Skip to content
Snippets Groups Projects
Commit 915e419e authored by Léo Schneider's avatar Léo Schneider Committed by Schneider Leo
Browse files

res

parent a790c5c2
No related branches found
No related tags found
No related merge requests found
Showing
with 122 additions and 0 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
4868.725482129676,1719491306,checkpoint_000000,True,False,1,46437290,2024-06-27_14-28-26,398.2001099586487,398.2001099586487,35196,r8i6n8,10.159.28.66,398.2001099586487,1
{"loss": 4868.725482129676, "timestamp": 1719491306, "checkpoint_dir_name": "checkpoint_000000", "should_checkpoint": true, "done": false, "training_iteration": 1, "trial_id": "46437290", "date": "2024-06-27_14-28-26", "time_this_iter_s": 398.2001099586487, "time_total_s": 398.2001099586487, "pid": 35196, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 4, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 512, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 1, "drop_rate": 0.701917375344629, "lr": 0.07215703780021865, "batch_size": 1024}, "time_since_restore": 398.2001099586487, "iterations_since_restore": 1}
{
"batch_size": 1024,
"decoder_int_ff": 512,
"decoder_int_num_layer": 1,
"decoder_rt_ff": 1024,
"decoder_rt_num_layer": 1,
"drop_rate": 0.5276525795479664,
"embedding_dim": 1024,
"encoder_ff": 512,
"encoder_num_layer": 1,
"lr": 0.018787488390354802,
"n_head": 16
}
\ 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
2563.930910125492,1719536463,checkpoint_000000,True,False,1,4fa4a8c6,2024-06-28_03-01-03,200.39984393119812,200.39984393119812,242786,r8i6n8,10.159.28.66,200.39984393119812,1
2529.025635246217,1719536650,checkpoint_000001,True,False,2,4fa4a8c6,2024-06-28_03-04-10,187.0065529346466,387.4063968658447,242786,r8i6n8,10.159.28.66,387.4063968658447,2
2461.8067434716413,1719536837,checkpoint_000002,True,False,3,4fa4a8c6,2024-06-28_03-07-17,187.09328150749207,574.4996783733368,242786,r8i6n8,10.159.28.66,574.4996783733368,3
2404.339845672367,1719537024,checkpoint_000003,True,False,4,4fa4a8c6,2024-06-28_03-10-24,186.51477193832397,761.0144503116608,242786,r8i6n8,10.159.28.66,761.0144503116608,4
2310.48677315299,1719537211,checkpoint_000004,True,False,5,4fa4a8c6,2024-06-28_03-13-31,187.13084053993225,948.145290851593,242786,r8i6n8,10.159.28.66,948.145290851593,5
2235.7468713475023,1719537398,checkpoint_000005,True,False,6,4fa4a8c6,2024-06-28_03-16-38,187.11876249313354,1135.2640533447266,242786,r8i6n8,10.159.28.66,1135.2640533447266,6
2146.1736969234435,1719537585,checkpoint_000006,True,False,7,4fa4a8c6,2024-06-28_03-19-45,187.01839590072632,1322.2824492454529,242786,r8i6n8,10.159.28.66,1322.2824492454529,7
2036.06691615788,1719537772,checkpoint_000007,True,False,8,4fa4a8c6,2024-06-28_03-22-52,186.76070404052734,1509.0431532859802,242786,r8i6n8,10.159.28.66,1509.0431532859802,8
1721.8955308809054,1719537958,checkpoint_000008,True,False,9,4fa4a8c6,2024-06-28_03-25-59,186.67871117591858,1695.7218644618988,242786,r8i6n8,10.159.28.66,1695.7218644618988,9
1612.084331842858,1719538145,checkpoint_000009,True,False,10,4fa4a8c6,2024-06-28_03-29-05,186.78013014793396,1882.5019946098328,242786,r8i6n8,10.159.28.66,1882.5019946098328,10
{"loss": 2563.930910125492, "timestamp": 1719536463, "checkpoint_dir_name": "checkpoint_000000", "should_checkpoint": true, "done": false, "training_iteration": 1, "trial_id": "4fa4a8c6", "date": "2024-06-28_03-01-03", "time_this_iter_s": 200.39984393119812, "time_total_s": 200.39984393119812, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 1, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.5276525795479664, "lr": 0.018787488390354802, "batch_size": 1024}, "time_since_restore": 200.39984393119812, "iterations_since_restore": 1}
{"loss": 2529.025635246217, "timestamp": 1719536650, "checkpoint_dir_name": "checkpoint_000001", "should_checkpoint": true, "done": false, "training_iteration": 2, "trial_id": "4fa4a8c6", "date": "2024-06-28_03-04-10", "time_this_iter_s": 187.0065529346466, "time_total_s": 387.4063968658447, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 1, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.5276525795479664, "lr": 0.018787488390354802, "batch_size": 1024}, "time_since_restore": 387.4063968658447, "iterations_since_restore": 2}
{"loss": 2461.8067434716413, "timestamp": 1719536837, "checkpoint_dir_name": "checkpoint_000002", "should_checkpoint": true, "done": false, "training_iteration": 3, "trial_id": "4fa4a8c6", "date": "2024-06-28_03-07-17", "time_this_iter_s": 187.09328150749207, "time_total_s": 574.4996783733368, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 1, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.5276525795479664, "lr": 0.018787488390354802, "batch_size": 1024}, "time_since_restore": 574.4996783733368, "iterations_since_restore": 3}
{"loss": 2404.339845672367, "timestamp": 1719537024, "checkpoint_dir_name": "checkpoint_000003", "should_checkpoint": true, "done": false, "training_iteration": 4, "trial_id": "4fa4a8c6", "date": "2024-06-28_03-10-24", "time_this_iter_s": 186.51477193832397, "time_total_s": 761.0144503116608, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 1, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.5276525795479664, "lr": 0.018787488390354802, "batch_size": 1024}, "time_since_restore": 761.0144503116608, "iterations_since_restore": 4}
{"loss": 2310.48677315299, "timestamp": 1719537211, "checkpoint_dir_name": "checkpoint_000004", "should_checkpoint": true, "done": false, "training_iteration": 5, "trial_id": "4fa4a8c6", "date": "2024-06-28_03-13-31", "time_this_iter_s": 187.13084053993225, "time_total_s": 948.145290851593, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 1, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.5276525795479664, "lr": 0.018787488390354802, "batch_size": 1024}, "time_since_restore": 948.145290851593, "iterations_since_restore": 5}
{"loss": 2235.7468713475023, "timestamp": 1719537398, "checkpoint_dir_name": "checkpoint_000005", "should_checkpoint": true, "done": false, "training_iteration": 6, "trial_id": "4fa4a8c6", "date": "2024-06-28_03-16-38", "time_this_iter_s": 187.11876249313354, "time_total_s": 1135.2640533447266, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 1, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.5276525795479664, "lr": 0.018787488390354802, "batch_size": 1024}, "time_since_restore": 1135.2640533447266, "iterations_since_restore": 6}
{"loss": 2146.1736969234435, "timestamp": 1719537585, "checkpoint_dir_name": "checkpoint_000006", "should_checkpoint": true, "done": false, "training_iteration": 7, "trial_id": "4fa4a8c6", "date": "2024-06-28_03-19-45", "time_this_iter_s": 187.01839590072632, "time_total_s": 1322.2824492454529, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 1, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.5276525795479664, "lr": 0.018787488390354802, "batch_size": 1024}, "time_since_restore": 1322.2824492454529, "iterations_since_restore": 7}
{"loss": 2036.06691615788, "timestamp": 1719537772, "checkpoint_dir_name": "checkpoint_000007", "should_checkpoint": true, "done": false, "training_iteration": 8, "trial_id": "4fa4a8c6", "date": "2024-06-28_03-22-52", "time_this_iter_s": 186.76070404052734, "time_total_s": 1509.0431532859802, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 1, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.5276525795479664, "lr": 0.018787488390354802, "batch_size": 1024}, "time_since_restore": 1509.0431532859802, "iterations_since_restore": 8}
{"loss": 1721.8955308809054, "timestamp": 1719537958, "checkpoint_dir_name": "checkpoint_000008", "should_checkpoint": true, "done": false, "training_iteration": 9, "trial_id": "4fa4a8c6", "date": "2024-06-28_03-25-59", "time_this_iter_s": 186.67871117591858, "time_total_s": 1695.7218644618988, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 1, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.5276525795479664, "lr": 0.018787488390354802, "batch_size": 1024}, "time_since_restore": 1695.7218644618988, "iterations_since_restore": 9}
{"loss": 1612.084331842858, "timestamp": 1719538145, "checkpoint_dir_name": "checkpoint_000009", "should_checkpoint": true, "done": false, "training_iteration": 10, "trial_id": "4fa4a8c6", "date": "2024-06-28_03-29-05", "time_this_iter_s": 186.78013014793396, "time_total_s": 1882.5019946098328, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 1, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.5276525795479664, "lr": 0.018787488390354802, "batch_size": 1024}, "time_since_restore": 1882.5019946098328, "iterations_since_restore": 10}
{
"batch_size": 1024,
"decoder_int_ff": 512,
"decoder_int_num_layer": 1,
"decoder_rt_ff": 1024,
"decoder_rt_num_layer": 4,
"drop_rate": 0.7819934077823693,
"embedding_dim": 256,
"encoder_ff": 512,
"encoder_num_layer": 4,
"lr": 0.00395752526712301,
"n_head": 1
}
\ 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
2042.3615145946112,1719499294,checkpoint_000000,True,False,1,52268eca,2024-06-27_16-41-34,132.02876591682434,132.02876591682434,242786,r8i6n8,10.159.28.66,132.02876591682434,1
2037.3184742364358,1719499413,checkpoint_000001,True,False,2,52268eca,2024-06-27_16-43-33,118.6520447731018,250.68081068992615,242786,r8i6n8,10.159.28.66,250.68081068992615,2
{"loss": 2042.3615145946112, "timestamp": 1719499294, "checkpoint_dir_name": "checkpoint_000000", "should_checkpoint": true, "done": false, "training_iteration": 1, "trial_id": "52268eca", "date": "2024-06-27_16-41-34", "time_this_iter_s": 132.02876591682434, "time_total_s": 132.02876591682434, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 4, "decoder_rt_num_layer": 4, "decoder_int_num_layer": 1, "embedding_dim": 256, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 1, "drop_rate": 0.7819934077823693, "lr": 0.00395752526712301, "batch_size": 1024}, "time_since_restore": 132.02876591682434, "iterations_since_restore": 1}
{"loss": 2037.3184742364358, "timestamp": 1719499413, "checkpoint_dir_name": "checkpoint_000001", "should_checkpoint": true, "done": false, "training_iteration": 2, "trial_id": "52268eca", "date": "2024-06-27_16-43-33", "time_this_iter_s": 118.6520447731018, "time_total_s": 250.68081068992615, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 4, "decoder_rt_num_layer": 4, "decoder_int_num_layer": 1, "embedding_dim": 256, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 1, "drop_rate": 0.7819934077823693, "lr": 0.00395752526712301, "batch_size": 1024}, "time_since_restore": 250.68081068992615, "iterations_since_restore": 2}
{
"batch_size": 2048,
"decoder_int_ff": 512,
"decoder_int_num_layer": 1,
"decoder_rt_ff": 1024,
"decoder_rt_num_layer": 8,
"drop_rate": 0.049405145459166966,
"embedding_dim": 16,
"encoder_ff": 2048,
"encoder_num_layer": 2,
"lr": 0.0917460389036109,
"n_head": 2
}
\ 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
1963.1659531480684,1719518209,checkpoint_000000,True,False,1,5436b378,2024-06-27_21-56-49,81.73000359535217,81.73000359535217,242786,r8i6n8,10.159.28.66,81.73000359535217,1
1991.797592042938,1719518277,checkpoint_000001,True,False,2,5436b378,2024-06-27_21-57-57,68.002121925354,149.73212552070618,242786,r8i6n8,10.159.28.66,149.73212552070618,2
1962.9070631612942,1719518345,checkpoint_000002,True,False,3,5436b378,2024-06-27_21-59-05,68.36926174163818,218.10138726234436,242786,r8i6n8,10.159.28.66,218.10138726234436,3
1963.723276213398,1719518413,checkpoint_000003,True,False,4,5436b378,2024-06-27_22-00-13,68.3394775390625,286.44086480140686,242786,r8i6n8,10.159.28.66,286.44086480140686,4
1964.6577398345225,1719518481,checkpoint_000004,True,False,5,5436b378,2024-06-27_22-01-21,67.95102214813232,354.3918869495392,242786,r8i6n8,10.159.28.66,354.3918869495392,5
1963.233094703494,1719518550,checkpoint_000005,True,False,6,5436b378,2024-06-27_22-02-30,68.2700297832489,422.6619167327881,242786,r8i6n8,10.159.28.66,422.6619167327881,6
1998.2474076879307,1719518618,checkpoint_000006,True,False,7,5436b378,2024-06-27_22-03-38,67.93067574501038,490.59259247779846,242786,r8i6n8,10.159.28.66,490.59259247779846,7
1966.4671976885459,1719518686,checkpoint_000007,True,False,8,5436b378,2024-06-27_22-04-46,68.20492196083069,558.7975144386292,242786,r8i6n8,10.159.28.66,558.7975144386292,8
1997.90943055641,1719518754,checkpoint_000008,True,False,9,5436b378,2024-06-27_22-05-54,68.2099084854126,627.0074229240417,242786,r8i6n8,10.159.28.66,627.0074229240417,9
1964.396376722441,1719518822,checkpoint_000009,True,False,10,5436b378,2024-06-27_22-07-02,67.73129034042358,694.7387132644653,242786,r8i6n8,10.159.28.66,694.7387132644653,10
1971.7665900282973,1719520288,checkpoint_000010,True,False,11,5436b378,2024-06-27_22-31-28,81.72813010215759,776.4668433666229,242786,r8i6n8,10.159.28.66,81.72813010215759,1
1962.3812928687869,1719520357,checkpoint_000011,True,False,12,5436b378,2024-06-27_22-32-37,68.32595419883728,844.7927975654602,242786,r8i6n8,10.159.28.66,150.05408430099487,2
1961.6378394900344,1719520425,checkpoint_000012,True,False,13,5436b378,2024-06-27_22-33-45,67.94392895698547,912.7367265224457,242786,r8i6n8,10.159.28.66,217.99801325798035,3
1963.4142201341044,1719520493,checkpoint_000013,True,False,14,5436b378,2024-06-27_22-34-53,68.2390410900116,980.9757676124573,242786,r8i6n8,10.159.28.66,286.23705434799194,4
1974.0520605853224,1719520561,checkpoint_000014,True,False,15,5436b378,2024-06-27_22-36-01,68.27515816688538,1049.2509257793427,242786,r8i6n8,10.159.28.66,354.5122125148773,5
1966.7488004429133,1719520630,checkpoint_000015,True,False,16,5436b378,2024-06-27_22-37-10,68.31270408630371,1117.5636298656464,242786,r8i6n8,10.159.28.66,422.82491660118103,6
1962.6332181194637,1719520698,checkpoint_000016,True,False,17,5436b378,2024-06-27_22-38-18,67.964919090271,1185.5285489559174,242786,r8i6n8,10.159.28.66,490.789835691452,7
1953.7692371278297,1719520766,checkpoint_000017,True,False,18,5436b378,2024-06-27_22-39-26,68.35524988174438,1253.8837988376617,242786,r8i6n8,10.159.28.66,559.1450855731964,8
1954.2639188991757,1719520834,checkpoint_000018,True,False,19,5436b378,2024-06-27_22-40-34,68.39789581298828,1322.28169465065,242786,r8i6n8,10.159.28.66,627.5429813861847,9
1954.128303587906,1719520903,checkpoint_000019,True,False,20,5436b378,2024-06-27_22-41-43,68.36882543563843,1390.6505200862885,242786,r8i6n8,10.159.28.66,695.9118068218231,10
{"loss": 1963.1659531480684, "timestamp": 1719518209, "checkpoint_dir_name": "checkpoint_000000", "should_checkpoint": true, "done": false, "training_iteration": 1, "trial_id": "5436b378", "date": "2024-06-27_21-56-49", "time_this_iter_s": 81.73000359535217, "time_total_s": 81.73000359535217, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 81.73000359535217, "iterations_since_restore": 1}
{"loss": 1991.797592042938, "timestamp": 1719518277, "checkpoint_dir_name": "checkpoint_000001", "should_checkpoint": true, "done": false, "training_iteration": 2, "trial_id": "5436b378", "date": "2024-06-27_21-57-57", "time_this_iter_s": 68.002121925354, "time_total_s": 149.73212552070618, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 149.73212552070618, "iterations_since_restore": 2}
{"loss": 1962.9070631612942, "timestamp": 1719518345, "checkpoint_dir_name": "checkpoint_000002", "should_checkpoint": true, "done": false, "training_iteration": 3, "trial_id": "5436b378", "date": "2024-06-27_21-59-05", "time_this_iter_s": 68.36926174163818, "time_total_s": 218.10138726234436, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 218.10138726234436, "iterations_since_restore": 3}
{"loss": 1963.723276213398, "timestamp": 1719518413, "checkpoint_dir_name": "checkpoint_000003", "should_checkpoint": true, "done": false, "training_iteration": 4, "trial_id": "5436b378", "date": "2024-06-27_22-00-13", "time_this_iter_s": 68.3394775390625, "time_total_s": 286.44086480140686, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 286.44086480140686, "iterations_since_restore": 4}
{"loss": 1964.6577398345225, "timestamp": 1719518481, "checkpoint_dir_name": "checkpoint_000004", "should_checkpoint": true, "done": false, "training_iteration": 5, "trial_id": "5436b378", "date": "2024-06-27_22-01-21", "time_this_iter_s": 67.95102214813232, "time_total_s": 354.3918869495392, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 354.3918869495392, "iterations_since_restore": 5}
{"loss": 1963.233094703494, "timestamp": 1719518550, "checkpoint_dir_name": "checkpoint_000005", "should_checkpoint": true, "done": false, "training_iteration": 6, "trial_id": "5436b378", "date": "2024-06-27_22-02-30", "time_this_iter_s": 68.2700297832489, "time_total_s": 422.6619167327881, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 422.6619167327881, "iterations_since_restore": 6}
{"loss": 1998.2474076879307, "timestamp": 1719518618, "checkpoint_dir_name": "checkpoint_000006", "should_checkpoint": true, "done": false, "training_iteration": 7, "trial_id": "5436b378", "date": "2024-06-27_22-03-38", "time_this_iter_s": 67.93067574501038, "time_total_s": 490.59259247779846, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 490.59259247779846, "iterations_since_restore": 7}
{"loss": 1966.4671976885459, "timestamp": 1719518686, "checkpoint_dir_name": "checkpoint_000007", "should_checkpoint": true, "done": false, "training_iteration": 8, "trial_id": "5436b378", "date": "2024-06-27_22-04-46", "time_this_iter_s": 68.20492196083069, "time_total_s": 558.7975144386292, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 558.7975144386292, "iterations_since_restore": 8}
{"loss": 1997.90943055641, "timestamp": 1719518754, "checkpoint_dir_name": "checkpoint_000008", "should_checkpoint": true, "done": false, "training_iteration": 9, "trial_id": "5436b378", "date": "2024-06-27_22-05-54", "time_this_iter_s": 68.2099084854126, "time_total_s": 627.0074229240417, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 627.0074229240417, "iterations_since_restore": 9}
{"loss": 1964.396376722441, "timestamp": 1719518822, "checkpoint_dir_name": "checkpoint_000009", "should_checkpoint": true, "done": false, "training_iteration": 10, "trial_id": "5436b378", "date": "2024-06-27_22-07-02", "time_this_iter_s": 67.73129034042358, "time_total_s": 694.7387132644653, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 694.7387132644653, "iterations_since_restore": 10}
{"loss": 1971.7665900282973, "timestamp": 1719520288, "checkpoint_dir_name": "checkpoint_000010", "should_checkpoint": true, "done": false, "training_iteration": 11, "trial_id": "5436b378", "date": "2024-06-27_22-31-28", "time_this_iter_s": 81.72813010215759, "time_total_s": 776.4668433666229, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 81.72813010215759, "iterations_since_restore": 1}
{"loss": 1962.3812928687869, "timestamp": 1719520357, "checkpoint_dir_name": "checkpoint_000011", "should_checkpoint": true, "done": false, "training_iteration": 12, "trial_id": "5436b378", "date": "2024-06-27_22-32-37", "time_this_iter_s": 68.32595419883728, "time_total_s": 844.7927975654602, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 150.05408430099487, "iterations_since_restore": 2}
{"loss": 1961.6378394900344, "timestamp": 1719520425, "checkpoint_dir_name": "checkpoint_000012", "should_checkpoint": true, "done": false, "training_iteration": 13, "trial_id": "5436b378", "date": "2024-06-27_22-33-45", "time_this_iter_s": 67.94392895698547, "time_total_s": 912.7367265224457, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 217.99801325798035, "iterations_since_restore": 3}
{"loss": 1963.4142201341044, "timestamp": 1719520493, "checkpoint_dir_name": "checkpoint_000013", "should_checkpoint": true, "done": false, "training_iteration": 14, "trial_id": "5436b378", "date": "2024-06-27_22-34-53", "time_this_iter_s": 68.2390410900116, "time_total_s": 980.9757676124573, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 286.23705434799194, "iterations_since_restore": 4}
{"loss": 1974.0520605853224, "timestamp": 1719520561, "checkpoint_dir_name": "checkpoint_000014", "should_checkpoint": true, "done": false, "training_iteration": 15, "trial_id": "5436b378", "date": "2024-06-27_22-36-01", "time_this_iter_s": 68.27515816688538, "time_total_s": 1049.2509257793427, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 354.5122125148773, "iterations_since_restore": 5}
{"loss": 1966.7488004429133, "timestamp": 1719520630, "checkpoint_dir_name": "checkpoint_000015", "should_checkpoint": true, "done": false, "training_iteration": 16, "trial_id": "5436b378", "date": "2024-06-27_22-37-10", "time_this_iter_s": 68.31270408630371, "time_total_s": 1117.5636298656464, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 422.82491660118103, "iterations_since_restore": 6}
{"loss": 1962.6332181194637, "timestamp": 1719520698, "checkpoint_dir_name": "checkpoint_000016", "should_checkpoint": true, "done": false, "training_iteration": 17, "trial_id": "5436b378", "date": "2024-06-27_22-38-18", "time_this_iter_s": 67.964919090271, "time_total_s": 1185.5285489559174, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 490.789835691452, "iterations_since_restore": 7}
{"loss": 1953.7692371278297, "timestamp": 1719520766, "checkpoint_dir_name": "checkpoint_000017", "should_checkpoint": true, "done": false, "training_iteration": 18, "trial_id": "5436b378", "date": "2024-06-27_22-39-26", "time_this_iter_s": 68.35524988174438, "time_total_s": 1253.8837988376617, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 559.1450855731964, "iterations_since_restore": 8}
{"loss": 1954.2639188991757, "timestamp": 1719520834, "checkpoint_dir_name": "checkpoint_000018", "should_checkpoint": true, "done": false, "training_iteration": 19, "trial_id": "5436b378", "date": "2024-06-27_22-40-34", "time_this_iter_s": 68.39789581298828, "time_total_s": 1322.28169465065, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 627.5429813861847, "iterations_since_restore": 9}
{"loss": 1954.128303587906, "timestamp": 1719520903, "checkpoint_dir_name": "checkpoint_000019", "should_checkpoint": true, "done": false, "training_iteration": 20, "trial_id": "5436b378", "date": "2024-06-27_22-41-43", "time_this_iter_s": 68.36882543563843, "time_total_s": 1390.6505200862885, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 2048, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 2, "drop_rate": 0.049405145459166966, "lr": 0.0917460389036109, "batch_size": 2048}, "time_since_restore": 695.9118068218231, "iterations_since_restore": 10}
{
"batch_size": 1024,
"decoder_int_ff": 512,
"decoder_int_num_layer": 1,
"decoder_rt_ff": 2048,
"decoder_rt_num_layer": 8,
"drop_rate": 0.3048722403961074,
"embedding_dim": 16,
"encoder_ff": 2048,
"encoder_num_layer": 4,
"lr": 0.0003667007874849629,
"n_head": 2
}
\ No newline at end of file
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