Skip to content
Snippets Groups Projects
Commit a790c5c2 authored by Léo Schneider's avatar Léo Schneider Committed by Schneider Leo
Browse files

res

parent efd6839c
No related branches found
No related tags found
No related merge requests found
Showing
with 386 additions and 0 deletions
This diff is collapsed.
source diff could not be displayed: it is too large. Options to address this: view the blob.
This diff is collapsed.
File added
File added
File added
File added
File added
File added
{
"batch_size": 2048,
"decoder_int_ff": 512,
"decoder_int_num_layer": 1,
"decoder_rt_ff": 512,
"decoder_rt_num_layer": 4,
"drop_rate": 0.18759871111111892,
"embedding_dim": 16,
"encoder_ff": 1024,
"encoder_num_layer": 1,
"lr": 0.02750689103642202,
"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
2019.4176592488927,1719329610,checkpoint_000000,True,False,1,040fcf09,2024-06-25_17-33-30,65.59718012809753,65.59718012809753,2195253,r8i6n2,10.159.28.60,65.59718012809753,1
{"loss": 2019.4176592488927, "timestamp": 1719329610, "checkpoint_dir_name": "checkpoint_000000", "should_checkpoint": true, "done": false, "training_iteration": 1, "trial_id": "040fcf09", "date": "2024-06-25_17-33-30", "time_this_iter_s": 65.59718012809753, "time_total_s": 65.59718012809753, "pid": 2195253, "hostname": "r8i6n2", "node_ip": "10.159.28.60", "config": {"encoder_num_layer": 1, "decoder_rt_num_layer": 4, "decoder_int_num_layer": 1, "embedding_dim": 16, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 1, "drop_rate": 0.18759871111111892, "lr": 0.02750689103642202, "batch_size": 2048}, "time_since_restore": 65.59718012809753, "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": 0.023920599186226577,
"embedding_dim": 1024,
"encoder_ff": 1024,
"encoder_num_layer": 2,
"lr": 0.0024687399238039302,
"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
1986.2198524775467,1719348983,checkpoint_000000,True,False,1,0f80a6d7,2024-06-25_22-56-24,363.18635082244873,363.18635082244873,2195253,r8i6n2,10.159.28.60,363.18635082244873,1
1979.5493135226993,1719349334,checkpoint_000001,True,False,2,0f80a6d7,2024-06-25_23-02-14,350.295019865036,713.4813706874847,2195253,r8i6n2,10.159.28.60,713.4813706874847,2
1964.9348182978592,1719349683,checkpoint_000002,True,False,3,0f80a6d7,2024-06-25_23-08-04,349.6246259212494,1063.1059966087341,2195253,r8i6n2,10.159.28.60,1063.1059966087341,3
1955.6751497523992,1719350034,checkpoint_000003,True,False,4,0f80a6d7,2024-06-25_23-13-54,350.46285796165466,1413.5688545703888,2195253,r8i6n2,10.159.28.60,1413.5688545703888,4
1956.1783514548474,1719350384,checkpoint_000004,True,False,5,0f80a6d7,2024-06-25_23-19-44,350.18478202819824,1763.753636598587,2195253,r8i6n2,10.159.28.60,1763.753636598587,5
1971.8988527312993,1719355866,checkpoint_000005,True,False,6,0f80a6d7,2024-06-26_00-51-07,365.2865264415741,2129.040163040161,2850562,r8i6n2,10.159.28.60,365.2865264415741,1
1955.6729476808564,1719356216,checkpoint_000006,True,False,7,0f80a6d7,2024-06-26_00-56-56,349.18421268463135,2478.2243757247925,2850562,r8i6n2,10.159.28.60,714.4707391262054,2
1957.4972913847196,1719356565,checkpoint_000007,True,False,8,0f80a6d7,2024-06-26_01-02-46,349.7124717235565,2827.936847448349,2850562,r8i6n2,10.159.28.60,1064.183210849762,3
1967.2758471871923,1719356915,checkpoint_000008,True,False,9,0f80a6d7,2024-06-26_01-08-35,349.3587329387665,3177.2955803871155,2850562,r8i6n2,10.159.28.60,1413.5419437885284,4
1959.91755063515,1719357265,checkpoint_000009,True,True,10,0f80a6d7,2024-06-26_01-14-25,349.87603521347046,3527.171615600586,2850562,r8i6n2,10.159.28.60,1763.417979001999,5
{"loss": 1986.2198524775467, "timestamp": 1719348983, "checkpoint_dir_name": "checkpoint_000000", "should_checkpoint": true, "done": false, "training_iteration": 1, "trial_id": "0f80a6d7", "date": "2024-06-25_22-56-24", "time_this_iter_s": 363.18635082244873, "time_total_s": 363.18635082244873, "pid": 2195253, "hostname": "r8i6n2", "node_ip": "10.159.28.60", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.023920599186226577, "lr": 0.0024687399238039302, "batch_size": 2048}, "time_since_restore": 363.18635082244873, "iterations_since_restore": 1}
{"loss": 1979.5493135226993, "timestamp": 1719349334, "checkpoint_dir_name": "checkpoint_000001", "should_checkpoint": true, "done": false, "training_iteration": 2, "trial_id": "0f80a6d7", "date": "2024-06-25_23-02-14", "time_this_iter_s": 350.295019865036, "time_total_s": 713.4813706874847, "pid": 2195253, "hostname": "r8i6n2", "node_ip": "10.159.28.60", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.023920599186226577, "lr": 0.0024687399238039302, "batch_size": 2048}, "time_since_restore": 713.4813706874847, "iterations_since_restore": 2}
{"loss": 1964.9348182978592, "timestamp": 1719349683, "checkpoint_dir_name": "checkpoint_000002", "should_checkpoint": true, "done": false, "training_iteration": 3, "trial_id": "0f80a6d7", "date": "2024-06-25_23-08-04", "time_this_iter_s": 349.6246259212494, "time_total_s": 1063.1059966087341, "pid": 2195253, "hostname": "r8i6n2", "node_ip": "10.159.28.60", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.023920599186226577, "lr": 0.0024687399238039302, "batch_size": 2048}, "time_since_restore": 1063.1059966087341, "iterations_since_restore": 3}
{"loss": 1955.6751497523992, "timestamp": 1719350034, "checkpoint_dir_name": "checkpoint_000003", "should_checkpoint": true, "done": false, "training_iteration": 4, "trial_id": "0f80a6d7", "date": "2024-06-25_23-13-54", "time_this_iter_s": 350.46285796165466, "time_total_s": 1413.5688545703888, "pid": 2195253, "hostname": "r8i6n2", "node_ip": "10.159.28.60", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.023920599186226577, "lr": 0.0024687399238039302, "batch_size": 2048}, "time_since_restore": 1413.5688545703888, "iterations_since_restore": 4}
{"loss": 1956.1783514548474, "timestamp": 1719350384, "checkpoint_dir_name": "checkpoint_000004", "should_checkpoint": true, "done": false, "training_iteration": 5, "trial_id": "0f80a6d7", "date": "2024-06-25_23-19-44", "time_this_iter_s": 350.18478202819824, "time_total_s": 1763.753636598587, "pid": 2195253, "hostname": "r8i6n2", "node_ip": "10.159.28.60", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.023920599186226577, "lr": 0.0024687399238039302, "batch_size": 2048}, "time_since_restore": 1763.753636598587, "iterations_since_restore": 5}
{"loss": 1971.8988527312993, "timestamp": 1719355866, "checkpoint_dir_name": "checkpoint_000005", "should_checkpoint": true, "done": false, "training_iteration": 6, "trial_id": "0f80a6d7", "date": "2024-06-26_00-51-07", "time_this_iter_s": 365.2865264415741, "time_total_s": 2129.040163040161, "pid": 2850562, "hostname": "r8i6n2", "node_ip": "10.159.28.60", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.023920599186226577, "lr": 0.0024687399238039302, "batch_size": 2048}, "time_since_restore": 365.2865264415741, "iterations_since_restore": 1}
{"loss": 1955.6729476808564, "timestamp": 1719356216, "checkpoint_dir_name": "checkpoint_000006", "should_checkpoint": true, "done": false, "training_iteration": 7, "trial_id": "0f80a6d7", "date": "2024-06-26_00-56-56", "time_this_iter_s": 349.18421268463135, "time_total_s": 2478.2243757247925, "pid": 2850562, "hostname": "r8i6n2", "node_ip": "10.159.28.60", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.023920599186226577, "lr": 0.0024687399238039302, "batch_size": 2048}, "time_since_restore": 714.4707391262054, "iterations_since_restore": 2}
{"loss": 1957.4972913847196, "timestamp": 1719356565, "checkpoint_dir_name": "checkpoint_000007", "should_checkpoint": true, "done": false, "training_iteration": 8, "trial_id": "0f80a6d7", "date": "2024-06-26_01-02-46", "time_this_iter_s": 349.7124717235565, "time_total_s": 2827.936847448349, "pid": 2850562, "hostname": "r8i6n2", "node_ip": "10.159.28.60", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.023920599186226577, "lr": 0.0024687399238039302, "batch_size": 2048}, "time_since_restore": 1064.183210849762, "iterations_since_restore": 3}
{"loss": 1967.2758471871923, "timestamp": 1719356915, "checkpoint_dir_name": "checkpoint_000008", "should_checkpoint": true, "done": false, "training_iteration": 9, "trial_id": "0f80a6d7", "date": "2024-06-26_01-08-35", "time_this_iter_s": 349.3587329387665, "time_total_s": 3177.2955803871155, "pid": 2850562, "hostname": "r8i6n2", "node_ip": "10.159.28.60", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.023920599186226577, "lr": 0.0024687399238039302, "batch_size": 2048}, "time_since_restore": 1413.5419437885284, "iterations_since_restore": 4}
{"loss": 1959.91755063515, "timestamp": 1719357265, "checkpoint_dir_name": "checkpoint_000009", "should_checkpoint": true, "done": true, "training_iteration": 10, "trial_id": "0f80a6d7", "date": "2024-06-26_01-14-25", "time_this_iter_s": 349.87603521347046, "time_total_s": 3527.171615600586, "pid": 2850562, "hostname": "r8i6n2", "node_ip": "10.159.28.60", "config": {"encoder_num_layer": 2, "decoder_rt_num_layer": 2, "decoder_int_num_layer": 1, "embedding_dim": 1024, "encoder_ff": 1024, "decoder_rt_ff": 512, "decoder_int_ff": 512, "n_head": 16, "drop_rate": 0.023920599186226577, "lr": 0.0024687399238039302, "batch_size": 2048}, "time_since_restore": 1763.417979001999, "iterations_since_restore": 5}
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