3N3G commited on
Commit
e97e491
·
verified ·
1 Parent(s): 4849640

Training in progress, step 352

Browse files
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbb5a892c7bcd146f6eee0ac485a21efd55a8ffbc4d42c3ed0640fc44f041c63
3
  size 4969539560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:096439a15e0b06aee20e3753c9fc04b16d480adc998310ef78cc635894ce0439
3
  size 4969539560
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f51a049f43d70a0eb667a892f9ae752e6fde71c884bf47a93a4de8f13fcb645
3
  size 1912795688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baf6e5b35338a330f50e7e5f5405f807ca31d11aeffe1893d6a171ddc95e8f71
3
  size 1912795688
trainer_log.jsonl CHANGED
@@ -832,3 +832,37 @@
832
  {"current_steps": 335, "total_steps": 400, "loss": 0.7323, "lr": 1.7259824442455922e-08, "epoch": 83.87272727272727, "percentage": 83.75, "elapsed_time": "0:40:48", "remaining_time": "0:07:55"}
833
  {"current_steps": 336, "total_steps": 400, "loss": 0.6316, "lr": 1.704738493842015e-08, "epoch": 84.0, "percentage": 84.0, "elapsed_time": "0:40:51", "remaining_time": "0:07:47"}
834
  {"current_steps": 336, "total_steps": 400, "eval_loss": 0.6387331485748291, "epoch": 84.0, "percentage": 84.0, "elapsed_time": "0:40:52", "remaining_time": "0:07:47"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
832
  {"current_steps": 335, "total_steps": 400, "loss": 0.7323, "lr": 1.7259824442455922e-08, "epoch": 83.87272727272727, "percentage": 83.75, "elapsed_time": "0:40:48", "remaining_time": "0:07:55"}
833
  {"current_steps": 336, "total_steps": 400, "loss": 0.6316, "lr": 1.704738493842015e-08, "epoch": 84.0, "percentage": 84.0, "elapsed_time": "0:40:51", "remaining_time": "0:07:47"}
834
  {"current_steps": 336, "total_steps": 400, "eval_loss": 0.6387331485748291, "epoch": 84.0, "percentage": 84.0, "elapsed_time": "0:40:52", "remaining_time": "0:07:47"}
835
+ {"current_steps": 337, "total_steps": 400, "loss": 0.6576, "lr": 1.6837835672960833e-08, "epoch": 84.2909090909091, "percentage": 84.25, "elapsed_time": "0:41:17", "remaining_time": "0:07:43"}
836
+ {"current_steps": 338, "total_steps": 400, "loss": 0.6216, "lr": 1.663119260406585e-08, "epoch": 84.58181818181818, "percentage": 84.5, "elapsed_time": "0:41:24", "remaining_time": "0:07:35"}
837
+ {"current_steps": 339, "total_steps": 400, "loss": 0.6975, "lr": 1.642747146840495e-08, "epoch": 84.87272727272727, "percentage": 84.75, "elapsed_time": "0:41:31", "remaining_time": "0:07:28"}
838
+ {"current_steps": 340, "total_steps": 400, "loss": 0.6022, "lr": 1.6226687780131337e-08, "epoch": 85.0, "percentage": 85.0, "elapsed_time": "0:41:34", "remaining_time": "0:07:20"}
839
+ {"current_steps": 341, "total_steps": 400, "loss": 0.6316, "lr": 1.602885682970026e-08, "epoch": 85.2909090909091, "percentage": 85.25, "elapsed_time": "0:41:41", "remaining_time": "0:07:12"}
840
+ {"current_steps": 342, "total_steps": 400, "loss": 0.6725, "lr": 1.5833993682704515e-08, "epoch": 85.58181818181818, "percentage": 85.5, "elapsed_time": "0:41:47", "remaining_time": "0:07:05"}
841
+ {"current_steps": 343, "total_steps": 400, "loss": 0.6319, "lr": 1.5642113178727193e-08, "epoch": 85.87272727272727, "percentage": 85.75, "elapsed_time": "0:41:54", "remaining_time": "0:06:57"}
842
+ {"current_steps": 344, "total_steps": 400, "loss": 0.72, "lr": 1.5453229930211566e-08, "epoch": 86.0, "percentage": 86.0, "elapsed_time": "0:41:57", "remaining_time": "0:06:49"}
843
+ {"current_steps": 345, "total_steps": 400, "loss": 0.7343, "lr": 1.5267358321348288e-08, "epoch": 86.2909090909091, "percentage": 86.25, "elapsed_time": "0:42:04", "remaining_time": "0:06:42"}
844
+ {"current_steps": 346, "total_steps": 400, "loss": 0.6112, "lr": 1.5084512506980025e-08, "epoch": 86.58181818181818, "percentage": 86.5, "elapsed_time": "0:42:11", "remaining_time": "0:06:35"}
845
+ {"current_steps": 347, "total_steps": 400, "loss": 0.6377, "lr": 1.490470641152345e-08, "epoch": 86.87272727272727, "percentage": 86.75, "elapsed_time": "0:42:17", "remaining_time": "0:06:27"}
846
+ {"current_steps": 348, "total_steps": 400, "loss": 0.603, "lr": 1.4727953727908877e-08, "epoch": 87.0, "percentage": 87.0, "elapsed_time": "0:42:20", "remaining_time": "0:06:19"}
847
+ {"current_steps": 349, "total_steps": 400, "loss": 0.6832, "lr": 1.4554267916537493e-08, "epoch": 87.2909090909091, "percentage": 87.25, "elapsed_time": "0:42:27", "remaining_time": "0:06:12"}
848
+ {"current_steps": 350, "total_steps": 400, "loss": 0.6086, "lr": 1.438366220425628e-08, "epoch": 87.58181818181818, "percentage": 87.5, "elapsed_time": "0:42:34", "remaining_time": "0:06:04"}
849
+ {"current_steps": 351, "total_steps": 400, "loss": 0.6735, "lr": 1.4216149583350753e-08, "epoch": 87.87272727272727, "percentage": 87.75, "elapsed_time": "0:42:40", "remaining_time": "0:05:57"}
850
+ {"current_steps": 352, "total_steps": 400, "loss": 0.6232, "lr": 1.405174281055556e-08, "epoch": 88.0, "percentage": 88.0, "elapsed_time": "0:42:44", "remaining_time": "0:05:49"}
851
+ {"current_steps": 352, "total_steps": 400, "eval_loss": 0.6380465030670166, "epoch": 88.0, "percentage": 88.0, "elapsed_time": "0:42:44", "remaining_time": "0:05:49"}
852
+ {"current_steps": 353, "total_steps": 400, "loss": 0.6388, "lr": 1.3890454406082957e-08, "epoch": 88.2909090909091, "percentage": 88.25, "elapsed_time": "0:43:14", "remaining_time": "0:05:45"}
853
+ {"current_steps": 354, "total_steps": 400, "loss": 0.6658, "lr": 1.3732296652669417e-08, "epoch": 88.58181818181818, "percentage": 88.5, "elapsed_time": "0:43:21", "remaining_time": "0:05:37"}
854
+ {"current_steps": 355, "total_steps": 400, "loss": 0.6671, "lr": 1.3577281594640182e-08, "epoch": 88.87272727272727, "percentage": 88.75, "elapsed_time": "0:43:28", "remaining_time": "0:05:30"}
855
+ {"current_steps": 356, "total_steps": 400, "loss": 0.6185, "lr": 1.3425421036992096e-08, "epoch": 89.0, "percentage": 89.0, "elapsed_time": "0:43:31", "remaining_time": "0:05:22"}
856
+ {"current_steps": 357, "total_steps": 400, "loss": 0.6648, "lr": 1.327672654449457e-08, "epoch": 89.2909090909091, "percentage": 89.25, "elapsed_time": "0:43:37", "remaining_time": "0:05:15"}
857
+ {"current_steps": 358, "total_steps": 400, "loss": 0.6731, "lr": 1.3131209440808898e-08, "epoch": 89.58181818181818, "percentage": 89.5, "elapsed_time": "0:43:45", "remaining_time": "0:05:08"}
858
+ {"current_steps": 359, "total_steps": 400, "loss": 0.5938, "lr": 1.2988880807625927e-08, "epoch": 89.87272727272727, "percentage": 89.75, "elapsed_time": "0:43:52", "remaining_time": "0:05:00"}
859
+ {"current_steps": 360, "total_steps": 400, "loss": 0.7107, "lr": 1.284975148382211e-08, "epoch": 90.0, "percentage": 90.0, "elapsed_time": "0:43:55", "remaining_time": "0:04:52"}
860
+ {"current_steps": 361, "total_steps": 400, "loss": 0.6798, "lr": 1.2713832064634124e-08, "epoch": 90.2909090909091, "percentage": 90.25, "elapsed_time": "0:44:01", "remaining_time": "0:04:45"}
861
+ {"current_steps": 362, "total_steps": 400, "loss": 0.6249, "lr": 1.2581132900851971e-08, "epoch": 90.58181818181818, "percentage": 90.5, "elapsed_time": "0:44:09", "remaining_time": "0:04:38"}
862
+ {"current_steps": 363, "total_steps": 400, "loss": 0.6616, "lr": 1.2451664098030743e-08, "epoch": 90.87272727272727, "percentage": 90.75, "elapsed_time": "0:44:15", "remaining_time": "0:04:30"}
863
+ {"current_steps": 364, "total_steps": 400, "loss": 0.6418, "lr": 1.232543551572103e-08, "epoch": 91.0, "percentage": 91.0, "elapsed_time": "0:44:18", "remaining_time": "0:04:22"}
864
+ {"current_steps": 365, "total_steps": 400, "loss": 0.707, "lr": 1.2202456766718091e-08, "epoch": 91.2909090909091, "percentage": 91.25, "elapsed_time": "0:44:25", "remaining_time": "0:04:15"}
865
+ {"current_steps": 366, "total_steps": 400, "loss": 0.6083, "lr": 1.2082737216329793e-08, "epoch": 91.58181818181818, "percentage": 91.5, "elapsed_time": "0:44:32", "remaining_time": "0:04:08"}
866
+ {"current_steps": 367, "total_steps": 400, "loss": 0.6327, "lr": 1.1966285981663406e-08, "epoch": 91.87272727272727, "percentage": 91.75, "elapsed_time": "0:44:39", "remaining_time": "0:04:00"}
867
+ {"current_steps": 368, "total_steps": 400, "loss": 0.6545, "lr": 1.1853111930931313e-08, "epoch": 92.0, "percentage": 92.0, "elapsed_time": "0:44:42", "remaining_time": "0:03:53"}
868
+ {"current_steps": 368, "total_steps": 400, "eval_loss": 0.6371535062789917, "epoch": 92.0, "percentage": 92.0, "elapsed_time": "0:44:43", "remaining_time": "0:03:53"}