823c59dc0089e0cbf99b
|
3 |
+
size 10680
|
training_eval/mc4_nedd_wiki_news_mix_1/events.out.tfevents.1671186857.t1v-n-7fd9879f-w-0.50950.2.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:620c5fb96a01bdfb5df0833908fb7dc5ed132e2290bc75e28669fb1ec2f134bc
|
3 |
+
size 527826
|
training_eval/mc4_nl_span_corruption/events.out.tfevents.1670764801.t1v-n-82e561a1-w-0.1168530.1.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a72fb5a79ba2e902beb1263bad445a1fa0715a0ba61a48725017030e3376114
|
3 |
+
size 351757
|
training_eval/mc4_nl_span_corruption/events.out.tfevents.1671135229.t1v-n-82e561a1-w-0.1383256.1.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e0986b4fba5b5f4e592af08fc61c904572ec415c4f74caf9e8897581b168c29
|
3 |
+
size 10680
|
training_eval/mc4_nl_span_corruption/events.out.tfevents.1671186857.t1v-n-7fd9879f-w-0.50950.1.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89a2c296e18254dbef6016c3a3844571073c40acbb554e0a194012a215dda2a9
|
3 |
+
size 527826
|