furmaniak commited on
Commit
df7da37
·
verified ·
1 Parent(s): 923188b

Training in progress, step 500

Browse files
Files changed (2) hide show
  1. trainer_log.jsonl +100 -45
  2. training_args.bin +1 -1
trainer_log.jsonl CHANGED
@@ -1,45 +1,100 @@
1
- {"current_steps": 356, "total_steps": 557, "loss": 1.5054, "lr": 2e-05, "epoch": 0.6385650224215247, "percentage": 63.91, "elapsed_time": "0:07:34", "remaining_time": "0:04:16"}
2
- {"current_steps": 357, "total_steps": 557, "loss": 1.5118, "lr": 2e-05, "epoch": 0.6403587443946188, "percentage": 64.09, "elapsed_time": "0:14:19", "remaining_time": "0:08:01"}
3
- {"current_steps": 358, "total_steps": 557, "loss": 1.5226, "lr": 2e-05, "epoch": 0.6421524663677131, "percentage": 64.27, "elapsed_time": "0:20:56", "remaining_time": "0:11:38"}
4
- {"current_steps": 359, "total_steps": 557, "loss": 1.5078, "lr": 2e-05, "epoch": 0.6439461883408072, "percentage": 64.45, "elapsed_time": "0:27:30", "remaining_time": "0:15:10"}
5
- {"current_steps": 360, "total_steps": 557, "loss": 1.5167, "lr": 2e-05, "epoch": 0.6457399103139013, "percentage": 64.63, "elapsed_time": "0:34:06", "remaining_time": "0:18:39"}
6
- {"current_steps": 361, "total_steps": 557, "loss": 1.5142, "lr": 2e-05, "epoch": 0.6475336322869956, "percentage": 64.81, "elapsed_time": "0:40:40", "remaining_time": "0:22:04"}
7
- {"current_steps": 362, "total_steps": 557, "loss": 1.5136, "lr": 2e-05, "epoch": 0.6493273542600897, "percentage": 64.99, "elapsed_time": "0:47:13", "remaining_time": "0:25:26"}
8
- {"current_steps": 363, "total_steps": 557, "loss": 1.5112, "lr": 2e-05, "epoch": 0.6511210762331838, "percentage": 65.17, "elapsed_time": "0:53:45", "remaining_time": "0:28:43"}
9
- {"current_steps": 364, "total_steps": 557, "loss": 1.5114, "lr": 2e-05, "epoch": 0.6529147982062781, "percentage": 65.35, "elapsed_time": "1:00:16", "remaining_time": "0:31:57"}
10
- {"current_steps": 365, "total_steps": 557, "loss": 1.5173, "lr": 2e-05, "epoch": 0.6547085201793722, "percentage": 65.53, "elapsed_time": "1:06:49", "remaining_time": "0:35:09"}
11
- {"current_steps": 366, "total_steps": 557, "loss": 1.5063, "lr": 2e-05, "epoch": 0.6565022421524663, "percentage": 65.71, "elapsed_time": "1:13:21", "remaining_time": "0:38:16"}
12
- {"current_steps": 367, "total_steps": 557, "loss": 1.5031, "lr": 2e-05, "epoch": 0.6582959641255606, "percentage": 65.89, "elapsed_time": "1:19:52", "remaining_time": "0:41:21"}
13
- {"current_steps": 368, "total_steps": 557, "loss": 1.5207, "lr": 2e-05, "epoch": 0.6600896860986547, "percentage": 66.07, "elapsed_time": "1:26:26", "remaining_time": "0:44:23"}
14
- {"current_steps": 369, "total_steps": 557, "loss": 1.5361, "lr": 2e-05, "epoch": 0.6618834080717488, "percentage": 66.25, "elapsed_time": "1:33:00", "remaining_time": "0:47:23"}
15
- {"current_steps": 370, "total_steps": 557, "loss": 1.5215, "lr": 2e-05, "epoch": 0.6636771300448431, "percentage": 66.43, "elapsed_time": "1:39:32", "remaining_time": "0:50:18"}
16
- {"current_steps": 371, "total_steps": 557, "loss": 1.5262, "lr": 2e-05, "epoch": 0.6654708520179372, "percentage": 66.61, "elapsed_time": "1:46:05", "remaining_time": "0:53:11"}
17
- {"current_steps": 372, "total_steps": 557, "loss": 1.5183, "lr": 2e-05, "epoch": 0.6672645739910313, "percentage": 66.79, "elapsed_time": "1:52:38", "remaining_time": "0:56:01"}
18
- {"current_steps": 373, "total_steps": 557, "loss": 1.5183, "lr": 2e-05, "epoch": 0.6690582959641256, "percentage": 66.97, "elapsed_time": "1:59:13", "remaining_time": "0:58:48"}
19
- {"current_steps": 374, "total_steps": 557, "loss": 1.5245, "lr": 2e-05, "epoch": 0.6708520179372197, "percentage": 67.15, "elapsed_time": "2:05:48", "remaining_time": "1:01:33"}
20
- {"current_steps": 375, "total_steps": 557, "loss": 1.5169, "lr": 2e-05, "epoch": 0.672645739910314, "percentage": 67.32, "elapsed_time": "2:12:26", "remaining_time": "1:04:16"}
21
- {"current_steps": 376, "total_steps": 557, "loss": 1.5185, "lr": 2e-05, "epoch": 0.6744394618834081, "percentage": 67.5, "elapsed_time": "2:19:01", "remaining_time": "1:06:55"}
22
- {"current_steps": 377, "total_steps": 557, "loss": 1.5161, "lr": 2e-05, "epoch": 0.6762331838565022, "percentage": 67.68, "elapsed_time": "2:25:38", "remaining_time": "1:09:32"}
23
- {"current_steps": 378, "total_steps": 557, "loss": 1.5119, "lr": 2e-05, "epoch": 0.6780269058295965, "percentage": 67.86, "elapsed_time": "2:32:16", "remaining_time": "1:12:06"}
24
- {"current_steps": 379, "total_steps": 557, "loss": 1.5126, "lr": 2e-05, "epoch": 0.6798206278026906, "percentage": 68.04, "elapsed_time": "2:38:51", "remaining_time": "1:14:36"}
25
- {"current_steps": 380, "total_steps": 557, "loss": 1.5173, "lr": 2e-05, "epoch": 0.6816143497757847, "percentage": 68.22, "elapsed_time": "2:45:26", "remaining_time": "1:17:03"}
26
- {"current_steps": 381, "total_steps": 557, "loss": 1.5075, "lr": 2e-05, "epoch": 0.683408071748879, "percentage": 68.4, "elapsed_time": "2:52:02", "remaining_time": "1:19:28"}
27
- {"current_steps": 382, "total_steps": 557, "loss": 1.5123, "lr": 2e-05, "epoch": 0.6852017937219731, "percentage": 68.58, "elapsed_time": "2:58:37", "remaining_time": "1:21:49"}
28
- {"current_steps": 383, "total_steps": 557, "loss": 1.5151, "lr": 2e-05, "epoch": 0.6869955156950672, "percentage": 68.76, "elapsed_time": "3:05:08", "remaining_time": "1:24:06"}
29
- {"current_steps": 384, "total_steps": 557, "loss": 1.5211, "lr": 2e-05, "epoch": 0.6887892376681615, "percentage": 68.94, "elapsed_time": "3:11:39", "remaining_time": "1:26:20"}
30
- {"current_steps": 385, "total_steps": 557, "loss": 1.5191, "lr": 2e-05, "epoch": 0.6905829596412556, "percentage": 69.12, "elapsed_time": "3:18:15", "remaining_time": "1:28:34"}
31
- {"current_steps": 386, "total_steps": 557, "loss": 1.5261, "lr": 2e-05, "epoch": 0.6923766816143497, "percentage": 69.3, "elapsed_time": "3:24:50", "remaining_time": "1:30:44"}
32
- {"current_steps": 387, "total_steps": 557, "loss": 1.5232, "lr": 2e-05, "epoch": 0.694170403587444, "percentage": 69.48, "elapsed_time": "3:31:23", "remaining_time": "1:32:51"}
33
- {"current_steps": 388, "total_steps": 557, "loss": 1.5212, "lr": 2e-05, "epoch": 0.6959641255605381, "percentage": 69.66, "elapsed_time": "3:37:57", "remaining_time": "1:34:56"}
34
- {"current_steps": 389, "total_steps": 557, "loss": 1.5094, "lr": 2e-05, "epoch": 0.6977578475336322, "percentage": 69.84, "elapsed_time": "3:44:33", "remaining_time": "1:36:58"}
35
- {"current_steps": 390, "total_steps": 557, "loss": 1.5115, "lr": 2e-05, "epoch": 0.6995515695067265, "percentage": 70.02, "elapsed_time": "3:51:05", "remaining_time": "1:38:57"}
36
- {"current_steps": 391, "total_steps": 557, "loss": 1.5195, "lr": 2e-05, "epoch": 0.7013452914798206, "percentage": 70.2, "elapsed_time": "3:57:36", "remaining_time": "1:40:52"}
37
- {"current_steps": 392, "total_steps": 557, "loss": 1.5048, "lr": 2e-05, "epoch": 0.7031390134529149, "percentage": 70.38, "elapsed_time": "4:04:11", "remaining_time": "1:42:46"}
38
- {"current_steps": 393, "total_steps": 557, "loss": 1.5162, "lr": 2e-05, "epoch": 0.704932735426009, "percentage": 70.56, "elapsed_time": "4:10:48", "remaining_time": "1:44:39"}
39
- {"current_steps": 394, "total_steps": 557, "loss": 1.5258, "lr": 2e-05, "epoch": 0.7067264573991031, "percentage": 70.74, "elapsed_time": "4:17:23", "remaining_time": "1:46:29"}
40
- {"current_steps": 395, "total_steps": 557, "loss": 1.5094, "lr": 2e-05, "epoch": 0.7085201793721974, "percentage": 70.92, "elapsed_time": "4:23:58", "remaining_time": "1:48:15"}
41
- {"current_steps": 396, "total_steps": 557, "loss": 1.5172, "lr": 2e-05, "epoch": 0.7103139013452915, "percentage": 71.1, "elapsed_time": "4:30:31", "remaining_time": "1:49:59"}
42
- {"current_steps": 397, "total_steps": 557, "loss": 1.5117, "lr": 2e-05, "epoch": 0.7121076233183856, "percentage": 71.27, "elapsed_time": "4:37:09", "remaining_time": "1:51:42"}
43
- {"current_steps": 398, "total_steps": 557, "loss": 1.5268, "lr": 2e-05, "epoch": 0.7139013452914799, "percentage": 71.45, "elapsed_time": "4:43:43", "remaining_time": "1:53:20"}
44
- {"current_steps": 399, "total_steps": 557, "loss": 1.5211, "lr": 2e-05, "epoch": 0.715695067264574, "percentage": 71.63, "elapsed_time": "4:50:21", "remaining_time": "1:54:58"}
45
- {"current_steps": 400, "total_steps": 557, "loss": 1.5199, "lr": 2e-05, "epoch": 0.7174887892376681, "percentage": 71.81, "elapsed_time": "4:56:57", "remaining_time": "1:56:33"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 401, "total_steps": 557, "loss": 1.5168, "lr": 2e-05, "epoch": 0.7192825112107624, "percentage": 71.99, "elapsed_time": "0:06:53", "remaining_time": "0:02:41"}
2
+ {"current_steps": 402, "total_steps": 557, "loss": 1.5175, "lr": 2e-05, "epoch": 0.7210762331838565, "percentage": 72.17, "elapsed_time": "0:13:41", "remaining_time": "0:05:16"}
3
+ {"current_steps": 403, "total_steps": 557, "loss": 1.5211, "lr": 2e-05, "epoch": 0.7228699551569506, "percentage": 72.35, "elapsed_time": "0:20:23", "remaining_time": "0:07:47"}
4
+ {"current_steps": 404, "total_steps": 557, "loss": 1.5228, "lr": 2e-05, "epoch": 0.7246636771300449, "percentage": 72.53, "elapsed_time": "0:27:04", "remaining_time": "0:10:15"}
5
+ {"current_steps": 405, "total_steps": 557, "loss": 1.522, "lr": 2e-05, "epoch": 0.726457399103139, "percentage": 72.71, "elapsed_time": "0:33:46", "remaining_time": "0:12:40"}
6
+ {"current_steps": 406, "total_steps": 557, "loss": 1.525, "lr": 2e-05, "epoch": 0.7282511210762331, "percentage": 72.89, "elapsed_time": "0:40:27", "remaining_time": "0:15:02"}
7
+ {"current_steps": 407, "total_steps": 557, "loss": 1.5172, "lr": 2e-05, "epoch": 0.7300448430493274, "percentage": 73.07, "elapsed_time": "0:47:12", "remaining_time": "0:17:23"}
8
+ {"current_steps": 408, "total_steps": 557, "loss": 1.5246, "lr": 2e-05, "epoch": 0.7318385650224215, "percentage": 73.25, "elapsed_time": "0:53:49", "remaining_time": "0:19:39"}
9
+ {"current_steps": 409, "total_steps": 557, "loss": 1.5132, "lr": 2e-05, "epoch": 0.7336322869955157, "percentage": 73.43, "elapsed_time": "1:00:26", "remaining_time": "0:21:52"}
10
+ {"current_steps": 410, "total_steps": 557, "loss": 1.5248, "lr": 2e-05, "epoch": 0.7354260089686099, "percentage": 73.61, "elapsed_time": "1:07:01", "remaining_time": "0:24:01"}
11
+ {"current_steps": 411, "total_steps": 557, "loss": 1.5196, "lr": 2e-05, "epoch": 0.737219730941704, "percentage": 73.79, "elapsed_time": "1:13:40", "remaining_time": "0:26:10"}
12
+ {"current_steps": 412, "total_steps": 557, "loss": 1.5096, "lr": 2e-05, "epoch": 0.7390134529147983, "percentage": 73.97, "elapsed_time": "1:20:15", "remaining_time": "0:28:14"}
13
+ {"current_steps": 413, "total_steps": 557, "loss": 1.5162, "lr": 2e-05, "epoch": 0.7408071748878924, "percentage": 74.15, "elapsed_time": "1:26:59", "remaining_time": "0:30:19"}
14
+ {"current_steps": 414, "total_steps": 557, "loss": 1.5189, "lr": 2e-05, "epoch": 0.7426008968609865, "percentage": 74.33, "elapsed_time": "1:33:36", "remaining_time": "0:32:19"}
15
+ {"current_steps": 415, "total_steps": 557, "loss": 1.5194, "lr": 2e-05, "epoch": 0.7443946188340808, "percentage": 74.51, "elapsed_time": "1:40:13", "remaining_time": "0:34:17"}
16
+ {"current_steps": 416, "total_steps": 557, "loss": 1.5191, "lr": 2e-05, "epoch": 0.7461883408071749, "percentage": 74.69, "elapsed_time": "1:46:52", "remaining_time": "0:36:13"}
17
+ {"current_steps": 417, "total_steps": 557, "loss": 1.5177, "lr": 2e-05, "epoch": 0.747982062780269, "percentage": 74.87, "elapsed_time": "1:53:30", "remaining_time": "0:38:06"}
18
+ {"current_steps": 418, "total_steps": 557, "loss": 1.514, "lr": 2e-05, "epoch": 0.7497757847533633, "percentage": 75.04, "elapsed_time": "2:00:08", "remaining_time": "0:39:56"}
19
+ {"current_steps": 419, "total_steps": 557, "loss": 1.5154, "lr": 2e-05, "epoch": 0.7515695067264574, "percentage": 75.22, "elapsed_time": "2:06:46", "remaining_time": "0:41:45"}
20
+ {"current_steps": 420, "total_steps": 557, "loss": 1.5223, "lr": 2e-05, "epoch": 0.7533632286995515, "percentage": 75.4, "elapsed_time": "2:13:24", "remaining_time": "0:43:30"}
21
+ {"current_steps": 421, "total_steps": 557, "loss": 1.5152, "lr": 2e-05, "epoch": 0.7551569506726458, "percentage": 75.58, "elapsed_time": "2:20:00", "remaining_time": "0:45:13"}
22
+ {"current_steps": 422, "total_steps": 557, "loss": 1.5185, "lr": 2e-05, "epoch": 0.7569506726457399, "percentage": 75.76, "elapsed_time": "2:26:37", "remaining_time": "0:46:54"}
23
+ {"current_steps": 423, "total_steps": 557, "loss": 1.4986, "lr": 2e-05, "epoch": 0.758744394618834, "percentage": 75.94, "elapsed_time": "2:33:15", "remaining_time": "0:48:33"}
24
+ {"current_steps": 424, "total_steps": 557, "loss": 1.5071, "lr": 2e-05, "epoch": 0.7605381165919283, "percentage": 76.12, "elapsed_time": "2:39:53", "remaining_time": "0:50:09"}
25
+ {"current_steps": 425, "total_steps": 557, "loss": 1.5006, "lr": 2e-05, "epoch": 0.7623318385650224, "percentage": 76.3, "elapsed_time": "2:46:32", "remaining_time": "0:51:43"}
26
+ {"current_steps": 426, "total_steps": 557, "loss": 1.5201, "lr": 2e-05, "epoch": 0.7641255605381166, "percentage": 76.48, "elapsed_time": "2:53:09", "remaining_time": "0:53:14"}
27
+ {"current_steps": 427, "total_steps": 557, "loss": 1.5213, "lr": 2e-05, "epoch": 0.7659192825112108, "percentage": 76.66, "elapsed_time": "2:59:46", "remaining_time": "0:54:44"}
28
+ {"current_steps": 428, "total_steps": 557, "loss": 1.5178, "lr": 2e-05, "epoch": 0.7677130044843049, "percentage": 76.84, "elapsed_time": "3:06:23", "remaining_time": "0:56:10"}
29
+ {"current_steps": 429, "total_steps": 557, "loss": 1.5085, "lr": 2e-05, "epoch": 0.7695067264573991, "percentage": 77.02, "elapsed_time": "3:13:02", "remaining_time": "0:57:35"}
30
+ {"current_steps": 430, "total_steps": 557, "loss": 1.5124, "lr": 2e-05, "epoch": 0.7713004484304933, "percentage": 77.2, "elapsed_time": "3:19:39", "remaining_time": "0:58:58"}
31
+ {"current_steps": 431, "total_steps": 557, "loss": 1.5299, "lr": 2e-05, "epoch": 0.7730941704035874, "percentage": 77.38, "elapsed_time": "3:26:23", "remaining_time": "1:00:20"}
32
+ {"current_steps": 432, "total_steps": 557, "loss": 1.5095, "lr": 2e-05, "epoch": 0.7748878923766817, "percentage": 77.56, "elapsed_time": "3:33:03", "remaining_time": "1:01:39"}
33
+ {"current_steps": 433, "total_steps": 557, "loss": 1.5193, "lr": 2e-05, "epoch": 0.7766816143497758, "percentage": 77.74, "elapsed_time": "3:39:45", "remaining_time": "1:02:56"}
34
+ {"current_steps": 434, "total_steps": 557, "loss": 1.5214, "lr": 2e-05, "epoch": 0.7784753363228699, "percentage": 77.92, "elapsed_time": "3:46:26", "remaining_time": "1:04:10"}
35
+ {"current_steps": 435, "total_steps": 557, "loss": 1.5208, "lr": 2e-05, "epoch": 0.7802690582959642, "percentage": 78.1, "elapsed_time": "3:53:05", "remaining_time": "1:05:22"}
36
+ {"current_steps": 436, "total_steps": 557, "loss": 1.5227, "lr": 2e-05, "epoch": 0.7820627802690583, "percentage": 78.28, "elapsed_time": "3:59:43", "remaining_time": "1:06:31"}
37
+ {"current_steps": 437, "total_steps": 557, "loss": 1.5248, "lr": 2e-05, "epoch": 0.7838565022421524, "percentage": 78.46, "elapsed_time": "4:06:20", "remaining_time": "1:07:38"}
38
+ {"current_steps": 438, "total_steps": 557, "loss": 1.5222, "lr": 2e-05, "epoch": 0.7856502242152467, "percentage": 78.64, "elapsed_time": "4:13:00", "remaining_time": "1:08:44"}
39
+ {"current_steps": 439, "total_steps": 557, "loss": 1.5205, "lr": 2e-05, "epoch": 0.7874439461883408, "percentage": 78.82, "elapsed_time": "4:19:37", "remaining_time": "1:09:47"}
40
+ {"current_steps": 440, "total_steps": 557, "loss": 1.5189, "lr": 2e-05, "epoch": 0.7892376681614349, "percentage": 78.99, "elapsed_time": "4:26:15", "remaining_time": "1:10:48"}
41
+ {"current_steps": 441, "total_steps": 557, "loss": 1.5156, "lr": 2e-05, "epoch": 0.7910313901345292, "percentage": 79.17, "elapsed_time": "4:32:52", "remaining_time": "1:11:46"}
42
+ {"current_steps": 442, "total_steps": 557, "loss": 1.5116, "lr": 2e-05, "epoch": 0.7928251121076233, "percentage": 79.35, "elapsed_time": "4:39:32", "remaining_time": "1:12:43"}
43
+ {"current_steps": 443, "total_steps": 557, "loss": 1.5153, "lr": 2e-05, "epoch": 0.7946188340807175, "percentage": 79.53, "elapsed_time": "4:46:09", "remaining_time": "1:13:38"}
44
+ {"current_steps": 444, "total_steps": 557, "loss": 1.5246, "lr": 2e-05, "epoch": 0.7964125560538117, "percentage": 79.71, "elapsed_time": "4:52:46", "remaining_time": "1:14:30"}
45
+ {"current_steps": 445, "total_steps": 557, "loss": 1.5282, "lr": 2e-05, "epoch": 0.7982062780269058, "percentage": 79.89, "elapsed_time": "4:59:22", "remaining_time": "1:15:20"}
46
+ {"current_steps": 446, "total_steps": 557, "loss": 1.5108, "lr": 2e-05, "epoch": 0.8, "percentage": 80.07, "elapsed_time": "5:06:00", "remaining_time": "1:16:09"}
47
+ {"current_steps": 447, "total_steps": 557, "loss": 1.51, "lr": 2e-05, "epoch": 0.8017937219730942, "percentage": 80.25, "elapsed_time": "5:12:37", "remaining_time": "1:16:55"}
48
+ {"current_steps": 448, "total_steps": 557, "loss": 1.5139, "lr": 2e-05, "epoch": 0.8035874439461883, "percentage": 80.43, "elapsed_time": "5:19:17", "remaining_time": "1:17:40"}
49
+ {"current_steps": 449, "total_steps": 557, "loss": 1.5091, "lr": 2e-05, "epoch": 0.8053811659192825, "percentage": 80.61, "elapsed_time": "5:25:54", "remaining_time": "1:18:23"}
50
+ {"current_steps": 450, "total_steps": 557, "loss": 1.5122, "lr": 2e-05, "epoch": 0.8071748878923767, "percentage": 80.79, "elapsed_time": "5:32:30", "remaining_time": "1:19:03"}
51
+ {"current_steps": 451, "total_steps": 557, "loss": 1.52, "lr": 2e-05, "epoch": 0.8089686098654708, "percentage": 80.97, "elapsed_time": "5:39:15", "remaining_time": "1:19:44"}
52
+ {"current_steps": 452, "total_steps": 557, "loss": 1.5197, "lr": 2e-05, "epoch": 0.810762331838565, "percentage": 81.15, "elapsed_time": "5:45:57", "remaining_time": "1:20:22"}
53
+ {"current_steps": 453, "total_steps": 557, "loss": 1.5117, "lr": 2e-05, "epoch": 0.8125560538116592, "percentage": 81.33, "elapsed_time": "5:52:37", "remaining_time": "1:20:57"}
54
+ {"current_steps": 454, "total_steps": 557, "loss": 1.5033, "lr": 2e-05, "epoch": 0.8143497757847533, "percentage": 81.51, "elapsed_time": "5:59:14", "remaining_time": "1:21:30"}
55
+ {"current_steps": 455, "total_steps": 557, "loss": 1.5166, "lr": 2e-05, "epoch": 0.8161434977578476, "percentage": 81.69, "elapsed_time": "6:05:59", "remaining_time": "1:22:02"}
56
+ {"current_steps": 456, "total_steps": 557, "loss": 1.5149, "lr": 2e-05, "epoch": 0.8179372197309417, "percentage": 81.87, "elapsed_time": "6:12:37", "remaining_time": "1:22:32"}
57
+ {"current_steps": 457, "total_steps": 557, "loss": 1.5093, "lr": 2e-05, "epoch": 0.8197309417040358, "percentage": 82.05, "elapsed_time": "6:19:15", "remaining_time": "1:22:59"}
58
+ {"current_steps": 458, "total_steps": 557, "loss": 1.5141, "lr": 2e-05, "epoch": 0.8215246636771301, "percentage": 82.23, "elapsed_time": "6:26:00", "remaining_time": "1:23:26"}
59
+ {"current_steps": 459, "total_steps": 557, "loss": 1.5241, "lr": 2e-05, "epoch": 0.8233183856502242, "percentage": 82.41, "elapsed_time": "6:32:38", "remaining_time": "1:23:49"}
60
+ {"current_steps": 460, "total_steps": 557, "loss": 1.5068, "lr": 2e-05, "epoch": 0.8251121076233184, "percentage": 82.59, "elapsed_time": "6:39:15", "remaining_time": "1:24:11"}
61
+ {"current_steps": 461, "total_steps": 557, "loss": 1.5052, "lr": 2e-05, "epoch": 0.8269058295964126, "percentage": 82.76, "elapsed_time": "6:45:53", "remaining_time": "1:24:31"}
62
+ {"current_steps": 462, "total_steps": 557, "loss": 1.5071, "lr": 2e-05, "epoch": 0.8286995515695067, "percentage": 82.94, "elapsed_time": "6:52:31", "remaining_time": "1:24:49"}
63
+ {"current_steps": 463, "total_steps": 557, "loss": 1.5189, "lr": 2e-05, "epoch": 0.8304932735426009, "percentage": 83.12, "elapsed_time": "6:59:08", "remaining_time": "1:25:05"}
64
+ {"current_steps": 464, "total_steps": 557, "loss": 1.5183, "lr": 2e-05, "epoch": 0.8322869955156951, "percentage": 83.3, "elapsed_time": "7:05:47", "remaining_time": "1:25:20"}
65
+ {"current_steps": 465, "total_steps": 557, "loss": 1.5213, "lr": 2e-05, "epoch": 0.8340807174887892, "percentage": 83.48, "elapsed_time": "7:12:25", "remaining_time": "1:25:33"}
66
+ {"current_steps": 466, "total_steps": 557, "loss": 1.5182, "lr": 2e-05, "epoch": 0.8358744394618834, "percentage": 83.66, "elapsed_time": "7:19:05", "remaining_time": "1:25:44"}
67
+ {"current_steps": 467, "total_steps": 557, "loss": 1.5092, "lr": 2e-05, "epoch": 0.8376681614349776, "percentage": 83.84, "elapsed_time": "7:25:43", "remaining_time": "1:25:54"}
68
+ {"current_steps": 468, "total_steps": 557, "loss": 1.5186, "lr": 2e-05, "epoch": 0.8394618834080717, "percentage": 84.02, "elapsed_time": "7:32:20", "remaining_time": "1:26:01"}
69
+ {"current_steps": 469, "total_steps": 557, "loss": 1.5097, "lr": 2e-05, "epoch": 0.841255605381166, "percentage": 84.2, "elapsed_time": "7:38:58", "remaining_time": "1:26:07"}
70
+ {"current_steps": 470, "total_steps": 557, "loss": 1.5173, "lr": 2e-05, "epoch": 0.8430493273542601, "percentage": 84.38, "elapsed_time": "7:45:36", "remaining_time": "1:26:11"}
71
+ {"current_steps": 471, "total_steps": 557, "loss": 1.5108, "lr": 2e-05, "epoch": 0.8448430493273542, "percentage": 84.56, "elapsed_time": "7:52:13", "remaining_time": "1:26:13"}
72
+ {"current_steps": 472, "total_steps": 557, "loss": 1.5272, "lr": 2e-05, "epoch": 0.8466367713004485, "percentage": 84.74, "elapsed_time": "7:58:52", "remaining_time": "1:26:14"}
73
+ {"current_steps": 473, "total_steps": 557, "loss": 1.5193, "lr": 2e-05, "epoch": 0.8484304932735426, "percentage": 84.92, "elapsed_time": "8:05:31", "remaining_time": "1:26:13"}
74
+ {"current_steps": 474, "total_steps": 557, "loss": 1.5165, "lr": 2e-05, "epoch": 0.8502242152466367, "percentage": 85.1, "elapsed_time": "8:12:09", "remaining_time": "1:26:10"}
75
+ {"current_steps": 475, "total_steps": 557, "loss": 1.5228, "lr": 2e-05, "epoch": 0.852017937219731, "percentage": 85.28, "elapsed_time": "8:18:47", "remaining_time": "1:26:06"}
76
+ {"current_steps": 476, "total_steps": 557, "loss": 1.5188, "lr": 2e-05, "epoch": 0.8538116591928251, "percentage": 85.46, "elapsed_time": "8:25:27", "remaining_time": "1:26:00"}
77
+ {"current_steps": 477, "total_steps": 557, "loss": 1.5199, "lr": 2e-05, "epoch": 0.8556053811659193, "percentage": 85.64, "elapsed_time": "8:32:03", "remaining_time": "1:25:52"}
78
+ {"current_steps": 478, "total_steps": 557, "loss": 1.516, "lr": 2e-05, "epoch": 0.8573991031390135, "percentage": 85.82, "elapsed_time": "8:38:42", "remaining_time": "1:25:43"}
79
+ {"current_steps": 479, "total_steps": 557, "loss": 1.5218, "lr": 2e-05, "epoch": 0.8591928251121076, "percentage": 86.0, "elapsed_time": "8:45:19", "remaining_time": "1:25:32"}
80
+ {"current_steps": 480, "total_steps": 557, "loss": 1.5155, "lr": 2e-05, "epoch": 0.8609865470852018, "percentage": 86.18, "elapsed_time": "8:51:58", "remaining_time": "1:25:20"}
81
+ {"current_steps": 481, "total_steps": 557, "loss": 1.5205, "lr": 2e-05, "epoch": 0.862780269058296, "percentage": 86.36, "elapsed_time": "8:58:36", "remaining_time": "1:25:06"}
82
+ {"current_steps": 482, "total_steps": 557, "loss": 1.5019, "lr": 2e-05, "epoch": 0.8645739910313901, "percentage": 86.54, "elapsed_time": "9:05:13", "remaining_time": "1:24:50"}
83
+ {"current_steps": 483, "total_steps": 557, "loss": 1.5217, "lr": 2e-05, "epoch": 0.8663677130044843, "percentage": 86.71, "elapsed_time": "9:11:50", "remaining_time": "1:24:32"}
84
+ {"current_steps": 484, "total_steps": 557, "loss": 1.5073, "lr": 2e-05, "epoch": 0.8681614349775785, "percentage": 86.89, "elapsed_time": "9:18:28", "remaining_time": "1:24:13"}
85
+ {"current_steps": 485, "total_steps": 557, "loss": 1.5101, "lr": 2e-05, "epoch": 0.8699551569506726, "percentage": 87.07, "elapsed_time": "9:25:05", "remaining_time": "1:23:53"}
86
+ {"current_steps": 486, "total_steps": 557, "loss": 1.5209, "lr": 2e-05, "epoch": 0.8717488789237668, "percentage": 87.25, "elapsed_time": "9:31:41", "remaining_time": "1:23:31"}
87
+ {"current_steps": 487, "total_steps": 557, "loss": 1.5275, "lr": 2e-05, "epoch": 0.873542600896861, "percentage": 87.43, "elapsed_time": "9:38:18", "remaining_time": "1:23:07"}
88
+ {"current_steps": 488, "total_steps": 557, "loss": 1.521, "lr": 2e-05, "epoch": 0.8753363228699551, "percentage": 87.61, "elapsed_time": "9:44:55", "remaining_time": "1:22:42"}
89
+ {"current_steps": 489, "total_steps": 557, "loss": 1.5253, "lr": 2e-05, "epoch": 0.8771300448430494, "percentage": 87.79, "elapsed_time": "9:51:35", "remaining_time": "1:22:16"}
90
+ {"current_steps": 490, "total_steps": 557, "loss": 1.5128, "lr": 2e-05, "epoch": 0.8789237668161435, "percentage": 87.97, "elapsed_time": "9:58:15", "remaining_time": "1:21:48"}
91
+ {"current_steps": 491, "total_steps": 557, "loss": 1.5216, "lr": 2e-05, "epoch": 0.8807174887892377, "percentage": 88.15, "elapsed_time": "10:04:56", "remaining_time": "1:21:18"}
92
+ {"current_steps": 492, "total_steps": 557, "loss": 1.5102, "lr": 2e-05, "epoch": 0.8825112107623319, "percentage": 88.33, "elapsed_time": "10:11:37", "remaining_time": "1:20:48"}
93
+ {"current_steps": 493, "total_steps": 557, "loss": 1.5152, "lr": 2e-05, "epoch": 0.884304932735426, "percentage": 88.51, "elapsed_time": "10:18:20", "remaining_time": "1:20:16"}
94
+ {"current_steps": 494, "total_steps": 557, "loss": 1.5134, "lr": 2e-05, "epoch": 0.8860986547085202, "percentage": 88.69, "elapsed_time": "10:25:04", "remaining_time": "1:19:43"}
95
+ {"current_steps": 495, "total_steps": 557, "loss": 1.5213, "lr": 2e-05, "epoch": 0.8878923766816144, "percentage": 88.87, "elapsed_time": "10:31:46", "remaining_time": "1:19:07"}
96
+ {"current_steps": 496, "total_steps": 557, "loss": 1.5254, "lr": 2e-05, "epoch": 0.8896860986547085, "percentage": 89.05, "elapsed_time": "10:38:28", "remaining_time": "1:18:31"}
97
+ {"current_steps": 497, "total_steps": 557, "loss": 1.5042, "lr": 2e-05, "epoch": 0.8914798206278027, "percentage": 89.23, "elapsed_time": "10:45:10", "remaining_time": "1:17:53"}
98
+ {"current_steps": 498, "total_steps": 557, "loss": 1.5141, "lr": 2e-05, "epoch": 0.8932735426008969, "percentage": 89.41, "elapsed_time": "10:51:50", "remaining_time": "1:17:13"}
99
+ {"current_steps": 499, "total_steps": 557, "loss": 1.5189, "lr": 2e-05, "epoch": 0.895067264573991, "percentage": 89.59, "elapsed_time": "10:58:32", "remaining_time": "1:16:32"}
100
+ {"current_steps": 500, "total_steps": 557, "loss": 1.5128, "lr": 2e-05, "epoch": 0.8968609865470852, "percentage": 89.77, "elapsed_time": "11:05:12", "remaining_time": "1:15:50"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03384a49165840082ae3d6ced7620c1cd73926c210110e3a49250f7f4a26bdaa
3
  size 7736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ad09cbd3278e201ac3fa5ce175ad9e8e7ad1e91b6d045ffa313186b1a9162b8
3
  size 7736