Matthewfranglen's workspace
Runs
636
Name
636 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
_n_gpu
_name_or_path
adafactor
adam_beta1
adam_beta2
adam_epsilon
add_cross_attention
alpha
architectures
attention_probs_dropout_prob
bf16
bf16_full_eval
bos_token_id
chunk_size_feed_forward
data_seed
dataloader_drop_last
dataloader_num_workers
dataloader_pin_memory
ddp_bucket_cap_mb
ddp_find_unused_parameters
debug
deepspeed
disable_tqdm
diversity_penalty
do_eval
do_predict
do_sample
do_train
early_stopping
encoder_no_repeat_ngram_size
eos_token_id
epochs
eval_accumulation_steps
eval_batch_size
eval_delay
eval_steps
evaluation_strategy
fp16
fp16_backend
fp16_full_eval
fp16_opt_level
gradient_accumulation_steps
gradient_checkpointing
greater_is_better
Finished
-
matthewfranglen
3m 47s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.0096518
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 57s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.63449
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 57s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.976
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 57s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.97602
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 56s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.22455
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 57s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.7596
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 56s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.29144
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 54s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.28029
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 43s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.56517
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 58s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.55423
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 59s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.01159
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 54s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.43736
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 45s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.99257
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 56s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.9259
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 56s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.19517
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 49s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.95225
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 59s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.65207
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 56s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.10374
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 55s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.30727
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
Finished
-
matthewfranglen
3m 59s
1
nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large
false
0.9
0.999
1.0000e-8
false
0.18125
["RobertaForMaskedLM"]
0.1
false
false
0
0
None
false
0
true
None
None
[]
None
false
0
true
false
false
false
false
0
2
10
None
64
0
None
epoch
true
auto
false
O1
1
false
true
1-20
of 636