rbelanec commited on
Commit
954cdb7
verified
1 Parent(s): ea400d4

Training in progress, step 38160

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +380 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:433dc2426232d452f1b352915ec295120df45128e3b9b5e67f197c9f7dd5b6a1
3
  size 1074144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0dce263319ab669eeb68c1e7486d3876225393704b84185fede135dfd0ed023
3
  size 1074144
trainer_log.jsonl CHANGED
@@ -7271,3 +7271,383 @@
7271
  {"current_steps": 36260, "total_steps": 38160, "loss": 0.4218, "lr": 3.7703146230519126e-07, "epoch": 19.0041928721174, "percentage": 95.02, "elapsed_time": "1:43:36", "remaining_time": "0:05:25", "throughput": 3812.23, "total_tokens": 23700072}
7272
  {"current_steps": 36265, "total_steps": 38160, "loss": 0.5444, "lr": 3.7505570583069306e-07, "epoch": 19.006813417190777, "percentage": 95.03, "elapsed_time": "1:43:37", "remaining_time": "0:05:24", "throughput": 3812.19, "total_tokens": 23702856}
7273
  {"current_steps": 36270, "total_steps": 38160, "loss": 0.4783, "lr": 3.7308510061360435e-07, "epoch": 19.00943396226415, "percentage": 95.05, "elapsed_time": "1:43:38", "remaining_time": "0:05:24", "throughput": 3812.23, "total_tokens": 23706184}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7271
  {"current_steps": 36260, "total_steps": 38160, "loss": 0.4218, "lr": 3.7703146230519126e-07, "epoch": 19.0041928721174, "percentage": 95.02, "elapsed_time": "1:43:36", "remaining_time": "0:05:25", "throughput": 3812.23, "total_tokens": 23700072}
7272
  {"current_steps": 36265, "total_steps": 38160, "loss": 0.5444, "lr": 3.7505570583069306e-07, "epoch": 19.006813417190777, "percentage": 95.03, "elapsed_time": "1:43:37", "remaining_time": "0:05:24", "throughput": 3812.19, "total_tokens": 23702856}
7273
  {"current_steps": 36270, "total_steps": 38160, "loss": 0.4783, "lr": 3.7308510061360435e-07, "epoch": 19.00943396226415, "percentage": 95.05, "elapsed_time": "1:43:38", "remaining_time": "0:05:24", "throughput": 3812.23, "total_tokens": 23706184}
7274
+ {"current_steps": 36275, "total_steps": 38160, "loss": 0.466, "lr": 3.7111964706615374e-07, "epoch": 19.012054507337528, "percentage": 95.06, "elapsed_time": "1:43:39", "remaining_time": "0:05:23", "throughput": 3812.19, "total_tokens": 23709128}
7275
+ {"current_steps": 36280, "total_steps": 38160, "loss": 0.6097, "lr": 3.691593455994929e-07, "epoch": 19.0146750524109, "percentage": 95.07, "elapsed_time": "1:43:40", "remaining_time": "0:05:22", "throughput": 3812.25, "total_tokens": 23712808}
7276
+ {"current_steps": 36285, "total_steps": 38160, "loss": 0.4153, "lr": 3.672041966236911e-07, "epoch": 19.017295597484278, "percentage": 95.09, "elapsed_time": "1:43:40", "remaining_time": "0:05:21", "throughput": 3812.31, "total_tokens": 23716168}
7277
+ {"current_steps": 36290, "total_steps": 38160, "loss": 0.3562, "lr": 3.6525420054774884e-07, "epoch": 19.01991614255765, "percentage": 95.1, "elapsed_time": "1:43:41", "remaining_time": "0:05:20", "throughput": 3812.35, "total_tokens": 23719688}
7278
+ {"current_steps": 36295, "total_steps": 38160, "loss": 0.408, "lr": 3.6330935777957597e-07, "epoch": 19.02253668763103, "percentage": 95.11, "elapsed_time": "1:43:42", "remaining_time": "0:05:19", "throughput": 3812.43, "total_tokens": 23723752}
7279
+ {"current_steps": 36300, "total_steps": 38160, "loss": 0.3599, "lr": 3.613696687260193e-07, "epoch": 19.0251572327044, "percentage": 95.13, "elapsed_time": "1:43:43", "remaining_time": "0:05:18", "throughput": 3812.5, "total_tokens": 23727432}
7280
+ {"current_steps": 36305, "total_steps": 38160, "loss": 0.4295, "lr": 3.59435133792832e-07, "epoch": 19.02777777777778, "percentage": 95.14, "elapsed_time": "1:43:44", "remaining_time": "0:05:18", "throughput": 3812.49, "total_tokens": 23730312}
7281
+ {"current_steps": 36310, "total_steps": 38160, "loss": 0.4831, "lr": 3.575057533847043e-07, "epoch": 19.030398322851152, "percentage": 95.15, "elapsed_time": "1:43:45", "remaining_time": "0:05:17", "throughput": 3812.51, "total_tokens": 23733448}
7282
+ {"current_steps": 36315, "total_steps": 38160, "loss": 0.4458, "lr": 3.555815279052327e-07, "epoch": 19.03301886792453, "percentage": 95.17, "elapsed_time": "1:43:46", "remaining_time": "0:05:16", "throughput": 3812.58, "total_tokens": 23737320}
7283
+ {"current_steps": 36320, "total_steps": 38160, "loss": 0.5092, "lr": 3.5366245775694805e-07, "epoch": 19.035639412997902, "percentage": 95.18, "elapsed_time": "1:43:46", "remaining_time": "0:05:15", "throughput": 3812.48, "total_tokens": 23739752}
7284
+ {"current_steps": 36325, "total_steps": 38160, "loss": 0.3528, "lr": 3.517485433412987e-07, "epoch": 19.03825995807128, "percentage": 95.19, "elapsed_time": "1:43:47", "remaining_time": "0:05:14", "throughput": 3812.41, "total_tokens": 23742152}
7285
+ {"current_steps": 36330, "total_steps": 38160, "loss": 0.3944, "lr": 3.4983978505865044e-07, "epoch": 19.040880503144653, "percentage": 95.2, "elapsed_time": "1:43:48", "remaining_time": "0:05:13", "throughput": 3812.44, "total_tokens": 23745448}
7286
+ {"current_steps": 36335, "total_steps": 38160, "loss": 0.4012, "lr": 3.47936183308295e-07, "epoch": 19.04350104821803, "percentage": 95.22, "elapsed_time": "1:43:49", "remaining_time": "0:05:12", "throughput": 3812.53, "total_tokens": 23749864}
7287
+ {"current_steps": 36340, "total_steps": 38160, "loss": 0.4658, "lr": 3.460377384884472e-07, "epoch": 19.046121593291403, "percentage": 95.23, "elapsed_time": "1:43:50", "remaining_time": "0:05:12", "throughput": 3812.5, "total_tokens": 23752552}
7288
+ {"current_steps": 36345, "total_steps": 38160, "loss": 0.3638, "lr": 3.4414445099623384e-07, "epoch": 19.04874213836478, "percentage": 95.24, "elapsed_time": "1:43:50", "remaining_time": "0:05:11", "throughput": 3812.5, "total_tokens": 23755528}
7289
+ {"current_steps": 36350, "total_steps": 38160, "loss": 0.3294, "lr": 3.42256321227713e-07, "epoch": 19.051362683438157, "percentage": 95.26, "elapsed_time": "1:43:51", "remaining_time": "0:05:10", "throughput": 3812.55, "total_tokens": 23758600}
7290
+ {"current_steps": 36355, "total_steps": 38160, "loss": 0.4351, "lr": 3.403733495778605e-07, "epoch": 19.05398322851153, "percentage": 95.27, "elapsed_time": "1:43:52", "remaining_time": "0:05:09", "throughput": 3812.53, "total_tokens": 23761480}
7291
+ {"current_steps": 36360, "total_steps": 38160, "loss": 0.4039, "lr": 3.3849553644056955e-07, "epoch": 19.056603773584907, "percentage": 95.28, "elapsed_time": "1:43:53", "remaining_time": "0:05:08", "throughput": 3812.49, "total_tokens": 23764168}
7292
+ {"current_steps": 36365, "total_steps": 38160, "loss": 0.4971, "lr": 3.36622882208662e-07, "epoch": 19.05922431865828, "percentage": 95.3, "elapsed_time": "1:43:53", "remaining_time": "0:05:07", "throughput": 3812.48, "total_tokens": 23766920}
7293
+ {"current_steps": 36370, "total_steps": 38160, "loss": 0.4481, "lr": 3.347553872738718e-07, "epoch": 19.061844863731658, "percentage": 95.31, "elapsed_time": "1:43:54", "remaining_time": "0:05:06", "throughput": 3812.51, "total_tokens": 23770056}
7294
+ {"current_steps": 36375, "total_steps": 38160, "loss": 0.316, "lr": 3.3289305202685583e-07, "epoch": 19.06446540880503, "percentage": 95.32, "elapsed_time": "1:43:55", "remaining_time": "0:05:05", "throughput": 3812.52, "total_tokens": 23773096}
7295
+ {"current_steps": 36380, "total_steps": 38160, "loss": 0.3882, "lr": 3.310358768571997e-07, "epoch": 19.067085953878408, "percentage": 95.34, "elapsed_time": "1:43:56", "remaining_time": "0:05:05", "throughput": 3812.46, "total_tokens": 23775496}
7296
+ {"current_steps": 36385, "total_steps": 38160, "loss": 0.4545, "lr": 3.2918386215339827e-07, "epoch": 19.06970649895178, "percentage": 95.35, "elapsed_time": "1:43:57", "remaining_time": "0:05:04", "throughput": 3812.49, "total_tokens": 23778600}
7297
+ {"current_steps": 36390, "total_steps": 38160, "loss": 0.4067, "lr": 3.2733700830287205e-07, "epoch": 19.072327044025158, "percentage": 95.36, "elapsed_time": "1:43:58", "remaining_time": "0:05:03", "throughput": 3812.56, "total_tokens": 23783688}
7298
+ {"current_steps": 36395, "total_steps": 38160, "loss": 0.5105, "lr": 3.254953156919649e-07, "epoch": 19.07494758909853, "percentage": 95.37, "elapsed_time": "1:43:59", "remaining_time": "0:05:02", "throughput": 3812.54, "total_tokens": 23786440}
7299
+ {"current_steps": 36400, "total_steps": 38160, "loss": 0.5049, "lr": 3.2365878470593527e-07, "epoch": 19.07756813417191, "percentage": 95.39, "elapsed_time": "1:43:59", "remaining_time": "0:05:01", "throughput": 3812.59, "total_tokens": 23789768}
7300
+ {"current_steps": 36405, "total_steps": 38160, "loss": 0.4687, "lr": 3.2182741572896747e-07, "epoch": 19.080188679245282, "percentage": 95.4, "elapsed_time": "1:44:00", "remaining_time": "0:05:00", "throughput": 3812.53, "total_tokens": 23792264}
7301
+ {"current_steps": 36410, "total_steps": 38160, "loss": 0.4153, "lr": 3.2000120914415786e-07, "epoch": 19.08280922431866, "percentage": 95.41, "elapsed_time": "1:44:01", "remaining_time": "0:04:59", "throughput": 3812.57, "total_tokens": 23795816}
7302
+ {"current_steps": 36415, "total_steps": 38160, "loss": 0.4933, "lr": 3.181801653335315e-07, "epoch": 19.085429769392032, "percentage": 95.43, "elapsed_time": "1:44:02", "remaining_time": "0:04:59", "throughput": 3812.61, "total_tokens": 23798984}
7303
+ {"current_steps": 36420, "total_steps": 38160, "loss": 0.424, "lr": 3.163642846780307e-07, "epoch": 19.08805031446541, "percentage": 95.44, "elapsed_time": "1:44:02", "remaining_time": "0:04:58", "throughput": 3812.61, "total_tokens": 23802056}
7304
+ {"current_steps": 36425, "total_steps": 38160, "loss": 0.3971, "lr": 3.1455356755751565e-07, "epoch": 19.090670859538783, "percentage": 95.45, "elapsed_time": "1:44:03", "remaining_time": "0:04:57", "throughput": 3812.52, "total_tokens": 23804424}
7305
+ {"current_steps": 36430, "total_steps": 38160, "loss": 0.3633, "lr": 3.127480143507666e-07, "epoch": 19.09329140461216, "percentage": 95.47, "elapsed_time": "1:44:04", "remaining_time": "0:04:56", "throughput": 3812.49, "total_tokens": 23807112}
7306
+ {"current_steps": 36435, "total_steps": 38160, "loss": 0.3897, "lr": 3.1094762543548704e-07, "epoch": 19.095911949685533, "percentage": 95.48, "elapsed_time": "1:44:05", "remaining_time": "0:04:55", "throughput": 3812.52, "total_tokens": 23810184}
7307
+ {"current_steps": 36440, "total_steps": 38160, "loss": 0.4078, "lr": 3.091524011882951e-07, "epoch": 19.09853249475891, "percentage": 95.49, "elapsed_time": "1:44:05", "remaining_time": "0:04:54", "throughput": 3812.49, "total_tokens": 23812776}
7308
+ {"current_steps": 36445, "total_steps": 38160, "loss": 0.5297, "lr": 3.073623419847349e-07, "epoch": 19.101153039832287, "percentage": 95.51, "elapsed_time": "1:44:06", "remaining_time": "0:04:53", "throughput": 3812.52, "total_tokens": 23816296}
7309
+ {"current_steps": 36450, "total_steps": 38160, "loss": 0.4854, "lr": 3.0557744819926235e-07, "epoch": 19.10377358490566, "percentage": 95.52, "elapsed_time": "1:44:07", "remaining_time": "0:04:53", "throughput": 3812.53, "total_tokens": 23819432}
7310
+ {"current_steps": 36455, "total_steps": 38160, "loss": 0.5117, "lr": 3.037977202052594e-07, "epoch": 19.106394129979037, "percentage": 95.53, "elapsed_time": "1:44:08", "remaining_time": "0:04:52", "throughput": 3812.52, "total_tokens": 23822600}
7311
+ {"current_steps": 36460, "total_steps": 38160, "loss": 0.4163, "lr": 3.020231583750255e-07, "epoch": 19.10901467505241, "percentage": 95.55, "elapsed_time": "1:44:09", "remaining_time": "0:04:51", "throughput": 3812.53, "total_tokens": 23825512}
7312
+ {"current_steps": 36465, "total_steps": 38160, "loss": 0.4493, "lr": 3.002537630797747e-07, "epoch": 19.111635220125788, "percentage": 95.56, "elapsed_time": "1:44:10", "remaining_time": "0:04:50", "throughput": 3812.52, "total_tokens": 23828456}
7313
+ {"current_steps": 36470, "total_steps": 38160, "loss": 0.3633, "lr": 2.984895346896499e-07, "epoch": 19.11425576519916, "percentage": 95.57, "elapsed_time": "1:44:10", "remaining_time": "0:04:49", "throughput": 3812.55, "total_tokens": 23831656}
7314
+ {"current_steps": 36475, "total_steps": 38160, "loss": 0.4055, "lr": 2.967304735737031e-07, "epoch": 19.116876310272538, "percentage": 95.58, "elapsed_time": "1:44:11", "remaining_time": "0:04:48", "throughput": 3812.52, "total_tokens": 23834312}
7315
+ {"current_steps": 36480, "total_steps": 38160, "loss": 0.454, "lr": 2.9497658009991214e-07, "epoch": 19.11949685534591, "percentage": 95.6, "elapsed_time": "1:44:12", "remaining_time": "0:04:47", "throughput": 3812.5, "total_tokens": 23836968}
7316
+ {"current_steps": 36485, "total_steps": 38160, "loss": 0.4318, "lr": 2.932278546351724e-07, "epoch": 19.122117400419288, "percentage": 95.61, "elapsed_time": "1:44:13", "remaining_time": "0:04:47", "throughput": 3812.55, "total_tokens": 23840616}
7317
+ {"current_steps": 36490, "total_steps": 38160, "loss": 0.411, "lr": 2.9148429754529137e-07, "epoch": 19.12473794549266, "percentage": 95.62, "elapsed_time": "1:44:13", "remaining_time": "0:04:46", "throughput": 3812.64, "total_tokens": 23844168}
7318
+ {"current_steps": 36495, "total_steps": 38160, "loss": 0.3713, "lr": 2.897459091950078e-07, "epoch": 19.12735849056604, "percentage": 95.64, "elapsed_time": "1:44:14", "remaining_time": "0:04:45", "throughput": 3812.61, "total_tokens": 23846888}
7319
+ {"current_steps": 36500, "total_steps": 38160, "loss": 0.4945, "lr": 2.880126899479724e-07, "epoch": 19.129979035639412, "percentage": 95.65, "elapsed_time": "1:44:15", "remaining_time": "0:04:44", "throughput": 3812.72, "total_tokens": 23850856}
7320
+ {"current_steps": 36505, "total_steps": 38160, "loss": 0.4338, "lr": 2.862846401667507e-07, "epoch": 19.13259958071279, "percentage": 95.66, "elapsed_time": "1:44:16", "remaining_time": "0:04:43", "throughput": 3812.74, "total_tokens": 23853992}
7321
+ {"current_steps": 36510, "total_steps": 38160, "loss": 0.4346, "lr": 2.8456176021283697e-07, "epoch": 19.135220125786162, "percentage": 95.68, "elapsed_time": "1:44:17", "remaining_time": "0:04:42", "throughput": 3812.8, "total_tokens": 23857864}
7322
+ {"current_steps": 36515, "total_steps": 38160, "loss": 0.4505, "lr": 2.8284405044662897e-07, "epoch": 19.13784067085954, "percentage": 95.69, "elapsed_time": "1:44:18", "remaining_time": "0:04:41", "throughput": 3812.82, "total_tokens": 23861480}
7323
+ {"current_steps": 36520, "total_steps": 38160, "loss": 0.418, "lr": 2.8113151122745874e-07, "epoch": 19.140461215932913, "percentage": 95.7, "elapsed_time": "1:44:19", "remaining_time": "0:04:41", "throughput": 3812.8, "total_tokens": 23864424}
7324
+ {"current_steps": 36525, "total_steps": 38160, "loss": 0.5305, "lr": 2.7942414291357023e-07, "epoch": 19.14308176100629, "percentage": 95.72, "elapsed_time": "1:44:19", "remaining_time": "0:04:40", "throughput": 3812.79, "total_tokens": 23867272}
7325
+ {"current_steps": 36530, "total_steps": 38160, "loss": 0.3761, "lr": 2.777219458621222e-07, "epoch": 19.145702306079663, "percentage": 95.73, "elapsed_time": "1:44:20", "remaining_time": "0:04:39", "throughput": 3812.9, "total_tokens": 23871272}
7326
+ {"current_steps": 36535, "total_steps": 38160, "loss": 0.4119, "lr": 2.7602492042919923e-07, "epoch": 19.14832285115304, "percentage": 95.74, "elapsed_time": "1:44:21", "remaining_time": "0:04:38", "throughput": 3812.92, "total_tokens": 23874376}
7327
+ {"current_steps": 36540, "total_steps": 38160, "loss": 0.3657, "lr": 2.7433306696979523e-07, "epoch": 19.150943396226417, "percentage": 95.75, "elapsed_time": "1:44:22", "remaining_time": "0:04:37", "throughput": 3812.88, "total_tokens": 23877096}
7328
+ {"current_steps": 36545, "total_steps": 38160, "loss": 0.3646, "lr": 2.7264638583782973e-07, "epoch": 19.15356394129979, "percentage": 95.77, "elapsed_time": "1:44:23", "remaining_time": "0:04:36", "throughput": 3812.93, "total_tokens": 23880776}
7329
+ {"current_steps": 36550, "total_steps": 38160, "loss": 0.3024, "lr": 2.7096487738613177e-07, "epoch": 19.156184486373167, "percentage": 95.78, "elapsed_time": "1:44:24", "remaining_time": "0:04:35", "throughput": 3813.05, "total_tokens": 23885000}
7330
+ {"current_steps": 36555, "total_steps": 38160, "loss": 0.3554, "lr": 2.6928854196646147e-07, "epoch": 19.15880503144654, "percentage": 95.79, "elapsed_time": "1:44:24", "remaining_time": "0:04:35", "throughput": 3813.03, "total_tokens": 23887720}
7331
+ {"current_steps": 36560, "total_steps": 38160, "loss": 0.3936, "lr": 2.6761737992948565e-07, "epoch": 19.161425576519918, "percentage": 95.81, "elapsed_time": "1:44:25", "remaining_time": "0:04:34", "throughput": 3813.03, "total_tokens": 23890760}
7332
+ {"current_steps": 36565, "total_steps": 38160, "loss": 0.3822, "lr": 2.6595139162479134e-07, "epoch": 19.16404612159329, "percentage": 95.82, "elapsed_time": "1:44:26", "remaining_time": "0:04:33", "throughput": 3812.99, "total_tokens": 23893640}
7333
+ {"current_steps": 36570, "total_steps": 38160, "loss": 0.3758, "lr": 2.6429057740088303e-07, "epoch": 19.166666666666668, "percentage": 95.83, "elapsed_time": "1:44:27", "remaining_time": "0:04:32", "throughput": 3812.99, "total_tokens": 23896584}
7334
+ {"current_steps": 36575, "total_steps": 38160, "loss": 0.4969, "lr": 2.6263493760518564e-07, "epoch": 19.16928721174004, "percentage": 95.85, "elapsed_time": "1:44:28", "remaining_time": "0:04:31", "throughput": 3813.13, "total_tokens": 23901480}
7335
+ {"current_steps": 36580, "total_steps": 38160, "loss": 0.4649, "lr": 2.6098447258404157e-07, "epoch": 19.171907756813418, "percentage": 95.86, "elapsed_time": "1:44:28", "remaining_time": "0:04:30", "throughput": 3813.18, "total_tokens": 23904680}
7336
+ {"current_steps": 36585, "total_steps": 38160, "loss": 0.3038, "lr": 2.593391826827107e-07, "epoch": 19.17452830188679, "percentage": 95.87, "elapsed_time": "1:44:29", "remaining_time": "0:04:29", "throughput": 3813.09, "total_tokens": 23907144}
7337
+ {"current_steps": 36590, "total_steps": 38160, "loss": 0.4256, "lr": 2.5769906824536225e-07, "epoch": 19.17714884696017, "percentage": 95.89, "elapsed_time": "1:44:30", "remaining_time": "0:04:29", "throughput": 3813.16, "total_tokens": 23910888}
7338
+ {"current_steps": 36595, "total_steps": 38160, "loss": 0.5746, "lr": 2.560641296150967e-07, "epoch": 19.179769392033542, "percentage": 95.9, "elapsed_time": "1:44:31", "remaining_time": "0:04:28", "throughput": 3813.18, "total_tokens": 23914184}
7339
+ {"current_steps": 36600, "total_steps": 38160, "loss": 0.4059, "lr": 2.544343671339211e-07, "epoch": 19.18238993710692, "percentage": 95.91, "elapsed_time": "1:44:32", "remaining_time": "0:04:27", "throughput": 3813.22, "total_tokens": 23917608}
7340
+ {"current_steps": 36605, "total_steps": 38160, "loss": 0.4326, "lr": 2.5280978114276264e-07, "epoch": 19.185010482180292, "percentage": 95.93, "elapsed_time": "1:44:33", "remaining_time": "0:04:26", "throughput": 3813.32, "total_tokens": 23922312}
7341
+ {"current_steps": 36610, "total_steps": 38160, "loss": 0.4996, "lr": 2.511903719814662e-07, "epoch": 19.18763102725367, "percentage": 95.94, "elapsed_time": "1:44:34", "remaining_time": "0:04:25", "throughput": 3813.32, "total_tokens": 23925096}
7342
+ {"current_steps": 36615, "total_steps": 38160, "loss": 0.4514, "lr": 2.4957613998879695e-07, "epoch": 19.190251572327043, "percentage": 95.95, "elapsed_time": "1:44:34", "remaining_time": "0:04:24", "throughput": 3813.33, "total_tokens": 23927976}
7343
+ {"current_steps": 36620, "total_steps": 38160, "loss": 0.4032, "lr": 2.479670855024291e-07, "epoch": 19.19287211740042, "percentage": 95.96, "elapsed_time": "1:44:36", "remaining_time": "0:04:23", "throughput": 3813.54, "total_tokens": 23934760}
7344
+ {"current_steps": 36625, "total_steps": 38160, "loss": 0.4669, "lr": 2.463632088589629e-07, "epoch": 19.195492662473793, "percentage": 95.98, "elapsed_time": "1:44:37", "remaining_time": "0:04:23", "throughput": 3813.57, "total_tokens": 23937960}
7345
+ {"current_steps": 36630, "total_steps": 38160, "loss": 0.3588, "lr": 2.447645103939078e-07, "epoch": 19.19811320754717, "percentage": 95.99, "elapsed_time": "1:44:37", "remaining_time": "0:04:22", "throughput": 3813.57, "total_tokens": 23940904}
7346
+ {"current_steps": 36635, "total_steps": 38160, "loss": 0.385, "lr": 2.431709904416962e-07, "epoch": 19.200733752620547, "percentage": 96.0, "elapsed_time": "1:44:38", "remaining_time": "0:04:21", "throughput": 3813.56, "total_tokens": 23943848}
7347
+ {"current_steps": 36640, "total_steps": 38160, "loss": 0.4242, "lr": 2.4158264933567264e-07, "epoch": 19.20335429769392, "percentage": 96.02, "elapsed_time": "1:44:39", "remaining_time": "0:04:20", "throughput": 3813.58, "total_tokens": 23947112}
7348
+ {"current_steps": 36645, "total_steps": 38160, "loss": 0.3444, "lr": 2.399994874080963e-07, "epoch": 19.205974842767297, "percentage": 96.03, "elapsed_time": "1:44:40", "remaining_time": "0:04:19", "throughput": 3813.57, "total_tokens": 23950056}
7349
+ {"current_steps": 36650, "total_steps": 38160, "loss": 0.4696, "lr": 2.3842150499015504e-07, "epoch": 19.20859538784067, "percentage": 96.04, "elapsed_time": "1:44:40", "remaining_time": "0:04:18", "throughput": 3813.62, "total_tokens": 23953320}
7350
+ {"current_steps": 36655, "total_steps": 38160, "loss": 0.4437, "lr": 2.368487024119348e-07, "epoch": 19.211215932914047, "percentage": 96.06, "elapsed_time": "1:44:41", "remaining_time": "0:04:17", "throughput": 3813.63, "total_tokens": 23956168}
7351
+ {"current_steps": 36660, "total_steps": 38160, "loss": 0.4088, "lr": 2.3528108000245573e-07, "epoch": 19.21383647798742, "percentage": 96.07, "elapsed_time": "1:44:42", "remaining_time": "0:04:17", "throughput": 3813.7, "total_tokens": 23959528}
7352
+ {"current_steps": 36665, "total_steps": 38160, "loss": 0.4435, "lr": 2.3371863808964445e-07, "epoch": 19.216457023060798, "percentage": 96.08, "elapsed_time": "1:44:43", "remaining_time": "0:04:16", "throughput": 3813.71, "total_tokens": 23962504}
7353
+ {"current_steps": 36670, "total_steps": 38160, "loss": 0.3731, "lr": 2.32161377000345e-07, "epoch": 19.21907756813417, "percentage": 96.1, "elapsed_time": "1:44:44", "remaining_time": "0:04:15", "throughput": 3813.76, "total_tokens": 23965736}
7354
+ {"current_steps": 36675, "total_steps": 38160, "loss": 0.3596, "lr": 2.306092970603163e-07, "epoch": 19.221698113207548, "percentage": 96.11, "elapsed_time": "1:44:44", "remaining_time": "0:04:14", "throughput": 3813.71, "total_tokens": 23968328}
7355
+ {"current_steps": 36680, "total_steps": 38160, "loss": 0.388, "lr": 2.2906239859424306e-07, "epoch": 19.22431865828092, "percentage": 96.12, "elapsed_time": "1:44:45", "remaining_time": "0:04:13", "throughput": 3813.8, "total_tokens": 23972360}
7356
+ {"current_steps": 36685, "total_steps": 38160, "loss": 0.4302, "lr": 2.2752068192571084e-07, "epoch": 19.2269392033543, "percentage": 96.13, "elapsed_time": "1:44:46", "remaining_time": "0:04:12", "throughput": 3813.84, "total_tokens": 23975688}
7357
+ {"current_steps": 36690, "total_steps": 38160, "loss": 0.4851, "lr": 2.2598414737723396e-07, "epoch": 19.229559748427672, "percentage": 96.15, "elapsed_time": "1:44:47", "remaining_time": "0:04:11", "throughput": 3813.94, "total_tokens": 23979656}
7358
+ {"current_steps": 36695, "total_steps": 38160, "loss": 0.4721, "lr": 2.2445279527023578e-07, "epoch": 19.23218029350105, "percentage": 96.16, "elapsed_time": "1:44:48", "remaining_time": "0:04:11", "throughput": 3813.91, "total_tokens": 23982568}
7359
+ {"current_steps": 36700, "total_steps": 38160, "loss": 0.4868, "lr": 2.2292662592506007e-07, "epoch": 19.234800838574422, "percentage": 96.17, "elapsed_time": "1:44:48", "remaining_time": "0:04:10", "throughput": 3813.92, "total_tokens": 23985640}
7360
+ {"current_steps": 36705, "total_steps": 38160, "loss": 0.4764, "lr": 2.2140563966095985e-07, "epoch": 19.2374213836478, "percentage": 96.19, "elapsed_time": "1:44:49", "remaining_time": "0:04:09", "throughput": 3813.97, "total_tokens": 23989000}
7361
+ {"current_steps": 36710, "total_steps": 38160, "loss": 0.4434, "lr": 2.1988983679611386e-07, "epoch": 19.240041928721173, "percentage": 96.2, "elapsed_time": "1:44:50", "remaining_time": "0:04:08", "throughput": 3813.96, "total_tokens": 23991784}
7362
+ {"current_steps": 36715, "total_steps": 38160, "loss": 0.4087, "lr": 2.1837921764760462e-07, "epoch": 19.24266247379455, "percentage": 96.21, "elapsed_time": "1:44:51", "remaining_time": "0:04:07", "throughput": 3814.03, "total_tokens": 23996328}
7363
+ {"current_steps": 36720, "total_steps": 38160, "loss": 0.5159, "lr": 2.1687378253144043e-07, "epoch": 19.245283018867923, "percentage": 96.23, "elapsed_time": "1:44:52", "remaining_time": "0:04:06", "throughput": 3814.08, "total_tokens": 23999816}
7364
+ {"current_steps": 36725, "total_steps": 38160, "loss": 0.4818, "lr": 2.153735317625416e-07, "epoch": 19.2479035639413, "percentage": 96.24, "elapsed_time": "1:44:53", "remaining_time": "0:04:05", "throughput": 3814.06, "total_tokens": 24002472}
7365
+ {"current_steps": 36730, "total_steps": 38160, "loss": 0.2916, "lr": 2.1387846565474045e-07, "epoch": 19.250524109014677, "percentage": 96.25, "elapsed_time": "1:44:53", "remaining_time": "0:04:05", "throughput": 3814.06, "total_tokens": 24005256}
7366
+ {"current_steps": 36735, "total_steps": 38160, "loss": 0.4169, "lr": 2.123885845207896e-07, "epoch": 19.25314465408805, "percentage": 96.27, "elapsed_time": "1:44:54", "remaining_time": "0:04:04", "throughput": 3814.09, "total_tokens": 24008776}
7367
+ {"current_steps": 36740, "total_steps": 38160, "loss": 0.3313, "lr": 2.1090388867235356e-07, "epoch": 19.255765199161427, "percentage": 96.28, "elapsed_time": "1:44:55", "remaining_time": "0:04:03", "throughput": 3814.21, "total_tokens": 24012904}
7368
+ {"current_steps": 36745, "total_steps": 38160, "loss": 0.392, "lr": 2.0942437842001728e-07, "epoch": 19.2583857442348, "percentage": 96.29, "elapsed_time": "1:44:56", "remaining_time": "0:04:02", "throughput": 3814.24, "total_tokens": 24016040}
7369
+ {"current_steps": 36750, "total_steps": 38160, "loss": 0.4397, "lr": 2.0795005407327483e-07, "epoch": 19.261006289308177, "percentage": 96.31, "elapsed_time": "1:44:57", "remaining_time": "0:04:01", "throughput": 3814.22, "total_tokens": 24018760}
7370
+ {"current_steps": 36755, "total_steps": 38160, "loss": 0.4753, "lr": 2.0648091594053508e-07, "epoch": 19.26362683438155, "percentage": 96.32, "elapsed_time": "1:44:57", "remaining_time": "0:04:00", "throughput": 3814.26, "total_tokens": 24022088}
7371
+ {"current_steps": 36760, "total_steps": 38160, "loss": 0.4067, "lr": 2.0501696432913275e-07, "epoch": 19.266247379454928, "percentage": 96.33, "elapsed_time": "1:44:58", "remaining_time": "0:03:59", "throughput": 3814.27, "total_tokens": 24025064}
7372
+ {"current_steps": 36765, "total_steps": 38160, "loss": 0.4162, "lr": 2.035581995453034e-07, "epoch": 19.2688679245283, "percentage": 96.34, "elapsed_time": "1:44:59", "remaining_time": "0:03:59", "throughput": 3814.31, "total_tokens": 24028264}
7373
+ {"current_steps": 36770, "total_steps": 38160, "loss": 0.4724, "lr": 2.0210462189420577e-07, "epoch": 19.271488469601678, "percentage": 96.36, "elapsed_time": "1:45:00", "remaining_time": "0:03:58", "throughput": 3814.32, "total_tokens": 24031560}
7374
+ {"current_steps": 36775, "total_steps": 38160, "loss": 0.4924, "lr": 2.006562316799132e-07, "epoch": 19.27410901467505, "percentage": 96.37, "elapsed_time": "1:45:01", "remaining_time": "0:03:57", "throughput": 3814.41, "total_tokens": 24035944}
7375
+ {"current_steps": 36780, "total_steps": 38160, "loss": 0.6033, "lr": 1.992130292054084e-07, "epoch": 19.27672955974843, "percentage": 96.38, "elapsed_time": "1:45:02", "remaining_time": "0:03:56", "throughput": 3814.46, "total_tokens": 24039912}
7376
+ {"current_steps": 36785, "total_steps": 38160, "loss": 0.3655, "lr": 1.9777501477259708e-07, "epoch": 19.279350104821802, "percentage": 96.4, "elapsed_time": "1:45:03", "remaining_time": "0:03:55", "throughput": 3814.45, "total_tokens": 24042792}
7377
+ {"current_steps": 36790, "total_steps": 38160, "loss": 0.4335, "lr": 1.9634218868229414e-07, "epoch": 19.28197064989518, "percentage": 96.41, "elapsed_time": "1:45:03", "remaining_time": "0:03:54", "throughput": 3814.49, "total_tokens": 24046184}
7378
+ {"current_steps": 36795, "total_steps": 38160, "loss": 0.4555, "lr": 1.9491455123423207e-07, "epoch": 19.284591194968552, "percentage": 96.42, "elapsed_time": "1:45:04", "remaining_time": "0:03:53", "throughput": 3814.55, "total_tokens": 24049576}
7379
+ {"current_steps": 36800, "total_steps": 38160, "loss": 0.3928, "lr": 1.9349210272705253e-07, "epoch": 19.28721174004193, "percentage": 96.44, "elapsed_time": "1:45:05", "remaining_time": "0:03:53", "throughput": 3814.5, "total_tokens": 24051944}
7380
+ {"current_steps": 36805, "total_steps": 38160, "loss": 0.4784, "lr": 1.920748434583175e-07, "epoch": 19.289832285115303, "percentage": 96.45, "elapsed_time": "1:45:06", "remaining_time": "0:03:52", "throughput": 3814.52, "total_tokens": 24055112}
7381
+ {"current_steps": 36810, "total_steps": 38160, "loss": 0.4418, "lr": 1.906627737245009e-07, "epoch": 19.29245283018868, "percentage": 96.46, "elapsed_time": "1:45:07", "remaining_time": "0:03:51", "throughput": 3814.61, "total_tokens": 24058888}
7382
+ {"current_steps": 36815, "total_steps": 38160, "loss": 0.3904, "lr": 1.8925589382099152e-07, "epoch": 19.295073375262053, "percentage": 96.48, "elapsed_time": "1:45:07", "remaining_time": "0:03:50", "throughput": 3814.68, "total_tokens": 24062728}
7383
+ {"current_steps": 36820, "total_steps": 38160, "loss": 0.6113, "lr": 1.8785420404209553e-07, "epoch": 19.29769392033543, "percentage": 96.49, "elapsed_time": "1:45:08", "remaining_time": "0:03:49", "throughput": 3814.76, "total_tokens": 24066504}
7384
+ {"current_steps": 36825, "total_steps": 38160, "loss": 0.3991, "lr": 1.864577046810284e-07, "epoch": 19.300314465408803, "percentage": 96.5, "elapsed_time": "1:45:09", "remaining_time": "0:03:48", "throughput": 3814.75, "total_tokens": 24069256}
7385
+ {"current_steps": 36830, "total_steps": 38160, "loss": 0.3964, "lr": 1.8506639602992038e-07, "epoch": 19.30293501048218, "percentage": 96.51, "elapsed_time": "1:45:10", "remaining_time": "0:03:47", "throughput": 3814.71, "total_tokens": 24071720}
7386
+ {"current_steps": 36835, "total_steps": 38160, "loss": 0.2941, "lr": 1.836802783798164e-07, "epoch": 19.305555555555557, "percentage": 96.53, "elapsed_time": "1:45:11", "remaining_time": "0:03:47", "throughput": 3814.77, "total_tokens": 24075720}
7387
+ {"current_steps": 36840, "total_steps": 38160, "loss": 0.367, "lr": 1.822993520206817e-07, "epoch": 19.30817610062893, "percentage": 96.54, "elapsed_time": "1:45:11", "remaining_time": "0:03:46", "throughput": 3814.79, "total_tokens": 24078920}
7388
+ {"current_steps": 36845, "total_steps": 38160, "loss": 0.4179, "lr": 1.8092361724138528e-07, "epoch": 19.310796645702307, "percentage": 96.55, "elapsed_time": "1:45:12", "remaining_time": "0:03:45", "throughput": 3814.83, "total_tokens": 24082376}
7389
+ {"current_steps": 36850, "total_steps": 38160, "loss": 0.3792, "lr": 1.7955307432971914e-07, "epoch": 19.31341719077568, "percentage": 96.57, "elapsed_time": "1:45:13", "remaining_time": "0:03:44", "throughput": 3814.92, "total_tokens": 24085928}
7390
+ {"current_steps": 36855, "total_steps": 38160, "loss": 0.4272, "lr": 1.7818772357238445e-07, "epoch": 19.316037735849058, "percentage": 96.58, "elapsed_time": "1:45:14", "remaining_time": "0:03:43", "throughput": 3814.91, "total_tokens": 24088648}
7391
+ {"current_steps": 36860, "total_steps": 38160, "loss": 0.3622, "lr": 1.7682756525499166e-07, "epoch": 19.31865828092243, "percentage": 96.59, "elapsed_time": "1:45:15", "remaining_time": "0:03:42", "throughput": 3814.97, "total_tokens": 24092136}
7392
+ {"current_steps": 36865, "total_steps": 38160, "loss": 0.4952, "lr": 1.7547259966207708e-07, "epoch": 19.321278825995808, "percentage": 96.61, "elapsed_time": "1:45:15", "remaining_time": "0:03:41", "throughput": 3814.94, "total_tokens": 24094632}
7393
+ {"current_steps": 36870, "total_steps": 38160, "loss": 0.4643, "lr": 1.7412282707708062e-07, "epoch": 19.32389937106918, "percentage": 96.62, "elapsed_time": "1:45:16", "remaining_time": "0:03:41", "throughput": 3815.01, "total_tokens": 24098248}
7394
+ {"current_steps": 36875, "total_steps": 38160, "loss": 0.4447, "lr": 1.7277824778235974e-07, "epoch": 19.32651991614256, "percentage": 96.63, "elapsed_time": "1:45:17", "remaining_time": "0:03:40", "throughput": 3814.97, "total_tokens": 24100872}
7395
+ {"current_steps": 36880, "total_steps": 38160, "loss": 0.5099, "lr": 1.714388620591867e-07, "epoch": 19.329140461215932, "percentage": 96.65, "elapsed_time": "1:45:18", "remaining_time": "0:03:39", "throughput": 3815.01, "total_tokens": 24104520}
7396
+ {"current_steps": 36885, "total_steps": 38160, "loss": 0.4417, "lr": 1.701046701877429e-07, "epoch": 19.33176100628931, "percentage": 96.66, "elapsed_time": "1:45:19", "remaining_time": "0:03:38", "throughput": 3815.15, "total_tokens": 24111048}
7397
+ {"current_steps": 36890, "total_steps": 38160, "loss": 0.4282, "lr": 1.6877567244713011e-07, "epoch": 19.334381551362682, "percentage": 96.67, "elapsed_time": "1:45:20", "remaining_time": "0:03:37", "throughput": 3815.09, "total_tokens": 24113448}
7398
+ {"current_steps": 36895, "total_steps": 38160, "loss": 0.4024, "lr": 1.6745186911535372e-07, "epoch": 19.33700209643606, "percentage": 96.69, "elapsed_time": "1:45:21", "remaining_time": "0:03:36", "throughput": 3815.06, "total_tokens": 24116264}
7399
+ {"current_steps": 36900, "total_steps": 38160, "loss": 0.4014, "lr": 1.6613326046934497e-07, "epoch": 19.339622641509433, "percentage": 96.7, "elapsed_time": "1:45:22", "remaining_time": "0:03:35", "throughput": 3814.97, "total_tokens": 24118888}
7400
+ {"current_steps": 36905, "total_steps": 38160, "loss": 0.4775, "lr": 1.64819846784936e-07, "epoch": 19.34224318658281, "percentage": 96.71, "elapsed_time": "1:45:26", "remaining_time": "0:03:35", "throughput": 3813.11, "total_tokens": 24122056}
7401
+ {"current_steps": 36910, "total_steps": 38160, "loss": 0.5093, "lr": 1.6351162833688204e-07, "epoch": 19.344863731656183, "percentage": 96.72, "elapsed_time": "1:45:26", "remaining_time": "0:03:34", "throughput": 3813.14, "total_tokens": 24125288}
7402
+ {"current_steps": 36915, "total_steps": 38160, "loss": 0.5065, "lr": 1.6220860539884475e-07, "epoch": 19.34748427672956, "percentage": 96.74, "elapsed_time": "1:45:27", "remaining_time": "0:03:33", "throughput": 3813.17, "total_tokens": 24128904}
7403
+ {"current_steps": 36920, "total_steps": 38160, "loss": 0.5227, "lr": 1.6091077824340327e-07, "epoch": 19.350104821802937, "percentage": 96.75, "elapsed_time": "1:45:28", "remaining_time": "0:03:32", "throughput": 3813.2, "total_tokens": 24131880}
7404
+ {"current_steps": 36925, "total_steps": 38160, "loss": 0.414, "lr": 1.5961814714204605e-07, "epoch": 19.35272536687631, "percentage": 96.76, "elapsed_time": "1:45:29", "remaining_time": "0:03:31", "throughput": 3813.19, "total_tokens": 24134600}
7405
+ {"current_steps": 36930, "total_steps": 38160, "loss": 0.3986, "lr": 1.5833071236518172e-07, "epoch": 19.355345911949687, "percentage": 96.78, "elapsed_time": "1:45:30", "remaining_time": "0:03:30", "throughput": 3813.14, "total_tokens": 24137448}
7406
+ {"current_steps": 36935, "total_steps": 38160, "loss": 0.5902, "lr": 1.5704847418212266e-07, "epoch": 19.35796645702306, "percentage": 96.79, "elapsed_time": "1:45:30", "remaining_time": "0:03:29", "throughput": 3813.19, "total_tokens": 24141064}
7407
+ {"current_steps": 36940, "total_steps": 38160, "loss": 0.3595, "lr": 1.5577143286109875e-07, "epoch": 19.360587002096437, "percentage": 96.8, "elapsed_time": "1:45:31", "remaining_time": "0:03:29", "throughput": 3813.15, "total_tokens": 24143688}
7408
+ {"current_steps": 36945, "total_steps": 38160, "loss": 0.304, "lr": 1.5449958866925185e-07, "epoch": 19.36320754716981, "percentage": 96.82, "elapsed_time": "1:45:32", "remaining_time": "0:03:28", "throughput": 3813.15, "total_tokens": 24146984}
7409
+ {"current_steps": 36950, "total_steps": 38160, "loss": 0.5304, "lr": 1.532329418726386e-07, "epoch": 19.365828092243188, "percentage": 96.83, "elapsed_time": "1:45:33", "remaining_time": "0:03:27", "throughput": 3813.28, "total_tokens": 24151784}
7410
+ {"current_steps": 36955, "total_steps": 38160, "loss": 0.4546, "lr": 1.5197149273623036e-07, "epoch": 19.36844863731656, "percentage": 96.84, "elapsed_time": "1:45:34", "remaining_time": "0:03:26", "throughput": 3813.27, "total_tokens": 24154792}
7411
+ {"current_steps": 36960, "total_steps": 38160, "loss": 0.468, "lr": 1.5071524152389936e-07, "epoch": 19.371069182389938, "percentage": 96.86, "elapsed_time": "1:45:35", "remaining_time": "0:03:25", "throughput": 3813.21, "total_tokens": 24157512}
7412
+ {"current_steps": 36965, "total_steps": 38160, "loss": 0.5373, "lr": 1.4946418849844934e-07, "epoch": 19.37368972746331, "percentage": 96.87, "elapsed_time": "1:45:36", "remaining_time": "0:03:24", "throughput": 3813.15, "total_tokens": 24160392}
7413
+ {"current_steps": 36970, "total_steps": 38160, "loss": 0.4106, "lr": 1.4821833392157923e-07, "epoch": 19.37631027253669, "percentage": 96.88, "elapsed_time": "1:45:36", "remaining_time": "0:03:23", "throughput": 3813.18, "total_tokens": 24163656}
7414
+ {"current_steps": 36975, "total_steps": 38160, "loss": 0.4531, "lr": 1.4697767805390838e-07, "epoch": 19.378930817610062, "percentage": 96.89, "elapsed_time": "1:45:37", "remaining_time": "0:03:23", "throughput": 3813.19, "total_tokens": 24166632}
7415
+ {"current_steps": 36980, "total_steps": 38160, "loss": 0.4414, "lr": 1.4574222115497084e-07, "epoch": 19.38155136268344, "percentage": 96.91, "elapsed_time": "1:45:38", "remaining_time": "0:03:22", "throughput": 3813.14, "total_tokens": 24169320}
7416
+ {"current_steps": 36985, "total_steps": 38160, "loss": 0.5452, "lr": 1.4451196348320706e-07, "epoch": 19.384171907756812, "percentage": 96.92, "elapsed_time": "1:45:39", "remaining_time": "0:03:21", "throughput": 3813.18, "total_tokens": 24172520}
7417
+ {"current_steps": 36990, "total_steps": 38160, "loss": 0.333, "lr": 1.4328690529597232e-07, "epoch": 19.38679245283019, "percentage": 96.93, "elapsed_time": "1:45:40", "remaining_time": "0:03:20", "throughput": 3813.26, "total_tokens": 24176232}
7418
+ {"current_steps": 36995, "total_steps": 38160, "loss": 0.448, "lr": 1.4206704684953943e-07, "epoch": 19.389412997903563, "percentage": 96.95, "elapsed_time": "1:45:40", "remaining_time": "0:03:19", "throughput": 3813.3, "total_tokens": 24179400}
7419
+ {"current_steps": 37000, "total_steps": 38160, "loss": 0.4791, "lr": 1.4085238839908476e-07, "epoch": 19.39203354297694, "percentage": 96.96, "elapsed_time": "1:45:41", "remaining_time": "0:03:18", "throughput": 3813.26, "total_tokens": 24182568}
7420
+ {"current_steps": 37005, "total_steps": 38160, "loss": 0.4492, "lr": 1.3964293019870235e-07, "epoch": 19.394654088050313, "percentage": 96.97, "elapsed_time": "1:45:42", "remaining_time": "0:03:17", "throughput": 3813.28, "total_tokens": 24185640}
7421
+ {"current_steps": 37010, "total_steps": 38160, "loss": 0.494, "lr": 1.3843867250139807e-07, "epoch": 19.39727463312369, "percentage": 96.99, "elapsed_time": "1:45:43", "remaining_time": "0:03:17", "throughput": 3813.31, "total_tokens": 24189256}
7422
+ {"current_steps": 37015, "total_steps": 38160, "loss": 0.4076, "lr": 1.3723961555908715e-07, "epoch": 19.399895178197063, "percentage": 97.0, "elapsed_time": "1:45:44", "remaining_time": "0:03:16", "throughput": 3813.37, "total_tokens": 24192744}
7423
+ {"current_steps": 37020, "total_steps": 38160, "loss": 0.4929, "lr": 1.3604575962259947e-07, "epoch": 19.40251572327044, "percentage": 97.01, "elapsed_time": "1:45:45", "remaining_time": "0:03:15", "throughput": 3813.44, "total_tokens": 24197128}
7424
+ {"current_steps": 37025, "total_steps": 38160, "loss": 0.3619, "lr": 1.3485710494167692e-07, "epoch": 19.405136268343817, "percentage": 97.03, "elapsed_time": "1:45:46", "remaining_time": "0:03:14", "throughput": 3813.48, "total_tokens": 24200552}
7425
+ {"current_steps": 37030, "total_steps": 38160, "loss": 0.4185, "lr": 1.3367365176496783e-07, "epoch": 19.40775681341719, "percentage": 97.04, "elapsed_time": "1:45:46", "remaining_time": "0:03:13", "throughput": 3813.5, "total_tokens": 24203880}
7426
+ {"current_steps": 37035, "total_steps": 38160, "loss": 0.4738, "lr": 1.324954003400436e-07, "epoch": 19.410377358490567, "percentage": 97.05, "elapsed_time": "1:45:47", "remaining_time": "0:03:12", "throughput": 3813.61, "total_tokens": 24207752}
7427
+ {"current_steps": 37040, "total_steps": 38160, "loss": 0.5024, "lr": 1.313223509133793e-07, "epoch": 19.41299790356394, "percentage": 97.06, "elapsed_time": "1:45:48", "remaining_time": "0:03:11", "throughput": 3813.7, "total_tokens": 24211752}
7428
+ {"current_steps": 37045, "total_steps": 38160, "loss": 0.4029, "lr": 1.301545037303592e-07, "epoch": 19.415618448637318, "percentage": 97.08, "elapsed_time": "1:45:49", "remaining_time": "0:03:11", "throughput": 3813.6, "total_tokens": 24213992}
7429
+ {"current_steps": 37050, "total_steps": 38160, "loss": 0.4904, "lr": 1.2899185903529066e-07, "epoch": 19.41823899371069, "percentage": 97.09, "elapsed_time": "1:45:50", "remaining_time": "0:03:10", "throughput": 3813.55, "total_tokens": 24216584}
7430
+ {"current_steps": 37055, "total_steps": 38160, "loss": 0.4096, "lr": 1.278344170713791e-07, "epoch": 19.420859538784068, "percentage": 97.1, "elapsed_time": "1:45:50", "remaining_time": "0:03:09", "throughput": 3813.55, "total_tokens": 24219336}
7431
+ {"current_steps": 37060, "total_steps": 38160, "loss": 0.4119, "lr": 1.2668217808075033e-07, "epoch": 19.42348008385744, "percentage": 97.12, "elapsed_time": "1:45:51", "remaining_time": "0:03:08", "throughput": 3813.52, "total_tokens": 24222024}
7432
+ {"current_steps": 37065, "total_steps": 38160, "loss": 0.4455, "lr": 1.255351423044393e-07, "epoch": 19.42610062893082, "percentage": 97.13, "elapsed_time": "1:45:52", "remaining_time": "0:03:07", "throughput": 3813.57, "total_tokens": 24225384}
7433
+ {"current_steps": 37070, "total_steps": 38160, "loss": 0.4075, "lr": 1.2439330998239572e-07, "epoch": 19.428721174004192, "percentage": 97.14, "elapsed_time": "1:45:53", "remaining_time": "0:03:06", "throughput": 3813.51, "total_tokens": 24228232}
7434
+ {"current_steps": 37075, "total_steps": 38160, "loss": 0.498, "lr": 1.2325668135347578e-07, "epoch": 19.43134171907757, "percentage": 97.16, "elapsed_time": "1:45:54", "remaining_time": "0:03:05", "throughput": 3813.48, "total_tokens": 24231432}
7435
+ {"current_steps": 37080, "total_steps": 38160, "loss": 0.3734, "lr": 1.221252566554476e-07, "epoch": 19.433962264150942, "percentage": 97.17, "elapsed_time": "1:45:55", "remaining_time": "0:03:05", "throughput": 3813.52, "total_tokens": 24234952}
7436
+ {"current_steps": 37085, "total_steps": 38160, "loss": 0.3886, "lr": 1.2099903612499685e-07, "epoch": 19.43658280922432, "percentage": 97.18, "elapsed_time": "1:45:55", "remaining_time": "0:03:04", "throughput": 3813.5, "total_tokens": 24237768}
7437
+ {"current_steps": 37090, "total_steps": 38160, "loss": 0.4956, "lr": 1.198780199977101e-07, "epoch": 19.439203354297693, "percentage": 97.2, "elapsed_time": "1:45:56", "remaining_time": "0:03:03", "throughput": 3813.48, "total_tokens": 24241032}
7438
+ {"current_steps": 37095, "total_steps": 38160, "loss": 0.4756, "lr": 1.1876220850809416e-07, "epoch": 19.44182389937107, "percentage": 97.21, "elapsed_time": "1:45:57", "remaining_time": "0:03:02", "throughput": 3813.57, "total_tokens": 24245416}
7439
+ {"current_steps": 37100, "total_steps": 38160, "loss": 0.4978, "lr": 1.1765160188956514e-07, "epoch": 19.444444444444443, "percentage": 97.22, "elapsed_time": "1:45:58", "remaining_time": "0:03:01", "throughput": 3813.6, "total_tokens": 24249128}
7440
+ {"current_steps": 37105, "total_steps": 38160, "loss": 0.3804, "lr": 1.1654620037445107e-07, "epoch": 19.44706498951782, "percentage": 97.24, "elapsed_time": "1:45:59", "remaining_time": "0:03:00", "throughput": 3813.62, "total_tokens": 24252200}
7441
+ {"current_steps": 37110, "total_steps": 38160, "loss": 0.4231, "lr": 1.1544600419398088e-07, "epoch": 19.449685534591197, "percentage": 97.25, "elapsed_time": "1:46:00", "remaining_time": "0:02:59", "throughput": 3813.6, "total_tokens": 24255112}
7442
+ {"current_steps": 37115, "total_steps": 38160, "loss": 0.5847, "lr": 1.1435101357831213e-07, "epoch": 19.45230607966457, "percentage": 97.26, "elapsed_time": "1:46:00", "remaining_time": "0:02:59", "throughput": 3813.65, "total_tokens": 24258504}
7443
+ {"current_steps": 37120, "total_steps": 38160, "loss": 0.475, "lr": 1.1326122875650047e-07, "epoch": 19.454926624737947, "percentage": 97.27, "elapsed_time": "1:46:01", "remaining_time": "0:02:58", "throughput": 3813.53, "total_tokens": 24260776}
7444
+ {"current_steps": 37125, "total_steps": 38160, "loss": 0.3722, "lr": 1.1217664995651633e-07, "epoch": 19.45754716981132, "percentage": 97.29, "elapsed_time": "1:46:02", "remaining_time": "0:02:57", "throughput": 3813.54, "total_tokens": 24263976}
7445
+ {"current_steps": 37130, "total_steps": 38160, "loss": 0.4245, "lr": 1.1109727740523935e-07, "epoch": 19.460167714884697, "percentage": 97.3, "elapsed_time": "1:46:03", "remaining_time": "0:02:56", "throughput": 3813.57, "total_tokens": 24267144}
7446
+ {"current_steps": 37135, "total_steps": 38160, "loss": 0.4354, "lr": 1.1002311132846944e-07, "epoch": 19.46278825995807, "percentage": 97.31, "elapsed_time": "1:46:04", "remaining_time": "0:02:55", "throughput": 3813.58, "total_tokens": 24270312}
7447
+ {"current_steps": 37140, "total_steps": 38160, "loss": 0.4082, "lr": 1.0895415195090186e-07, "epoch": 19.465408805031448, "percentage": 97.33, "elapsed_time": "1:46:05", "remaining_time": "0:02:54", "throughput": 3813.59, "total_tokens": 24274632}
7448
+ {"current_steps": 37145, "total_steps": 38160, "loss": 0.577, "lr": 1.0789039949615221e-07, "epoch": 19.46802935010482, "percentage": 97.34, "elapsed_time": "1:46:06", "remaining_time": "0:02:53", "throughput": 3813.71, "total_tokens": 24279144}
7449
+ {"current_steps": 37150, "total_steps": 38160, "loss": 0.484, "lr": 1.0683185418674801e-07, "epoch": 19.470649895178198, "percentage": 97.35, "elapsed_time": "1:46:07", "remaining_time": "0:02:53", "throughput": 3813.46, "total_tokens": 24282024}
7450
+ {"current_steps": 37155, "total_steps": 38160, "loss": 0.5095, "lr": 1.0577851624412604e-07, "epoch": 19.47327044025157, "percentage": 97.37, "elapsed_time": "1:46:08", "remaining_time": "0:02:52", "throughput": 3813.47, "total_tokens": 24285288}
7451
+ {"current_steps": 37160, "total_steps": 38160, "loss": 0.3604, "lr": 1.0473038588862672e-07, "epoch": 19.47589098532495, "percentage": 97.38, "elapsed_time": "1:46:09", "remaining_time": "0:02:51", "throughput": 3813.57, "total_tokens": 24289384}
7452
+ {"current_steps": 37165, "total_steps": 38160, "loss": 0.581, "lr": 1.0368746333951351e-07, "epoch": 19.478511530398322, "percentage": 97.39, "elapsed_time": "1:46:10", "remaining_time": "0:02:50", "throughput": 3813.46, "total_tokens": 24291848}
7453
+ {"current_steps": 37170, "total_steps": 38160, "loss": 0.3464, "lr": 1.0264974881494805e-07, "epoch": 19.4811320754717, "percentage": 97.41, "elapsed_time": "1:46:11", "remaining_time": "0:02:49", "throughput": 3813.54, "total_tokens": 24296296}
7454
+ {"current_steps": 37175, "total_steps": 38160, "loss": 0.6834, "lr": 1.0161724253201222e-07, "epoch": 19.483752620545072, "percentage": 97.42, "elapsed_time": "1:46:11", "remaining_time": "0:02:48", "throughput": 3813.54, "total_tokens": 24299176}
7455
+ {"current_steps": 37180, "total_steps": 38160, "loss": 0.3602, "lr": 1.0058994470669436e-07, "epoch": 19.48637316561845, "percentage": 97.43, "elapsed_time": "1:46:12", "remaining_time": "0:02:47", "throughput": 3813.53, "total_tokens": 24302216}
7456
+ {"current_steps": 37185, "total_steps": 38160, "loss": 0.5161, "lr": 9.956785555388926e-08, "epoch": 19.488993710691823, "percentage": 97.44, "elapsed_time": "1:46:13", "remaining_time": "0:02:47", "throughput": 3813.42, "total_tokens": 24304648}
7457
+ {"current_steps": 37190, "total_steps": 38160, "loss": 0.4142, "lr": 9.855097528741475e-08, "epoch": 19.4916142557652, "percentage": 97.46, "elapsed_time": "1:46:14", "remaining_time": "0:02:46", "throughput": 3813.46, "total_tokens": 24308712}
7458
+ {"current_steps": 37195, "total_steps": 38160, "loss": 0.411, "lr": 9.753930411998402e-08, "epoch": 19.494234800838573, "percentage": 97.47, "elapsed_time": "1:46:15", "remaining_time": "0:02:45", "throughput": 3813.52, "total_tokens": 24312072}
7459
+ {"current_steps": 37200, "total_steps": 38160, "loss": 0.3572, "lr": 9.653284226322501e-08, "epoch": 19.49685534591195, "percentage": 97.48, "elapsed_time": "1:46:16", "remaining_time": "0:02:44", "throughput": 3813.66, "total_tokens": 24318312}
7460
+ {"current_steps": 37205, "total_steps": 38160, "loss": 0.4715, "lr": 9.553158992768318e-08, "epoch": 19.499475890985323, "percentage": 97.5, "elapsed_time": "1:46:17", "remaining_time": "0:02:43", "throughput": 3813.63, "total_tokens": 24321128}
7461
+ {"current_steps": 37210, "total_steps": 38160, "loss": 0.382, "lr": 9.453554732281044e-08, "epoch": 19.5020964360587, "percentage": 97.51, "elapsed_time": "1:46:18", "remaining_time": "0:02:42", "throughput": 3813.67, "total_tokens": 24324392}
7462
+ {"current_steps": 37215, "total_steps": 38160, "loss": 0.6231, "lr": 9.354471465696236e-08, "epoch": 19.504716981132077, "percentage": 97.52, "elapsed_time": "1:46:19", "remaining_time": "0:02:41", "throughput": 3813.67, "total_tokens": 24327560}
7463
+ {"current_steps": 37220, "total_steps": 38160, "loss": 0.5343, "lr": 9.255909213741199e-08, "epoch": 19.50733752620545, "percentage": 97.54, "elapsed_time": "1:46:19", "remaining_time": "0:02:41", "throughput": 3813.67, "total_tokens": 24330504}
7464
+ {"current_steps": 37225, "total_steps": 38160, "loss": 0.3562, "lr": 9.157867997034164e-08, "epoch": 19.509958071278827, "percentage": 97.55, "elapsed_time": "1:46:20", "remaining_time": "0:02:40", "throughput": 3813.68, "total_tokens": 24333800}
7465
+ {"current_steps": 37230, "total_steps": 38160, "loss": 0.4231, "lr": 9.060347836084004e-08, "epoch": 19.5125786163522, "percentage": 97.56, "elapsed_time": "1:46:21", "remaining_time": "0:02:39", "throughput": 3813.6, "total_tokens": 24336264}
7466
+ {"current_steps": 37235, "total_steps": 38160, "loss": 0.5148, "lr": 8.96334875129079e-08, "epoch": 19.515199161425578, "percentage": 97.58, "elapsed_time": "1:46:22", "remaining_time": "0:02:38", "throughput": 3813.55, "total_tokens": 24338696}
7467
+ {"current_steps": 37240, "total_steps": 38160, "loss": 0.4085, "lr": 8.866870762946067e-08, "epoch": 19.51781970649895, "percentage": 97.59, "elapsed_time": "1:46:23", "remaining_time": "0:02:37", "throughput": 3813.56, "total_tokens": 24342056}
7468
+ {"current_steps": 37245, "total_steps": 38160, "loss": 0.4558, "lr": 8.77091389123147e-08, "epoch": 19.520440251572328, "percentage": 97.6, "elapsed_time": "1:46:23", "remaining_time": "0:02:36", "throughput": 3813.61, "total_tokens": 24345480}
7469
+ {"current_steps": 37250, "total_steps": 38160, "loss": 0.4462, "lr": 8.675478156220385e-08, "epoch": 19.5230607966457, "percentage": 97.62, "elapsed_time": "1:46:24", "remaining_time": "0:02:35", "throughput": 3813.65, "total_tokens": 24348680}
7470
+ {"current_steps": 37255, "total_steps": 38160, "loss": 0.3846, "lr": 8.580563577876566e-08, "epoch": 19.52568134171908, "percentage": 97.63, "elapsed_time": "1:46:25", "remaining_time": "0:02:35", "throughput": 3813.65, "total_tokens": 24351624}
7471
+ {"current_steps": 37260, "total_steps": 38160, "loss": 0.4651, "lr": 8.486170176055242e-08, "epoch": 19.528301886792452, "percentage": 97.64, "elapsed_time": "1:46:26", "remaining_time": "0:02:34", "throughput": 3813.81, "total_tokens": 24356552}
7472
+ {"current_steps": 37265, "total_steps": 38160, "loss": 0.3945, "lr": 8.392297970502282e-08, "epoch": 19.53092243186583, "percentage": 97.65, "elapsed_time": "1:46:27", "remaining_time": "0:02:33", "throughput": 3813.81, "total_tokens": 24359688}
7473
+ {"current_steps": 37270, "total_steps": 38160, "loss": 0.4343, "lr": 8.298946980855315e-08, "epoch": 19.533542976939202, "percentage": 97.67, "elapsed_time": "1:46:28", "remaining_time": "0:02:32", "throughput": 3813.91, "total_tokens": 24364328}
7474
+ {"current_steps": 37275, "total_steps": 38160, "loss": 0.3014, "lr": 8.206117226641497e-08, "epoch": 19.53616352201258, "percentage": 97.68, "elapsed_time": "1:46:29", "remaining_time": "0:02:31", "throughput": 3813.98, "total_tokens": 24367752}
7475
+ {"current_steps": 37280, "total_steps": 38160, "loss": 0.458, "lr": 8.113808727280015e-08, "epoch": 19.538784067085953, "percentage": 97.69, "elapsed_time": "1:46:29", "remaining_time": "0:02:30", "throughput": 3814.05, "total_tokens": 24371208}
7476
+ {"current_steps": 37285, "total_steps": 38160, "loss": 0.3503, "lr": 8.022021502080979e-08, "epoch": 19.54140461215933, "percentage": 97.71, "elapsed_time": "1:46:30", "remaining_time": "0:02:29", "throughput": 3814.1, "total_tokens": 24374824}
7477
+ {"current_steps": 37290, "total_steps": 38160, "loss": 0.3512, "lr": 7.930755570244863e-08, "epoch": 19.544025157232703, "percentage": 97.72, "elapsed_time": "1:46:31", "remaining_time": "0:02:29", "throughput": 3814.13, "total_tokens": 24378408}
7478
+ {"current_steps": 37295, "total_steps": 38160, "loss": 0.544, "lr": 7.840010950863619e-08, "epoch": 19.54664570230608, "percentage": 97.73, "elapsed_time": "1:46:32", "remaining_time": "0:02:28", "throughput": 3814.09, "total_tokens": 24381160}
7479
+ {"current_steps": 37300, "total_steps": 38160, "loss": 0.5857, "lr": 7.749787662920116e-08, "epoch": 19.549266247379457, "percentage": 97.75, "elapsed_time": "1:46:33", "remaining_time": "0:02:27", "throughput": 3814.1, "total_tokens": 24384072}
7480
+ {"current_steps": 37305, "total_steps": 38160, "loss": 0.36, "lr": 7.660085725288146e-08, "epoch": 19.55188679245283, "percentage": 97.76, "elapsed_time": "1:46:33", "remaining_time": "0:02:26", "throughput": 3814.07, "total_tokens": 24386952}
7481
+ {"current_steps": 37310, "total_steps": 38160, "loss": 0.3809, "lr": 7.570905156731867e-08, "epoch": 19.554507337526207, "percentage": 97.77, "elapsed_time": "1:46:34", "remaining_time": "0:02:25", "throughput": 3814.13, "total_tokens": 24390600}
7482
+ {"current_steps": 37315, "total_steps": 38160, "loss": 0.4289, "lr": 7.482245975907188e-08, "epoch": 19.55712788259958, "percentage": 97.79, "elapsed_time": "1:46:35", "remaining_time": "0:02:24", "throughput": 3814.08, "total_tokens": 24393416}
7483
+ {"current_steps": 37320, "total_steps": 38160, "loss": 0.4035, "lr": 7.394108201360383e-08, "epoch": 19.559748427672957, "percentage": 97.8, "elapsed_time": "1:46:36", "remaining_time": "0:02:23", "throughput": 3814.07, "total_tokens": 24396328}
7484
+ {"current_steps": 37325, "total_steps": 38160, "loss": 0.3631, "lr": 7.306491851529206e-08, "epoch": 19.56236897274633, "percentage": 97.81, "elapsed_time": "1:46:38", "remaining_time": "0:02:23", "throughput": 3814.24, "total_tokens": 24404040}
7485
+ {"current_steps": 37330, "total_steps": 38160, "loss": 0.4798, "lr": 7.219396944741774e-08, "epoch": 19.564989517819708, "percentage": 97.82, "elapsed_time": "1:46:38", "remaining_time": "0:02:22", "throughput": 3814.28, "total_tokens": 24407304}
7486
+ {"current_steps": 37335, "total_steps": 38160, "loss": 0.5418, "lr": 7.132823499217123e-08, "epoch": 19.56761006289308, "percentage": 97.84, "elapsed_time": "1:46:39", "remaining_time": "0:02:21", "throughput": 3814.39, "total_tokens": 24411496}
7487
+ {"current_steps": 37340, "total_steps": 38160, "loss": 0.4115, "lr": 7.046771533065766e-08, "epoch": 19.570230607966458, "percentage": 97.85, "elapsed_time": "1:46:40", "remaining_time": "0:02:20", "throughput": 3814.39, "total_tokens": 24414280}
7488
+ {"current_steps": 37345, "total_steps": 38160, "loss": 0.3438, "lr": 6.961241064288859e-08, "epoch": 19.57285115303983, "percentage": 97.86, "elapsed_time": "1:46:41", "remaining_time": "0:02:19", "throughput": 3814.37, "total_tokens": 24417352}
7489
+ {"current_steps": 37350, "total_steps": 38160, "loss": 0.5177, "lr": 6.876232110778202e-08, "epoch": 19.57547169811321, "percentage": 97.88, "elapsed_time": "1:46:42", "remaining_time": "0:02:18", "throughput": 3814.45, "total_tokens": 24421192}
7490
+ {"current_steps": 37355, "total_steps": 38160, "loss": 0.4716, "lr": 6.791744690316515e-08, "epoch": 19.578092243186582, "percentage": 97.89, "elapsed_time": "1:46:43", "remaining_time": "0:02:17", "throughput": 3814.5, "total_tokens": 24424744}
7491
+ {"current_steps": 37360, "total_steps": 38160, "loss": 0.4328, "lr": 6.707778820577715e-08, "epoch": 19.58071278825996, "percentage": 97.9, "elapsed_time": "1:46:43", "remaining_time": "0:02:17", "throughput": 3814.52, "total_tokens": 24427592}
7492
+ {"current_steps": 37365, "total_steps": 38160, "loss": 0.5384, "lr": 6.624334519126919e-08, "epoch": 19.583333333333332, "percentage": 97.92, "elapsed_time": "1:46:44", "remaining_time": "0:02:16", "throughput": 3814.48, "total_tokens": 24430600}
7493
+ {"current_steps": 37370, "total_steps": 38160, "loss": 0.4324, "lr": 6.541411803419329e-08, "epoch": 19.58595387840671, "percentage": 97.93, "elapsed_time": "1:46:45", "remaining_time": "0:02:15", "throughput": 3814.4, "total_tokens": 24433160}
7494
+ {"current_steps": 37375, "total_steps": 38160, "loss": 0.5886, "lr": 6.459010690801626e-08, "epoch": 19.588574423480082, "percentage": 97.94, "elapsed_time": "1:46:46", "remaining_time": "0:02:14", "throughput": 3814.29, "total_tokens": 24435656}
7495
+ {"current_steps": 37380, "total_steps": 38160, "loss": 0.5076, "lr": 6.377131198510855e-08, "epoch": 19.59119496855346, "percentage": 97.96, "elapsed_time": "1:46:47", "remaining_time": "0:02:13", "throughput": 3814.29, "total_tokens": 24438440}
7496
+ {"current_steps": 37385, "total_steps": 38160, "loss": 0.4128, "lr": 6.295773343675537e-08, "epoch": 19.593815513626833, "percentage": 97.97, "elapsed_time": "1:46:47", "remaining_time": "0:02:12", "throughput": 3814.3, "total_tokens": 24441416}
7497
+ {"current_steps": 37390, "total_steps": 38160, "loss": 0.3427, "lr": 6.214937143314837e-08, "epoch": 19.59643605870021, "percentage": 97.98, "elapsed_time": "1:46:48", "remaining_time": "0:02:11", "throughput": 3814.3, "total_tokens": 24444328}
7498
+ {"current_steps": 37395, "total_steps": 38160, "loss": 0.4014, "lr": 6.134622614338559e-08, "epoch": 19.599056603773583, "percentage": 98.0, "elapsed_time": "1:46:49", "remaining_time": "0:02:11", "throughput": 3814.18, "total_tokens": 24446472}
7499
+ {"current_steps": 37400, "total_steps": 38160, "loss": 0.4751, "lr": 6.05482977354771e-08, "epoch": 19.60167714884696, "percentage": 98.01, "elapsed_time": "1:46:50", "remaining_time": "0:02:10", "throughput": 3814.2, "total_tokens": 24449544}
7500
+ {"current_steps": 37405, "total_steps": 38160, "loss": 0.4578, "lr": 5.975558637634215e-08, "epoch": 19.604297693920337, "percentage": 98.02, "elapsed_time": "1:46:50", "remaining_time": "0:02:09", "throughput": 3814.25, "total_tokens": 24452776}
7501
+ {"current_steps": 37410, "total_steps": 38160, "loss": 0.4429, "lr": 5.896809223180366e-08, "epoch": 19.60691823899371, "percentage": 98.03, "elapsed_time": "1:46:51", "remaining_time": "0:02:08", "throughput": 3814.23, "total_tokens": 24455560}
7502
+ {"current_steps": 37415, "total_steps": 38160, "loss": 0.4642, "lr": 5.8185815466596516e-08, "epoch": 19.609538784067087, "percentage": 98.05, "elapsed_time": "1:46:52", "remaining_time": "0:02:07", "throughput": 3814.24, "total_tokens": 24458408}
7503
+ {"current_steps": 37420, "total_steps": 38160, "loss": 0.3711, "lr": 5.7408756244370365e-08, "epoch": 19.61215932914046, "percentage": 98.06, "elapsed_time": "1:46:53", "remaining_time": "0:02:06", "throughput": 3814.24, "total_tokens": 24461576}
7504
+ {"current_steps": 37425, "total_steps": 38160, "loss": 0.4304, "lr": 5.663691472766741e-08, "epoch": 19.614779874213838, "percentage": 98.07, "elapsed_time": "1:46:54", "remaining_time": "0:02:05", "throughput": 3814.28, "total_tokens": 24464840}
7505
+ {"current_steps": 37430, "total_steps": 38160, "loss": 0.4123, "lr": 5.587029107795572e-08, "epoch": 19.61740041928721, "percentage": 98.09, "elapsed_time": "1:46:54", "remaining_time": "0:02:05", "throughput": 3814.31, "total_tokens": 24468200}
7506
+ {"current_steps": 37435, "total_steps": 38160, "loss": 0.4981, "lr": 5.510888545559867e-08, "epoch": 19.620020964360588, "percentage": 98.1, "elapsed_time": "1:46:55", "remaining_time": "0:02:04", "throughput": 3814.34, "total_tokens": 24471176}
7507
+ {"current_steps": 37440, "total_steps": 38160, "loss": 0.3239, "lr": 5.435269801987997e-08, "epoch": 19.62264150943396, "percentage": 98.11, "elapsed_time": "1:46:56", "remaining_time": "0:02:03", "throughput": 3814.31, "total_tokens": 24473960}
7508
+ {"current_steps": 37445, "total_steps": 38160, "loss": 0.341, "lr": 5.360172892897863e-08, "epoch": 19.62526205450734, "percentage": 98.13, "elapsed_time": "1:46:57", "remaining_time": "0:02:02", "throughput": 3814.28, "total_tokens": 24476776}
7509
+ {"current_steps": 37450, "total_steps": 38160, "loss": 0.483, "lr": 5.285597833999401e-08, "epoch": 19.627882599580712, "percentage": 98.14, "elapsed_time": "1:46:58", "remaining_time": "0:02:01", "throughput": 3814.3, "total_tokens": 24480456}
7510
+ {"current_steps": 37455, "total_steps": 38160, "loss": 0.3244, "lr": 5.2115446408926295e-08, "epoch": 19.63050314465409, "percentage": 98.15, "elapsed_time": "1:46:58", "remaining_time": "0:02:00", "throughput": 3814.3, "total_tokens": 24483400}
7511
+ {"current_steps": 37460, "total_steps": 38160, "loss": 0.5697, "lr": 5.138013329068769e-08, "epoch": 19.633123689727462, "percentage": 98.17, "elapsed_time": "1:46:59", "remaining_time": "0:01:59", "throughput": 3814.32, "total_tokens": 24486536}
7512
+ {"current_steps": 37465, "total_steps": 38160, "loss": 0.3423, "lr": 5.065003913909405e-08, "epoch": 19.63574423480084, "percentage": 98.18, "elapsed_time": "1:47:00", "remaining_time": "0:01:59", "throughput": 3814.34, "total_tokens": 24490056}
7513
+ {"current_steps": 37470, "total_steps": 38160, "loss": 0.4421, "lr": 4.9925164106875975e-08, "epoch": 19.638364779874212, "percentage": 98.19, "elapsed_time": "1:47:01", "remaining_time": "0:01:58", "throughput": 3814.36, "total_tokens": 24493160}
7514
+ {"current_steps": 37475, "total_steps": 38160, "loss": 0.5037, "lr": 4.9205508345670506e-08, "epoch": 19.64098532494759, "percentage": 98.2, "elapsed_time": "1:47:02", "remaining_time": "0:01:57", "throughput": 3814.38, "total_tokens": 24496200}
7515
+ {"current_steps": 37480, "total_steps": 38160, "loss": 0.3433, "lr": 4.8491072006015546e-08, "epoch": 19.643605870020963, "percentage": 98.22, "elapsed_time": "1:47:03", "remaining_time": "0:01:56", "throughput": 3814.44, "total_tokens": 24500680}
7516
+ {"current_steps": 37485, "total_steps": 38160, "loss": 0.6433, "lr": 4.778185523736933e-08, "epoch": 19.64622641509434, "percentage": 98.23, "elapsed_time": "1:47:03", "remaining_time": "0:01:55", "throughput": 3814.43, "total_tokens": 24503720}
7517
+ {"current_steps": 37490, "total_steps": 38160, "loss": 0.4494, "lr": 4.7077858188085414e-08, "epoch": 19.648846960167717, "percentage": 98.24, "elapsed_time": "1:47:04", "remaining_time": "0:01:54", "throughput": 3814.4, "total_tokens": 24506440}
7518
+ {"current_steps": 37495, "total_steps": 38160, "loss": 0.5013, "lr": 4.6379081005437644e-08, "epoch": 19.65146750524109, "percentage": 98.26, "elapsed_time": "1:47:05", "remaining_time": "0:01:53", "throughput": 3814.39, "total_tokens": 24509384}
7519
+ {"current_steps": 37500, "total_steps": 38160, "loss": 0.4148, "lr": 4.568552383560076e-08, "epoch": 19.654088050314467, "percentage": 98.27, "elapsed_time": "1:47:06", "remaining_time": "0:01:53", "throughput": 3814.3, "total_tokens": 24511720}
7520
+ {"current_steps": 37505, "total_steps": 38160, "loss": 0.4663, "lr": 4.4997186823655945e-08, "epoch": 19.65670859538784, "percentage": 98.28, "elapsed_time": "1:47:07", "remaining_time": "0:01:52", "throughput": 3814.23, "total_tokens": 24514472}
7521
+ {"current_steps": 37510, "total_steps": 38160, "loss": 0.4162, "lr": 4.431407011360189e-08, "epoch": 19.659329140461217, "percentage": 98.3, "elapsed_time": "1:47:07", "remaining_time": "0:01:51", "throughput": 3814.21, "total_tokens": 24517224}
7522
+ {"current_steps": 37515, "total_steps": 38160, "loss": 0.4348, "lr": 4.3636173848332627e-08, "epoch": 19.66194968553459, "percentage": 98.31, "elapsed_time": "1:47:08", "remaining_time": "0:01:50", "throughput": 3814.18, "total_tokens": 24519944}
7523
+ {"current_steps": 37520, "total_steps": 38160, "loss": 0.4855, "lr": 4.2963498169656946e-08, "epoch": 19.664570230607968, "percentage": 98.32, "elapsed_time": "1:47:09", "remaining_time": "0:01:49", "throughput": 3814.29, "total_tokens": 24524840}
7524
+ {"current_steps": 37525, "total_steps": 38160, "loss": 0.4447, "lr": 4.229604321829561e-08, "epoch": 19.66719077568134, "percentage": 98.34, "elapsed_time": "1:47:10", "remaining_time": "0:01:48", "throughput": 3814.31, "total_tokens": 24527912}
7525
+ {"current_steps": 37530, "total_steps": 38160, "loss": 0.3428, "lr": 4.16338091338675e-08, "epoch": 19.669811320754718, "percentage": 98.35, "elapsed_time": "1:47:11", "remaining_time": "0:01:47", "throughput": 3814.22, "total_tokens": 24530696}
7526
+ {"current_steps": 37535, "total_steps": 38160, "loss": 0.2957, "lr": 4.097679605490623e-08, "epoch": 19.67243186582809, "percentage": 98.36, "elapsed_time": "1:47:12", "remaining_time": "0:01:47", "throughput": 3814.13, "total_tokens": 24533256}
7527
+ {"current_steps": 37540, "total_steps": 38160, "loss": 0.487, "lr": 4.032500411885465e-08, "epoch": 19.67505241090147, "percentage": 98.38, "elapsed_time": "1:47:13", "remaining_time": "0:01:46", "throughput": 3814.13, "total_tokens": 24536552}
7528
+ {"current_steps": 37545, "total_steps": 38160, "loss": 0.44, "lr": 3.967843346205369e-08, "epoch": 19.677672955974842, "percentage": 98.39, "elapsed_time": "1:47:13", "remaining_time": "0:01:45", "throughput": 3814.13, "total_tokens": 24539464}
7529
+ {"current_steps": 37550, "total_steps": 38160, "loss": 0.3768, "lr": 3.903708421976182e-08, "epoch": 19.68029350104822, "percentage": 98.4, "elapsed_time": "1:47:14", "remaining_time": "0:01:44", "throughput": 3814.11, "total_tokens": 24542312}
7530
+ {"current_steps": 37555, "total_steps": 38160, "loss": 0.3896, "lr": 3.840095652614395e-08, "epoch": 19.682914046121592, "percentage": 98.41, "elapsed_time": "1:47:15", "remaining_time": "0:01:43", "throughput": 3814.18, "total_tokens": 24546056}
7531
+ {"current_steps": 37560, "total_steps": 38160, "loss": 0.4339, "lr": 3.777005051426863e-08, "epoch": 19.68553459119497, "percentage": 98.43, "elapsed_time": "1:47:16", "remaining_time": "0:01:42", "throughput": 3814.2, "total_tokens": 24549512}
7532
+ {"current_steps": 37565, "total_steps": 38160, "loss": 0.4094, "lr": 3.71443663161164e-08, "epoch": 19.688155136268342, "percentage": 98.44, "elapsed_time": "1:47:17", "remaining_time": "0:01:41", "throughput": 3814.27, "total_tokens": 24553000}
7533
+ {"current_steps": 37570, "total_steps": 38160, "loss": 0.658, "lr": 3.652390406256867e-08, "epoch": 19.69077568134172, "percentage": 98.45, "elapsed_time": "1:47:17", "remaining_time": "0:01:41", "throughput": 3814.29, "total_tokens": 24555944}
7534
+ {"current_steps": 37575, "total_steps": 38160, "loss": 0.3453, "lr": 3.5908663883421624e-08, "epoch": 19.693396226415093, "percentage": 98.47, "elapsed_time": "1:47:18", "remaining_time": "0:01:40", "throughput": 3814.2, "total_tokens": 24558600}
7535
+ {"current_steps": 37580, "total_steps": 38160, "loss": 0.4103, "lr": 3.529864590737786e-08, "epoch": 19.69601677148847, "percentage": 98.48, "elapsed_time": "1:47:19", "remaining_time": "0:01:39", "throughput": 3814.21, "total_tokens": 24562440}
7536
+ {"current_steps": 37585, "total_steps": 38160, "loss": 0.4311, "lr": 3.4693850262046415e-08, "epoch": 19.698637316561843, "percentage": 98.49, "elapsed_time": "1:47:20", "remaining_time": "0:01:38", "throughput": 3814.2, "total_tokens": 24565736}
7537
+ {"current_steps": 37590, "total_steps": 38160, "loss": 0.4263, "lr": 3.409427707394275e-08, "epoch": 19.70125786163522, "percentage": 98.51, "elapsed_time": "1:47:21", "remaining_time": "0:01:37", "throughput": 3814.23, "total_tokens": 24569064}
7538
+ {"current_steps": 37595, "total_steps": 38160, "loss": 0.4361, "lr": 3.349992646848599e-08, "epoch": 19.703878406708597, "percentage": 98.52, "elapsed_time": "1:47:22", "remaining_time": "0:01:36", "throughput": 3814.29, "total_tokens": 24572584}
7539
+ {"current_steps": 37600, "total_steps": 38160, "loss": 0.5914, "lr": 3.291079857001556e-08, "epoch": 19.70649895178197, "percentage": 98.53, "elapsed_time": "1:47:22", "remaining_time": "0:01:35", "throughput": 3814.27, "total_tokens": 24575240}
7540
+ {"current_steps": 37605, "total_steps": 38160, "loss": 0.6015, "lr": 3.2326893501763436e-08, "epoch": 19.709119496855347, "percentage": 98.55, "elapsed_time": "1:47:23", "remaining_time": "0:01:35", "throughput": 3814.3, "total_tokens": 24578408}
7541
+ {"current_steps": 37610, "total_steps": 38160, "loss": 0.407, "lr": 3.174821138588191e-08, "epoch": 19.71174004192872, "percentage": 98.56, "elapsed_time": "1:47:24", "remaining_time": "0:01:34", "throughput": 3814.27, "total_tokens": 24581064}
7542
+ {"current_steps": 37615, "total_steps": 38160, "loss": 0.4045, "lr": 3.11747523434186e-08, "epoch": 19.714360587002098, "percentage": 98.57, "elapsed_time": "1:47:25", "remaining_time": "0:01:33", "throughput": 3814.28, "total_tokens": 24584200}
7543
+ {"current_steps": 37620, "total_steps": 38160, "loss": 0.5271, "lr": 3.060651649434143e-08, "epoch": 19.71698113207547, "percentage": 98.58, "elapsed_time": "1:47:26", "remaining_time": "0:01:32", "throughput": 3814.31, "total_tokens": 24587400}
7544
+ {"current_steps": 37625, "total_steps": 38160, "loss": 0.3444, "lr": 3.004350395751088e-08, "epoch": 19.719601677148848, "percentage": 98.6, "elapsed_time": "1:47:26", "remaining_time": "0:01:31", "throughput": 3814.27, "total_tokens": 24590088}
7545
+ {"current_steps": 37630, "total_steps": 38160, "loss": 0.5675, "lr": 2.94857148507105e-08, "epoch": 19.72222222222222, "percentage": 98.61, "elapsed_time": "1:47:27", "remaining_time": "0:01:30", "throughput": 3814.26, "total_tokens": 24593064}
7546
+ {"current_steps": 37635, "total_steps": 38160, "loss": 0.4497, "lr": 2.893314929061641e-08, "epoch": 19.7248427672956, "percentage": 98.62, "elapsed_time": "1:47:28", "remaining_time": "0:01:29", "throughput": 3814.25, "total_tokens": 24595816}
7547
+ {"current_steps": 37640, "total_steps": 38160, "loss": 0.3495, "lr": 2.8385807392825037e-08, "epoch": 19.72746331236897, "percentage": 98.64, "elapsed_time": "1:47:29", "remaining_time": "0:01:29", "throughput": 3814.25, "total_tokens": 24598824}
7548
+ {"current_steps": 37645, "total_steps": 38160, "loss": 0.4608, "lr": 2.7843689271830897e-08, "epoch": 19.73008385744235, "percentage": 98.65, "elapsed_time": "1:47:29", "remaining_time": "0:01:28", "throughput": 3814.19, "total_tokens": 24601480}
7549
+ {"current_steps": 37650, "total_steps": 38160, "loss": 0.358, "lr": 2.7306795041040502e-08, "epoch": 19.732704402515722, "percentage": 98.66, "elapsed_time": "1:47:30", "remaining_time": "0:01:27", "throughput": 3814.17, "total_tokens": 24604296}
7550
+ {"current_steps": 37655, "total_steps": 38160, "loss": 0.3801, "lr": 2.677512481276401e-08, "epoch": 19.7353249475891, "percentage": 98.68, "elapsed_time": "1:47:31", "remaining_time": "0:01:26", "throughput": 3814.12, "total_tokens": 24607336}
7551
+ {"current_steps": 37660, "total_steps": 38160, "loss": 0.5249, "lr": 2.6248678698220785e-08, "epoch": 19.737945492662472, "percentage": 98.69, "elapsed_time": "1:47:32", "remaining_time": "0:01:25", "throughput": 3814.2, "total_tokens": 24610984}
7552
+ {"current_steps": 37665, "total_steps": 38160, "loss": 0.3792, "lr": 2.5727456807542183e-08, "epoch": 19.74056603773585, "percentage": 98.7, "elapsed_time": "1:47:33", "remaining_time": "0:01:24", "throughput": 3814.18, "total_tokens": 24613800}
7553
+ {"current_steps": 37670, "total_steps": 38160, "loss": 0.3587, "lr": 2.5211459249754875e-08, "epoch": 19.743186582809223, "percentage": 98.72, "elapsed_time": "1:47:34", "remaining_time": "0:01:23", "throughput": 3814.2, "total_tokens": 24617064}
7554
+ {"current_steps": 37675, "total_steps": 38160, "loss": 0.4091, "lr": 2.4700686132803076e-08, "epoch": 19.7458071278826, "percentage": 98.73, "elapsed_time": "1:47:35", "remaining_time": "0:01:23", "throughput": 3814.3, "total_tokens": 24621416}
7555
+ {"current_steps": 37680, "total_steps": 38160, "loss": 0.4602, "lr": 2.4195137563534643e-08, "epoch": 19.748427672955973, "percentage": 98.74, "elapsed_time": "1:47:35", "remaining_time": "0:01:22", "throughput": 3814.39, "total_tokens": 24625160}
7556
+ {"current_steps": 37685, "total_steps": 38160, "loss": 0.3958, "lr": 2.369481364770387e-08, "epoch": 19.75104821802935, "percentage": 98.76, "elapsed_time": "1:47:36", "remaining_time": "0:01:21", "throughput": 3814.44, "total_tokens": 24628520}
7557
+ {"current_steps": 37690, "total_steps": 38160, "loss": 0.5234, "lr": 2.3199714489974266e-08, "epoch": 19.753668763102727, "percentage": 98.77, "elapsed_time": "1:47:37", "remaining_time": "0:01:20", "throughput": 3814.48, "total_tokens": 24631528}
7558
+ {"current_steps": 37695, "total_steps": 38160, "loss": 0.5287, "lr": 2.2709840193912978e-08, "epoch": 19.7562893081761, "percentage": 98.78, "elapsed_time": "1:47:38", "remaining_time": "0:01:19", "throughput": 3814.47, "total_tokens": 24634440}
7559
+ {"current_steps": 37700, "total_steps": 38160, "loss": 0.4445, "lr": 2.2225190861999146e-08, "epoch": 19.758909853249477, "percentage": 98.79, "elapsed_time": "1:47:38", "remaining_time": "0:01:18", "throughput": 3814.49, "total_tokens": 24637704}
7560
+ {"current_steps": 37705, "total_steps": 38160, "loss": 0.5668, "lr": 2.1745766595612783e-08, "epoch": 19.76153039832285, "percentage": 98.81, "elapsed_time": "1:47:39", "remaining_time": "0:01:17", "throughput": 3814.51, "total_tokens": 24640776}
7561
+ {"current_steps": 37710, "total_steps": 38160, "loss": 0.3072, "lr": 2.1271567495045886e-08, "epoch": 19.764150943396228, "percentage": 98.82, "elapsed_time": "1:47:40", "remaining_time": "0:01:17", "throughput": 3814.47, "total_tokens": 24643624}
7562
+ {"current_steps": 37715, "total_steps": 38160, "loss": 0.5016, "lr": 2.0802593659491333e-08, "epoch": 19.7667714884696, "percentage": 98.83, "elapsed_time": "1:47:41", "remaining_time": "0:01:16", "throughput": 3814.55, "total_tokens": 24647496}
7563
+ {"current_steps": 37720, "total_steps": 38160, "loss": 0.5639, "lr": 2.0338845187059528e-08, "epoch": 19.769392033542978, "percentage": 98.85, "elapsed_time": "1:47:42", "remaining_time": "0:01:15", "throughput": 3814.59, "total_tokens": 24651048}
7564
+ {"current_steps": 37725, "total_steps": 38160, "loss": 0.4969, "lr": 1.988032217475899e-08, "epoch": 19.77201257861635, "percentage": 98.86, "elapsed_time": "1:47:43", "remaining_time": "0:01:14", "throughput": 3814.55, "total_tokens": 24653736}
7565
+ {"current_steps": 37730, "total_steps": 38160, "loss": 0.4174, "lr": 1.942702471850466e-08, "epoch": 19.77463312368973, "percentage": 98.87, "elapsed_time": "1:47:43", "remaining_time": "0:01:13", "throughput": 3814.59, "total_tokens": 24657032}
7566
+ {"current_steps": 37735, "total_steps": 38160, "loss": 0.4258, "lr": 1.897895291312346e-08, "epoch": 19.7772536687631, "percentage": 98.89, "elapsed_time": "1:47:44", "remaining_time": "0:01:12", "throughput": 3814.6, "total_tokens": 24660136}
7567
+ {"current_steps": 37740, "total_steps": 38160, "loss": 0.5925, "lr": 1.8536106852348746e-08, "epoch": 19.77987421383648, "percentage": 98.9, "elapsed_time": "1:47:45", "remaining_time": "0:01:11", "throughput": 3814.55, "total_tokens": 24663048}
7568
+ {"current_steps": 37745, "total_steps": 38160, "loss": 0.4161, "lr": 1.8098486628814748e-08, "epoch": 19.782494758909852, "percentage": 98.91, "elapsed_time": "1:47:46", "remaining_time": "0:01:11", "throughput": 3814.65, "total_tokens": 24667016}
7569
+ {"current_steps": 37750, "total_steps": 38160, "loss": 0.4694, "lr": 1.7666092334067684e-08, "epoch": 19.78511530398323, "percentage": 98.93, "elapsed_time": "1:47:47", "remaining_time": "0:01:10", "throughput": 3814.66, "total_tokens": 24670568}
7570
+ {"current_steps": 37755, "total_steps": 38160, "loss": 0.5188, "lr": 1.7238924058562977e-08, "epoch": 19.787735849056602, "percentage": 98.94, "elapsed_time": "1:47:48", "remaining_time": "0:01:09", "throughput": 3814.71, "total_tokens": 24674024}
7571
+ {"current_steps": 37760, "total_steps": 38160, "loss": 0.5386, "lr": 1.6816981891656924e-08, "epoch": 19.79035639412998, "percentage": 98.95, "elapsed_time": "1:47:48", "remaining_time": "0:01:08", "throughput": 3814.72, "total_tokens": 24677320}
7572
+ {"current_steps": 37765, "total_steps": 38160, "loss": 0.3922, "lr": 1.6400265921615032e-08, "epoch": 19.792976939203353, "percentage": 98.96, "elapsed_time": "1:47:49", "remaining_time": "0:01:07", "throughput": 3814.79, "total_tokens": 24681096}
7573
+ {"current_steps": 37770, "total_steps": 38160, "loss": 0.4556, "lr": 1.598877623560924e-08, "epoch": 19.79559748427673, "percentage": 98.98, "elapsed_time": "1:47:50", "remaining_time": "0:01:06", "throughput": 3814.72, "total_tokens": 24684168}
7574
+ {"current_steps": 37775, "total_steps": 38160, "loss": 0.433, "lr": 1.5582512919717908e-08, "epoch": 19.798218029350103, "percentage": 98.99, "elapsed_time": "1:47:51", "remaining_time": "0:01:05", "throughput": 3814.75, "total_tokens": 24687464}
7575
+ {"current_steps": 37780, "total_steps": 38160, "loss": 0.4935, "lr": 1.5181476058928613e-08, "epoch": 19.80083857442348, "percentage": 99.0, "elapsed_time": "1:47:52", "remaining_time": "0:01:05", "throughput": 3814.79, "total_tokens": 24690920}
7576
+ {"current_steps": 37785, "total_steps": 38160, "loss": 0.3051, "lr": 1.4785665737129805e-08, "epoch": 19.803459119496857, "percentage": 99.02, "elapsed_time": "1:47:53", "remaining_time": "0:01:04", "throughput": 3814.73, "total_tokens": 24693768}
7577
+ {"current_steps": 37790, "total_steps": 38160, "loss": 0.4803, "lr": 1.4395082037127471e-08, "epoch": 19.80607966457023, "percentage": 99.03, "elapsed_time": "1:47:54", "remaining_time": "0:01:03", "throughput": 3814.72, "total_tokens": 24696552}
7578
+ {"current_steps": 37795, "total_steps": 38160, "loss": 0.3834, "lr": 1.4009725040620148e-08, "epoch": 19.808700209643607, "percentage": 99.04, "elapsed_time": "1:47:54", "remaining_time": "0:01:02", "throughput": 3814.75, "total_tokens": 24699656}
7579
+ {"current_steps": 37800, "total_steps": 38160, "loss": 0.5348, "lr": 1.3629594828223902e-08, "epoch": 19.81132075471698, "percentage": 99.06, "elapsed_time": "1:47:55", "remaining_time": "0:01:01", "throughput": 3814.82, "total_tokens": 24703496}
7580
+ {"current_steps": 37805, "total_steps": 38160, "loss": 0.5285, "lr": 1.3254691479458458e-08, "epoch": 19.813941299790358, "percentage": 99.07, "elapsed_time": "1:47:56", "remaining_time": "0:01:00", "throughput": 3814.84, "total_tokens": 24706760}
7581
+ {"current_steps": 37810, "total_steps": 38160, "loss": 0.4829, "lr": 1.2885015072747197e-08, "epoch": 19.81656184486373, "percentage": 99.08, "elapsed_time": "1:47:57", "remaining_time": "0:00:59", "throughput": 3814.91, "total_tokens": 24710952}
7582
+ {"current_steps": 37815, "total_steps": 38160, "loss": 0.32, "lr": 1.2520565685419927e-08, "epoch": 19.819182389937108, "percentage": 99.1, "elapsed_time": "1:47:58", "remaining_time": "0:00:59", "throughput": 3814.88, "total_tokens": 24714088}
7583
+ {"current_steps": 37820, "total_steps": 38160, "loss": 0.4383, "lr": 1.2161343393721214e-08, "epoch": 19.82180293501048, "percentage": 99.11, "elapsed_time": "1:47:59", "remaining_time": "0:00:58", "throughput": 3814.9, "total_tokens": 24717064}
7584
+ {"current_steps": 37825, "total_steps": 38160, "loss": 0.4915, "lr": 1.1807348272790952e-08, "epoch": 19.82442348008386, "percentage": 99.12, "elapsed_time": "1:47:59", "remaining_time": "0:00:57", "throughput": 3814.93, "total_tokens": 24720712}
7585
+ {"current_steps": 37830, "total_steps": 38160, "loss": 0.6143, "lr": 1.1458580396683794e-08, "epoch": 19.82704402515723, "percentage": 99.14, "elapsed_time": "1:48:00", "remaining_time": "0:00:56", "throughput": 3814.92, "total_tokens": 24723560}
7586
+ {"current_steps": 37835, "total_steps": 38160, "loss": 0.5707, "lr": 1.1115039838358044e-08, "epoch": 19.82966457023061, "percentage": 99.15, "elapsed_time": "1:48:02", "remaining_time": "0:00:55", "throughput": 3815.12, "total_tokens": 24731656}
7587
+ {"current_steps": 37840, "total_steps": 38160, "loss": 0.6379, "lr": 1.0776726669678439e-08, "epoch": 19.832285115303982, "percentage": 99.16, "elapsed_time": "1:48:03", "remaining_time": "0:00:54", "throughput": 3815.06, "total_tokens": 24734280}
7588
+ {"current_steps": 37845, "total_steps": 38160, "loss": 0.5822, "lr": 1.044364096141337e-08, "epoch": 19.83490566037736, "percentage": 99.17, "elapsed_time": "1:48:04", "remaining_time": "0:00:53", "throughput": 3814.99, "total_tokens": 24736840}
7589
+ {"current_steps": 37850, "total_steps": 38160, "loss": 0.4223, "lr": 1.0115782783243211e-08, "epoch": 19.837526205450732, "percentage": 99.19, "elapsed_time": "1:48:04", "remaining_time": "0:00:53", "throughput": 3815.05, "total_tokens": 24740200}
7590
+ {"current_steps": 37855, "total_steps": 38160, "loss": 0.402, "lr": 9.793152203751988e-09, "epoch": 19.84014675052411, "percentage": 99.2, "elapsed_time": "1:48:05", "remaining_time": "0:00:52", "throughput": 3815.11, "total_tokens": 24743592}
7591
+ {"current_steps": 37860, "total_steps": 38160, "loss": 0.4387, "lr": 9.475749290430158e-09, "epoch": 19.842767295597483, "percentage": 99.21, "elapsed_time": "1:48:06", "remaining_time": "0:00:51", "throughput": 3815.09, "total_tokens": 24746344}
7592
+ {"current_steps": 37865, "total_steps": 38160, "loss": 0.3425, "lr": 9.16357410967461e-09, "epoch": 19.84538784067086, "percentage": 99.23, "elapsed_time": "1:48:07", "remaining_time": "0:00:50", "throughput": 3814.97, "total_tokens": 24748712}
7593
+ {"current_steps": 37870, "total_steps": 38160, "loss": 0.431, "lr": 8.856626726788664e-09, "epoch": 19.848008385744233, "percentage": 99.24, "elapsed_time": "1:48:08", "remaining_time": "0:00:49", "throughput": 3815.03, "total_tokens": 24752264}
7594
+ {"current_steps": 37875, "total_steps": 38160, "loss": 0.3426, "lr": 8.554907205982066e-09, "epoch": 19.85062893081761, "percentage": 99.25, "elapsed_time": "1:48:09", "remaining_time": "0:00:48", "throughput": 3815.04, "total_tokens": 24755816}
7595
+ {"current_steps": 37880, "total_steps": 38160, "loss": 0.4623, "lr": 8.258415610373772e-09, "epoch": 19.853249475890987, "percentage": 99.27, "elapsed_time": "1:48:09", "remaining_time": "0:00:47", "throughput": 3815.04, "total_tokens": 24758792}
7596
+ {"current_steps": 37885, "total_steps": 38160, "loss": 0.4056, "lr": 7.967152001980838e-09, "epoch": 19.85587002096436, "percentage": 99.28, "elapsed_time": "1:48:10", "remaining_time": "0:00:47", "throughput": 3815.11, "total_tokens": 24762504}
7597
+ {"current_steps": 37890, "total_steps": 38160, "loss": 0.5382, "lr": 7.681116441737856e-09, "epoch": 19.858490566037737, "percentage": 99.29, "elapsed_time": "1:48:11", "remaining_time": "0:00:46", "throughput": 3815.2, "total_tokens": 24766760}
7598
+ {"current_steps": 37895, "total_steps": 38160, "loss": 0.4877, "lr": 7.4003089894747464e-09, "epoch": 19.86111111111111, "percentage": 99.31, "elapsed_time": "1:48:12", "remaining_time": "0:00:45", "throughput": 3815.23, "total_tokens": 24770536}
7599
+ {"current_steps": 37900, "total_steps": 38160, "loss": 0.3968, "lr": 7.12472970393896e-09, "epoch": 19.863731656184488, "percentage": 99.32, "elapsed_time": "1:48:13", "remaining_time": "0:00:44", "throughput": 3815.29, "total_tokens": 24773960}
7600
+ {"current_steps": 37905, "total_steps": 38160, "loss": 0.3865, "lr": 6.854378642776049e-09, "epoch": 19.86635220125786, "percentage": 99.33, "elapsed_time": "1:48:14", "remaining_time": "0:00:43", "throughput": 3815.27, "total_tokens": 24776744}
7601
+ {"current_steps": 37910, "total_steps": 38160, "loss": 0.4728, "lr": 6.589255862538002e-09, "epoch": 19.868972746331238, "percentage": 99.34, "elapsed_time": "1:48:15", "remaining_time": "0:00:42", "throughput": 3815.39, "total_tokens": 24781128}
7602
+ {"current_steps": 37915, "total_steps": 38160, "loss": 0.3655, "lr": 6.32936141869156e-09, "epoch": 19.87159329140461, "percentage": 99.36, "elapsed_time": "1:48:15", "remaining_time": "0:00:41", "throughput": 3815.41, "total_tokens": 24784072}
7603
+ {"current_steps": 37920, "total_steps": 38160, "loss": 0.4791, "lr": 6.074695365596017e-09, "epoch": 19.87421383647799, "percentage": 99.37, "elapsed_time": "1:48:16", "remaining_time": "0:00:41", "throughput": 3815.43, "total_tokens": 24787304}
7604
+ {"current_steps": 37925, "total_steps": 38160, "loss": 0.3939, "lr": 5.8252577565309775e-09, "epoch": 19.87683438155136, "percentage": 99.38, "elapsed_time": "1:48:17", "remaining_time": "0:00:40", "throughput": 3815.42, "total_tokens": 24790216}
7605
+ {"current_steps": 37930, "total_steps": 38160, "loss": 0.4655, "lr": 5.581048643671371e-09, "epoch": 19.87945492662474, "percentage": 99.4, "elapsed_time": "1:48:18", "remaining_time": "0:00:39", "throughput": 3815.5, "total_tokens": 24794024}
7606
+ {"current_steps": 37935, "total_steps": 38160, "loss": 0.4257, "lr": 5.342068078106888e-09, "epoch": 19.882075471698112, "percentage": 99.41, "elapsed_time": "1:48:19", "remaining_time": "0:00:38", "throughput": 3815.46, "total_tokens": 24797032}
7607
+ {"current_steps": 37940, "total_steps": 38160, "loss": 0.4, "lr": 5.1083161098253175e-09, "epoch": 19.88469601677149, "percentage": 99.42, "elapsed_time": "1:48:19", "remaining_time": "0:00:37", "throughput": 3815.39, "total_tokens": 24799592}
7608
+ {"current_steps": 37945, "total_steps": 38160, "loss": 0.4392, "lr": 4.87979278772921e-09, "epoch": 19.887316561844862, "percentage": 99.44, "elapsed_time": "1:48:20", "remaining_time": "0:00:36", "throughput": 3815.46, "total_tokens": 24803944}
7609
+ {"current_steps": 37950, "total_steps": 38160, "loss": 0.4957, "lr": 4.656498159619216e-09, "epoch": 19.88993710691824, "percentage": 99.45, "elapsed_time": "1:48:21", "remaining_time": "0:00:35", "throughput": 3815.49, "total_tokens": 24807816}
7610
+ {"current_steps": 37955, "total_steps": 38160, "loss": 0.3922, "lr": 4.438432272210746e-09, "epoch": 19.892557651991613, "percentage": 99.46, "elapsed_time": "1:48:22", "remaining_time": "0:00:35", "throughput": 3815.53, "total_tokens": 24811272}
7611
+ {"current_steps": 37960, "total_steps": 38160, "loss": 0.4115, "lr": 4.225595171114538e-09, "epoch": 19.89517819706499, "percentage": 99.48, "elapsed_time": "1:48:23", "remaining_time": "0:00:34", "throughput": 3815.57, "total_tokens": 24815048}
7612
+ {"current_steps": 37965, "total_steps": 38160, "loss": 0.4815, "lr": 4.017986900858861e-09, "epoch": 19.897798742138363, "percentage": 99.49, "elapsed_time": "1:48:24", "remaining_time": "0:00:33", "throughput": 3815.57, "total_tokens": 24818120}
7613
+ {"current_steps": 37970, "total_steps": 38160, "loss": 0.4264, "lr": 3.815607504870089e-09, "epoch": 19.90041928721174, "percentage": 99.5, "elapsed_time": "1:48:25", "remaining_time": "0:00:32", "throughput": 3815.66, "total_tokens": 24822280}
7614
+ {"current_steps": 37975, "total_steps": 38160, "loss": 0.4423, "lr": 3.618457025486577e-09, "epoch": 19.903039832285117, "percentage": 99.52, "elapsed_time": "1:48:26", "remaining_time": "0:00:31", "throughput": 3815.78, "total_tokens": 24826568}
7615
+ {"current_steps": 37980, "total_steps": 38160, "loss": 0.4445, "lr": 3.426535503947559e-09, "epoch": 19.90566037735849, "percentage": 99.53, "elapsed_time": "1:48:27", "remaining_time": "0:00:30", "throughput": 3815.83, "total_tokens": 24829768}
7616
+ {"current_steps": 37985, "total_steps": 38160, "loss": 0.4009, "lr": 3.2398429803986997e-09, "epoch": 19.908280922431867, "percentage": 99.54, "elapsed_time": "1:48:27", "remaining_time": "0:00:29", "throughput": 3815.79, "total_tokens": 24832392}
7617
+ {"current_steps": 37990, "total_steps": 38160, "loss": 0.5549, "lr": 3.058379493900421e-09, "epoch": 19.91090146750524, "percentage": 99.55, "elapsed_time": "1:48:28", "remaining_time": "0:00:29", "throughput": 3815.72, "total_tokens": 24834856}
7618
+ {"current_steps": 37995, "total_steps": 38160, "loss": 0.606, "lr": 2.882145082405696e-09, "epoch": 19.913522012578618, "percentage": 99.57, "elapsed_time": "1:48:29", "remaining_time": "0:00:28", "throughput": 3815.77, "total_tokens": 24838248}
7619
+ {"current_steps": 38000, "total_steps": 38160, "loss": 0.3747, "lr": 2.711139782785033e-09, "epoch": 19.91614255765199, "percentage": 99.58, "elapsed_time": "1:48:30", "remaining_time": "0:00:27", "throughput": 3815.83, "total_tokens": 24841864}
7620
+ {"current_steps": 38005, "total_steps": 38160, "loss": 0.4352, "lr": 2.5453636308098163e-09, "epoch": 19.918763102725368, "percentage": 99.59, "elapsed_time": "1:48:31", "remaining_time": "0:00:26", "throughput": 3815.81, "total_tokens": 24844776}
7621
+ {"current_steps": 38010, "total_steps": 38160, "loss": 0.4518, "lr": 2.3848166611606383e-09, "epoch": 19.92138364779874, "percentage": 99.61, "elapsed_time": "1:48:31", "remaining_time": "0:00:25", "throughput": 3815.8, "total_tokens": 24848360}
7622
+ {"current_steps": 38015, "total_steps": 38160, "loss": 0.4942, "lr": 2.2294989074161943e-09, "epoch": 19.92400419287212, "percentage": 99.62, "elapsed_time": "1:48:32", "remaining_time": "0:00:24", "throughput": 3815.74, "total_tokens": 24851496}
7623
+ {"current_steps": 38020, "total_steps": 38160, "loss": 0.379, "lr": 2.0794104020727125e-09, "epoch": 19.92662473794549, "percentage": 99.63, "elapsed_time": "1:48:33", "remaining_time": "0:00:23", "throughput": 3815.8, "total_tokens": 24855144}
7624
+ {"current_steps": 38025, "total_steps": 38160, "loss": 0.4124, "lr": 1.9345511765272993e-09, "epoch": 19.92924528301887, "percentage": 99.65, "elapsed_time": "1:48:34", "remaining_time": "0:00:23", "throughput": 3815.79, "total_tokens": 24858120}
7625
+ {"current_steps": 38030, "total_steps": 38160, "loss": 0.4846, "lr": 1.794921261077942e-09, "epoch": 19.931865828092242, "percentage": 99.66, "elapsed_time": "1:48:35", "remaining_time": "0:00:22", "throughput": 3815.9, "total_tokens": 24862248}
7626
+ {"current_steps": 38035, "total_steps": 38160, "loss": 0.4611, "lr": 1.6605206849373833e-09, "epoch": 19.93448637316562, "percentage": 99.67, "elapsed_time": "1:48:36", "remaining_time": "0:00:21", "throughput": 3815.86, "total_tokens": 24864776}
7627
+ {"current_steps": 38040, "total_steps": 38160, "loss": 0.4588, "lr": 1.531349476219246e-09, "epoch": 19.937106918238992, "percentage": 99.69, "elapsed_time": "1:48:37", "remaining_time": "0:00:20", "throughput": 3815.89, "total_tokens": 24868200}
7628
+ {"current_steps": 38045, "total_steps": 38160, "loss": 0.4189, "lr": 1.4074076619463584e-09, "epoch": 19.93972746331237, "percentage": 99.7, "elapsed_time": "1:48:37", "remaining_time": "0:00:19", "throughput": 3815.84, "total_tokens": 24870824}
7629
+ {"current_steps": 38050, "total_steps": 38160, "loss": 0.4505, "lr": 1.2886952680452036e-09, "epoch": 19.942348008385743, "percentage": 99.71, "elapsed_time": "1:48:38", "remaining_time": "0:00:18", "throughput": 3815.84, "total_tokens": 24874056}
7630
+ {"current_steps": 38055, "total_steps": 38160, "loss": 0.3713, "lr": 1.1752123193459197e-09, "epoch": 19.94496855345912, "percentage": 99.72, "elapsed_time": "1:48:39", "remaining_time": "0:00:17", "throughput": 3815.85, "total_tokens": 24877096}
7631
+ {"current_steps": 38060, "total_steps": 38160, "loss": 0.4185, "lr": 1.0669588395934017e-09, "epoch": 19.947589098532493, "percentage": 99.74, "elapsed_time": "1:48:40", "remaining_time": "0:00:17", "throughput": 3815.88, "total_tokens": 24880104}
7632
+ {"current_steps": 38065, "total_steps": 38160, "loss": 0.5079, "lr": 9.639348514278722e-10, "epoch": 19.95020964360587, "percentage": 99.75, "elapsed_time": "1:48:40", "remaining_time": "0:00:16", "throughput": 3815.89, "total_tokens": 24883112}
7633
+ {"current_steps": 38070, "total_steps": 38160, "loss": 0.4459, "lr": 8.661403764043119e-10, "epoch": 19.952830188679247, "percentage": 99.76, "elapsed_time": "1:48:41", "remaining_time": "0:00:15", "throughput": 3815.98, "total_tokens": 24886824}
7634
+ {"current_steps": 38075, "total_steps": 38160, "loss": 0.4265, "lr": 7.735754349785795e-10, "epoch": 19.95545073375262, "percentage": 99.78, "elapsed_time": "1:48:42", "remaining_time": "0:00:14", "throughput": 3815.89, "total_tokens": 24889096}
7635
+ {"current_steps": 38080, "total_steps": 38160, "loss": 0.41, "lr": 6.862400465157403e-10, "epoch": 19.958071278825997, "percentage": 99.79, "elapsed_time": "1:48:43", "remaining_time": "0:00:13", "throughput": 3816.01, "total_tokens": 24893640}
7636
+ {"current_steps": 38085, "total_steps": 38160, "loss": 0.4807, "lr": 6.041342292817387e-10, "epoch": 19.96069182389937, "percentage": 99.8, "elapsed_time": "1:48:44", "remaining_time": "0:00:12", "throughput": 3815.99, "total_tokens": 24896264}
7637
+ {"current_steps": 38090, "total_steps": 38160, "loss": 0.4063, "lr": 5.272580004572758e-10, "epoch": 19.963312368972748, "percentage": 99.82, "elapsed_time": "1:48:44", "remaining_time": "0:00:11", "throughput": 3815.98, "total_tokens": 24899080}
7638
+ {"current_steps": 38095, "total_steps": 38160, "loss": 0.4219, "lr": 4.556113761211567e-10, "epoch": 19.96593291404612, "percentage": 99.83, "elapsed_time": "1:48:45", "remaining_time": "0:00:11", "throughput": 3815.98, "total_tokens": 24902024}
7639
+ {"current_steps": 38100, "total_steps": 38160, "loss": 0.3893, "lr": 3.8919437125861657e-10, "epoch": 19.968553459119498, "percentage": 99.84, "elapsed_time": "1:48:46", "remaining_time": "0:00:10", "throughput": 3816.06, "total_tokens": 24906088}
7640
+ {"current_steps": 38105, "total_steps": 38160, "loss": 0.4853, "lr": 3.280069997696478e-10, "epoch": 19.97117400419287, "percentage": 99.86, "elapsed_time": "1:48:47", "remaining_time": "0:00:09", "throughput": 3816.06, "total_tokens": 24908968}
7641
+ {"current_steps": 38110, "total_steps": 38160, "loss": 0.4606, "lr": 2.720492744467951e-10, "epoch": 19.97379454926625, "percentage": 99.87, "elapsed_time": "1:48:48", "remaining_time": "0:00:08", "throughput": 3816.09, "total_tokens": 24912104}
7642
+ {"current_steps": 38115, "total_steps": 38160, "loss": 0.4902, "lr": 2.2132120700291136e-10, "epoch": 19.97641509433962, "percentage": 99.88, "elapsed_time": "1:48:48", "remaining_time": "0:00:07", "throughput": 3816.13, "total_tokens": 24915464}
7643
+ {"current_steps": 38120, "total_steps": 38160, "loss": 0.3711, "lr": 1.7582280804340213e-10, "epoch": 19.979035639413, "percentage": 99.9, "elapsed_time": "1:48:49", "remaining_time": "0:00:06", "throughput": 3816.14, "total_tokens": 24918632}
7644
+ {"current_steps": 38125, "total_steps": 38160, "loss": 0.5329, "lr": 1.3555408708842977e-10, "epoch": 19.981656184486372, "percentage": 99.91, "elapsed_time": "1:48:50", "remaining_time": "0:00:05", "throughput": 3816.06, "total_tokens": 24921032}
7645
+ {"current_steps": 38130, "total_steps": 38160, "loss": 0.4413, "lr": 1.0051505256458704e-10, "epoch": 19.98427672955975, "percentage": 99.92, "elapsed_time": "1:48:51", "remaining_time": "0:00:05", "throughput": 3816.07, "total_tokens": 24923912}
7646
+ {"current_steps": 38135, "total_steps": 38160, "loss": 0.4817, "lr": 7.070571179657037e-11, "epoch": 19.986897274633122, "percentage": 99.93, "elapsed_time": "1:48:52", "remaining_time": "0:00:04", "throughput": 3816.09, "total_tokens": 24926952}
7647
+ {"current_steps": 38140, "total_steps": 38160, "loss": 0.4958, "lr": 4.612607102383315e-11, "epoch": 19.9895178197065, "percentage": 99.95, "elapsed_time": "1:48:52", "remaining_time": "0:00:03", "throughput": 3816.18, "total_tokens": 24930984}
7648
+ {"current_steps": 38145, "total_steps": 38160, "loss": 0.5802, "lr": 2.677613538670798e-11, "epoch": 19.992138364779873, "percentage": 99.96, "elapsed_time": "1:48:53", "remaining_time": "0:00:02", "throughput": 3816.15, "total_tokens": 24933832}
7649
+ {"current_steps": 38150, "total_steps": 38160, "loss": 0.4092, "lr": 1.2655908931957782e-11, "epoch": 19.99475890985325, "percentage": 99.97, "elapsed_time": "1:48:54", "remaining_time": "0:00:01", "throughput": 3816.13, "total_tokens": 24936584}
7650
+ {"current_steps": 38155, "total_steps": 38160, "loss": 0.362, "lr": 3.765394615551366e-12, "epoch": 19.997379454926623, "percentage": 99.99, "elapsed_time": "1:48:55", "remaining_time": "0:00:00", "throughput": 3816.11, "total_tokens": 24939432}
7651
+ {"current_steps": 38160, "total_steps": 38160, "loss": 0.614, "lr": 1.0459429711229262e-13, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "1:48:56", "remaining_time": "0:00:00", "throughput": 3816.02, "total_tokens": 24941912}
7652
+ {"current_steps": 38160, "total_steps": 38160, "eval_loss": 0.4749854803085327, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "1:49:05", "remaining_time": "0:00:00", "throughput": 3810.35, "total_tokens": 24941912}
7653
+ {"current_steps": 38160, "total_steps": 38160, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "1:49:07", "remaining_time": "0:00:00", "throughput": 3809.48, "total_tokens": 24941912}