Pszemraj's workspace
Runs
55
Name
55 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
_label_trainable_num_channels
_name_or_path
accelerator_config.even_batches
accelerator_config.split_batches
accelerator_config.use_seedable_sampler
activation
adafactor
adam_beta1
adam_beta2
adam_epsilon
add_cross_attention
add_lm_hidden_dense_layer
add_token_type_embeddings
approx_mode
architectures
attention_activation
attention_probs_dropout_prob
audio_samples_per_frame
auto_find_batch_size
bert_model_name
bf16
bf16_full_eval
bidirectional
block_per_row
bos_token_id
chunk_size
chunk_size_feed_forward
classifier_dropout
classifier_dropout_prob
cls_token_id
cross_attention_shape_for_attention
cross_attention_widening_factor
d_ff
d_kv
d_latents
d_model
dataloader_drop_last
dataloader_num_workers
dataloader_persistent_workers
dataloader_pin_memory
dataset
dataset_name_heldout
ddp_timeout
debug
Finished
-
pszemraj
5h 32m 35s
-
-
BEE-spoke-data/bert-plus-L8-4096-v1.0
true
false
true
-
false
0.9
0.98
1.0000e-8
false
-
-
-
["BertForMaskedLM"]
-
0.04
-
false
-
true
false
-
-
-
-
0
-
-
-
-
-
-
-
-
-
false
0
false
true
-
none
1800
[]
Killed
this loaded in bf16
pszemraj
29m 43s
-
-
BEE-spoke-data/bert-plus-L8-4096-v1.0
true
false
true
-
false
0.9
0.98
1.0000e-8
false
-
-
-
["BertForMaskedLM"]
-
0.04
-
false
-
true
false
-
-
-
-
0
-
-
-
-
-
-
-
-
-
false
0
false
true
-
-
1800
[]
Finished
-
pszemraj
3h 47m 30s
-
-
BEE-spoke-data/roformer-4096-v0.3-minipile
-
-
-
-
false
0.9
0.98
1.0000e-8
false
-
-
-
["RoFormerForMaskedLM"]
-
0.1
-
false
-
false
false
-
-
-
-
0
-
-
101
-
-
-
-
-
-
false
0
false
true
-
none
1800
[]
Failed
-
pszemraj
29s
-
-
BEE-spoke-data/roformer-4096-v0.3-minipile
-
-
-
-
false
0.9
0.98
1.0000e-8
false
-
-
-
["RoFormerForMaskedLM"]
-
0.1
-
false
-
false
false
-
-
-
-
0
-
-
101
-
-
-
-
-
-
false
0
false
true
-
-
1800
[]
Killed
-
pszemraj
8m 21s
-
-
local-mra-512
-
-
-
-
false
0.9
0.98
1.0000e-8
false
-
-
full
["MraForSequenceClassification"]
-
0.1
-
false
-
false
false
-
4
0
-
0
-
-
-
-
-
-
-
-
-
false
0
false
true
datasets/roberta-train-sl_512-bs_512-nb_1000-ne_200-bookcorpus-english_wiki
-
1800
[]
Failed
-
pszemraj
6s
-
-
local-mra-512
-
-
-
-
false
0.9
0.98
1.0000e-8
false
-
-
full
["MraForSequenceClassification"]
-
0.1
-
false
-
false
false
-
4
0
-
0
-
-
-
-
-
-
-
-
-
false
0
false
true
datasets/roberta-train-sl_512-bs_512-nb_1000-ne_200-bookcorpus-english_wiki
-
1800
[]
Finished
-
pszemraj
3h 42m 20s
-
-
BEE-spoke-data/bert-plus-L8-4096-v1.0
-
-
-
-
false
0.9
0.98
1.0000e-8
false
-
-
-
["BertForMaskedLM"]
-
0.04
-
false
-
false
false
-
-
-
-
0
-
-
-
-
-
-
-
-
-
false
0
false
true
-
none
1800
[]
Killed
-
pszemraj
1m 45s
-
-
BEE-spoke-data/bert-plus-L8-4096-v1.0
-
-
-
-
false
0.9
0.98
1.0000e-8
false
-
-
-
["BertForMaskedLM"]
-
0.04
-
false
-
false
false
-
-
-
-
0
-
-
-
-
-
-
-
-
-
false
0
false
true
-
-
1800
[]
Killed
-
pszemraj
12m 56s
-
-
microsoft/mpnet-base
-
-
-
-
false
0.9
0.98
1.0000e-8
false
-
-
-
["MPNetForMaskedLM"]
-
0.1
-
false
-
true
false
-
-
0
-
0
-
-
-
-
-
-
-
-
-
false
0
false
true
-
-
1800
[]
Killed
-
pszemraj
6m 54s
-
-
studio-ousia/luke-base
-
-
-
-
false
0.9
0.98
1.0000e-8
false
-
-
-
["LukeForMaskedLM"]
-
0.1
-
false
roberta-base
true
false
-
-
0
-
0
-
-
-
-
-
-
-
-
-
false
0
false
true
-
-
1800
[]
Killed
-
pszemraj
9m 26s
-
-
studio-ousia/luke-base-lite
-
-
-
-
false
0.9
0.98
1.0000e-8
false
-
-
-
["LukeForMaskedLM"]
-
0.1
-
false
roberta-base
true
false
-
-
0
-
0
-
-
-
-
-
-
-
-
-
false
0
false
true
-
-
1800
[]
Killed
-
pszemraj
10m 6s
-
-
pszemraj/t5-efficient-small-nl20-encoder
-
-
-
-
false
0.9
0.98
1.0000e-8
false
-
-
-
["T5EncoderModel"]
-
-
-
false
-
true
false
-
-
-
-
0
0
-
-
-
-
2048
64
-
512
false
0
false
true
-
-
1800
[]
Killed
-
pszemraj
6m 45s
-
-
pszemraj/t5-efficient-base-nl24-encoder
-
-
-
-
false
0.9
0.98
1.0000e-8
false
-
-
-
["T5EncoderModel"]
-
-
-
false
-
true
false
-
-
-
-
0
0
-
-
-
-
3072
64
-
768
false
0
false
true
-
-
1800
[]
Killed
-
pszemraj
6m 3s
-
-
pszemraj/t5-efficient-large-nl8-encoder
-
-
-
-
false
0.9
0.98
1.0000e-8
false
-
-
-
["T5EncoderModel"]
-
-
-
false
-
true
false
-
-
-
-
0
0
-
-
-
-
4096
64
-
1024
false
0
false
true
-
-
1800
[]
Killed
-
pszemraj
9m 5s
-
-
google/t5-efficient-small-el32
-
-
-
-
false
0.9
0.98
1.0000e-8
false
-
-
-
["T5ForConditionalGeneration"]
-
-
-
false
-
true
false
-
-
-
-
0
0
-
-
-
-
2048
64
-
512
false
0
false
true
-
-
1800
[]
Killed
-
pszemraj
8m 6s
-
-
google/t5-efficient-small-el16-dl1
-
-
-
-
false
0.9
0.98
1.0000e-8
false
-
-
-
["T5ForConditionalGeneration"]
-
-
-
false
-
true
false
-
-
-
-
0
0
-
-
-
-
2048
64
-
512
false
0
false
true
-
-
1800
[]
Finished
-
pszemraj
7h 4m 55s
-
-
BEE-spoke-data/mega-enc-L8-MKIV-v0.3-ki_2k_ww
-
-
-
silu
false
0.9
0.98
1.0000e-8
false
false
true
-
["MegaForMaskedLM"]
softmax
0
-
false
-
true
true
true
-
50259
1024
0
-
-
-
-
-
-
-
-
-
false
0
false
true
-
none
1800
[]
Killed
-
pszemraj
12m 18s
-
-
BEE-spoke-data/mega-enc-L8-MKIV-v0.3-ki_2k_ww
-
-
-
silu
false
0.9
0.98
1.0000e-8
false
false
true
-
["MegaForMaskedLM"]
softmax
0
-
false
-
true
true
true
-
50259
1024
0
-
-
-
-
-
-
-
-
-
false
0
false
true
-
-
1800
[]
Killed
-
pszemraj
19m 5s
-
-
BEE-spoke-data/mega-enc-L8-MKIV-v0.3-ki_2k_ww
-
-
-
silu
false
0.9
0.98
1.0000e-8
false
false
true
-
["MegaForMaskedLM"]
softmax
0
-
false
-
true
true
true
-
50259
1024
0
-
-
-
-
-
-
-
-
-
false
0
false
true
-
-
1800
[]
Killed
-
pszemraj
28m 36s
-
-
BEE-spoke-data/mega-enc-L8-MKIV-v0.3-ki_2k_ww
-
-
-
silu
false
0.9
0.98
1.0000e-8
false
false
true
-
["MegaForMaskedLM"]
softmax
0
-
false
-
false
false
true
-
50259
1024
0
-
-
-
-
-
-
-
-
-
false
0
false
true
-
-
1800
[]
1-20
of 55