Skip to content
Snippets Groups Projects
Commit 02f95633 authored by Schneider Leo's avatar Schneider Leo
Browse files

del raysesult

parent b844726e
No related branches found
No related tags found
No related merge requests found
Showing
with 0 additions and 91 deletions
loss,timestamp,checkpoint_dir_name,should_checkpoint,done,training_iteration,trial_id,date,time_this_iter_s,time_total_s,pid,hostname,node_ip,time_since_restore,iterations_since_restore
510.42659056656004,1719324728,checkpoint_000000,True,False,1,6a62b85a,2024-06-25_16-12-08,64.32230615615845,64.32230615615845,69318,r3i5n6,10.159.8.159,64.32230615615845,1
310.75900604968933,1719327245,checkpoint_000001,True,False,2,6a62b85a,2024-06-25_16-54-05,63.18879699707031,127.51110315322876,130020,r3i5n6,10.159.8.159,63.18879699707031,1
{"loss": 510.42659056656004, "timestamp": 1719324728, "checkpoint_dir_name": "checkpoint_000000", "should_checkpoint": true, "done": false, "training_iteration": 1, "trial_id": "6a62b85a", "date": "2024-06-25_16-12-08", "time_this_iter_s": 64.32230615615845, "time_total_s": 64.32230615615845, "pid": 69318, "hostname": "r3i5n6", "node_ip": "10.159.8.159", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 1024, "n_head": 4, "drop_rate": 0.06860896590384413, "lr": 0.00016561766448063182, "batch_size": 2048}, "time_since_restore": 64.32230615615845, "iterations_since_restore": 1}
{"loss": 310.75900604968933, "timestamp": 1719327245, "checkpoint_dir_name": "checkpoint_000001", "should_checkpoint": true, "done": false, "training_iteration": 2, "trial_id": "6a62b85a", "date": "2024-06-25_16-54-05", "time_this_iter_s": 63.18879699707031, "time_total_s": 127.51110315322876, "pid": 130020, "hostname": "r3i5n6", "node_ip": "10.159.8.159", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 1024, "n_head": 4, "drop_rate": 0.06860896590384413, "lr": 0.00016561766448063182, "batch_size": 2048}, "time_since_restore": 63.18879699707031, "iterations_since_restore": 1}
{
"batch_size": 2048,
"decoder_int_ff": 512,
"decoder_int_num_layer": 1,
"decoder_rt_ff": 512,
"decoder_rt_num_layer": 2,
"drop_rate": 0.18647509291243747,
"embedding_dim": 16,
"encoder_ff": 1024,
"encoder_num_layer": 1,
"lr": 0.09874663205229757,
"n_head": 4
}
\ No newline at end of file
loss,timestamp,checkpoint_dir_name,should_checkpoint,done,training_iteration,trial_id,date,time_this_iter_s,time_total_s,pid,hostname,node_ip,time_since_restore,iterations_since_restore
3081.7005067359746,1719531344,checkpoint_000000,True,False,1,6a8b96c3,2024-06-28_01-35-44,63.290406703948975,63.290406703948975,242786,r8i6n8,10.159.28.66,63.290406703948975,1
2150.0786584568773,1719531394,checkpoint_000001,True,False,2,6a8b96c3,2024-06-28_01-36-34,49.63099932670593,112.92140603065491,242786,r8i6n8,10.159.28.66,112.92140603065491,2
1974.6818732314223,1719531444,checkpoint_000002,True,False,3,6a8b96c3,2024-06-28_01-37-24,49.58891534805298,162.51032137870789,242786,r8i6n8,10.159.28.66,162.51032137870789,3
1956.0451112281619,1719531494,checkpoint_000003,True,False,4,6a8b96c3,2024-06-28_01-38-14,50.049054861068726,212.5593762397766,242786,r8i6n8,10.159.28.66,212.5593762397766,4
1954.3213630736343,1719531543,checkpoint_000004,True,False,5,6a8b96c3,2024-06-28_01-39-03,49.60325813293457,262.1626343727112,242786,r8i6n8,10.159.28.66,262.1626343727112,5
1953.8488356222317,1719531592,checkpoint_000005,True,False,6,6a8b96c3,2024-06-28_01-39-52,49.1952109336853,311.3578453063965,242786,r8i6n8,10.159.28.66,311.3578453063965,6
1953.7962627260704,1719531642,checkpoint_000006,True,False,7,6a8b96c3,2024-06-28_01-40-42,50.036651611328125,361.3944969177246,242786,r8i6n8,10.159.28.66,361.3944969177246,7
1953.8618644654282,1719531692,checkpoint_000007,True,False,8,6a8b96c3,2024-06-28_01-41-32,49.76662850379944,411.16112542152405,242786,r8i6n8,10.159.28.66,411.16112542152405,8
1954.3857364203986,1719531742,checkpoint_000008,True,False,9,6a8b96c3,2024-06-28_01-42-22,49.68609666824341,460.84722208976746,242786,r8i6n8,10.159.28.66,460.84722208976746,9
1953.720588744156,1719531792,checkpoint_000009,True,False,10,6a8b96c3,2024-06-28_01-43-12,50.06679081916809,510.91401290893555,242786,r8i6n8,10.159.28.66,510.91401290893555,10
{"loss": 3081.7005067359746, "timestamp": 1719531344, "checkpoint_dir_name": "checkpoint_000000", "should_checkpoint": true, "done": false, "training_iteration": 1, "trial_id": "6a8b96c3", "date": "2024-06-28_01-35-44", "time_this_iter_s": 63.290406703948975, "time_total_s": 63.290406703948975, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.18647509291243747, "lr": 0.09874663205229757, "batch_size": 2048}, "time_since_restore": 63.290406703948975, "iterations_since_restore": 1}
{"loss": 2150.0786584568773, "timestamp": 1719531394, "checkpoint_dir_name": "checkpoint_000001", "should_checkpoint": true, "done": false, "training_iteration": 2, "trial_id": "6a8b96c3", "date": "2024-06-28_01-36-34", "time_this_iter_s": 49.63099932670593, "time_total_s": 112.92140603065491, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.18647509291243747, "lr": 0.09874663205229757, "batch_size": 2048}, "time_since_restore": 112.92140603065491, "iterations_since_restore": 2}
{"loss": 1974.6818732314223, "timestamp": 1719531444, "checkpoint_dir_name": "checkpoint_000002", "should_checkpoint": true, "done": false, "training_iteration": 3, "trial_id": "6a8b96c3", "date": "2024-06-28_01-37-24", "time_this_iter_s": 49.58891534805298, "time_total_s": 162.51032137870789, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.18647509291243747, "lr": 0.09874663205229757, "batch_size": 2048}, "time_since_restore": 162.51032137870789, "iterations_since_restore": 3}
{"loss": 1956.0451112281619, "timestamp": 1719531494, "checkpoint_dir_name": "checkpoint_000003", "should_checkpoint": true, "done": false, "training_iteration": 4, "trial_id": "6a8b96c3", "date": "2024-06-28_01-38-14", "time_this_iter_s": 50.049054861068726, "time_total_s": 212.5593762397766, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.18647509291243747, "lr": 0.09874663205229757, "batch_size": 2048}, "time_since_restore": 212.5593762397766, "iterations_since_restore": 4}
{"loss": 1954.3213630736343, "timestamp": 1719531543, "checkpoint_dir_name": "checkpoint_000004", "should_checkpoint": true, "done": false, "training_iteration": 5, "trial_id": "6a8b96c3", "date": "2024-06-28_01-39-03", "time_this_iter_s": 49.60325813293457, "time_total_s": 262.1626343727112, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.18647509291243747, "lr": 0.09874663205229757, "batch_size": 2048}, "time_since_restore": 262.1626343727112, "iterations_since_restore": 5}
{"loss": 1953.8488356222317, "timestamp": 1719531592, "checkpoint_dir_name": "checkpoint_000005", "should_checkpoint": true, "done": false, "training_iteration": 6, "trial_id": "6a8b96c3", "date": "2024-06-28_01-39-52", "time_this_iter_s": 49.1952109336853, "time_total_s": 311.3578453063965, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.18647509291243747, "lr": 0.09874663205229757, "batch_size": 2048}, "time_since_restore": 311.3578453063965, "iterations_since_restore": 6}
{"loss": 1953.7962627260704, "timestamp": 1719531642, "checkpoint_dir_name": "checkpoint_000006", "should_checkpoint": true, "done": false, "training_iteration": 7, "trial_id": "6a8b96c3", "date": "2024-06-28_01-40-42", "time_this_iter_s": 50.036651611328125, "time_total_s": 361.3944969177246, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.18647509291243747, "lr": 0.09874663205229757, "batch_size": 2048}, "time_since_restore": 361.3944969177246, "iterations_since_restore": 7}
{"loss": 1953.8618644654282, "timestamp": 1719531692, "checkpoint_dir_name": "checkpoint_000007", "should_checkpoint": true, "done": false, "training_iteration": 8, "trial_id": "6a8b96c3", "date": "2024-06-28_01-41-32", "time_this_iter_s": 49.76662850379944, "time_total_s": 411.16112542152405, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.18647509291243747, "lr": 0.09874663205229757, "batch_size": 2048}, "time_since_restore": 411.16112542152405, "iterations_since_restore": 8}
{"loss": 1954.3857364203986, "timestamp": 1719531742, "checkpoint_dir_name": "checkpoint_000008", "should_checkpoint": true, "done": false, "training_iteration": 9, "trial_id": "6a8b96c3", "date": "2024-06-28_01-42-22", "time_this_iter_s": 49.68609666824341, "time_total_s": 460.84722208976746, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.18647509291243747, "lr": 0.09874663205229757, "batch_size": 2048}, "time_since_restore": 460.84722208976746, "iterations_since_restore": 9}
{"loss": 1953.720588744156, "timestamp": 1719531792, "checkpoint_dir_name": "checkpoint_000009", "should_checkpoint": true, "done": false, "training_iteration": 10, "trial_id": "6a8b96c3", "date": "2024-06-28_01-43-12", "time_this_iter_s": 50.06679081916809, "time_total_s": 510.91401290893555, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.18647509291243747, "lr": 0.09874663205229757, "batch_size": 2048}, "time_since_restore": 510.91401290893555, "iterations_since_restore": 10}
{
"batch_size": 1024,
"decoder_int_ff": 512,
"decoder_int_num_layer": 1,
"decoder_rt_ff": 1024,
"decoder_rt_num_layer": 8,
"drop_rate": 0.3756319644523144,
"embedding_dim": 16,
"encoder_ff": 1024,
"encoder_num_layer": 1,
"lr": 0.003959565870439527,
"n_head": 4
}
\ No newline at end of file
loss,timestamp,checkpoint_dir_name,should_checkpoint,done,training_iteration,trial_id,date,time_this_iter_s,time_total_s,pid,hostname,node_ip,time_since_restore,iterations_since_restore
1989.802595964567,1719509621,checkpoint_000000,True,False,1,6b7688f2,2024-06-27_19-33-41,83.60843539237976,83.60843539237976,242786,r8i6n8,10.159.28.66,83.60843539237976,1
1962.6643076018086,1719509692,checkpoint_000001,True,False,2,6b7688f2,2024-06-27_19-34-52,70.66612339019775,154.27455878257751,242786,r8i6n8,10.159.28.66,154.27455878257751,2
1970.6976669191376,1719509763,checkpoint_000002,True,False,3,6b7688f2,2024-06-27_19-36-03,70.83067870140076,225.10523748397827,242786,r8i6n8,10.159.28.66,225.10523748397827,3
1984.9167043130228,1719509833,checkpoint_000003,True,False,4,6b7688f2,2024-06-27_19-37-13,70.6679790019989,295.7732164859772,242786,r8i6n8,10.159.28.66,295.7732164859772,4
1964.9003257451095,1719509904,checkpoint_000004,True,False,5,6b7688f2,2024-06-27_19-38-24,70.81649136543274,366.5897078514099,242786,r8i6n8,10.159.28.66,366.5897078514099,5
1964.2627097302534,1719512416,checkpoint_000005,True,False,6,6b7688f2,2024-06-27_20-20-16,82.97016429901123,449.55987215042114,242786,r8i6n8,10.159.28.66,82.97016429901123,1
1965.1521044152928,1719512486,checkpoint_000006,True,False,7,6b7688f2,2024-06-27_20-21-26,70.53654623031616,520.0964183807373,242786,r8i6n8,10.159.28.66,153.5067105293274,2
1963.2242965097503,1719512557,checkpoint_000007,True,False,8,6b7688f2,2024-06-27_20-22-37,70.63850402832031,590.7349224090576,242786,r8i6n8,10.159.28.66,224.1452145576477,3
1966.0343594288263,1719512628,checkpoint_000008,True,False,9,6b7688f2,2024-06-27_20-23-48,70.55560326576233,661.29052567482,242786,r8i6n8,10.159.28.66,294.70081782341003,4
1977.05159056656,1719512699,checkpoint_000009,True,True,10,6b7688f2,2024-06-27_20-24-59,71.11927580833435,732.4098014831543,242786,r8i6n8,10.159.28.66,365.8200936317444,5
{"loss": 1989.802595964567, "timestamp": 1719509621, "checkpoint_dir_name": "checkpoint_000000", "should_checkpoint": true, "done": false, "training_iteration": 1, "trial_id": "6b7688f2", "date": "2024-06-27_19-33-41", "time_this_iter_s": 83.60843539237976, "time_total_s": 83.60843539237976, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.3756319644523144, "lr": 0.003959565870439527, "batch_size": 1024}, "time_since_restore": 83.60843539237976, "iterations_since_restore": 1}
{"loss": 1962.6643076018086, "timestamp": 1719509692, "checkpoint_dir_name": "checkpoint_000001", "should_checkpoint": true, "done": false, "training_iteration": 2, "trial_id": "6b7688f2", "date": "2024-06-27_19-34-52", "time_this_iter_s": 70.66612339019775, "time_total_s": 154.27455878257751, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.3756319644523144, "lr": 0.003959565870439527, "batch_size": 1024}, "time_since_restore": 154.27455878257751, "iterations_since_restore": 2}
{"loss": 1970.6976669191376, "timestamp": 1719509763, "checkpoint_dir_name": "checkpoint_000002", "should_checkpoint": true, "done": false, "training_iteration": 3, "trial_id": "6b7688f2", "date": "2024-06-27_19-36-03", "time_this_iter_s": 70.83067870140076, "time_total_s": 225.10523748397827, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.3756319644523144, "lr": 0.003959565870439527, "batch_size": 1024}, "time_since_restore": 225.10523748397827, "iterations_since_restore": 3}
{"loss": 1984.9167043130228, "timestamp": 1719509833, "checkpoint_dir_name": "checkpoint_000003", "should_checkpoint": true, "done": false, "training_iteration": 4, "trial_id": "6b7688f2", "date": "2024-06-27_19-37-13", "time_this_iter_s": 70.6679790019989, "time_total_s": 295.7732164859772, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.3756319644523144, "lr": 0.003959565870439527, "batch_size": 1024}, "time_since_restore": 295.7732164859772, "iterations_since_restore": 4}
{"loss": 1964.9003257451095, "timestamp": 1719509904, "checkpoint_dir_name": "checkpoint_000004", "should_checkpoint": true, "done": false, "training_iteration": 5, "trial_id": "6b7688f2", "date": "2024-06-27_19-38-24", "time_this_iter_s": 70.81649136543274, "time_total_s": 366.5897078514099, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.3756319644523144, "lr": 0.003959565870439527, "batch_size": 1024}, "time_since_restore": 366.5897078514099, "iterations_since_restore": 5}
{"loss": 1964.2627097302534, "timestamp": 1719512416, "checkpoint_dir_name": "checkpoint_000005", "should_checkpoint": true, "done": false, "training_iteration": 6, "trial_id": "6b7688f2", "date": "2024-06-27_20-20-16", "time_this_iter_s": 82.97016429901123, "time_total_s": 449.55987215042114, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.3756319644523144, "lr": 0.003959565870439527, "batch_size": 1024}, "time_since_restore": 82.97016429901123, "iterations_since_restore": 1}
{"loss": 1965.1521044152928, "timestamp": 1719512486, "checkpoint_dir_name": "checkpoint_000006", "should_checkpoint": true, "done": false, "training_iteration": 7, "trial_id": "6b7688f2", "date": "2024-06-27_20-21-26", "time_this_iter_s": 70.53654623031616, "time_total_s": 520.0964183807373, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.3756319644523144, "lr": 0.003959565870439527, "batch_size": 1024}, "time_since_restore": 153.5067105293274, "iterations_since_restore": 2}
{"loss": 1963.2242965097503, "timestamp": 1719512557, "checkpoint_dir_name": "checkpoint_000007", "should_checkpoint": true, "done": false, "training_iteration": 8, "trial_id": "6b7688f2", "date": "2024-06-27_20-22-37", "time_this_iter_s": 70.63850402832031, "time_total_s": 590.7349224090576, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.3756319644523144, "lr": 0.003959565870439527, "batch_size": 1024}, "time_since_restore": 224.1452145576477, "iterations_since_restore": 3}
{"loss": 1966.0343594288263, "timestamp": 1719512628, "checkpoint_dir_name": "checkpoint_000008", "should_checkpoint": true, "done": false, "training_iteration": 9, "trial_id": "6b7688f2", "date": "2024-06-27_20-23-48", "time_this_iter_s": 70.55560326576233, "time_total_s": 661.29052567482, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.3756319644523144, "lr": 0.003959565870439527, "batch_size": 1024}, "time_since_restore": 294.70081782341003, "iterations_since_restore": 4}
{"loss": 1977.05159056656, "timestamp": 1719512699, "checkpoint_dir_name": "checkpoint_000009", "should_checkpoint": true, "done": true, "training_iteration": 10, "trial_id": "6b7688f2", "date": "2024-06-27_20-24-59", "time_this_iter_s": 71.11927580833435, "time_total_s": 732.4098014831543, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.3756319644523144, "lr": 0.003959565870439527, "batch_size": 1024}, "time_since_restore": 365.8200936317444, "iterations_since_restore": 5}
{
"batch_size": 1024,
"decoder_int_ff": 512,
"decoder_int_num_layer": 1,
"decoder_rt_ff": 1024,
"decoder_rt_num_layer": 2,
"drop_rate": 0.7446531774853204,
"embedding_dim": 64,
"encoder_ff": 2048,
"encoder_num_layer": 1,
"lr": 0.006000257122673396,
"n_head": 8
}
\ No newline at end of file
loss,timestamp,checkpoint_dir_name,should_checkpoint,done,training_iteration,trial_id,date,time_this_iter_s,time_total_s,pid,hostname,node_ip,time_since_restore,iterations_since_restore
2020.6805025836613,1719335855,checkpoint_000000,True,False,1,6be79717,2024-06-25_19-17-35,71.47419285774231,71.47419285774231,2195253,r8i6n2,10.159.28.60,71.47419285774231,1
2003.3902054433747,1719335912,checkpoint_000001,True,False,2,6be79717,2024-06-25_19-18-32,57.25079274177551,128.72498559951782,2195253,r8i6n2,10.159.28.60,128.72498559951782,2
{"loss": 2020.6805025836613, "timestamp": 1719335855, "checkpoint_dir_name": "checkpoint_000000", "should_checkpoint": true, "done": false, "training_iteration": 1, "trial_id": "6be79717", "date": "2024-06-25_19-17-35", "time_this_iter_s": 71.47419285774231, "time_total_s": 71.47419285774231, "pid": 2195253, "hostname": "r8i6n2", "node_ip": "10.159.28.60", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 64, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 8, "drop_rate": 0.7446531774853204, "lr": 0.006000257122673396, "batch_size": 1024}, "time_since_restore": 71.47419285774231, "iterations_since_restore": 1}
{"loss": 2003.3902054433747, "timestamp": 1719335912, "checkpoint_dir_name": "checkpoint_000001", "should_checkpoint": true, "done": false, "training_iteration": 2, "trial_id": "6be79717", "date": "2024-06-25_19-18-32", "time_this_iter_s": 57.25079274177551, "time_total_s": 128.72498559951782, "pid": 2195253, "hostname": "r8i6n2", "node_ip": "10.159.28.60", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 64, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 8, "drop_rate": 0.7446531774853204, "lr": 0.006000257122673396, "batch_size": 1024}, "time_since_restore": 128.72498559951782, "iterations_since_restore": 2}
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment