added CMS model from 2024 April 5 PF meeting
Browse files- cms/2024_04_05/pyg-cms_20240324_235743_208080/checkpoint-32-17.877384.pth +3 -0
- cms/2024_04_05/pyg-cms_20240324_235743_208080/hyperparameters.json +1 -0
- cms/2024_04_05/pyg-cms_20240324_235743_208080/mlpf_losses.pkl +3 -0
- cms/2024_04_05/pyg-cms_20240324_235743_208080/model_kwargs.pkl +3 -0
- cms/2024_04_05/pyg-cms_20240324_235743_208080/runs/train/events.out.tfevents.1711317469.gpu1.local.2556485.0 +3 -0
- cms/2024_04_05/pyg-cms_20240324_235743_208080/runs/train/events.out.tfevents.1712129489.joosep-desktop-work.646614.0 +3 -0
- cms/2024_04_05/pyg-cms_20240324_235743_208080/runs/train/events.out.tfevents.1712129556.joosep-desktop-work.647125.0 +3 -0
- cms/2024_04_05/pyg-cms_20240324_235743_208080/runs/train/events.out.tfevents.1712129684.joosep-desktop-work.647708.0 +3 -0
- cms/2024_04_05/pyg-cms_20240324_235743_208080/runs/valid/events.out.tfevents.1711317469.gpu1.local.2556485.1 +3 -0
- cms/2024_04_05/pyg-cms_20240324_235743_208080/runs/valid/events.out.tfevents.1712129489.joosep-desktop-work.646614.1 +3 -0
- cms/2024_04_05/pyg-cms_20240324_235743_208080/runs/valid/events.out.tfevents.1712129556.joosep-desktop-work.647125.1 +3 -0
- cms/2024_04_05/pyg-cms_20240324_235743_208080/runs/valid/events.out.tfevents.1712129684.joosep-desktop-work.647708.1 +3 -0
- cms/2024_04_05/pyg-cms_20240324_235743_208080/test-config.yaml +123 -0
- cms/2024_04_05/pyg-cms_20240324_235743_208080/train-config.yaml +129 -0
- cms/2024_04_05/pyg-cms_20240324_235743_208080/train.log +821 -0
cms/2024_04_05/pyg-cms_20240324_235743_208080/checkpoint-32-17.877384.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:131b35416593e8a69c529d85446cdbdd55e1d11f8870ac54c72448a75c72b57d
|
3 |
+
size 255893234
|
cms/2024_04_05/pyg-cms_20240324_235743_208080/hyperparameters.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"Num of mlpf parameters": 21304339, "config": "parameters/pytorch/pyg-cms.yaml", "prefix": null, "data_dir": "/scratch/persistent/joosep/tensorflow_datasets", "gpus": 1, "gpu_batch_multiplier": 20, "dataset": "cms", "num_workers": 4, "prefetch_factor": 50, "resume_training": null, "load": null, "train": true, "test": null, "num_epochs": 100, "patience": null, "lr": null, "conv_type": "attention", "num_convs": null, "make_plots": null, "export_onnx": null, "ntrain": null, "ntest": null, "nvalid": null, "val_freq": null, "checkpoint_freq": 1, "hpo": null, "ray_train": false, "local": null, "ray_cpus": null, "ray_gpus": null, "comet": true, "comet_offline": false, "comet_step_freq": null, "experiments_dir": null, "pipeline": null, "dtype": null, "attention_type": null, "test_datasets": {"cms_pf_ttbar": {"version": "1.7.1"}, "cms_pf_qcd_high_pt": {"version": "1.7.0"}, "cms_pf_qcd": {"version": "1.7.0"}, "cms_pf_ztt": {"version": "1.7.0"}, "cms_pf_sms_t1tttt": {"version": "1.7.0"}}}
|
cms/2024_04_05/pyg-cms_20240324_235743_208080/mlpf_losses.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:234fc7ea5a30d4927e05dbd27bbb5725d5c1f80589fd202ab593289a10ea4205
|
3 |
+
size 1836
|
cms/2024_04_05/pyg-cms_20240324_235743_208080/model_kwargs.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfd634217a0268a8cc4e2d4f7ec0c5aa90697a9159c5b3092585a23f6ee20200
|
3 |
+
size 554
|
cms/2024_04_05/pyg-cms_20240324_235743_208080/runs/train/events.out.tfevents.1711317469.gpu1.local.2556485.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c52c5673bf17a6d231904f796ab11c3a8d0811b632231cab6f35169339f77caa
|
3 |
+
size 110493839
|
cms/2024_04_05/pyg-cms_20240324_235743_208080/runs/train/events.out.tfevents.1712129489.joosep-desktop-work.646614.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6fecae60774c0ccdd10889871e01aaa6dc7dbacd4f29a4a3cfb66bf04584301
|
3 |
+
size 8739
|
cms/2024_04_05/pyg-cms_20240324_235743_208080/runs/train/events.out.tfevents.1712129556.joosep-desktop-work.647125.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:312f1568be932b846927c63a3f0d90ce6a88ac0ffff2e4539bd0256a0fd26cea
|
3 |
+
size 16350
|
cms/2024_04_05/pyg-cms_20240324_235743_208080/runs/train/events.out.tfevents.1712129684.joosep-desktop-work.647708.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc54dbdf81a50f9e9b9f91024169683f25fb0aba1f368e966f4bdc1037e388f4
|
3 |
+
size 23961
|
cms/2024_04_05/pyg-cms_20240324_235743_208080/runs/valid/events.out.tfevents.1711317469.gpu1.local.2556485.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0811b521707025790c075d064a05992d40ce0da97127912e8e34b252c882223f
|
3 |
+
size 39256
|
cms/2024_04_05/pyg-cms_20240324_235743_208080/runs/valid/events.out.tfevents.1712129489.joosep-desktop-work.646614.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f13d9ae9963f649a22ce1378b4d792e99f5950b4ad72add0b791a13a93c8fbd9
|
3 |
+
size 88
|
cms/2024_04_05/pyg-cms_20240324_235743_208080/runs/valid/events.out.tfevents.1712129556.joosep-desktop-work.647125.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbbc8fb83b45fae2fee80aa9f687ead4d28db6d8bf11dacda1048a2e29836cea
|
3 |
+
size 1312
|
cms/2024_04_05/pyg-cms_20240324_235743_208080/runs/valid/events.out.tfevents.1712129684.joosep-desktop-work.647708.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a85e631dde89ac409373f2e1445ed69d1dedacfc29262171e13eb44e267a9d7
|
3 |
+
size 2536
|
cms/2024_04_05/pyg-cms_20240324_235743_208080/test-config.yaml
ADDED
@@ -0,0 +1,123 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
attention_type: efficient
|
2 |
+
backend: pytorch
|
3 |
+
checkpoint_freq: 1
|
4 |
+
comet: false
|
5 |
+
comet_name: particleflow-pt
|
6 |
+
comet_offline: false
|
7 |
+
comet_step_freq: 10
|
8 |
+
config: parameters/pytorch/pyg-cms.yaml
|
9 |
+
conv_type: attention
|
10 |
+
data_dir: null
|
11 |
+
dataset: cms
|
12 |
+
dtype: float16
|
13 |
+
experiments_dir: experiments/
|
14 |
+
gpu_batch_multiplier: 10
|
15 |
+
gpus: 1
|
16 |
+
load: experiments/pyg-cms_20240324_235743_208080/checkpoints/checkpoint-32-17.877384.pth
|
17 |
+
lr: 0.0001
|
18 |
+
lr_schedule: cosinedecay
|
19 |
+
lr_schedule_config:
|
20 |
+
onecycle:
|
21 |
+
pct_start: 0.3
|
22 |
+
make_plots: true
|
23 |
+
model:
|
24 |
+
attention:
|
25 |
+
activation: relu
|
26 |
+
attention_type: efficient
|
27 |
+
conv_type: attention
|
28 |
+
dropout_conv_id_ff: 0.0
|
29 |
+
dropout_conv_id_mha: 0.0
|
30 |
+
dropout_conv_reg_ff: 0.0
|
31 |
+
dropout_conv_reg_mha: 0.0
|
32 |
+
dropout_ff: 0.0
|
33 |
+
head_dim: 16
|
34 |
+
num_convs: 6
|
35 |
+
num_heads: 32
|
36 |
+
cos_phi_mode: linear
|
37 |
+
energy_mode: linear
|
38 |
+
eta_mode: linear
|
39 |
+
gnn_lsh:
|
40 |
+
activation: elu
|
41 |
+
bin_size: 640
|
42 |
+
conv_type: gnn_lsh
|
43 |
+
distance_dim: 128
|
44 |
+
dropout_ff: 0.0
|
45 |
+
embedding_dim: 512
|
46 |
+
ffn_dist_hidden_dim: 128
|
47 |
+
ffn_dist_num_layers: 2
|
48 |
+
layernorm: true
|
49 |
+
max_num_bins: 200
|
50 |
+
num_convs: 3
|
51 |
+
num_node_messages: 2
|
52 |
+
width: 512
|
53 |
+
gravnet:
|
54 |
+
activation: elu
|
55 |
+
conv_type: gravnet
|
56 |
+
dropout_ff: 0.1
|
57 |
+
embedding_dim: 512
|
58 |
+
k: 16
|
59 |
+
num_convs: 3
|
60 |
+
propagate_dimensions: 32
|
61 |
+
space_dimensions: 4
|
62 |
+
width: 512
|
63 |
+
input_encoding: joint
|
64 |
+
learned_representation_mode: last
|
65 |
+
mamba:
|
66 |
+
activation: elu
|
67 |
+
conv_type: mamba
|
68 |
+
d_conv: 4
|
69 |
+
d_state: 32
|
70 |
+
dropout_ff: 0.0
|
71 |
+
embedding_dim: 1024
|
72 |
+
expand: 2
|
73 |
+
num_convs: 4
|
74 |
+
width: 1024
|
75 |
+
pt_mode: linear
|
76 |
+
sin_phi_mode: linear
|
77 |
+
trainable: all
|
78 |
+
ntest: null
|
79 |
+
ntrain: null
|
80 |
+
num_epochs: 100
|
81 |
+
num_workers: 4
|
82 |
+
nvalid: null
|
83 |
+
patience: 20
|
84 |
+
prefetch_factor: 50
|
85 |
+
ray_train: false
|
86 |
+
raytune:
|
87 |
+
asha:
|
88 |
+
brackets: 1
|
89 |
+
grace_period: 10
|
90 |
+
max_t: 200
|
91 |
+
reduction_factor: 4
|
92 |
+
default_metric: val_loss
|
93 |
+
default_mode: min
|
94 |
+
hyperband:
|
95 |
+
max_t: 200
|
96 |
+
reduction_factor: 4
|
97 |
+
hyperopt:
|
98 |
+
n_random_steps: 10
|
99 |
+
local_dir: null
|
100 |
+
nevergrad:
|
101 |
+
n_random_steps: 10
|
102 |
+
sched: asha
|
103 |
+
search_alg: hyperopt
|
104 |
+
sort_data: true
|
105 |
+
test_dataset:
|
106 |
+
cms_pf_qcd:
|
107 |
+
version: 1.7.1
|
108 |
+
test_datasets: []
|
109 |
+
train_dataset:
|
110 |
+
cms:
|
111 |
+
physical:
|
112 |
+
batch_size: 1
|
113 |
+
samples:
|
114 |
+
cms_pf_qcd:
|
115 |
+
version: 1.7.1
|
116 |
+
val_freq: null
|
117 |
+
valid_dataset:
|
118 |
+
cms:
|
119 |
+
physical:
|
120 |
+
batch_size: 1
|
121 |
+
samples:
|
122 |
+
cms_pf_qcd:
|
123 |
+
version: 1.7.1
|
cms/2024_04_05/pyg-cms_20240324_235743_208080/train-config.yaml
ADDED
@@ -0,0 +1,129 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
backend: pytorch
|
2 |
+
checkpoint_freq: 1
|
3 |
+
comet: true
|
4 |
+
comet_name: particleflow-pt
|
5 |
+
comet_offline: false
|
6 |
+
comet_step_freq: 10
|
7 |
+
config: parameters/pytorch/pyg-cms.yaml
|
8 |
+
conv_type: attention
|
9 |
+
data_dir: /scratch/persistent/joosep/tensorflow_datasets
|
10 |
+
dataset: cms
|
11 |
+
dtype: bfloat16
|
12 |
+
gpu_batch_multiplier: 20
|
13 |
+
gpus: 1
|
14 |
+
load: null
|
15 |
+
lr: 0.0001
|
16 |
+
lr_schedule: cosinedecay
|
17 |
+
lr_schedule_config:
|
18 |
+
onecycle:
|
19 |
+
pct_start: 0.3
|
20 |
+
model:
|
21 |
+
attention:
|
22 |
+
activation: relu
|
23 |
+
attention_type: flash
|
24 |
+
conv_type: attention
|
25 |
+
dropout_conv_id_ff: 0.0
|
26 |
+
dropout_conv_id_mha: 0.0
|
27 |
+
dropout_conv_reg_ff: 0.0
|
28 |
+
dropout_conv_reg_mha: 0.0
|
29 |
+
dropout_ff: 0.0
|
30 |
+
head_dim: 16
|
31 |
+
num_convs: 6
|
32 |
+
num_heads: 32
|
33 |
+
cos_phi_mode: linear
|
34 |
+
energy_mode: linear
|
35 |
+
eta_mode: linear
|
36 |
+
gnn_lsh:
|
37 |
+
activation: elu
|
38 |
+
bin_size: 640
|
39 |
+
conv_type: gnn_lsh
|
40 |
+
distance_dim: 128
|
41 |
+
dropout_ff: 0.0
|
42 |
+
embedding_dim: 512
|
43 |
+
ffn_dist_hidden_dim: 128
|
44 |
+
ffn_dist_num_layers: 2
|
45 |
+
layernorm: true
|
46 |
+
max_num_bins: 200
|
47 |
+
num_convs: 3
|
48 |
+
num_node_messages: 2
|
49 |
+
width: 512
|
50 |
+
gravnet:
|
51 |
+
activation: elu
|
52 |
+
conv_type: gravnet
|
53 |
+
dropout_ff: 0.1
|
54 |
+
embedding_dim: 512
|
55 |
+
k: 16
|
56 |
+
num_convs: 3
|
57 |
+
propagate_dimensions: 32
|
58 |
+
space_dimensions: 4
|
59 |
+
width: 512
|
60 |
+
input_encoding: joint
|
61 |
+
learned_representation_mode: last
|
62 |
+
mamba:
|
63 |
+
activation: elu
|
64 |
+
conv_type: mamba
|
65 |
+
d_conv: 4
|
66 |
+
d_state: 32
|
67 |
+
dropout_ff: 0.0
|
68 |
+
embedding_dim: 1024
|
69 |
+
expand: 2
|
70 |
+
num_convs: 4
|
71 |
+
width: 1024
|
72 |
+
pt_mode: linear
|
73 |
+
sin_phi_mode: linear
|
74 |
+
trainable: all
|
75 |
+
ntest: null
|
76 |
+
ntrain: null
|
77 |
+
num_epochs: 100
|
78 |
+
num_workers: 4
|
79 |
+
nvalid: null
|
80 |
+
patience: 20
|
81 |
+
prefetch_factor: 50
|
82 |
+
ray_train: false
|
83 |
+
raytune:
|
84 |
+
asha:
|
85 |
+
brackets: 1
|
86 |
+
grace_period: 10
|
87 |
+
max_t: 200
|
88 |
+
reduction_factor: 4
|
89 |
+
default_metric: val_loss
|
90 |
+
default_mode: min
|
91 |
+
hyperband:
|
92 |
+
max_t: 200
|
93 |
+
reduction_factor: 4
|
94 |
+
hyperopt:
|
95 |
+
n_random_steps: 10
|
96 |
+
local_dir: null
|
97 |
+
nevergrad:
|
98 |
+
n_random_steps: 10
|
99 |
+
sched: asha
|
100 |
+
search_alg: hyperopt
|
101 |
+
sort_data: true
|
102 |
+
test_dataset:
|
103 |
+
cms_pf_qcd:
|
104 |
+
version: 1.7.0
|
105 |
+
cms_pf_qcd_high_pt:
|
106 |
+
version: 1.7.0
|
107 |
+
cms_pf_sms_t1tttt:
|
108 |
+
version: 1.7.0
|
109 |
+
cms_pf_ttbar:
|
110 |
+
version: 1.7.1
|
111 |
+
cms_pf_ztt:
|
112 |
+
version: 1.7.0
|
113 |
+
test_datasets: []
|
114 |
+
train: true
|
115 |
+
train_dataset:
|
116 |
+
cms:
|
117 |
+
physical:
|
118 |
+
batch_size: 1
|
119 |
+
samples:
|
120 |
+
cms_pf_ttbar:
|
121 |
+
version: 1.7.1
|
122 |
+
val_freq: null
|
123 |
+
valid_dataset:
|
124 |
+
cms:
|
125 |
+
physical:
|
126 |
+
batch_size: 1
|
127 |
+
samples:
|
128 |
+
cms_pf_ttbar:
|
129 |
+
version: 1.7.1
|
cms/2024_04_05/pyg-cms_20240324_235743_208080/train.log
ADDED
@@ -0,0 +1,821 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[2024-03-24 23:57:43,238] INFO: [0;35mWill use single-gpu: NVIDIA A100 80GB PCIe[0m
|
2 |
+
[2024-03-24 23:57:43,242] INFO: using dtype=torch.bfloat16
|
3 |
+
[2024-03-24 23:57:43,242] INFO: using dtype=torch.bfloat16
|
4 |
+
[2024-03-24 23:57:43,277] INFO: using attention_type=flash
|
5 |
+
[2024-03-24 23:57:43,277] INFO: using attention_type=flash
|
6 |
+
[2024-03-24 23:57:43,290] INFO: using attention_type=flash
|
7 |
+
[2024-03-24 23:57:43,290] INFO: using attention_type=flash
|
8 |
+
[2024-03-24 23:57:43,302] INFO: using attention_type=flash
|
9 |
+
[2024-03-24 23:57:43,302] INFO: using attention_type=flash
|
10 |
+
[2024-03-24 23:57:43,314] INFO: using attention_type=flash
|
11 |
+
[2024-03-24 23:57:43,314] INFO: using attention_type=flash
|
12 |
+
[2024-03-24 23:57:43,330] INFO: using attention_type=flash
|
13 |
+
[2024-03-24 23:57:43,330] INFO: using attention_type=flash
|
14 |
+
[2024-03-24 23:57:43,342] INFO: using attention_type=flash
|
15 |
+
[2024-03-24 23:57:43,342] INFO: using attention_type=flash
|
16 |
+
[2024-03-24 23:57:43,354] INFO: using attention_type=flash
|
17 |
+
[2024-03-24 23:57:43,354] INFO: using attention_type=flash
|
18 |
+
[2024-03-24 23:57:43,367] INFO: using attention_type=flash
|
19 |
+
[2024-03-24 23:57:43,367] INFO: using attention_type=flash
|
20 |
+
[2024-03-24 23:57:43,380] INFO: using attention_type=flash
|
21 |
+
[2024-03-24 23:57:43,380] INFO: using attention_type=flash
|
22 |
+
[2024-03-24 23:57:43,392] INFO: using attention_type=flash
|
23 |
+
[2024-03-24 23:57:43,392] INFO: using attention_type=flash
|
24 |
+
[2024-03-24 23:57:43,404] INFO: using attention_type=flash
|
25 |
+
[2024-03-24 23:57:43,404] INFO: using attention_type=flash
|
26 |
+
[2024-03-24 23:57:43,415] INFO: using attention_type=flash
|
27 |
+
[2024-03-24 23:57:43,415] INFO: using attention_type=flash
|
28 |
+
[2024-03-24 23:57:43,660] INFO: MLPF(
|
29 |
+
(nn0_id): Sequential(
|
30 |
+
(0): Linear(in_features=55, out_features=512, bias=True)
|
31 |
+
(1): ReLU()
|
32 |
+
(2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
33 |
+
(3): Dropout(p=0.0, inplace=False)
|
34 |
+
(4): Linear(in_features=512, out_features=512, bias=True)
|
35 |
+
)
|
36 |
+
(nn0_reg): Sequential(
|
37 |
+
(0): Linear(in_features=55, out_features=512, bias=True)
|
38 |
+
(1): ReLU()
|
39 |
+
(2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
40 |
+
(3): Dropout(p=0.0, inplace=False)
|
41 |
+
(4): Linear(in_features=512, out_features=512, bias=True)
|
42 |
+
)
|
43 |
+
(conv_id): ModuleList(
|
44 |
+
(0-5): 6 x SelfAttentionLayer(
|
45 |
+
(mha): MultiheadAttention(
|
46 |
+
(out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
|
47 |
+
)
|
48 |
+
(norm0): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
49 |
+
(norm1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
50 |
+
(seq): Sequential(
|
51 |
+
(0): Linear(in_features=512, out_features=512, bias=True)
|
52 |
+
(1): ReLU()
|
53 |
+
(2): Linear(in_features=512, out_features=512, bias=True)
|
54 |
+
(3): ReLU()
|
55 |
+
)
|
56 |
+
(dropout): Dropout(p=0.0, inplace=False)
|
57 |
+
)
|
58 |
+
)
|
59 |
+
(conv_reg): ModuleList(
|
60 |
+
(0-5): 6 x SelfAttentionLayer(
|
61 |
+
(mha): MultiheadAttention(
|
62 |
+
(out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
|
63 |
+
)
|
64 |
+
(norm0): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
65 |
+
(norm1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
66 |
+
(seq): Sequential(
|
67 |
+
(0): Linear(in_features=512, out_features=512, bias=True)
|
68 |
+
(1): ReLU()
|
69 |
+
(2): Linear(in_features=512, out_features=512, bias=True)
|
70 |
+
(3): ReLU()
|
71 |
+
)
|
72 |
+
(dropout): Dropout(p=0.0, inplace=False)
|
73 |
+
)
|
74 |
+
)
|
75 |
+
(nn_id): Sequential(
|
76 |
+
(0): Linear(in_features=567, out_features=512, bias=True)
|
77 |
+
(1): ReLU()
|
78 |
+
(2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
79 |
+
(3): Dropout(p=0.0, inplace=False)
|
80 |
+
(4): Linear(in_features=512, out_features=9, bias=True)
|
81 |
+
)
|
82 |
+
(nn_pt): RegressionOutput(
|
83 |
+
(nn): Sequential(
|
84 |
+
(0): Linear(in_features=576, out_features=512, bias=True)
|
85 |
+
(1): ReLU()
|
86 |
+
(2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
87 |
+
(3): Dropout(p=0.0, inplace=False)
|
88 |
+
(4): Linear(in_features=512, out_features=2, bias=True)
|
89 |
+
)
|
90 |
+
)
|
91 |
+
(nn_eta): RegressionOutput(
|
92 |
+
(nn): Sequential(
|
93 |
+
(0): Linear(in_features=576, out_features=512, bias=True)
|
94 |
+
(1): ReLU()
|
95 |
+
(2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
96 |
+
(3): Dropout(p=0.0, inplace=False)
|
97 |
+
(4): Linear(in_features=512, out_features=2, bias=True)
|
98 |
+
)
|
99 |
+
)
|
100 |
+
(nn_sin_phi): RegressionOutput(
|
101 |
+
(nn): Sequential(
|
102 |
+
(0): Linear(in_features=576, out_features=512, bias=True)
|
103 |
+
(1): ReLU()
|
104 |
+
(2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
105 |
+
(3): Dropout(p=0.0, inplace=False)
|
106 |
+
(4): Linear(in_features=512, out_features=2, bias=True)
|
107 |
+
)
|
108 |
+
)
|
109 |
+
(nn_cos_phi): RegressionOutput(
|
110 |
+
(nn): Sequential(
|
111 |
+
(0): Linear(in_features=576, out_features=512, bias=True)
|
112 |
+
(1): ReLU()
|
113 |
+
(2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
114 |
+
(3): Dropout(p=0.0, inplace=False)
|
115 |
+
(4): Linear(in_features=512, out_features=2, bias=True)
|
116 |
+
)
|
117 |
+
)
|
118 |
+
(nn_energy): RegressionOutput(
|
119 |
+
(nn): Sequential(
|
120 |
+
(0): Linear(in_features=576, out_features=512, bias=True)
|
121 |
+
(1): ReLU()
|
122 |
+
(2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
123 |
+
(3): Dropout(p=0.0, inplace=False)
|
124 |
+
(4): Linear(in_features=512, out_features=2, bias=True)
|
125 |
+
)
|
126 |
+
)
|
127 |
+
)
|
128 |
+
[2024-03-24 23:57:43,660] INFO: MLPF(
|
129 |
+
(nn0_id): Sequential(
|
130 |
+
(0): Linear(in_features=55, out_features=512, bias=True)
|
131 |
+
(1): ReLU()
|
132 |
+
(2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
133 |
+
(3): Dropout(p=0.0, inplace=False)
|
134 |
+
(4): Linear(in_features=512, out_features=512, bias=True)
|
135 |
+
)
|
136 |
+
(nn0_reg): Sequential(
|
137 |
+
(0): Linear(in_features=55, out_features=512, bias=True)
|
138 |
+
(1): ReLU()
|
139 |
+
(2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
140 |
+
(3): Dropout(p=0.0, inplace=False)
|
141 |
+
(4): Linear(in_features=512, out_features=512, bias=True)
|
142 |
+
)
|
143 |
+
(conv_id): ModuleList(
|
144 |
+
(0-5): 6 x SelfAttentionLayer(
|
145 |
+
(mha): MultiheadAttention(
|
146 |
+
(out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
|
147 |
+
)
|
148 |
+
(norm0): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
149 |
+
(norm1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
150 |
+
(seq): Sequential(
|
151 |
+
(0): Linear(in_features=512, out_features=512, bias=True)
|
152 |
+
(1): ReLU()
|
153 |
+
(2): Linear(in_features=512, out_features=512, bias=True)
|
154 |
+
(3): ReLU()
|
155 |
+
)
|
156 |
+
(dropout): Dropout(p=0.0, inplace=False)
|
157 |
+
)
|
158 |
+
)
|
159 |
+
(conv_reg): ModuleList(
|
160 |
+
(0-5): 6 x SelfAttentionLayer(
|
161 |
+
(mha): MultiheadAttention(
|
162 |
+
(out_proj): NonDynamicallyQuantizableLinear(in_features=512, out_features=512, bias=True)
|
163 |
+
)
|
164 |
+
(norm0): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
165 |
+
(norm1): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
166 |
+
(seq): Sequential(
|
167 |
+
(0): Linear(in_features=512, out_features=512, bias=True)
|
168 |
+
(1): ReLU()
|
169 |
+
(2): Linear(in_features=512, out_features=512, bias=True)
|
170 |
+
(3): ReLU()
|
171 |
+
)
|
172 |
+
(dropout): Dropout(p=0.0, inplace=False)
|
173 |
+
)
|
174 |
+
)
|
175 |
+
(nn_id): Sequential(
|
176 |
+
(0): Linear(in_features=567, out_features=512, bias=True)
|
177 |
+
(1): ReLU()
|
178 |
+
(2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
179 |
+
(3): Dropout(p=0.0, inplace=False)
|
180 |
+
(4): Linear(in_features=512, out_features=9, bias=True)
|
181 |
+
)
|
182 |
+
(nn_pt): RegressionOutput(
|
183 |
+
(nn): Sequential(
|
184 |
+
(0): Linear(in_features=576, out_features=512, bias=True)
|
185 |
+
(1): ReLU()
|
186 |
+
(2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
187 |
+
(3): Dropout(p=0.0, inplace=False)
|
188 |
+
(4): Linear(in_features=512, out_features=2, bias=True)
|
189 |
+
)
|
190 |
+
)
|
191 |
+
(nn_eta): RegressionOutput(
|
192 |
+
(nn): Sequential(
|
193 |
+
(0): Linear(in_features=576, out_features=512, bias=True)
|
194 |
+
(1): ReLU()
|
195 |
+
(2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
196 |
+
(3): Dropout(p=0.0, inplace=False)
|
197 |
+
(4): Linear(in_features=512, out_features=2, bias=True)
|
198 |
+
)
|
199 |
+
)
|
200 |
+
(nn_sin_phi): RegressionOutput(
|
201 |
+
(nn): Sequential(
|
202 |
+
(0): Linear(in_features=576, out_features=512, bias=True)
|
203 |
+
(1): ReLU()
|
204 |
+
(2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
205 |
+
(3): Dropout(p=0.0, inplace=False)
|
206 |
+
(4): Linear(in_features=512, out_features=2, bias=True)
|
207 |
+
)
|
208 |
+
)
|
209 |
+
(nn_cos_phi): RegressionOutput(
|
210 |
+
(nn): Sequential(
|
211 |
+
(0): Linear(in_features=576, out_features=512, bias=True)
|
212 |
+
(1): ReLU()
|
213 |
+
(2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
214 |
+
(3): Dropout(p=0.0, inplace=False)
|
215 |
+
(4): Linear(in_features=512, out_features=2, bias=True)
|
216 |
+
)
|
217 |
+
)
|
218 |
+
(nn_energy): RegressionOutput(
|
219 |
+
(nn): Sequential(
|
220 |
+
(0): Linear(in_features=576, out_features=512, bias=True)
|
221 |
+
(1): ReLU()
|
222 |
+
(2): LayerNorm((512,), eps=1e-05, elementwise_affine=True)
|
223 |
+
(3): Dropout(p=0.0, inplace=False)
|
224 |
+
(4): Linear(in_features=512, out_features=2, bias=True)
|
225 |
+
)
|
226 |
+
)
|
227 |
+
)
|
228 |
+
[2024-03-24 23:57:43,666] INFO: Trainable parameters: 21304339
|
229 |
+
[2024-03-24 23:57:43,666] INFO: Trainable parameters: 21304339
|
230 |
+
[2024-03-24 23:57:43,668] INFO: Non-trainable parameters: 0
|
231 |
+
[2024-03-24 23:57:43,668] INFO: Non-trainable parameters: 0
|
232 |
+
[2024-03-24 23:57:43,671] INFO: Total parameters: 21304339
|
233 |
+
[2024-03-24 23:57:43,671] INFO: Total parameters: 21304339
|
234 |
+
[2024-03-24 23:57:43,682] INFO: Modules Trainable parameters Non-tranable parameters
|
235 |
+
nn0_id.0.weight 28160 0
|
236 |
+
nn0_id.0.bias 512 0
|
237 |
+
nn0_id.2.weight 512 0
|
238 |
+
nn0_id.2.bias 512 0
|
239 |
+
nn0_id.4.weight 262144 0
|
240 |
+
nn0_id.4.bias 512 0
|
241 |
+
nn0_reg.0.weight 28160 0
|
242 |
+
nn0_reg.0.bias 512 0
|
243 |
+
nn0_reg.2.weight 512 0
|
244 |
+
nn0_reg.2.bias 512 0
|
245 |
+
nn0_reg.4.weight 262144 0
|
246 |
+
nn0_reg.4.bias 512 0
|
247 |
+
conv_id.0.mha.in_proj_weight 786432 0
|
248 |
+
conv_id.0.mha.in_proj_bias 1536 0
|
249 |
+
conv_id.0.mha.out_proj.weight 262144 0
|
250 |
+
conv_id.0.mha.out_proj.bias 512 0
|
251 |
+
conv_id.0.norm0.weight 512 0
|
252 |
+
conv_id.0.norm0.bias 512 0
|
253 |
+
conv_id.0.norm1.weight 512 0
|
254 |
+
conv_id.0.norm1.bias 512 0
|
255 |
+
conv_id.0.seq.0.weight 262144 0
|
256 |
+
conv_id.0.seq.0.bias 512 0
|
257 |
+
conv_id.0.seq.2.weight 262144 0
|
258 |
+
conv_id.0.seq.2.bias 512 0
|
259 |
+
conv_id.1.mha.in_proj_weight 786432 0
|
260 |
+
conv_id.1.mha.in_proj_bias 1536 0
|
261 |
+
conv_id.1.mha.out_proj.weight 262144 0
|
262 |
+
conv_id.1.mha.out_proj.bias 512 0
|
263 |
+
conv_id.1.norm0.weight 512 0
|
264 |
+
conv_id.1.norm0.bias 512 0
|
265 |
+
conv_id.1.norm1.weight 512 0
|
266 |
+
conv_id.1.norm1.bias 512 0
|
267 |
+
conv_id.1.seq.0.weight 262144 0
|
268 |
+
conv_id.1.seq.0.bias 512 0
|
269 |
+
conv_id.1.seq.2.weight 262144 0
|
270 |
+
conv_id.1.seq.2.bias 512 0
|
271 |
+
conv_id.2.mha.in_proj_weight 786432 0
|
272 |
+
conv_id.2.mha.in_proj_bias 1536 0
|
273 |
+
conv_id.2.mha.out_proj.weight 262144 0
|
274 |
+
conv_id.2.mha.out_proj.bias 512 0
|
275 |
+
conv_id.2.norm0.weight 512 0
|
276 |
+
conv_id.2.norm0.bias 512 0
|
277 |
+
conv_id.2.norm1.weight 512 0
|
278 |
+
conv_id.2.norm1.bias 512 0
|
279 |
+
conv_id.2.seq.0.weight 262144 0
|
280 |
+
conv_id.2.seq.0.bias 512 0
|
281 |
+
conv_id.2.seq.2.weight 262144 0
|
282 |
+
conv_id.2.seq.2.bias 512 0
|
283 |
+
conv_id.3.mha.in_proj_weight 786432 0
|
284 |
+
conv_id.3.mha.in_proj_bias 1536 0
|
285 |
+
conv_id.3.mha.out_proj.weight 262144 0
|
286 |
+
conv_id.3.mha.out_proj.bias 512 0
|
287 |
+
conv_id.3.norm0.weight 512 0
|
288 |
+
conv_id.3.norm0.bias 512 0
|
289 |
+
conv_id.3.norm1.weight 512 0
|
290 |
+
conv_id.3.norm1.bias 512 0
|
291 |
+
conv_id.3.seq.0.weight 262144 0
|
292 |
+
conv_id.3.seq.0.bias 512 0
|
293 |
+
conv_id.3.seq.2.weight 262144 0
|
294 |
+
conv_id.3.seq.2.bias 512 0
|
295 |
+
conv_id.4.mha.in_proj_weight 786432 0
|
296 |
+
conv_id.4.mha.in_proj_bias 1536 0
|
297 |
+
conv_id.4.mha.out_proj.weight 262144 0
|
298 |
+
conv_id.4.mha.out_proj.bias 512 0
|
299 |
+
conv_id.4.norm0.weight 512 0
|
300 |
+
conv_id.4.norm0.bias 512 0
|
301 |
+
conv_id.4.norm1.weight 512 0
|
302 |
+
conv_id.4.norm1.bias 512 0
|
303 |
+
conv_id.4.seq.0.weight 262144 0
|
304 |
+
conv_id.4.seq.0.bias 512 0
|
305 |
+
conv_id.4.seq.2.weight 262144 0
|
306 |
+
conv_id.4.seq.2.bias 512 0
|
307 |
+
conv_id.5.mha.in_proj_weight 786432 0
|
308 |
+
conv_id.5.mha.in_proj_bias 1536 0
|
309 |
+
conv_id.5.mha.out_proj.weight 262144 0
|
310 |
+
conv_id.5.mha.out_proj.bias 512 0
|
311 |
+
conv_id.5.norm0.weight 512 0
|
312 |
+
conv_id.5.norm0.bias 512 0
|
313 |
+
conv_id.5.norm1.weight 512 0
|
314 |
+
conv_id.5.norm1.bias 512 0
|
315 |
+
conv_id.5.seq.0.weight 262144 0
|
316 |
+
conv_id.5.seq.0.bias 512 0
|
317 |
+
conv_id.5.seq.2.weight 262144 0
|
318 |
+
conv_id.5.seq.2.bias 512 0
|
319 |
+
conv_reg.0.mha.in_proj_weight 786432 0
|
320 |
+
conv_reg.0.mha.in_proj_bias 1536 0
|
321 |
+
conv_reg.0.mha.out_proj.weight 262144 0
|
322 |
+
conv_reg.0.mha.out_proj.bias 512 0
|
323 |
+
conv_reg.0.norm0.weight 512 0
|
324 |
+
conv_reg.0.norm0.bias 512 0
|
325 |
+
conv_reg.0.norm1.weight 512 0
|
326 |
+
conv_reg.0.norm1.bias 512 0
|
327 |
+
conv_reg.0.seq.0.weight 262144 0
|
328 |
+
conv_reg.0.seq.0.bias 512 0
|
329 |
+
conv_reg.0.seq.2.weight 262144 0
|
330 |
+
conv_reg.0.seq.2.bias 512 0
|
331 |
+
conv_reg.1.mha.in_proj_weight 786432 0
|
332 |
+
conv_reg.1.mha.in_proj_bias 1536 0
|
333 |
+
conv_reg.1.mha.out_proj.weight 262144 0
|
334 |
+
conv_reg.1.mha.out_proj.bias 512 0
|
335 |
+
conv_reg.1.norm0.weight 512 0
|
336 |
+
conv_reg.1.norm0.bias 512 0
|
337 |
+
conv_reg.1.norm1.weight 512 0
|
338 |
+
conv_reg.1.norm1.bias 512 0
|
339 |
+
conv_reg.1.seq.0.weight 262144 0
|
340 |
+
conv_reg.1.seq.0.bias 512 0
|
341 |
+
conv_reg.1.seq.2.weight 262144 0
|
342 |
+
conv_reg.1.seq.2.bias 512 0
|
343 |
+
conv_reg.2.mha.in_proj_weight 786432 0
|
344 |
+
conv_reg.2.mha.in_proj_bias 1536 0
|
345 |
+
conv_reg.2.mha.out_proj.weight 262144 0
|
346 |
+
conv_reg.2.mha.out_proj.bias 512 0
|
347 |
+
conv_reg.2.norm0.weight 512 0
|
348 |
+
conv_reg.2.norm0.bias 512 0
|
349 |
+
conv_reg.2.norm1.weight 512 0
|
350 |
+
conv_reg.2.norm1.bias 512 0
|
351 |
+
conv_reg.2.seq.0.weight 262144 0
|
352 |
+
conv_reg.2.seq.0.bias 512 0
|
353 |
+
conv_reg.2.seq.2.weight 262144 0
|
354 |
+
conv_reg.2.seq.2.bias 512 0
|
355 |
+
conv_reg.3.mha.in_proj_weight 786432 0
|
356 |
+
conv_reg.3.mha.in_proj_bias 1536 0
|
357 |
+
conv_reg.3.mha.out_proj.weight 262144 0
|
358 |
+
conv_reg.3.mha.out_proj.bias 512 0
|
359 |
+
conv_reg.3.norm0.weight 512 0
|
360 |
+
conv_reg.3.norm0.bias 512 0
|
361 |
+
conv_reg.3.norm1.weight 512 0
|
362 |
+
conv_reg.3.norm1.bias 512 0
|
363 |
+
conv_reg.3.seq.0.weight 262144 0
|
364 |
+
conv_reg.3.seq.0.bias 512 0
|
365 |
+
conv_reg.3.seq.2.weight 262144 0
|
366 |
+
conv_reg.3.seq.2.bias 512 0
|
367 |
+
conv_reg.4.mha.in_proj_weight 786432 0
|
368 |
+
conv_reg.4.mha.in_proj_bias 1536 0
|
369 |
+
conv_reg.4.mha.out_proj.weight 262144 0
|
370 |
+
conv_reg.4.mha.out_proj.bias 512 0
|
371 |
+
conv_reg.4.norm0.weight 512 0
|
372 |
+
conv_reg.4.norm0.bias 512 0
|
373 |
+
conv_reg.4.norm1.weight 512 0
|
374 |
+
conv_reg.4.norm1.bias 512 0
|
375 |
+
conv_reg.4.seq.0.weight 262144 0
|
376 |
+
conv_reg.4.seq.0.bias 512 0
|
377 |
+
conv_reg.4.seq.2.weight 262144 0
|
378 |
+
conv_reg.4.seq.2.bias 512 0
|
379 |
+
conv_reg.5.mha.in_proj_weight 786432 0
|
380 |
+
conv_reg.5.mha.in_proj_bias 1536 0
|
381 |
+
conv_reg.5.mha.out_proj.weight 262144 0
|
382 |
+
conv_reg.5.mha.out_proj.bias 512 0
|
383 |
+
conv_reg.5.norm0.weight 512 0
|
384 |
+
conv_reg.5.norm0.bias 512 0
|
385 |
+
conv_reg.5.norm1.weight 512 0
|
386 |
+
conv_reg.5.norm1.bias 512 0
|
387 |
+
conv_reg.5.seq.0.weight 262144 0
|
388 |
+
conv_reg.5.seq.0.bias 512 0
|
389 |
+
conv_reg.5.seq.2.weight 262144 0
|
390 |
+
conv_reg.5.seq.2.bias 512 0
|
391 |
+
nn_id.0.weight 290304 0
|
392 |
+
nn_id.0.bias 512 0
|
393 |
+
nn_id.2.weight 512 0
|
394 |
+
nn_id.2.bias 512 0
|
395 |
+
nn_id.4.weight 4608 0
|
396 |
+
nn_id.4.bias 9 0
|
397 |
+
nn_pt.nn.0.weight 294912 0
|
398 |
+
nn_pt.nn.0.bias 512 0
|
399 |
+
nn_pt.nn.2.weight 512 0
|
400 |
+
nn_pt.nn.2.bias 512 0
|
401 |
+
nn_pt.nn.4.weight 1024 0
|
402 |
+
nn_pt.nn.4.bias 2 0
|
403 |
+
nn_eta.nn.0.weight 294912 0
|
404 |
+
nn_eta.nn.0.bias 512 0
|
405 |
+
nn_eta.nn.2.weight 512 0
|
406 |
+
nn_eta.nn.2.bias 512 0
|
407 |
+
nn_eta.nn.4.weight 1024 0
|
408 |
+
nn_eta.nn.4.bias 2 0
|
409 |
+
nn_sin_phi.nn.0.weight 294912 0
|
410 |
+
nn_sin_phi.nn.0.bias 512 0
|
411 |
+
nn_sin_phi.nn.2.weight 512 0
|
412 |
+
nn_sin_phi.nn.2.bias 512 0
|
413 |
+
nn_sin_phi.nn.4.weight 1024 0
|
414 |
+
nn_sin_phi.nn.4.bias 2 0
|
415 |
+
nn_cos_phi.nn.0.weight 294912 0
|
416 |
+
nn_cos_phi.nn.0.bias 512 0
|
417 |
+
nn_cos_phi.nn.2.weight 512 0
|
418 |
+
nn_cos_phi.nn.2.bias 512 0
|
419 |
+
nn_cos_phi.nn.4.weight 1024 0
|
420 |
+
nn_cos_phi.nn.4.bias 2 0
|
421 |
+
nn_energy.nn.0.weight 294912 0
|
422 |
+
nn_energy.nn.0.bias 512 0
|
423 |
+
nn_energy.nn.2.weight 512 0
|
424 |
+
nn_energy.nn.2.bias 512 0
|
425 |
+
nn_energy.nn.4.weight 1024 0
|
426 |
+
nn_energy.nn.4.bias 2 0
|
427 |
+
[2024-03-24 23:57:43,682] INFO: Modules Trainable parameters Non-tranable parameters
|
428 |
+
nn0_id.0.weight 28160 0
|
429 |
+
nn0_id.0.bias 512 0
|
430 |
+
nn0_id.2.weight 512 0
|
431 |
+
nn0_id.2.bias 512 0
|
432 |
+
nn0_id.4.weight 262144 0
|
433 |
+
nn0_id.4.bias 512 0
|
434 |
+
nn0_reg.0.weight 28160 0
|
435 |
+
nn0_reg.0.bias 512 0
|
436 |
+
nn0_reg.2.weight 512 0
|
437 |
+
nn0_reg.2.bias 512 0
|
438 |
+
nn0_reg.4.weight 262144 0
|
439 |
+
nn0_reg.4.bias 512 0
|
440 |
+
conv_id.0.mha.in_proj_weight 786432 0
|
441 |
+
conv_id.0.mha.in_proj_bias 1536 0
|
442 |
+
conv_id.0.mha.out_proj.weight 262144 0
|
443 |
+
conv_id.0.mha.out_proj.bias 512 0
|
444 |
+
conv_id.0.norm0.weight 512 0
|
445 |
+
conv_id.0.norm0.bias 512 0
|
446 |
+
conv_id.0.norm1.weight 512 0
|
447 |
+
conv_id.0.norm1.bias 512 0
|
448 |
+
conv_id.0.seq.0.weight 262144 0
|
449 |
+
conv_id.0.seq.0.bias 512 0
|
450 |
+
conv_id.0.seq.2.weight 262144 0
|
451 |
+
conv_id.0.seq.2.bias 512 0
|
452 |
+
conv_id.1.mha.in_proj_weight 786432 0
|
453 |
+
conv_id.1.mha.in_proj_bias 1536 0
|
454 |
+
conv_id.1.mha.out_proj.weight 262144 0
|
455 |
+
conv_id.1.mha.out_proj.bias 512 0
|
456 |
+
conv_id.1.norm0.weight 512 0
|
457 |
+
conv_id.1.norm0.bias 512 0
|
458 |
+
conv_id.1.norm1.weight 512 0
|
459 |
+
conv_id.1.norm1.bias 512 0
|
460 |
+
conv_id.1.seq.0.weight 262144 0
|
461 |
+
conv_id.1.seq.0.bias 512 0
|
462 |
+
conv_id.1.seq.2.weight 262144 0
|
463 |
+
conv_id.1.seq.2.bias 512 0
|
464 |
+
conv_id.2.mha.in_proj_weight 786432 0
|
465 |
+
conv_id.2.mha.in_proj_bias 1536 0
|
466 |
+
conv_id.2.mha.out_proj.weight 262144 0
|
467 |
+
conv_id.2.mha.out_proj.bias 512 0
|
468 |
+
conv_id.2.norm0.weight 512 0
|
469 |
+
conv_id.2.norm0.bias 512 0
|
470 |
+
conv_id.2.norm1.weight 512 0
|
471 |
+
conv_id.2.norm1.bias 512 0
|
472 |
+
conv_id.2.seq.0.weight 262144 0
|
473 |
+
conv_id.2.seq.0.bias 512 0
|
474 |
+
conv_id.2.seq.2.weight 262144 0
|
475 |
+
conv_id.2.seq.2.bias 512 0
|
476 |
+
conv_id.3.mha.in_proj_weight 786432 0
|
477 |
+
conv_id.3.mha.in_proj_bias 1536 0
|
478 |
+
conv_id.3.mha.out_proj.weight 262144 0
|
479 |
+
conv_id.3.mha.out_proj.bias 512 0
|
480 |
+
conv_id.3.norm0.weight 512 0
|
481 |
+
conv_id.3.norm0.bias 512 0
|
482 |
+
conv_id.3.norm1.weight 512 0
|
483 |
+
conv_id.3.norm1.bias 512 0
|
484 |
+
conv_id.3.seq.0.weight 262144 0
|
485 |
+
conv_id.3.seq.0.bias 512 0
|
486 |
+
conv_id.3.seq.2.weight 262144 0
|
487 |
+
conv_id.3.seq.2.bias 512 0
|
488 |
+
conv_id.4.mha.in_proj_weight 786432 0
|
489 |
+
conv_id.4.mha.in_proj_bias 1536 0
|
490 |
+
conv_id.4.mha.out_proj.weight 262144 0
|
491 |
+
conv_id.4.mha.out_proj.bias 512 0
|
492 |
+
conv_id.4.norm0.weight 512 0
|
493 |
+
conv_id.4.norm0.bias 512 0
|
494 |
+
conv_id.4.norm1.weight 512 0
|
495 |
+
conv_id.4.norm1.bias 512 0
|
496 |
+
conv_id.4.seq.0.weight 262144 0
|
497 |
+
conv_id.4.seq.0.bias 512 0
|
498 |
+
conv_id.4.seq.2.weight 262144 0
|
499 |
+
conv_id.4.seq.2.bias 512 0
|
500 |
+
conv_id.5.mha.in_proj_weight 786432 0
|
501 |
+
conv_id.5.mha.in_proj_bias 1536 0
|
502 |
+
conv_id.5.mha.out_proj.weight 262144 0
|
503 |
+
conv_id.5.mha.out_proj.bias 512 0
|
504 |
+
conv_id.5.norm0.weight 512 0
|
505 |
+
conv_id.5.norm0.bias 512 0
|
506 |
+
conv_id.5.norm1.weight 512 0
|
507 |
+
conv_id.5.norm1.bias 512 0
|
508 |
+
conv_id.5.seq.0.weight 262144 0
|
509 |
+
conv_id.5.seq.0.bias 512 0
|
510 |
+
conv_id.5.seq.2.weight 262144 0
|
511 |
+
conv_id.5.seq.2.bias 512 0
|
512 |
+
conv_reg.0.mha.in_proj_weight 786432 0
|
513 |
+
conv_reg.0.mha.in_proj_bias 1536 0
|
514 |
+
conv_reg.0.mha.out_proj.weight 262144 0
|
515 |
+
conv_reg.0.mha.out_proj.bias 512 0
|
516 |
+
conv_reg.0.norm0.weight 512 0
|
517 |
+
conv_reg.0.norm0.bias 512 0
|
518 |
+
conv_reg.0.norm1.weight 512 0
|
519 |
+
conv_reg.0.norm1.bias 512 0
|
520 |
+
conv_reg.0.seq.0.weight 262144 0
|
521 |
+
conv_reg.0.seq.0.bias 512 0
|
522 |
+
conv_reg.0.seq.2.weight 262144 0
|
523 |
+
conv_reg.0.seq.2.bias 512 0
|
524 |
+
conv_reg.1.mha.in_proj_weight 786432 0
|
525 |
+
conv_reg.1.mha.in_proj_bias 1536 0
|
526 |
+
conv_reg.1.mha.out_proj.weight 262144 0
|
527 |
+
conv_reg.1.mha.out_proj.bias 512 0
|
528 |
+
conv_reg.1.norm0.weight 512 0
|
529 |
+
conv_reg.1.norm0.bias 512 0
|
530 |
+
conv_reg.1.norm1.weight 512 0
|
531 |
+
conv_reg.1.norm1.bias 512 0
|
532 |
+
conv_reg.1.seq.0.weight 262144 0
|
533 |
+
conv_reg.1.seq.0.bias 512 0
|
534 |
+
conv_reg.1.seq.2.weight 262144 0
|
535 |
+
conv_reg.1.seq.2.bias 512 0
|
536 |
+
conv_reg.2.mha.in_proj_weight 786432 0
|
537 |
+
conv_reg.2.mha.in_proj_bias 1536 0
|
538 |
+
conv_reg.2.mha.out_proj.weight 262144 0
|
539 |
+
conv_reg.2.mha.out_proj.bias 512 0
|
540 |
+
conv_reg.2.norm0.weight 512 0
|
541 |
+
conv_reg.2.norm0.bias 512 0
|
542 |
+
conv_reg.2.norm1.weight 512 0
|
543 |
+
conv_reg.2.norm1.bias 512 0
|
544 |
+
conv_reg.2.seq.0.weight 262144 0
|
545 |
+
conv_reg.2.seq.0.bias 512 0
|
546 |
+
conv_reg.2.seq.2.weight 262144 0
|
547 |
+
conv_reg.2.seq.2.bias 512 0
|
548 |
+
conv_reg.3.mha.in_proj_weight 786432 0
|
549 |
+
conv_reg.3.mha.in_proj_bias 1536 0
|
550 |
+
conv_reg.3.mha.out_proj.weight 262144 0
|
551 |
+
conv_reg.3.mha.out_proj.bias 512 0
|
552 |
+
conv_reg.3.norm0.weight 512 0
|
553 |
+
conv_reg.3.norm0.bias 512 0
|
554 |
+
conv_reg.3.norm1.weight 512 0
|
555 |
+
conv_reg.3.norm1.bias 512 0
|
556 |
+
conv_reg.3.seq.0.weight 262144 0
|
557 |
+
conv_reg.3.seq.0.bias 512 0
|
558 |
+
conv_reg.3.seq.2.weight 262144 0
|
559 |
+
conv_reg.3.seq.2.bias 512 0
|
560 |
+
conv_reg.4.mha.in_proj_weight 786432 0
|
561 |
+
conv_reg.4.mha.in_proj_bias 1536 0
|
562 |
+
conv_reg.4.mha.out_proj.weight 262144 0
|
563 |
+
conv_reg.4.mha.out_proj.bias 512 0
|
564 |
+
conv_reg.4.norm0.weight 512 0
|
565 |
+
conv_reg.4.norm0.bias 512 0
|
566 |
+
conv_reg.4.norm1.weight 512 0
|
567 |
+
conv_reg.4.norm1.bias 512 0
|
568 |
+
conv_reg.4.seq.0.weight 262144 0
|
569 |
+
conv_reg.4.seq.0.bias 512 0
|
570 |
+
conv_reg.4.seq.2.weight 262144 0
|
571 |
+
conv_reg.4.seq.2.bias 512 0
|
572 |
+
conv_reg.5.mha.in_proj_weight 786432 0
|
573 |
+
conv_reg.5.mha.in_proj_bias 1536 0
|
574 |
+
conv_reg.5.mha.out_proj.weight 262144 0
|
575 |
+
conv_reg.5.mha.out_proj.bias 512 0
|
576 |
+
conv_reg.5.norm0.weight 512 0
|
577 |
+
conv_reg.5.norm0.bias 512 0
|
578 |
+
conv_reg.5.norm1.weight 512 0
|
579 |
+
conv_reg.5.norm1.bias 512 0
|
580 |
+
conv_reg.5.seq.0.weight 262144 0
|
581 |
+
conv_reg.5.seq.0.bias 512 0
|
582 |
+
conv_reg.5.seq.2.weight 262144 0
|
583 |
+
conv_reg.5.seq.2.bias 512 0
|
584 |
+
nn_id.0.weight 290304 0
|
585 |
+
nn_id.0.bias 512 0
|
586 |
+
nn_id.2.weight 512 0
|
587 |
+
nn_id.2.bias 512 0
|
588 |
+
nn_id.4.weight 4608 0
|
589 |
+
nn_id.4.bias 9 0
|
590 |
+
nn_pt.nn.0.weight 294912 0
|
591 |
+
nn_pt.nn.0.bias 512 0
|
592 |
+
nn_pt.nn.2.weight 512 0
|
593 |
+
nn_pt.nn.2.bias 512 0
|
594 |
+
nn_pt.nn.4.weight 1024 0
|
595 |
+
nn_pt.nn.4.bias 2 0
|
596 |
+
nn_eta.nn.0.weight 294912 0
|
597 |
+
nn_eta.nn.0.bias 512 0
|
598 |
+
nn_eta.nn.2.weight 512 0
|
599 |
+
nn_eta.nn.2.bias 512 0
|
600 |
+
nn_eta.nn.4.weight 1024 0
|
601 |
+
nn_eta.nn.4.bias 2 0
|
602 |
+
nn_sin_phi.nn.0.weight 294912 0
|
603 |
+
nn_sin_phi.nn.0.bias 512 0
|
604 |
+
nn_sin_phi.nn.2.weight 512 0
|
605 |
+
nn_sin_phi.nn.2.bias 512 0
|
606 |
+
nn_sin_phi.nn.4.weight 1024 0
|
607 |
+
nn_sin_phi.nn.4.bias 2 0
|
608 |
+
nn_cos_phi.nn.0.weight 294912 0
|
609 |
+
nn_cos_phi.nn.0.bias 512 0
|
610 |
+
nn_cos_phi.nn.2.weight 512 0
|
611 |
+
nn_cos_phi.nn.2.bias 512 0
|
612 |
+
nn_cos_phi.nn.4.weight 1024 0
|
613 |
+
nn_cos_phi.nn.4.bias 2 0
|
614 |
+
nn_energy.nn.0.weight 294912 0
|
615 |
+
nn_energy.nn.0.bias 512 0
|
616 |
+
nn_energy.nn.2.weight 512 0
|
617 |
+
nn_energy.nn.2.bias 512 0
|
618 |
+
nn_energy.nn.4.weight 1024 0
|
619 |
+
nn_energy.nn.4.bias 2 0
|
620 |
+
[2024-03-24 23:57:43,685] INFO: Creating experiment dir experiments/pyg-cms_20240324_235743_208080
|
621 |
+
[2024-03-24 23:57:43,685] INFO: Creating experiment dir experiments/pyg-cms_20240324_235743_208080
|
622 |
+
[2024-03-24 23:57:43,690] INFO: [1mModel directory experiments/pyg-cms_20240324_235743_208080[0m
|
623 |
+
[2024-03-24 23:57:43,690] INFO: [1mModel directory experiments/pyg-cms_20240324_235743_208080[0m
|
624 |
+
[2024-03-24 23:57:49,345] INFO: [0;34mtrain_dataset: cms_pf_ttbar, 320100[0m
|
625 |
+
[2024-03-24 23:57:49,345] INFO: [0;34mtrain_dataset: cms_pf_ttbar, 320100[0m
|
626 |
+
[2024-03-24 23:57:49,622] INFO: [0;34mvalid_dataset: cms_pf_ttbar, 80040[0m
|
627 |
+
[2024-03-24 23:57:49,622] INFO: [0;34mvalid_dataset: cms_pf_ttbar, 80040[0m
|
628 |
+
[2024-03-24 23:57:49,736] INFO: [0;31mInitiating epoch #1 train run on device rank=0[0m
|
629 |
+
[2024-03-24 23:57:49,736] INFO: [0;31mInitiating epoch #1 train run on device rank=0[0m
|
630 |
+
[2024-03-25 04:22:50,148] INFO: [0;31mInitiating epoch #1 valid run on device rank=0[0m
|
631 |
+
[2024-03-25 04:22:50,148] INFO: [0;31mInitiating epoch #1 valid run on device rank=0[0m
|
632 |
+
[2024-03-25 04:42:43,853] INFO: [1mRank 0: epoch=1 / 100 train_loss=20.8840 valid_loss=19.4969 stale=0 time=284.9m eta=28205.3m[0m
|
633 |
+
[2024-03-25 04:42:43,853] INFO: [1mRank 0: epoch=1 / 100 train_loss=20.8840 valid_loss=19.4969 stale=0 time=284.9m eta=28205.3m[0m
|
634 |
+
[2024-03-25 04:42:43,865] INFO: [0;31mInitiating epoch #2 train run on device rank=0[0m
|
635 |
+
[2024-03-25 04:42:43,865] INFO: [0;31mInitiating epoch #2 train run on device rank=0[0m
|
636 |
+
[2024-03-25 09:08:30,154] INFO: [0;31mInitiating epoch #2 valid run on device rank=0[0m
|
637 |
+
[2024-03-25 09:08:30,154] INFO: [0;31mInitiating epoch #2 valid run on device rank=0[0m
|
638 |
+
[2024-03-25 09:28:30,625] INFO: [1mRank 0: epoch=2 / 100 train_loss=19.0650 valid_loss=18.8620 stale=0 time=285.78m eta=27963.4m[0m
|
639 |
+
[2024-03-25 09:28:30,625] INFO: [1mRank 0: epoch=2 / 100 train_loss=19.0650 valid_loss=18.8620 stale=0 time=285.78m eta=27963.4m[0m
|
640 |
+
[2024-03-25 09:28:30,647] INFO: [0;31mInitiating epoch #3 train run on device rank=0[0m
|
641 |
+
[2024-03-25 09:28:30,647] INFO: [0;31mInitiating epoch #3 train run on device rank=0[0m
|
642 |
+
[2024-03-25 13:55:12,130] INFO: [0;31mInitiating epoch #3 valid run on device rank=0[0m
|
643 |
+
[2024-03-25 13:55:12,130] INFO: [0;31mInitiating epoch #3 valid run on device rank=0[0m
|
644 |
+
[2024-03-25 14:15:15,806] INFO: [1mRank 0: epoch=3 / 100 train_loss=18.7688 valid_loss=18.6758 stale=0 time=286.75m eta=27723.7m[0m
|
645 |
+
[2024-03-25 14:15:15,806] INFO: [1mRank 0: epoch=3 / 100 train_loss=18.7688 valid_loss=18.6758 stale=0 time=286.75m eta=27723.7m[0m
|
646 |
+
[2024-03-25 14:15:15,821] INFO: [0;31mInitiating epoch #4 train run on device rank=0[0m
|
647 |
+
[2024-03-25 14:15:15,821] INFO: [0;31mInitiating epoch #4 train run on device rank=0[0m
|
648 |
+
[2024-03-25 18:42:35,229] INFO: [0;31mInitiating epoch #4 valid run on device rank=0[0m
|
649 |
+
[2024-03-25 18:42:35,229] INFO: [0;31mInitiating epoch #4 valid run on device rank=0[0m
|
650 |
+
[2024-03-25 19:02:40,697] INFO: [1mRank 0: epoch=4 / 100 train_loss=18.6170 valid_loss=18.5653 stale=0 time=287.41m eta=27476.4m[0m
|
651 |
+
[2024-03-25 19:02:40,697] INFO: [1mRank 0: epoch=4 / 100 train_loss=18.6170 valid_loss=18.5653 stale=0 time=287.41m eta=27476.4m[0m
|
652 |
+
[2024-03-25 19:02:40,717] INFO: [0;31mInitiating epoch #5 train run on device rank=0[0m
|
653 |
+
[2024-03-25 19:02:40,717] INFO: [0;31mInitiating epoch #5 train run on device rank=0[0m
|
654 |
+
[2024-03-25 23:29:55,640] INFO: [0;31mInitiating epoch #5 valid run on device rank=0[0m
|
655 |
+
[2024-03-25 23:29:55,640] INFO: [0;31mInitiating epoch #5 valid run on device rank=0[0m
|
656 |
+
[2024-03-25 23:50:00,453] INFO: [1mRank 0: epoch=5 / 100 train_loss=18.5102 valid_loss=18.4685 stale=0 time=287.33m eta=27211.4m[0m
|
657 |
+
[2024-03-25 23:50:00,453] INFO: [1mRank 0: epoch=5 / 100 train_loss=18.5102 valid_loss=18.4685 stale=0 time=287.33m eta=27211.4m[0m
|
658 |
+
[2024-03-25 23:50:00,467] INFO: [0;31mInitiating epoch #6 train run on device rank=0[0m
|
659 |
+
[2024-03-25 23:50:00,467] INFO: [0;31mInitiating epoch #6 train run on device rank=0[0m
|
660 |
+
[2024-03-26 04:16:46,611] INFO: [0;31mInitiating epoch #6 valid run on device rank=0[0m
|
661 |
+
[2024-03-26 04:16:46,611] INFO: [0;31mInitiating epoch #6 valid run on device rank=0[0m
|
662 |
+
[2024-03-26 04:36:44,551] INFO: [1mRank 0: epoch=6 / 100 train_loss=18.4325 valid_loss=18.4090 stale=0 time=286.73m eta=26929.6m[0m
|
663 |
+
[2024-03-26 04:36:44,551] INFO: [1mRank 0: epoch=6 / 100 train_loss=18.4325 valid_loss=18.4090 stale=0 time=286.73m eta=26929.6m[0m
|
664 |
+
[2024-03-26 04:36:44,567] INFO: [0;31mInitiating epoch #7 train run on device rank=0[0m
|
665 |
+
[2024-03-26 04:36:44,567] INFO: [0;31mInitiating epoch #7 train run on device rank=0[0m
|
666 |
+
[2024-03-26 09:01:18,997] INFO: [0;31mInitiating epoch #7 valid run on device rank=0[0m
|
667 |
+
[2024-03-26 09:01:18,997] INFO: [0;31mInitiating epoch #7 valid run on device rank=0[0m
|
668 |
+
[2024-03-26 09:21:17,339] INFO: [1mRank 0: epoch=7 / 100 train_loss=18.3752 valid_loss=18.3620 stale=0 time=284.55m eta=26617.4m[0m
|
669 |
+
[2024-03-26 09:21:17,339] INFO: [1mRank 0: epoch=7 / 100 train_loss=18.3752 valid_loss=18.3620 stale=0 time=284.55m eta=26617.4m[0m
|
670 |
+
[2024-03-26 09:21:17,356] INFO: [0;31mInitiating epoch #8 train run on device rank=0[0m
|
671 |
+
[2024-03-26 09:21:17,356] INFO: [0;31mInitiating epoch #8 train run on device rank=0[0m
|
672 |
+
[2024-03-26 13:46:38,478] INFO: [0;31mInitiating epoch #8 valid run on device rank=0[0m
|
673 |
+
[2024-03-26 13:46:38,478] INFO: [0;31mInitiating epoch #8 valid run on device rank=0[0m
|
674 |
+
[2024-03-26 14:06:32,269] INFO: [1mRank 0: epoch=8 / 100 train_loss=18.3286 valid_loss=18.3267 stale=0 time=285.25m eta=26320.2m[0m
|
675 |
+
[2024-03-26 14:06:32,269] INFO: [1mRank 0: epoch=8 / 100 train_loss=18.3286 valid_loss=18.3267 stale=0 time=285.25m eta=26320.2m[0m
|
676 |
+
[2024-03-26 14:06:32,282] INFO: [0;31mInitiating epoch #9 train run on device rank=0[0m
|
677 |
+
[2024-03-26 14:06:32,282] INFO: [0;31mInitiating epoch #9 train run on device rank=0[0m
|
678 |
+
[2024-03-26 18:32:18,831] INFO: [0;31mInitiating epoch #9 valid run on device rank=0[0m
|
679 |
+
[2024-03-26 18:32:18,831] INFO: [0;31mInitiating epoch #9 valid run on device rank=0[0m
|
680 |
+
[2024-03-26 18:52:20,399] INFO: [1mRank 0: epoch=9 / 100 train_loss=18.2890 valid_loss=18.2883 stale=0 time=285.8m eta=26031.2m[0m
|
681 |
+
[2024-03-26 18:52:20,399] INFO: [1mRank 0: epoch=9 / 100 train_loss=18.2890 valid_loss=18.2883 stale=0 time=285.8m eta=26031.2m[0m
|
682 |
+
[2024-03-26 18:52:20,416] INFO: [0;31mInitiating epoch #10 train run on device rank=0[0m
|
683 |
+
[2024-03-26 18:52:20,416] INFO: [0;31mInitiating epoch #10 train run on device rank=0[0m
|
684 |
+
[2024-03-26 23:18:19,010] INFO: [0;31mInitiating epoch #10 valid run on device rank=0[0m
|
685 |
+
[2024-03-26 23:18:19,010] INFO: [0;31mInitiating epoch #10 valid run on device rank=0[0m
|
686 |
+
[2024-03-26 23:38:18,380] INFO: [1mRank 0: epoch=10 / 100 train_loss=18.2532 valid_loss=18.2458 stale=0 time=285.97m eta=25744.3m[0m
|
687 |
+
[2024-03-26 23:38:18,380] INFO: [1mRank 0: epoch=10 / 100 train_loss=18.2532 valid_loss=18.2458 stale=0 time=285.97m eta=25744.3m[0m
|
688 |
+
[2024-03-26 23:38:18,395] INFO: [0;31mInitiating epoch #11 train run on device rank=0[0m
|
689 |
+
[2024-03-26 23:38:18,395] INFO: [0;31mInitiating epoch #11 train run on device rank=0[0m
|
690 |
+
[2024-03-27 04:04:16,483] INFO: [0;31mInitiating epoch #11 valid run on device rank=0[0m
|
691 |
+
[2024-03-27 04:04:16,483] INFO: [0;31mInitiating epoch #11 valid run on device rank=0[0m
|
692 |
+
[2024-03-27 04:24:14,645] INFO: [1mRank 0: epoch=11 / 100 train_loss=18.2191 valid_loss=18.2212 stale=0 time=285.94m eta=25457.4m[0m
|
693 |
+
[2024-03-27 04:24:14,645] INFO: [1mRank 0: epoch=11 / 100 train_loss=18.2191 valid_loss=18.2212 stale=0 time=285.94m eta=25457.4m[0m
|
694 |
+
[2024-03-27 04:24:14,659] INFO: [0;31mInitiating epoch #12 train run on device rank=0[0m
|
695 |
+
[2024-03-27 04:24:14,659] INFO: [0;31mInitiating epoch #12 train run on device rank=0[0m
|
696 |
+
[2024-03-27 08:50:12,730] INFO: [0;31mInitiating epoch #12 valid run on device rank=0[0m
|
697 |
+
[2024-03-27 08:50:12,730] INFO: [0;31mInitiating epoch #12 valid run on device rank=0[0m
|
698 |
+
[2024-03-27 09:10:07,240] INFO: [1mRank 0: epoch=12 / 100 train_loss=18.1875 valid_loss=18.2005 stale=0 time=285.88m eta=25170.1m[0m
|
699 |
+
[2024-03-27 09:10:07,240] INFO: [1mRank 0: epoch=12 / 100 train_loss=18.1875 valid_loss=18.2005 stale=0 time=285.88m eta=25170.1m[0m
|
700 |
+
[2024-03-27 09:10:07,255] INFO: [0;31mInitiating epoch #13 train run on device rank=0[0m
|
701 |
+
[2024-03-27 09:10:07,255] INFO: [0;31mInitiating epoch #13 train run on device rank=0[0m
|
702 |
+
[2024-03-27 13:36:41,534] INFO: [0;31mInitiating epoch #13 valid run on device rank=0[0m
|
703 |
+
[2024-03-27 13:36:41,534] INFO: [0;31mInitiating epoch #13 valid run on device rank=0[0m
|
704 |
+
[2024-03-27 13:56:51,429] INFO: [1mRank 0: epoch=13 / 100 train_loss=18.1578 valid_loss=18.1808 stale=0 time=286.74m eta=24888.9m[0m
|
705 |
+
[2024-03-27 13:56:51,429] INFO: [1mRank 0: epoch=13 / 100 train_loss=18.1578 valid_loss=18.1808 stale=0 time=286.74m eta=24888.9m[0m
|
706 |
+
[2024-03-27 13:56:51,446] INFO: [0;31mInitiating epoch #14 train run on device rank=0[0m
|
707 |
+
[2024-03-27 13:56:51,446] INFO: [0;31mInitiating epoch #14 train run on device rank=0[0m
|
708 |
+
[2024-03-27 18:24:24,174] INFO: [0;31mInitiating epoch #14 valid run on device rank=0[0m
|
709 |
+
[2024-03-27 18:24:24,174] INFO: [0;31mInitiating epoch #14 valid run on device rank=0[0m
|
710 |
+
[2024-03-27 18:44:20,853] INFO: [1mRank 0: epoch=14 / 100 train_loss=18.1282 valid_loss=18.1575 stale=0 time=287.49m eta=24611.5m[0m
|
711 |
+
[2024-03-27 18:44:20,853] INFO: [1mRank 0: epoch=14 / 100 train_loss=18.1282 valid_loss=18.1575 stale=0 time=287.49m eta=24611.5m[0m
|
712 |
+
[2024-03-27 18:44:20,870] INFO: [0;31mInitiating epoch #15 train run on device rank=0[0m
|
713 |
+
[2024-03-27 18:44:20,870] INFO: [0;31mInitiating epoch #15 train run on device rank=0[0m
|
714 |
+
[2024-03-27 23:12:11,710] INFO: [0;31mInitiating epoch #15 valid run on device rank=0[0m
|
715 |
+
[2024-03-27 23:12:11,710] INFO: [0;31mInitiating epoch #15 valid run on device rank=0[0m
|
716 |
+
[2024-03-27 23:32:20,988] INFO: [1mRank 0: epoch=15 / 100 train_loss=18.0996 valid_loss=18.1267 stale=0 time=288.0m eta=24335.6m[0m
|
717 |
+
[2024-03-27 23:32:20,988] INFO: [1mRank 0: epoch=15 / 100 train_loss=18.0996 valid_loss=18.1267 stale=0 time=288.0m eta=24335.6m[0m
|
718 |
+
[2024-03-27 23:32:21,002] INFO: [0;31mInitiating epoch #16 train run on device rank=0[0m
|
719 |
+
[2024-03-27 23:32:21,002] INFO: [0;31mInitiating epoch #16 train run on device rank=0[0m
|
720 |
+
[2024-03-28 03:58:27,660] INFO: [0;31mInitiating epoch #16 valid run on device rank=0[0m
|
721 |
+
[2024-03-28 03:58:27,660] INFO: [0;31mInitiating epoch #16 valid run on device rank=0[0m
|
722 |
+
[2024-03-28 04:18:21,127] INFO: [1mRank 0: epoch=16 / 100 train_loss=18.0729 valid_loss=18.1030 stale=0 time=286.0m eta=24047.7m[0m
|
723 |
+
[2024-03-28 04:18:21,127] INFO: [1mRank 0: epoch=16 / 100 train_loss=18.0729 valid_loss=18.1030 stale=0 time=286.0m eta=24047.7m[0m
|
724 |
+
[2024-03-28 04:18:21,141] INFO: [0;31mInitiating epoch #17 train run on device rank=0[0m
|
725 |
+
[2024-03-28 04:18:21,141] INFO: [0;31mInitiating epoch #17 train run on device rank=0[0m
|
726 |
+
[2024-03-28 08:44:11,691] INFO: [0;31mInitiating epoch #17 valid run on device rank=0[0m
|
727 |
+
[2024-03-28 08:44:11,691] INFO: [0;31mInitiating epoch #17 valid run on device rank=0[0m
|
728 |
+
[2024-03-28 09:04:09,550] INFO: [1mRank 0: epoch=17 / 100 train_loss=18.0478 valid_loss=18.0912 stale=0 time=285.81m eta=23759.1m[0m
|
729 |
+
[2024-03-28 09:04:09,550] INFO: [1mRank 0: epoch=17 / 100 train_loss=18.0478 valid_loss=18.0912 stale=0 time=285.81m eta=23759.1m[0m
|
730 |
+
[2024-03-28 09:04:09,566] INFO: [0;31mInitiating epoch #18 train run on device rank=0[0m
|
731 |
+
[2024-03-28 09:04:09,566] INFO: [0;31mInitiating epoch #18 train run on device rank=0[0m
|
732 |
+
[2024-03-28 13:29:43,054] INFO: [0;31mInitiating epoch #18 valid run on device rank=0[0m
|
733 |
+
[2024-03-28 13:29:43,054] INFO: [0;31mInitiating epoch #18 valid run on device rank=0[0m
|
734 |
+
[2024-03-28 13:49:42,746] INFO: [1mRank 0: epoch=18 / 100 train_loss=18.0235 valid_loss=18.0697 stale=0 time=285.55m eta=23469.7m[0m
|
735 |
+
[2024-03-28 13:49:42,746] INFO: [1mRank 0: epoch=18 / 100 train_loss=18.0235 valid_loss=18.0697 stale=0 time=285.55m eta=23469.7m[0m
|
736 |
+
[2024-03-28 13:49:42,760] INFO: [0;31mInitiating epoch #19 train run on device rank=0[0m
|
737 |
+
[2024-03-28 13:49:42,760] INFO: [0;31mInitiating epoch #19 train run on device rank=0[0m
|
738 |
+
[2024-03-28 18:15:26,865] INFO: [0;31mInitiating epoch #19 valid run on device rank=0[0m
|
739 |
+
[2024-03-28 18:15:26,865] INFO: [0;31mInitiating epoch #19 valid run on device rank=0[0m
|
740 |
+
[2024-03-28 18:35:24,119] INFO: [1mRank 0: epoch=19 / 100 train_loss=18.0008 valid_loss=18.0532 stale=0 time=285.69m eta=23181.2m[0m
|
741 |
+
[2024-03-28 18:35:24,119] INFO: [1mRank 0: epoch=19 / 100 train_loss=18.0008 valid_loss=18.0532 stale=0 time=285.69m eta=23181.2m[0m
|
742 |
+
[2024-03-28 18:35:24,137] INFO: [0;31mInitiating epoch #20 train run on device rank=0[0m
|
743 |
+
[2024-03-28 18:35:24,137] INFO: [0;31mInitiating epoch #20 train run on device rank=0[0m
|
744 |
+
[2024-03-28 23:00:36,705] INFO: [0;31mInitiating epoch #20 valid run on device rank=0[0m
|
745 |
+
[2024-03-28 23:00:36,705] INFO: [0;31mInitiating epoch #20 valid run on device rank=0[0m
|
746 |
+
[2024-03-28 23:20:35,806] INFO: [1mRank 0: epoch=20 / 100 train_loss=17.9783 valid_loss=18.0347 stale=0 time=285.19m eta=22891.1m[0m
|
747 |
+
[2024-03-28 23:20:35,806] INFO: [1mRank 0: epoch=20 / 100 train_loss=17.9783 valid_loss=18.0347 stale=0 time=285.19m eta=22891.1m[0m
|
748 |
+
[2024-03-28 23:20:35,825] INFO: [0;31mInitiating epoch #21 train run on device rank=0[0m
|
749 |
+
[2024-03-28 23:20:35,825] INFO: [0;31mInitiating epoch #21 train run on device rank=0[0m
|
750 |
+
[2024-03-29 03:46:25,188] INFO: [0;31mInitiating epoch #21 valid run on device rank=0[0m
|
751 |
+
[2024-03-29 03:46:25,188] INFO: [0;31mInitiating epoch #21 valid run on device rank=0[0m
|
752 |
+
[2024-03-29 04:06:24,286] INFO: [1mRank 0: epoch=21 / 100 train_loss=17.9565 valid_loss=18.0197 stale=0 time=285.81m eta=22603.7m[0m
|
753 |
+
[2024-03-29 04:06:24,286] INFO: [1mRank 0: epoch=21 / 100 train_loss=17.9565 valid_loss=18.0197 stale=0 time=285.81m eta=22603.7m[0m
|
754 |
+
[2024-03-29 04:06:24,301] INFO: [0;31mInitiating epoch #22 train run on device rank=0[0m
|
755 |
+
[2024-03-29 04:06:24,301] INFO: [0;31mInitiating epoch #22 train run on device rank=0[0m
|
756 |
+
[2024-03-29 08:31:11,736] INFO: [0;31mInitiating epoch #22 valid run on device rank=0[0m
|
757 |
+
[2024-03-29 08:31:11,736] INFO: [0;31mInitiating epoch #22 valid run on device rank=0[0m
|
758 |
+
[2024-03-29 08:51:08,443] INFO: [1mRank 0: epoch=22 / 100 train_loss=17.9356 valid_loss=18.0009 stale=0 time=284.74m eta=22312.7m[0m
|
759 |
+
[2024-03-29 08:51:08,443] INFO: [1mRank 0: epoch=22 / 100 train_loss=17.9356 valid_loss=18.0009 stale=0 time=284.74m eta=22312.7m[0m
|
760 |
+
[2024-03-29 08:51:08,458] INFO: [0;31mInitiating epoch #23 train run on device rank=0[0m
|
761 |
+
[2024-03-29 08:51:08,458] INFO: [0;31mInitiating epoch #23 train run on device rank=0[0m
|
762 |
+
[2024-03-29 13:16:30,304] INFO: [0;31mInitiating epoch #23 valid run on device rank=0[0m
|
763 |
+
[2024-03-29 13:16:30,304] INFO: [0;31mInitiating epoch #23 valid run on device rank=0[0m
|
764 |
+
[2024-03-29 13:36:29,623] INFO: [1mRank 0: epoch=23 / 100 train_loss=17.9150 valid_loss=17.9919 stale=0 time=285.35m eta=22024.2m[0m
|
765 |
+
[2024-03-29 13:36:29,623] INFO: [1mRank 0: epoch=23 / 100 train_loss=17.9150 valid_loss=17.9919 stale=0 time=285.35m eta=22024.2m[0m
|
766 |
+
[2024-03-29 13:36:29,637] INFO: [0;31mInitiating epoch #24 train run on device rank=0[0m
|
767 |
+
[2024-03-29 13:36:29,637] INFO: [0;31mInitiating epoch #24 train run on device rank=0[0m
|
768 |
+
[2024-03-29 18:01:59,324] INFO: [0;31mInitiating epoch #24 valid run on device rank=0[0m
|
769 |
+
[2024-03-29 18:01:59,324] INFO: [0;31mInitiating epoch #24 valid run on device rank=0[0m
|
770 |
+
[2024-03-29 18:21:58,557] INFO: [1mRank 0: epoch=24 / 100 train_loss=17.8948 valid_loss=17.9806 stale=0 time=285.48m eta=21736.5m[0m
|
771 |
+
[2024-03-29 18:21:58,557] INFO: [1mRank 0: epoch=24 / 100 train_loss=17.8948 valid_loss=17.9806 stale=0 time=285.48m eta=21736.5m[0m
|
772 |
+
[2024-03-29 18:21:58,573] INFO: [0;31mInitiating epoch #25 train run on device rank=0[0m
|
773 |
+
[2024-03-29 18:21:58,573] INFO: [0;31mInitiating epoch #25 train run on device rank=0[0m
|
774 |
+
[2024-03-29 22:47:04,103] INFO: [0;31mInitiating epoch #25 valid run on device rank=0[0m
|
775 |
+
[2024-03-29 22:47:04,103] INFO: [0;31mInitiating epoch #25 valid run on device rank=0[0m
|
776 |
+
[2024-03-29 23:06:58,509] INFO: [1mRank 0: epoch=25 / 100 train_loss=17.8745 valid_loss=17.9677 stale=0 time=285.0m eta=21447.4m[0m
|
777 |
+
[2024-03-29 23:06:58,509] INFO: [1mRank 0: epoch=25 / 100 train_loss=17.8745 valid_loss=17.9677 stale=0 time=285.0m eta=21447.4m[0m
|
778 |
+
[2024-03-29 23:06:58,528] INFO: [0;31mInitiating epoch #26 train run on device rank=0[0m
|
779 |
+
[2024-03-29 23:06:58,528] INFO: [0;31mInitiating epoch #26 train run on device rank=0[0m
|
780 |
+
[2024-03-30 03:32:08,173] INFO: [0;31mInitiating epoch #26 valid run on device rank=0[0m
|
781 |
+
[2024-03-30 03:32:08,173] INFO: [0;31mInitiating epoch #26 valid run on device rank=0[0m
|
782 |
+
[2024-03-30 03:52:08,592] INFO: [1mRank 0: epoch=26 / 100 train_loss=17.8549 valid_loss=17.9569 stale=0 time=285.17m eta=21159.2m[0m
|
783 |
+
[2024-03-30 03:52:08,592] INFO: [1mRank 0: epoch=26 / 100 train_loss=17.8549 valid_loss=17.9569 stale=0 time=285.17m eta=21159.2m[0m
|
784 |
+
[2024-03-30 03:52:08,608] INFO: [0;31mInitiating epoch #27 train run on device rank=0[0m
|
785 |
+
[2024-03-30 03:52:08,608] INFO: [0;31mInitiating epoch #27 train run on device rank=0[0m
|
786 |
+
[2024-03-30 08:17:59,526] INFO: [0;31mInitiating epoch #27 valid run on device rank=0[0m
|
787 |
+
[2024-03-30 08:17:59,526] INFO: [0;31mInitiating epoch #27 valid run on device rank=0[0m
|
788 |
+
[2024-03-30 08:38:00,700] INFO: [1mRank 0: epoch=27 / 100 train_loss=17.8347 valid_loss=17.9366 stale=0 time=285.87m eta=20873.1m[0m
|
789 |
+
[2024-03-30 08:38:00,700] INFO: [1mRank 0: epoch=27 / 100 train_loss=17.8347 valid_loss=17.9366 stale=0 time=285.87m eta=20873.1m[0m
|
790 |
+
[2024-03-30 08:38:00,714] INFO: [0;31mInitiating epoch #28 train run on device rank=0[0m
|
791 |
+
[2024-03-30 08:38:00,714] INFO: [0;31mInitiating epoch #28 train run on device rank=0[0m
|
792 |
+
[2024-03-30 13:03:33,057] INFO: [0;31mInitiating epoch #28 valid run on device rank=0[0m
|
793 |
+
[2024-03-30 13:03:33,057] INFO: [0;31mInitiating epoch #28 valid run on device rank=0[0m
|
794 |
+
[2024-03-30 13:23:29,411] INFO: [1mRank 0: epoch=28 / 100 train_loss=17.8149 valid_loss=17.9264 stale=0 time=285.48m eta=20586.0m[0m
|
795 |
+
[2024-03-30 13:23:29,411] INFO: [1mRank 0: epoch=28 / 100 train_loss=17.8149 valid_loss=17.9264 stale=0 time=285.48m eta=20586.0m[0m
|
796 |
+
[2024-03-30 13:23:29,424] INFO: [0;31mInitiating epoch #29 train run on device rank=0[0m
|
797 |
+
[2024-03-30 13:23:29,424] INFO: [0;31mInitiating epoch #29 train run on device rank=0[0m
|
798 |
+
[2024-03-30 17:49:27,995] INFO: [0;31mInitiating epoch #29 valid run on device rank=0[0m
|
799 |
+
[2024-03-30 17:49:27,995] INFO: [0;31mInitiating epoch #29 valid run on device rank=0[0m
|
800 |
+
[2024-03-30 18:09:26,968] INFO: [1mRank 0: epoch=29 / 100 train_loss=17.7950 valid_loss=17.9112 stale=0 time=285.96m eta=20300.2m[0m
|
801 |
+
[2024-03-30 18:09:26,968] INFO: [1mRank 0: epoch=29 / 100 train_loss=17.7950 valid_loss=17.9112 stale=0 time=285.96m eta=20300.2m[0m
|
802 |
+
[2024-03-30 18:09:26,982] INFO: [0;31mInitiating epoch #30 train run on device rank=0[0m
|
803 |
+
[2024-03-30 18:09:26,982] INFO: [0;31mInitiating epoch #30 train run on device rank=0[0m
|
804 |
+
[2024-03-30 22:34:51,876] INFO: [0;31mInitiating epoch #30 valid run on device rank=0[0m
|
805 |
+
[2024-03-30 22:34:51,876] INFO: [0;31mInitiating epoch #30 valid run on device rank=0[0m
|
806 |
+
[2024-03-30 22:54:53,145] INFO: [1mRank 0: epoch=30 / 100 train_loss=17.7757 valid_loss=17.9006 stale=0 time=285.44m eta=20013.1m[0m
|
807 |
+
[2024-03-30 22:54:53,145] INFO: [1mRank 0: epoch=30 / 100 train_loss=17.7757 valid_loss=17.9006 stale=0 time=285.44m eta=20013.1m[0m
|
808 |
+
[2024-03-30 22:54:53,159] INFO: [0;31mInitiating epoch #31 train run on device rank=0[0m
|
809 |
+
[2024-03-30 22:54:53,159] INFO: [0;31mInitiating epoch #31 train run on device rank=0[0m
|
810 |
+
[2024-03-31 04:20:44,340] INFO: [0;31mInitiating epoch #31 valid run on device rank=0[0m
|
811 |
+
[2024-03-31 04:20:44,340] INFO: [0;31mInitiating epoch #31 valid run on device rank=0[0m
|
812 |
+
[2024-03-31 04:40:42,326] INFO: [1mRank 0: epoch=31 / 100 train_loss=17.7565 valid_loss=17.8932 stale=0 time=285.82m eta=19727.0m[0m
|
813 |
+
[2024-03-31 04:40:42,326] INFO: [1mRank 0: epoch=31 / 100 train_loss=17.7565 valid_loss=17.8932 stale=0 time=285.82m eta=19727.0m[0m
|
814 |
+
[2024-03-31 04:40:42,350] INFO: [0;31mInitiating epoch #32 train run on device rank=0[0m
|
815 |
+
[2024-03-31 04:40:42,350] INFO: [0;31mInitiating epoch #32 train run on device rank=0[0m
|
816 |
+
[2024-03-31 09:06:05,665] INFO: [0;31mInitiating epoch #32 valid run on device rank=0[0m
|
817 |
+
[2024-03-31 09:06:05,665] INFO: [0;31mInitiating epoch #32 valid run on device rank=0[0m
|
818 |
+
[2024-03-31 09:26:03,353] INFO: [1mRank 0: epoch=32 / 100 train_loss=17.7375 valid_loss=17.8774 stale=0 time=285.35m eta=19440.0m[0m
|
819 |
+
[2024-03-31 09:26:03,353] INFO: [1mRank 0: epoch=32 / 100 train_loss=17.7375 valid_loss=17.8774 stale=0 time=285.35m eta=19440.0m[0m
|
820 |
+
[2024-03-31 09:26:03,368] INFO: [0;31mInitiating epoch #33 train run on device rank=0[0m
|
821 |
+
[2024-03-31 09:26:03,368] INFO: [0;31mInitiating epoch #33 train run on device rank=0[0m
|