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 376 additions and 0 deletions
This diff is collapsed.
File added
File added
{
"batch_size": 1024,
"decoder_int_ff": 512,
"decoder_int_num_layer": 1,
"decoder_rt_ff": 1024,
"decoder_rt_num_layer": 8,
"drop_rate": 0.9904174177662719,
"embedding_dim": 16,
"encoder_ff": 512,
"encoder_num_layer": 4,
"lr": 0.0015488652457456295,
"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
nan,1719523981,checkpoint_000000,True,False,1,04dab8e5,2024-06-27_23-33-01,90.10185432434082,90.10185432434082,242786,r8i6n8,10.159.28.66,90.10185432434082,1
nan,1719524057,checkpoint_000001,True,False,2,04dab8e5,2024-06-27_23-34-17,75.47974467277527,165.5815989971161,242786,r8i6n8,10.159.28.66,165.5815989971161,2
nan,1719524133,checkpoint_000002,True,False,3,04dab8e5,2024-06-27_23-35-33,76.8026487827301,242.3842477798462,242786,r8i6n8,10.159.28.66,242.3842477798462,3
nan,1719524210,checkpoint_000003,True,False,4,04dab8e5,2024-06-27_23-36-50,76.45394325256348,318.83819103240967,242786,r8i6n8,10.159.28.66,318.83819103240967,4
nan,1719524286,checkpoint_000004,True,False,5,04dab8e5,2024-06-27_23-38-06,76.52552080154419,395.36371183395386,242786,r8i6n8,10.159.28.66,395.36371183395386,5
nan,1719524372,checkpoint_000005,True,False,6,04dab8e5,2024-06-27_23-39-32,85.11763429641724,480.4813461303711,242786,r8i6n8,10.159.28.66,480.4813461303711,6
nan,1719524463,checkpoint_000006,True,False,7,04dab8e5,2024-06-27_23-41-03,90.97299361228943,571.4543397426605,242786,r8i6n8,10.159.28.66,571.4543397426605,7
nan,1719524553,checkpoint_000007,True,False,8,04dab8e5,2024-06-27_23-42-33,90.95869708061218,662.4130368232727,242786,r8i6n8,10.159.28.66,662.4130368232727,8
nan,1719524644,checkpoint_000008,True,False,9,04dab8e5,2024-06-27_23-44-04,90.53222966194153,752.9452664852142,242786,r8i6n8,10.159.28.66,752.9452664852142,9
nan,1719524735,checkpoint_000009,True,False,10,04dab8e5,2024-06-27_23-45-35,90.93833804130554,843.8836045265198,242786,r8i6n8,10.159.28.66,843.8836045265198,10
{"loss": NaN, "timestamp": 1719523981, "checkpoint_dir_name": "checkpoint_000000", "should_checkpoint": true, "done": false, "training_iteration": 1, "trial_id": "04dab8e5", "date": "2024-06-27_23-33-01", "time_this_iter_s": 90.10185432434082, "time_total_s": 90.10185432434082, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 4, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 1, "drop_rate": 0.9904174177662719, "lr": 0.0015488652457456295, "batch_size": 1024}, "time_since_restore": 90.10185432434082, "iterations_since_restore": 1}
{"loss": NaN, "timestamp": 1719524057, "checkpoint_dir_name": "checkpoint_000001", "should_checkpoint": true, "done": false, "training_iteration": 2, "trial_id": "04dab8e5", "date": "2024-06-27_23-34-17", "time_this_iter_s": 75.47974467277527, "time_total_s": 165.5815989971161, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 4, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 1, "drop_rate": 0.9904174177662719, "lr": 0.0015488652457456295, "batch_size": 1024}, "time_since_restore": 165.5815989971161, "iterations_since_restore": 2}
{"loss": NaN, "timestamp": 1719524133, "checkpoint_dir_name": "checkpoint_000002", "should_checkpoint": true, "done": false, "training_iteration": 3, "trial_id": "04dab8e5", "date": "2024-06-27_23-35-33", "time_this_iter_s": 76.8026487827301, "time_total_s": 242.3842477798462, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 4, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 1, "drop_rate": 0.9904174177662719, "lr": 0.0015488652457456295, "batch_size": 1024}, "time_since_restore": 242.3842477798462, "iterations_since_restore": 3}
{"loss": NaN, "timestamp": 1719524210, "checkpoint_dir_name": "checkpoint_000003", "should_checkpoint": true, "done": false, "training_iteration": 4, "trial_id": "04dab8e5", "date": "2024-06-27_23-36-50", "time_this_iter_s": 76.45394325256348, "time_total_s": 318.83819103240967, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 4, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 1, "drop_rate": 0.9904174177662719, "lr": 0.0015488652457456295, "batch_size": 1024}, "time_since_restore": 318.83819103240967, "iterations_since_restore": 4}
{"loss": NaN, "timestamp": 1719524286, "checkpoint_dir_name": "checkpoint_000004", "should_checkpoint": true, "done": false, "training_iteration": 5, "trial_id": "04dab8e5", "date": "2024-06-27_23-38-06", "time_this_iter_s": 76.52552080154419, "time_total_s": 395.36371183395386, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 4, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 1, "drop_rate": 0.9904174177662719, "lr": 0.0015488652457456295, "batch_size": 1024}, "time_since_restore": 395.36371183395386, "iterations_since_restore": 5}
{"loss": NaN, "timestamp": 1719524372, "checkpoint_dir_name": "checkpoint_000005", "should_checkpoint": true, "done": false, "training_iteration": 6, "trial_id": "04dab8e5", "date": "2024-06-27_23-39-32", "time_this_iter_s": 85.11763429641724, "time_total_s": 480.4813461303711, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 4, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 1, "drop_rate": 0.9904174177662719, "lr": 0.0015488652457456295, "batch_size": 1024}, "time_since_restore": 480.4813461303711, "iterations_since_restore": 6}
{"loss": NaN, "timestamp": 1719524463, "checkpoint_dir_name": "checkpoint_000006", "should_checkpoint": true, "done": false, "training_iteration": 7, "trial_id": "04dab8e5", "date": "2024-06-27_23-41-03", "time_this_iter_s": 90.97299361228943, "time_total_s": 571.4543397426605, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 4, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 1, "drop_rate": 0.9904174177662719, "lr": 0.0015488652457456295, "batch_size": 1024}, "time_since_restore": 571.4543397426605, "iterations_since_restore": 7}
{"loss": NaN, "timestamp": 1719524553, "checkpoint_dir_name": "checkpoint_000007", "should_checkpoint": true, "done": false, "training_iteration": 8, "trial_id": "04dab8e5", "date": "2024-06-27_23-42-33", "time_this_iter_s": 90.95869708061218, "time_total_s": 662.4130368232727, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 4, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 1, "drop_rate": 0.9904174177662719, "lr": 0.0015488652457456295, "batch_size": 1024}, "time_since_restore": 662.4130368232727, "iterations_since_restore": 8}
{"loss": NaN, "timestamp": 1719524644, "checkpoint_dir_name": "checkpoint_000008", "should_checkpoint": true, "done": false, "training_iteration": 9, "trial_id": "04dab8e5", "date": "2024-06-27_23-44-04", "time_this_iter_s": 90.53222966194153, "time_total_s": 752.9452664852142, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 4, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 1, "drop_rate": 0.9904174177662719, "lr": 0.0015488652457456295, "batch_size": 1024}, "time_since_restore": 752.9452664852142, "iterations_since_restore": 9}
{"loss": NaN, "timestamp": 1719524735, "checkpoint_dir_name": "checkpoint_000009", "should_checkpoint": true, "done": false, "training_iteration": 10, "trial_id": "04dab8e5", "date": "2024-06-27_23-45-35", "time_this_iter_s": 90.93833804130554, "time_total_s": 843.8836045265198, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 4, "decoder_rt_num_layer": 8, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 512, "decoder_rt_ff": 1024, "decoder_int_ff": 512, "n_head": 1, "drop_rate": 0.9904174177662719, "lr": 0.0015488652457456295, "batch_size": 1024}, "time_since_restore": 843.8836045265198, "iterations_since_restore": 10}
{
"batch_size": 2048,
"decoder_int_ff": 512,
"decoder_int_num_layer": 1,
"decoder_rt_ff": 2048,
"decoder_rt_num_layer": 2,
"drop_rate": 0.7685314783666725,
"embedding_dim": 64,
"encoder_ff": 512,
"encoder_num_layer": 8,
"lr": 0.056339001711097965,
"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
3700.8752076156497,1719551095,checkpoint_000000,True,False,1,08bd9367,2024-06-28_07-04-55,85.83756732940674,85.83756732940674,242786,r8i6n8,10.159.28.66,85.83756732940674,1
2637.508512241634,1719551167,checkpoint_000001,True,False,2,08bd9367,2024-06-28_07-06-07,72.44411158561707,158.2816789150238,242786,r8i6n8,10.159.28.66,158.2816789150238,2
2160.1915196696605,1719551239,checkpoint_000002,True,False,3,08bd9367,2024-06-28_07-07-20,72.27386951446533,230.55554842948914,242786,r8i6n8,10.159.28.66,230.55554842948914,3
2001.967397614727,1719551312,checkpoint_000003,True,False,4,08bd9367,2024-06-28_07-08-32,72.46391272544861,303.01946115493774,242786,r8i6n8,10.159.28.66,303.01946115493774,4
1963.2728338767224,1719551384,checkpoint_000004,True,False,5,08bd9367,2024-06-28_07-09-44,72.46509909629822,375.48456025123596,242786,r8i6n8,10.159.28.66,375.48456025123596,5
1955.7411042461245,1719551457,checkpoint_000005,True,False,6,08bd9367,2024-06-28_07-10-57,72.14350414276123,447.6280643939972,242786,r8i6n8,10.159.28.66,447.6280643939972,6
1954.256914754552,1719551529,checkpoint_000006,True,False,7,08bd9367,2024-06-28_07-12-09,72.5984845161438,520.226548910141,242786,r8i6n8,10.159.28.66,520.226548910141,7
1953.846070297121,1719551602,checkpoint_000007,True,False,8,08bd9367,2024-06-28_07-13-22,72.54622983932495,592.7727787494659,242786,r8i6n8,10.159.28.66,592.7727787494659,8
1954.4387774129552,1719551674,checkpoint_000008,True,False,9,08bd9367,2024-06-28_07-14-34,72.2018780708313,664.9746568202972,242786,r8i6n8,10.159.28.66,664.9746568202972,9
1954.1531540277435,1719551747,checkpoint_000009,True,False,10,08bd9367,2024-06-28_07-15-47,72.91625618934631,737.8909130096436,242786,r8i6n8,10.159.28.66,737.8909130096436,10
{"loss": 3700.8752076156497, "timestamp": 1719551095, "checkpoint_dir_name": "checkpoint_000000", "should_checkpoint": true, "done": false, "training_iteration": 1, "trial_id": "08bd9367", "date": "2024-06-28_07-04-55", "time_this_iter_s": 85.83756732940674, "time_total_s": 85.83756732940674, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 8, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 64, "encoder_ff": 512, "decoder_rt_ff": 2048, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.7685314783666725, "lr": 0.056339001711097965, "batch_size": 2048}, "time_since_restore": 85.83756732940674, "iterations_since_restore": 1}
{"loss": 2637.508512241634, "timestamp": 1719551167, "checkpoint_dir_name": "checkpoint_000001", "should_checkpoint": true, "done": false, "training_iteration": 2, "trial_id": "08bd9367", "date": "2024-06-28_07-06-07", "time_this_iter_s": 72.44411158561707, "time_total_s": 158.2816789150238, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 8, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 64, "encoder_ff": 512, "decoder_rt_ff": 2048, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.7685314783666725, "lr": 0.056339001711097965, "batch_size": 2048}, "time_since_restore": 158.2816789150238, "iterations_since_restore": 2}
{"loss": 2160.1915196696605, "timestamp": 1719551239, "checkpoint_dir_name": "checkpoint_000002", "should_checkpoint": true, "done": false, "training_iteration": 3, "trial_id": "08bd9367", "date": "2024-06-28_07-07-20", "time_this_iter_s": 72.27386951446533, "time_total_s": 230.55554842948914, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 8, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 64, "encoder_ff": 512, "decoder_rt_ff": 2048, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.7685314783666725, "lr": 0.056339001711097965, "batch_size": 2048}, "time_since_restore": 230.55554842948914, "iterations_since_restore": 3}
{"loss": 2001.967397614727, "timestamp": 1719551312, "checkpoint_dir_name": "checkpoint_000003", "should_checkpoint": true, "done": false, "training_iteration": 4, "trial_id": "08bd9367", "date": "2024-06-28_07-08-32", "time_this_iter_s": 72.46391272544861, "time_total_s": 303.01946115493774, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 8, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 64, "encoder_ff": 512, "decoder_rt_ff": 2048, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.7685314783666725, "lr": 0.056339001711097965, "batch_size": 2048}, "time_since_restore": 303.01946115493774, "iterations_since_restore": 4}
{"loss": 1963.2728338767224, "timestamp": 1719551384, "checkpoint_dir_name": "checkpoint_000004", "should_checkpoint": true, "done": false, "training_iteration": 5, "trial_id": "08bd9367", "date": "2024-06-28_07-09-44", "time_this_iter_s": 72.46509909629822, "time_total_s": 375.48456025123596, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 8, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 64, "encoder_ff": 512, "decoder_rt_ff": 2048, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.7685314783666725, "lr": 0.056339001711097965, "batch_size": 2048}, "time_since_restore": 375.48456025123596, "iterations_since_restore": 5}
{"loss": 1955.7411042461245, "timestamp": 1719551457, "checkpoint_dir_name": "checkpoint_000005", "should_checkpoint": true, "done": false, "training_iteration": 6, "trial_id": "08bd9367", "date": "2024-06-28_07-10-57", "time_this_iter_s": 72.14350414276123, "time_total_s": 447.6280643939972, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 8, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 64, "encoder_ff": 512, "decoder_rt_ff": 2048, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.7685314783666725, "lr": 0.056339001711097965, "batch_size": 2048}, "time_since_restore": 447.6280643939972, "iterations_since_restore": 6}
{"loss": 1954.256914754552, "timestamp": 1719551529, "checkpoint_dir_name": "checkpoint_000006", "should_checkpoint": true, "done": false, "training_iteration": 7, "trial_id": "08bd9367", "date": "2024-06-28_07-12-09", "time_this_iter_s": 72.5984845161438, "time_total_s": 520.226548910141, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 8, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 64, "encoder_ff": 512, "decoder_rt_ff": 2048, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.7685314783666725, "lr": 0.056339001711097965, "batch_size": 2048}, "time_since_restore": 520.226548910141, "iterations_since_restore": 7}
{"loss": 1953.846070297121, "timestamp": 1719551602, "checkpoint_dir_name": "checkpoint_000007", "should_checkpoint": true, "done": false, "training_iteration": 8, "trial_id": "08bd9367", "date": "2024-06-28_07-13-22", "time_this_iter_s": 72.54622983932495, "time_total_s": 592.7727787494659, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 8, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 64, "encoder_ff": 512, "decoder_rt_ff": 2048, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.7685314783666725, "lr": 0.056339001711097965, "batch_size": 2048}, "time_since_restore": 592.7727787494659, "iterations_since_restore": 8}
{"loss": 1954.4387774129552, "timestamp": 1719551674, "checkpoint_dir_name": "checkpoint_000008", "should_checkpoint": true, "done": false, "training_iteration": 9, "trial_id": "08bd9367", "date": "2024-06-28_07-14-34", "time_this_iter_s": 72.2018780708313, "time_total_s": 664.9746568202972, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 8, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 64, "encoder_ff": 512, "decoder_rt_ff": 2048, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.7685314783666725, "lr": 0.056339001711097965, "batch_size": 2048}, "time_since_restore": 664.9746568202972, "iterations_since_restore": 9}
{"loss": 1954.1531540277435, "timestamp": 1719551747, "checkpoint_dir_name": "checkpoint_000009", "should_checkpoint": true, "done": false, "training_iteration": 10, "trial_id": "08bd9367", "date": "2024-06-28_07-15-47", "time_this_iter_s": 72.91625618934631, "time_total_s": 737.8909130096436, "pid": 242786, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 8, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 64, "encoder_ff": 512, "decoder_rt_ff": 2048, "decoder_int_ff": 512, "n_head": 4, "drop_rate": 0.7685314783666725, "lr": 0.056339001711097965, "batch_size": 2048}, "time_since_restore": 737.8909130096436, "iterations_since_restore": 10}
{
"batch_size": 2048,
"decoder_int_ff": 512,
"decoder_int_num_layer": 1,
"decoder_rt_ff": 512,
"decoder_rt_num_layer": 2,
"drop_rate": 0.9176352757258278,
"embedding_dim": 256,
"encoder_ff": 2048,
"encoder_num_layer": 8,
"lr": 0.014441526763377911,
"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
2470.2349593996064,1719493562,checkpoint_000000,True,False,1,09d4c8af,2024-06-27_15-06-02,230.70093512535095,230.70093512535095,69992,r8i6n8,10.159.28.66,230.70093512535095,1
{"loss": 2470.2349593996064, "timestamp": 1719493562, "checkpoint_dir_name": "checkpoint_000000", "should_checkpoint": true, "done": false, "training_iteration": 1, "trial_id": "09d4c8af", "date": "2024-06-27_15-06-02", "time_this_iter_s": 230.70093512535095, "time_total_s": 230.70093512535095, "pid": 69992, "hostname": "r8i6n8", "node_ip": "10.159.28.66", "config": {"encoder_num_layer": 8, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 256, "encoder_ff": 2048, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 8, "drop_rate": 0.9176352757258278, "lr": 0.014441526763377911, "batch_size": 2048}, "time_since_restore": 230.70093512535095, "iterations_since_restore": 1}
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