Training in progress, step 14680
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +289 -0
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 8388736
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96474fbf5481dde448cdc0f157c20d9ce633d665f5fd0194dd1377410b149b7e
|
| 3 |
size 8388736
|
trainer_log.jsonl
CHANGED
|
@@ -2656,3 +2656,292 @@
|
|
| 2656 |
{"current_steps": 13235, "total_steps": 14680, "loss": 0.0, "lr": 2.9265529155455776e-07, "epoch": 18.03133514986376, "percentage": 90.16, "elapsed_time": "0:25:09", "remaining_time": "0:02:44", "throughput": 3591.75, "total_tokens": 5422624}
|
| 2657 |
{"current_steps": 13240, "total_steps": 14680, "loss": 0.0, "lr": 2.906547019996825e-07, "epoch": 18.03814713896458, "percentage": 90.19, "elapsed_time": "0:25:10", "remaining_time": "0:02:44", "throughput": 3591.92, "total_tokens": 5424736}
|
| 2658 |
{"current_steps": 13245, "total_steps": 14680, "loss": 0.0, "lr": 2.8866076920800014e-07, "epoch": 18.044959128065393, "percentage": 90.22, "elapsed_time": "0:25:10", "remaining_time": "0:02:43", "throughput": 3592.01, "total_tokens": 5426880}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2656 |
{"current_steps": 13235, "total_steps": 14680, "loss": 0.0, "lr": 2.9265529155455776e-07, "epoch": 18.03133514986376, "percentage": 90.16, "elapsed_time": "0:25:09", "remaining_time": "0:02:44", "throughput": 3591.75, "total_tokens": 5422624}
|
| 2657 |
{"current_steps": 13240, "total_steps": 14680, "loss": 0.0, "lr": 2.906547019996825e-07, "epoch": 18.03814713896458, "percentage": 90.19, "elapsed_time": "0:25:10", "remaining_time": "0:02:44", "throughput": 3591.92, "total_tokens": 5424736}
|
| 2658 |
{"current_steps": 13245, "total_steps": 14680, "loss": 0.0, "lr": 2.8866076920800014e-07, "epoch": 18.044959128065393, "percentage": 90.22, "elapsed_time": "0:25:10", "remaining_time": "0:02:43", "throughput": 3592.01, "total_tokens": 5426880}
|
| 2659 |
+
{"current_steps": 13250, "total_steps": 14680, "loss": 0.0, "lr": 2.866734959979811e-07, "epoch": 18.05177111716621, "percentage": 90.26, "elapsed_time": "0:25:11", "remaining_time": "0:02:43", "throughput": 3592.1, "total_tokens": 5429024}
|
| 2660 |
+
{"current_steps": 13255, "total_steps": 14680, "loss": 0.0, "lr": 2.8469288517867845e-07, "epoch": 18.05858310626703, "percentage": 90.29, "elapsed_time": "0:25:11", "remaining_time": "0:02:42", "throughput": 3592.14, "total_tokens": 5431104}
|
| 2661 |
+
{"current_steps": 13260, "total_steps": 14680, "loss": 0.0, "lr": 2.827189395497293e-07, "epoch": 18.065395095367847, "percentage": 90.33, "elapsed_time": "0:25:12", "remaining_time": "0:02:41", "throughput": 3592.17, "total_tokens": 5433152}
|
| 2662 |
+
{"current_steps": 13265, "total_steps": 14680, "loss": 0.0, "lr": 2.8075166190134895e-07, "epoch": 18.072207084468666, "percentage": 90.36, "elapsed_time": "0:25:13", "remaining_time": "0:02:41", "throughput": 3592.25, "total_tokens": 5435296}
|
| 2663 |
+
{"current_steps": 13270, "total_steps": 14680, "loss": 0.0, "lr": 2.7879105501432744e-07, "epoch": 18.079019073569484, "percentage": 90.4, "elapsed_time": "0:25:13", "remaining_time": "0:02:40", "throughput": 3592.32, "total_tokens": 5437312}
|
| 2664 |
+
{"current_steps": 13275, "total_steps": 14680, "loss": 0.0, "lr": 2.7683712166002683e-07, "epoch": 18.085831062670298, "percentage": 90.43, "elapsed_time": "0:25:14", "remaining_time": "0:02:40", "throughput": 3592.34, "total_tokens": 5439232}
|
| 2665 |
+
{"current_steps": 13280, "total_steps": 14680, "loss": 0.0, "lr": 2.748898646003745e-07, "epoch": 18.092643051771116, "percentage": 90.46, "elapsed_time": "0:25:14", "remaining_time": "0:02:39", "throughput": 3592.45, "total_tokens": 5441312}
|
| 2666 |
+
{"current_steps": 13285, "total_steps": 14680, "loss": 0.0, "lr": 2.7294928658785915e-07, "epoch": 18.099455040871934, "percentage": 90.5, "elapsed_time": "0:25:15", "remaining_time": "0:02:39", "throughput": 3592.6, "total_tokens": 5443392}
|
| 2667 |
+
{"current_steps": 13290, "total_steps": 14680, "loss": 0.0, "lr": 2.710153903655344e-07, "epoch": 18.106267029972752, "percentage": 90.53, "elapsed_time": "0:25:15", "remaining_time": "0:02:38", "throughput": 3592.67, "total_tokens": 5445408}
|
| 2668 |
+
{"current_steps": 13295, "total_steps": 14680, "loss": 0.0, "lr": 2.6908817866700244e-07, "epoch": 18.11307901907357, "percentage": 90.57, "elapsed_time": "0:25:16", "remaining_time": "0:02:37", "throughput": 3592.74, "total_tokens": 5447424}
|
| 2669 |
+
{"current_steps": 13300, "total_steps": 14680, "loss": 0.0, "lr": 2.6716765421641924e-07, "epoch": 18.11989100817439, "percentage": 90.6, "elapsed_time": "0:25:16", "remaining_time": "0:02:37", "throughput": 3592.81, "total_tokens": 5449440}
|
| 2670 |
+
{"current_steps": 13305, "total_steps": 14680, "loss": 0.0, "lr": 2.6525381972848873e-07, "epoch": 18.126702997275203, "percentage": 90.63, "elapsed_time": "0:25:17", "remaining_time": "0:02:36", "throughput": 3592.86, "total_tokens": 5451520}
|
| 2671 |
+
{"current_steps": 13310, "total_steps": 14680, "loss": 0.0, "lr": 2.6334667790845867e-07, "epoch": 18.13351498637602, "percentage": 90.67, "elapsed_time": "0:25:17", "remaining_time": "0:02:36", "throughput": 3592.96, "total_tokens": 5453472}
|
| 2672 |
+
{"current_steps": 13315, "total_steps": 14680, "loss": 0.0, "lr": 2.614462314521166e-07, "epoch": 18.14032697547684, "percentage": 90.7, "elapsed_time": "0:25:18", "remaining_time": "0:02:35", "throughput": 3593.06, "total_tokens": 5455456}
|
| 2673 |
+
{"current_steps": 13320, "total_steps": 14680, "loss": 0.0, "lr": 2.5955248304578406e-07, "epoch": 18.147138964577657, "percentage": 90.74, "elapsed_time": "0:25:18", "remaining_time": "0:02:35", "throughput": 3593.17, "total_tokens": 5457536}
|
| 2674 |
+
{"current_steps": 13325, "total_steps": 14680, "loss": 0.0, "lr": 2.5766543536631604e-07, "epoch": 18.153950953678475, "percentage": 90.77, "elapsed_time": "0:25:19", "remaining_time": "0:02:34", "throughput": 3593.28, "total_tokens": 5459616}
|
| 2675 |
+
{"current_steps": 13330, "total_steps": 14680, "loss": 0.0, "lr": 2.557850910810966e-07, "epoch": 18.160762942779293, "percentage": 90.8, "elapsed_time": "0:25:19", "remaining_time": "0:02:33", "throughput": 3593.39, "total_tokens": 5461504}
|
| 2676 |
+
{"current_steps": 13335, "total_steps": 14680, "loss": 0.0, "lr": 2.539114528480341e-07, "epoch": 18.167574931880107, "percentage": 90.84, "elapsed_time": "0:25:20", "remaining_time": "0:02:33", "throughput": 3593.41, "total_tokens": 5463520}
|
| 2677 |
+
{"current_steps": 13340, "total_steps": 14680, "loss": 0.0, "lr": 2.5204452331555606e-07, "epoch": 18.174386920980925, "percentage": 90.87, "elapsed_time": "0:25:20", "remaining_time": "0:02:32", "throughput": 3593.46, "total_tokens": 5465504}
|
| 2678 |
+
{"current_steps": 13345, "total_steps": 14680, "loss": 0.0, "lr": 2.5018430512260996e-07, "epoch": 18.181198910081743, "percentage": 90.91, "elapsed_time": "0:25:21", "remaining_time": "0:02:32", "throughput": 3593.56, "total_tokens": 5467488}
|
| 2679 |
+
{"current_steps": 13350, "total_steps": 14680, "loss": 0.0, "lr": 2.4833080089865457e-07, "epoch": 18.18801089918256, "percentage": 90.94, "elapsed_time": "0:25:21", "remaining_time": "0:02:31", "throughput": 3593.6, "total_tokens": 5469440}
|
| 2680 |
+
{"current_steps": 13355, "total_steps": 14680, "loss": 0.0, "lr": 2.4648401326365814e-07, "epoch": 18.19482288828338, "percentage": 90.97, "elapsed_time": "0:25:22", "remaining_time": "0:02:31", "throughput": 3593.69, "total_tokens": 5471584}
|
| 2681 |
+
{"current_steps": 13360, "total_steps": 14680, "loss": 0.0, "lr": 2.4464394482809685e-07, "epoch": 18.201634877384198, "percentage": 91.01, "elapsed_time": "0:25:23", "remaining_time": "0:02:30", "throughput": 3593.74, "total_tokens": 5473664}
|
| 2682 |
+
{"current_steps": 13365, "total_steps": 14680, "loss": 0.0, "lr": 2.4281059819294684e-07, "epoch": 18.208446866485012, "percentage": 91.04, "elapsed_time": "0:25:23", "remaining_time": "0:02:29", "throughput": 3593.8, "total_tokens": 5475776}
|
| 2683 |
+
{"current_steps": 13370, "total_steps": 14680, "loss": 0.0, "lr": 2.409839759496846e-07, "epoch": 18.21525885558583, "percentage": 91.08, "elapsed_time": "0:25:24", "remaining_time": "0:02:29", "throughput": 3593.89, "total_tokens": 5477728}
|
| 2684 |
+
{"current_steps": 13375, "total_steps": 14680, "loss": 0.0, "lr": 2.391640806802814e-07, "epoch": 18.222070844686648, "percentage": 91.11, "elapsed_time": "0:25:24", "remaining_time": "0:02:28", "throughput": 3594.02, "total_tokens": 5479744}
|
| 2685 |
+
{"current_steps": 13380, "total_steps": 14680, "loss": 0.0, "lr": 2.373509149571973e-07, "epoch": 18.228882833787466, "percentage": 91.14, "elapsed_time": "0:25:25", "remaining_time": "0:02:28", "throughput": 3594.03, "total_tokens": 5481856}
|
| 2686 |
+
{"current_steps": 13385, "total_steps": 14680, "loss": 0.0, "lr": 2.3554448134338436e-07, "epoch": 18.235694822888284, "percentage": 91.18, "elapsed_time": "0:25:25", "remaining_time": "0:02:27", "throughput": 3594.14, "total_tokens": 5483936}
|
| 2687 |
+
{"current_steps": 13390, "total_steps": 14680, "loss": 0.0, "lr": 2.337447823922745e-07, "epoch": 18.242506811989102, "percentage": 91.21, "elapsed_time": "0:25:26", "remaining_time": "0:02:27", "throughput": 3594.27, "total_tokens": 5485952}
|
| 2688 |
+
{"current_steps": 13395, "total_steps": 14680, "loss": 0.0, "lr": 2.319518206477822e-07, "epoch": 18.249318801089917, "percentage": 91.25, "elapsed_time": "0:25:26", "remaining_time": "0:02:26", "throughput": 3594.35, "total_tokens": 5488096}
|
| 2689 |
+
{"current_steps": 13400, "total_steps": 14680, "loss": 0.0, "lr": 2.3016559864429854e-07, "epoch": 18.256130790190735, "percentage": 91.28, "elapsed_time": "0:25:27", "remaining_time": "0:02:25", "throughput": 3594.41, "total_tokens": 5490176}
|
| 2690 |
+
{"current_steps": 13405, "total_steps": 14680, "loss": 0.0, "lr": 2.2838611890668773e-07, "epoch": 18.262942779291553, "percentage": 91.31, "elapsed_time": "0:25:27", "remaining_time": "0:02:25", "throughput": 3594.48, "total_tokens": 5492288}
|
| 2691 |
+
{"current_steps": 13410, "total_steps": 14680, "loss": 0.0, "lr": 2.2661338395028264e-07, "epoch": 18.26975476839237, "percentage": 91.35, "elapsed_time": "0:25:28", "remaining_time": "0:02:24", "throughput": 3594.54, "total_tokens": 5494400}
|
| 2692 |
+
{"current_steps": 13415, "total_steps": 14680, "loss": 0.0, "lr": 2.2484739628088503e-07, "epoch": 18.27656675749319, "percentage": 91.38, "elapsed_time": "0:25:29", "remaining_time": "0:02:24", "throughput": 3594.59, "total_tokens": 5496480}
|
| 2693 |
+
{"current_steps": 13420, "total_steps": 14680, "loss": 0.0, "lr": 2.230881583947553e-07, "epoch": 18.283378746594007, "percentage": 91.42, "elapsed_time": "0:25:29", "remaining_time": "0:02:23", "throughput": 3594.65, "total_tokens": 5498688}
|
| 2694 |
+
{"current_steps": 13425, "total_steps": 14680, "loss": 0.0, "lr": 2.2133567277861645e-07, "epoch": 18.29019073569482, "percentage": 91.45, "elapsed_time": "0:25:30", "remaining_time": "0:02:23", "throughput": 3594.74, "total_tokens": 5500736}
|
| 2695 |
+
{"current_steps": 13430, "total_steps": 14680, "loss": 0.0, "lr": 2.1958994190964421e-07, "epoch": 18.29700272479564, "percentage": 91.49, "elapsed_time": "0:25:30", "remaining_time": "0:02:22", "throughput": 3594.78, "total_tokens": 5502816}
|
| 2696 |
+
{"current_steps": 13435, "total_steps": 14680, "loss": 0.0, "lr": 2.1785096825546802e-07, "epoch": 18.303814713896458, "percentage": 91.52, "elapsed_time": "0:25:31", "remaining_time": "0:02:21", "throughput": 3594.91, "total_tokens": 5504736}
|
| 2697 |
+
{"current_steps": 13440, "total_steps": 14680, "loss": 0.0, "lr": 2.1611875427416607e-07, "epoch": 18.310626702997276, "percentage": 91.55, "elapsed_time": "0:25:31", "remaining_time": "0:02:21", "throughput": 3595.0, "total_tokens": 5506880}
|
| 2698 |
+
{"current_steps": 13445, "total_steps": 14680, "loss": 0.0, "lr": 2.1439330241426083e-07, "epoch": 18.317438692098094, "percentage": 91.59, "elapsed_time": "0:25:32", "remaining_time": "0:02:20", "throughput": 3595.14, "total_tokens": 5508992}
|
| 2699 |
+
{"current_steps": 13450, "total_steps": 14680, "loss": 0.0, "lr": 2.126746151147141e-07, "epoch": 18.32425068119891, "percentage": 91.62, "elapsed_time": "0:25:32", "remaining_time": "0:02:20", "throughput": 3595.22, "total_tokens": 5510912}
|
| 2700 |
+
{"current_steps": 13455, "total_steps": 14680, "loss": 0.0, "lr": 2.1096269480493203e-07, "epoch": 18.331062670299726, "percentage": 91.66, "elapsed_time": "0:25:33", "remaining_time": "0:02:19", "throughput": 3595.31, "total_tokens": 5512960}
|
| 2701 |
+
{"current_steps": 13460, "total_steps": 14680, "loss": 0.0, "lr": 2.0925754390474839e-07, "epoch": 18.337874659400544, "percentage": 91.69, "elapsed_time": "0:25:33", "remaining_time": "0:02:19", "throughput": 3595.4, "total_tokens": 5515104}
|
| 2702 |
+
{"current_steps": 13465, "total_steps": 14680, "loss": 0.0, "lr": 2.0755916482443405e-07, "epoch": 18.344686648501362, "percentage": 91.72, "elapsed_time": "0:25:34", "remaining_time": "0:02:18", "throughput": 3595.52, "total_tokens": 5517120}
|
| 2703 |
+
{"current_steps": 13470, "total_steps": 14680, "loss": 0.0, "lr": 2.058675599646831e-07, "epoch": 18.35149863760218, "percentage": 91.76, "elapsed_time": "0:25:34", "remaining_time": "0:02:17", "throughput": 3595.61, "total_tokens": 5519168}
|
| 2704 |
+
{"current_steps": 13475, "total_steps": 14680, "loss": 0.0, "lr": 2.0418273171661674e-07, "epoch": 18.358310626703, "percentage": 91.79, "elapsed_time": "0:25:35", "remaining_time": "0:02:17", "throughput": 3595.7, "total_tokens": 5521120}
|
| 2705 |
+
{"current_steps": 13480, "total_steps": 14680, "loss": 0.0, "lr": 2.0250468246177823e-07, "epoch": 18.365122615803816, "percentage": 91.83, "elapsed_time": "0:25:36", "remaining_time": "0:02:16", "throughput": 3595.78, "total_tokens": 5523136}
|
| 2706 |
+
{"current_steps": 13485, "total_steps": 14680, "loss": 0.0, "lr": 2.0083341457212579e-07, "epoch": 18.37193460490463, "percentage": 91.86, "elapsed_time": "0:25:36", "remaining_time": "0:02:16", "throughput": 3595.87, "total_tokens": 5525088}
|
| 2707 |
+
{"current_steps": 13490, "total_steps": 14680, "loss": 0.0, "lr": 1.991689304100325e-07, "epoch": 18.37874659400545, "percentage": 91.89, "elapsed_time": "0:25:37", "remaining_time": "0:02:15", "throughput": 3595.97, "total_tokens": 5527072}
|
| 2708 |
+
{"current_steps": 13495, "total_steps": 14680, "loss": 0.0, "lr": 1.9751123232828572e-07, "epoch": 18.385558583106267, "percentage": 91.93, "elapsed_time": "0:25:37", "remaining_time": "0:02:15", "throughput": 3596.05, "total_tokens": 5528992}
|
| 2709 |
+
{"current_steps": 13500, "total_steps": 14680, "loss": 0.0, "lr": 1.958603226700767e-07, "epoch": 18.392370572207085, "percentage": 91.96, "elapsed_time": "0:25:38", "remaining_time": "0:02:14", "throughput": 3596.15, "total_tokens": 5531168}
|
| 2710 |
+
{"current_steps": 13505, "total_steps": 14680, "loss": 0.0, "lr": 1.9421620376900207e-07, "epoch": 18.399182561307903, "percentage": 92.0, "elapsed_time": "0:25:38", "remaining_time": "0:02:13", "throughput": 3596.18, "total_tokens": 5533216}
|
| 2711 |
+
{"current_steps": 13510, "total_steps": 14680, "loss": 0.0, "lr": 1.9257887794906116e-07, "epoch": 18.40599455040872, "percentage": 92.03, "elapsed_time": "0:25:39", "remaining_time": "0:02:13", "throughput": 3596.27, "total_tokens": 5535360}
|
| 2712 |
+
{"current_steps": 13515, "total_steps": 14680, "loss": 0.0, "lr": 1.909483475246493e-07, "epoch": 18.412806539509535, "percentage": 92.06, "elapsed_time": "0:25:39", "remaining_time": "0:02:12", "throughput": 3596.36, "total_tokens": 5537440}
|
| 2713 |
+
{"current_steps": 13520, "total_steps": 14680, "loss": 0.0, "lr": 1.8932461480055785e-07, "epoch": 18.419618528610354, "percentage": 92.1, "elapsed_time": "0:25:40", "remaining_time": "0:02:12", "throughput": 3596.39, "total_tokens": 5539488}
|
| 2714 |
+
{"current_steps": 13525, "total_steps": 14680, "loss": 0.0, "lr": 1.8770768207196864e-07, "epoch": 18.42643051771117, "percentage": 92.13, "elapsed_time": "0:25:40", "remaining_time": "0:02:11", "throughput": 3596.46, "total_tokens": 5541504}
|
| 2715 |
+
{"current_steps": 13530, "total_steps": 14680, "loss": 0.0, "lr": 1.8609755162445065e-07, "epoch": 18.43324250681199, "percentage": 92.17, "elapsed_time": "0:25:41", "remaining_time": "0:02:11", "throughput": 3596.52, "total_tokens": 5543520}
|
| 2716 |
+
{"current_steps": 13535, "total_steps": 14680, "loss": 0.0, "lr": 1.8449422573395938e-07, "epoch": 18.440054495912808, "percentage": 92.2, "elapsed_time": "0:25:41", "remaining_time": "0:02:10", "throughput": 3596.63, "total_tokens": 5545600}
|
| 2717 |
+
{"current_steps": 13540, "total_steps": 14680, "loss": 0.0, "lr": 1.8289770666683192e-07, "epoch": 18.446866485013626, "percentage": 92.23, "elapsed_time": "0:25:42", "remaining_time": "0:02:09", "throughput": 3596.75, "total_tokens": 5547616}
|
| 2718 |
+
{"current_steps": 13545, "total_steps": 14680, "loss": 0.0, "lr": 1.8130799667978148e-07, "epoch": 18.45367847411444, "percentage": 92.27, "elapsed_time": "0:25:42", "remaining_time": "0:02:09", "throughput": 3596.85, "total_tokens": 5549600}
|
| 2719 |
+
{"current_steps": 13550, "total_steps": 14680, "loss": 0.0, "lr": 1.7972509801989947e-07, "epoch": 18.460490463215258, "percentage": 92.3, "elapsed_time": "0:25:43", "remaining_time": "0:02:08", "throughput": 3596.99, "total_tokens": 5551744}
|
| 2720 |
+
{"current_steps": 13555, "total_steps": 14680, "loss": 0.0, "lr": 1.7814901292464714e-07, "epoch": 18.467302452316076, "percentage": 92.34, "elapsed_time": "0:25:43", "remaining_time": "0:02:08", "throughput": 3597.12, "total_tokens": 5553760}
|
| 2721 |
+
{"current_steps": 13560, "total_steps": 14680, "loss": 0.0, "lr": 1.7657974362185692e-07, "epoch": 18.474114441416894, "percentage": 92.37, "elapsed_time": "0:25:44", "remaining_time": "0:02:07", "throughput": 3597.15, "total_tokens": 5555808}
|
| 2722 |
+
{"current_steps": 13565, "total_steps": 14680, "loss": 0.0, "lr": 1.7501729232972442e-07, "epoch": 18.480926430517712, "percentage": 92.4, "elapsed_time": "0:25:44", "remaining_time": "0:02:06", "throughput": 3597.26, "total_tokens": 5557696}
|
| 2723 |
+
{"current_steps": 13570, "total_steps": 14680, "loss": 0.0, "lr": 1.7346166125680796e-07, "epoch": 18.48773841961853, "percentage": 92.44, "elapsed_time": "0:25:45", "remaining_time": "0:02:06", "throughput": 3597.34, "total_tokens": 5559840}
|
| 2724 |
+
{"current_steps": 13575, "total_steps": 14680, "loss": 0.0, "lr": 1.7191285260202806e-07, "epoch": 18.494550408719345, "percentage": 92.47, "elapsed_time": "0:25:46", "remaining_time": "0:02:05", "throughput": 3597.46, "total_tokens": 5561952}
|
| 2725 |
+
{"current_steps": 13580, "total_steps": 14680, "loss": 0.0, "lr": 1.7037086855465902e-07, "epoch": 18.501362397820163, "percentage": 92.51, "elapsed_time": "0:25:46", "remaining_time": "0:02:05", "throughput": 3597.5, "total_tokens": 5563904}
|
| 2726 |
+
{"current_steps": 13585, "total_steps": 14680, "loss": 0.0, "lr": 1.688357112943284e-07, "epoch": 18.50817438692098, "percentage": 92.54, "elapsed_time": "0:25:47", "remaining_time": "0:02:04", "throughput": 3597.6, "total_tokens": 5565984}
|
| 2727 |
+
{"current_steps": 13590, "total_steps": 14680, "loss": 0.0, "lr": 1.6730738299101601e-07, "epoch": 18.5149863760218, "percentage": 92.57, "elapsed_time": "0:25:47", "remaining_time": "0:02:04", "throughput": 3597.73, "total_tokens": 5568000}
|
| 2728 |
+
{"current_steps": 13595, "total_steps": 14680, "loss": 0.0, "lr": 1.6578588580504818e-07, "epoch": 18.521798365122617, "percentage": 92.61, "elapsed_time": "0:25:48", "remaining_time": "0:02:03", "throughput": 3597.8, "total_tokens": 5570112}
|
| 2729 |
+
{"current_steps": 13600, "total_steps": 14680, "loss": 0.0, "lr": 1.6427122188709232e-07, "epoch": 18.52861035422343, "percentage": 92.64, "elapsed_time": "0:25:48", "remaining_time": "0:02:02", "throughput": 3597.88, "total_tokens": 5572256}
|
| 2730 |
+
{"current_steps": 13605, "total_steps": 14680, "loss": 0.0, "lr": 1.627633933781614e-07, "epoch": 18.53542234332425, "percentage": 92.68, "elapsed_time": "0:25:49", "remaining_time": "0:02:02", "throughput": 3597.96, "total_tokens": 5574304}
|
| 2731 |
+
{"current_steps": 13610, "total_steps": 14680, "loss": 0.0, "lr": 1.6126240240960267e-07, "epoch": 18.542234332425068, "percentage": 92.71, "elapsed_time": "0:25:49", "remaining_time": "0:02:01", "throughput": 3598.06, "total_tokens": 5576384}
|
| 2732 |
+
{"current_steps": 13615, "total_steps": 14680, "loss": 0.0, "lr": 1.5976825110310012e-07, "epoch": 18.549046321525886, "percentage": 92.75, "elapsed_time": "0:25:50", "remaining_time": "0:02:01", "throughput": 3598.14, "total_tokens": 5578528}
|
| 2733 |
+
{"current_steps": 13620, "total_steps": 14680, "loss": 0.0, "lr": 1.58280941570671e-07, "epoch": 18.555858310626704, "percentage": 92.78, "elapsed_time": "0:25:50", "remaining_time": "0:02:00", "throughput": 3598.29, "total_tokens": 5580704}
|
| 2734 |
+
{"current_steps": 13625, "total_steps": 14680, "loss": 0.0, "lr": 1.5680047591465797e-07, "epoch": 18.56267029972752, "percentage": 92.81, "elapsed_time": "0:25:51", "remaining_time": "0:02:00", "throughput": 3598.36, "total_tokens": 5582720}
|
| 2735 |
+
{"current_steps": 13630, "total_steps": 14680, "loss": 0.0, "lr": 1.553268562277338e-07, "epoch": 18.569482288828336, "percentage": 92.85, "elapsed_time": "0:25:52", "remaining_time": "0:01:59", "throughput": 3598.44, "total_tokens": 5584864}
|
| 2736 |
+
{"current_steps": 13635, "total_steps": 14680, "loss": 0.0, "lr": 1.538600845928906e-07, "epoch": 18.576294277929154, "percentage": 92.88, "elapsed_time": "0:25:52", "remaining_time": "0:01:58", "throughput": 3598.57, "total_tokens": 5586880}
|
| 2737 |
+
{"current_steps": 13640, "total_steps": 14680, "loss": 0.0, "lr": 1.5240016308344264e-07, "epoch": 18.583106267029972, "percentage": 92.92, "elapsed_time": "0:25:53", "remaining_time": "0:01:58", "throughput": 3598.57, "total_tokens": 5588960}
|
| 2738 |
+
{"current_steps": 13645, "total_steps": 14680, "loss": 0.0, "lr": 1.5094709376302253e-07, "epoch": 18.58991825613079, "percentage": 92.95, "elapsed_time": "0:25:53", "remaining_time": "0:01:57", "throughput": 3598.61, "total_tokens": 5591040}
|
| 2739 |
+
{"current_steps": 13650, "total_steps": 14680, "loss": 0.0, "lr": 1.4950087868557395e-07, "epoch": 18.59673024523161, "percentage": 92.98, "elapsed_time": "0:25:54", "remaining_time": "0:01:57", "throughput": 3598.7, "total_tokens": 5593120}
|
| 2740 |
+
{"current_steps": 13655, "total_steps": 14680, "loss": 0.0, "lr": 1.48061519895355e-07, "epoch": 18.603542234332426, "percentage": 93.02, "elapsed_time": "0:25:54", "remaining_time": "0:01:56", "throughput": 3598.82, "total_tokens": 5595264}
|
| 2741 |
+
{"current_steps": 13660, "total_steps": 14680, "loss": 0.0, "lr": 1.466290194269304e-07, "epoch": 18.61035422343324, "percentage": 93.05, "elapsed_time": "0:25:55", "remaining_time": "0:01:56", "throughput": 3598.88, "total_tokens": 5597376}
|
| 2742 |
+
{"current_steps": 13665, "total_steps": 14680, "loss": 0.0, "lr": 1.4520337930517102e-07, "epoch": 18.61716621253406, "percentage": 93.09, "elapsed_time": "0:25:55", "remaining_time": "0:01:55", "throughput": 3599.02, "total_tokens": 5599424}
|
| 2743 |
+
{"current_steps": 13670, "total_steps": 14680, "loss": 0.0, "lr": 1.4378460154525099e-07, "epoch": 18.623978201634877, "percentage": 93.12, "elapsed_time": "0:25:56", "remaining_time": "0:01:54", "throughput": 3599.11, "total_tokens": 5601376}
|
| 2744 |
+
{"current_steps": 13675, "total_steps": 14680, "loss": 0.0, "lr": 1.4237268815264326e-07, "epoch": 18.630790190735695, "percentage": 93.15, "elapsed_time": "0:25:56", "remaining_time": "0:01:54", "throughput": 3599.25, "total_tokens": 5603520}
|
| 2745 |
+
{"current_steps": 13680, "total_steps": 14680, "loss": 0.0, "lr": 1.4096764112311866e-07, "epoch": 18.637602179836513, "percentage": 93.19, "elapsed_time": "0:25:57", "remaining_time": "0:01:53", "throughput": 3599.33, "total_tokens": 5605664}
|
| 2746 |
+
{"current_steps": 13685, "total_steps": 14680, "loss": 0.0, "lr": 1.3956946244274294e-07, "epoch": 18.64441416893733, "percentage": 93.22, "elapsed_time": "0:25:57", "remaining_time": "0:01:53", "throughput": 3599.34, "total_tokens": 5607776}
|
| 2747 |
+
{"current_steps": 13690, "total_steps": 14680, "loss": 0.0, "lr": 1.3817815408787182e-07, "epoch": 18.651226158038146, "percentage": 93.26, "elapsed_time": "0:25:58", "remaining_time": "0:01:52", "throughput": 3599.43, "total_tokens": 5609824}
|
| 2748 |
+
{"current_steps": 13695, "total_steps": 14680, "loss": 0.0, "lr": 1.3679371802514884e-07, "epoch": 18.658038147138964, "percentage": 93.29, "elapsed_time": "0:25:59", "remaining_time": "0:01:52", "throughput": 3599.53, "total_tokens": 5611904}
|
| 2749 |
+
{"current_steps": 13700, "total_steps": 14680, "loss": 0.0, "lr": 1.3541615621150694e-07, "epoch": 18.66485013623978, "percentage": 93.32, "elapsed_time": "0:25:59", "remaining_time": "0:01:51", "throughput": 3599.58, "total_tokens": 5613984}
|
| 2750 |
+
{"current_steps": 13705, "total_steps": 14680, "loss": 0.0, "lr": 1.3404547059415962e-07, "epoch": 18.6716621253406, "percentage": 93.36, "elapsed_time": "0:26:00", "remaining_time": "0:01:50", "throughput": 3599.72, "total_tokens": 5615936}
|
| 2751 |
+
{"current_steps": 13710, "total_steps": 14680, "loss": 0.0, "lr": 1.3268166311060037e-07, "epoch": 18.678474114441418, "percentage": 93.39, "elapsed_time": "0:26:00", "remaining_time": "0:01:50", "throughput": 3599.77, "total_tokens": 5618144}
|
| 2752 |
+
{"current_steps": 13715, "total_steps": 14680, "loss": 0.0, "lr": 1.313247356886016e-07, "epoch": 18.685286103542236, "percentage": 93.43, "elapsed_time": "0:26:01", "remaining_time": "0:01:49", "throughput": 3599.87, "total_tokens": 5620256}
|
| 2753 |
+
{"current_steps": 13720, "total_steps": 14680, "loss": 0.0, "lr": 1.2997469024621012e-07, "epoch": 18.69209809264305, "percentage": 93.46, "elapsed_time": "0:26:01", "remaining_time": "0:01:49", "throughput": 3599.93, "total_tokens": 5622240}
|
| 2754 |
+
{"current_steps": 13725, "total_steps": 14680, "loss": 0.0, "lr": 1.28631528691745e-07, "epoch": 18.69891008174387, "percentage": 93.49, "elapsed_time": "0:26:02", "remaining_time": "0:01:48", "throughput": 3600.0, "total_tokens": 5624160}
|
| 2755 |
+
{"current_steps": 13730, "total_steps": 14680, "loss": 0.0, "lr": 1.2729525292379419e-07, "epoch": 18.705722070844686, "percentage": 93.53, "elapsed_time": "0:26:02", "remaining_time": "0:01:48", "throughput": 3600.07, "total_tokens": 5626080}
|
| 2756 |
+
{"current_steps": 13735, "total_steps": 14680, "loss": 0.0, "lr": 1.2596586483121232e-07, "epoch": 18.712534059945504, "percentage": 93.56, "elapsed_time": "0:26:03", "remaining_time": "0:01:47", "throughput": 3600.17, "total_tokens": 5628064}
|
| 2757 |
+
{"current_steps": 13740, "total_steps": 14680, "loss": 0.0, "lr": 1.246433662931207e-07, "epoch": 18.719346049046322, "percentage": 93.6, "elapsed_time": "0:26:03", "remaining_time": "0:01:46", "throughput": 3600.32, "total_tokens": 5630240}
|
| 2758 |
+
{"current_steps": 13745, "total_steps": 14680, "loss": 0.0, "lr": 1.233277591788984e-07, "epoch": 18.72615803814714, "percentage": 93.63, "elapsed_time": "0:26:04", "remaining_time": "0:01:46", "throughput": 3600.45, "total_tokens": 5632160}
|
| 2759 |
+
{"current_steps": 13750, "total_steps": 14680, "loss": 0.0, "lr": 1.220190453481851e-07, "epoch": 18.732970027247955, "percentage": 93.66, "elapsed_time": "0:26:04", "remaining_time": "0:01:45", "throughput": 3600.55, "total_tokens": 5634144}
|
| 2760 |
+
{"current_steps": 13755, "total_steps": 14680, "loss": 0.0, "lr": 1.207172266508777e-07, "epoch": 18.739782016348773, "percentage": 93.7, "elapsed_time": "0:26:05", "remaining_time": "0:01:45", "throughput": 3600.65, "total_tokens": 5636032}
|
| 2761 |
+
{"current_steps": 13760, "total_steps": 14680, "loss": 0.0, "lr": 1.1942230492712427e-07, "epoch": 18.74659400544959, "percentage": 93.73, "elapsed_time": "0:26:05", "remaining_time": "0:01:44", "throughput": 3600.73, "total_tokens": 5638272}
|
| 2762 |
+
{"current_steps": 13765, "total_steps": 14680, "loss": 0.0, "lr": 1.1813428200732613e-07, "epoch": 18.75340599455041, "percentage": 93.77, "elapsed_time": "0:26:06", "remaining_time": "0:01:44", "throughput": 3600.8, "total_tokens": 5640288}
|
| 2763 |
+
{"current_steps": 13770, "total_steps": 14680, "loss": 0.0, "lr": 1.1685315971213195e-07, "epoch": 18.760217983651227, "percentage": 93.8, "elapsed_time": "0:26:06", "remaining_time": "0:01:43", "throughput": 3600.91, "total_tokens": 5642432}
|
| 2764 |
+
{"current_steps": 13775, "total_steps": 14680, "loss": 0.0, "lr": 1.155789398524354e-07, "epoch": 18.767029972752045, "percentage": 93.84, "elapsed_time": "0:26:07", "remaining_time": "0:01:42", "throughput": 3601.05, "total_tokens": 5644384}
|
| 2765 |
+
{"current_steps": 13780, "total_steps": 14680, "loss": 0.0, "lr": 1.1431162422937514e-07, "epoch": 18.77384196185286, "percentage": 93.87, "elapsed_time": "0:26:07", "remaining_time": "0:01:42", "throughput": 3601.13, "total_tokens": 5646432}
|
| 2766 |
+
{"current_steps": 13785, "total_steps": 14680, "loss": 0.0, "lr": 1.1305121463432989e-07, "epoch": 18.780653950953678, "percentage": 93.9, "elapsed_time": "0:26:08", "remaining_time": "0:01:41", "throughput": 3601.27, "total_tokens": 5648352}
|
| 2767 |
+
{"current_steps": 13790, "total_steps": 14680, "loss": 0.0, "lr": 1.1179771284891505e-07, "epoch": 18.787465940054496, "percentage": 93.94, "elapsed_time": "0:26:08", "remaining_time": "0:01:41", "throughput": 3601.35, "total_tokens": 5650304}
|
| 2768 |
+
{"current_steps": 13795, "total_steps": 14680, "loss": 0.0, "lr": 1.1055112064498386e-07, "epoch": 18.794277929155314, "percentage": 93.97, "elapsed_time": "0:26:09", "remaining_time": "0:01:40", "throughput": 3601.45, "total_tokens": 5652288}
|
| 2769 |
+
{"current_steps": 13800, "total_steps": 14680, "loss": 0.0, "lr": 1.0931143978462233e-07, "epoch": 18.80108991825613, "percentage": 94.01, "elapsed_time": "0:26:09", "remaining_time": "0:01:40", "throughput": 3601.53, "total_tokens": 5654304}
|
| 2770 |
+
{"current_steps": 13805, "total_steps": 14680, "loss": 0.0, "lr": 1.0807867202014543e-07, "epoch": 18.80790190735695, "percentage": 94.04, "elapsed_time": "0:26:10", "remaining_time": "0:01:39", "throughput": 3601.68, "total_tokens": 5656480}
|
| 2771 |
+
{"current_steps": 13810, "total_steps": 14680, "loss": 0.0, "lr": 1.0685281909409872e-07, "epoch": 18.814713896457764, "percentage": 94.07, "elapsed_time": "0:26:11", "remaining_time": "0:01:38", "throughput": 3601.78, "total_tokens": 5658464}
|
| 2772 |
+
{"current_steps": 13815, "total_steps": 14680, "loss": 0.0, "lr": 1.0563388273925168e-07, "epoch": 18.821525885558582, "percentage": 94.11, "elapsed_time": "0:26:11", "remaining_time": "0:01:38", "throughput": 3601.9, "total_tokens": 5660480}
|
| 2773 |
+
{"current_steps": 13820, "total_steps": 14680, "loss": 0.0, "lr": 1.0442186467859717e-07, "epoch": 18.8283378746594, "percentage": 94.14, "elapsed_time": "0:26:12", "remaining_time": "0:01:37", "throughput": 3601.99, "total_tokens": 5662528}
|
| 2774 |
+
{"current_steps": 13825, "total_steps": 14680, "loss": 0.0, "lr": 1.0321676662535085e-07, "epoch": 18.83514986376022, "percentage": 94.18, "elapsed_time": "0:26:12", "remaining_time": "0:01:37", "throughput": 3602.0, "total_tokens": 5664640}
|
| 2775 |
+
{"current_steps": 13830, "total_steps": 14680, "loss": 0.0, "lr": 1.0201859028294347e-07, "epoch": 18.841961852861036, "percentage": 94.21, "elapsed_time": "0:26:13", "remaining_time": "0:01:36", "throughput": 3602.09, "total_tokens": 5666496}
|
| 2776 |
+
{"current_steps": 13835, "total_steps": 14680, "loss": 0.0, "lr": 1.0082733734502525e-07, "epoch": 18.848773841961854, "percentage": 94.24, "elapsed_time": "0:26:13", "remaining_time": "0:01:36", "throughput": 3602.16, "total_tokens": 5668608}
|
| 2777 |
+
{"current_steps": 13840, "total_steps": 14680, "loss": 0.0, "lr": 9.964300949545758e-08, "epoch": 18.85558583106267, "percentage": 94.28, "elapsed_time": "0:26:14", "remaining_time": "0:01:35", "throughput": 3602.23, "total_tokens": 5670624}
|
| 2778 |
+
{"current_steps": 13845, "total_steps": 14680, "loss": 0.0, "lr": 9.846560840831354e-08, "epoch": 18.862397820163487, "percentage": 94.31, "elapsed_time": "0:26:14", "remaining_time": "0:01:34", "throughput": 3602.28, "total_tokens": 5672640}
|
| 2779 |
+
{"current_steps": 13850, "total_steps": 14680, "loss": 0.0, "lr": 9.729513574787686e-08, "epoch": 18.869209809264305, "percentage": 94.35, "elapsed_time": "0:26:15", "remaining_time": "0:01:34", "throughput": 3602.32, "total_tokens": 5674720}
|
| 2780 |
+
{"current_steps": 13855, "total_steps": 14680, "loss": 0.0, "lr": 9.613159316863519e-08, "epoch": 18.876021798365123, "percentage": 94.38, "elapsed_time": "0:26:15", "remaining_time": "0:01:33", "throughput": 3602.39, "total_tokens": 5676736}
|
| 2781 |
+
{"current_steps": 13860, "total_steps": 14680, "loss": 0.0, "lr": 9.49749823152818e-08, "epoch": 18.88283378746594, "percentage": 94.41, "elapsed_time": "0:26:16", "remaining_time": "0:01:33", "throughput": 3602.5, "total_tokens": 5678720}
|
| 2782 |
+
{"current_steps": 13865, "total_steps": 14680, "loss": 0.0, "lr": 9.382530482271223e-08, "epoch": 18.88964577656676, "percentage": 94.45, "elapsed_time": "0:26:16", "remaining_time": "0:01:32", "throughput": 3602.56, "total_tokens": 5680736}
|
| 2783 |
+
{"current_steps": 13870, "total_steps": 14680, "loss": 0.0, "lr": 9.26825623160199e-08, "epoch": 18.896457765667574, "percentage": 94.48, "elapsed_time": "0:26:17", "remaining_time": "0:01:32", "throughput": 3602.6, "total_tokens": 5682912}
|
| 2784 |
+
{"current_steps": 13875, "total_steps": 14680, "loss": 0.0, "lr": 9.15467564104977e-08, "epoch": 18.90326975476839, "percentage": 94.52, "elapsed_time": "0:26:17", "remaining_time": "0:01:31", "throughput": 3602.71, "total_tokens": 5684800}
|
| 2785 |
+
{"current_steps": 13880, "total_steps": 14680, "loss": 0.0, "lr": 9.041788871163081e-08, "epoch": 18.91008174386921, "percentage": 94.55, "elapsed_time": "0:26:18", "remaining_time": "0:01:30", "throughput": 3602.84, "total_tokens": 5686944}
|
| 2786 |
+
{"current_steps": 13885, "total_steps": 14680, "loss": 0.0, "lr": 8.929596081509951e-08, "epoch": 18.916893732970028, "percentage": 94.58, "elapsed_time": "0:26:19", "remaining_time": "0:01:30", "throughput": 3602.85, "total_tokens": 5689056}
|
| 2787 |
+
{"current_steps": 13890, "total_steps": 14680, "loss": 0.0, "lr": 8.818097430677408e-08, "epoch": 18.923705722070846, "percentage": 94.62, "elapsed_time": "0:26:19", "remaining_time": "0:01:29", "throughput": 3602.95, "total_tokens": 5691136}
|
| 2788 |
+
{"current_steps": 13895, "total_steps": 14680, "loss": 0.0, "lr": 8.707293076271161e-08, "epoch": 18.930517711171664, "percentage": 94.65, "elapsed_time": "0:26:20", "remaining_time": "0:01:29", "throughput": 3603.12, "total_tokens": 5693248}
|
| 2789 |
+
{"current_steps": 13900, "total_steps": 14680, "loss": 0.0, "lr": 8.597183174915536e-08, "epoch": 18.93732970027248, "percentage": 94.69, "elapsed_time": "0:26:20", "remaining_time": "0:01:28", "throughput": 3603.2, "total_tokens": 5695200}
|
| 2790 |
+
{"current_steps": 13905, "total_steps": 14680, "loss": 0.0, "lr": 8.487767882253417e-08, "epoch": 18.944141689373296, "percentage": 94.72, "elapsed_time": "0:26:21", "remaining_time": "0:01:28", "throughput": 3603.28, "total_tokens": 5697120}
|
| 2791 |
+
{"current_steps": 13910, "total_steps": 14680, "loss": 0.0, "lr": 8.379047352945702e-08, "epoch": 18.950953678474114, "percentage": 94.75, "elapsed_time": "0:26:21", "remaining_time": "0:01:27", "throughput": 3603.39, "total_tokens": 5699232}
|
| 2792 |
+
{"current_steps": 13915, "total_steps": 14680, "loss": 0.0, "lr": 8.271021740671293e-08, "epoch": 18.957765667574932, "percentage": 94.79, "elapsed_time": "0:26:22", "remaining_time": "0:01:26", "throughput": 3603.39, "total_tokens": 5701216}
|
| 2793 |
+
{"current_steps": 13920, "total_steps": 14680, "loss": 0.0, "lr": 8.16369119812671e-08, "epoch": 18.96457765667575, "percentage": 94.82, "elapsed_time": "0:26:22", "remaining_time": "0:01:26", "throughput": 3603.5, "total_tokens": 5703328}
|
| 2794 |
+
{"current_steps": 13925, "total_steps": 14680, "loss": 0.0, "lr": 8.057055877025988e-08, "epoch": 18.97138964577657, "percentage": 94.86, "elapsed_time": "0:26:23", "remaining_time": "0:01:25", "throughput": 3603.55, "total_tokens": 5705312}
|
| 2795 |
+
{"current_steps": 13930, "total_steps": 14680, "loss": 0.0, "lr": 7.951115928100605e-08, "epoch": 18.978201634877383, "percentage": 94.89, "elapsed_time": "0:26:23", "remaining_time": "0:01:25", "throughput": 3603.56, "total_tokens": 5707424}
|
| 2796 |
+
{"current_steps": 13935, "total_steps": 14680, "loss": 0.0, "lr": 7.845871501099e-08, "epoch": 18.9850136239782, "percentage": 94.93, "elapsed_time": "0:26:24", "remaining_time": "0:01:24", "throughput": 3603.63, "total_tokens": 5709344}
|
| 2797 |
+
{"current_steps": 13940, "total_steps": 14680, "loss": 0.0, "lr": 7.741322744786339e-08, "epoch": 18.99182561307902, "percentage": 94.96, "elapsed_time": "0:26:24", "remaining_time": "0:01:24", "throughput": 3603.69, "total_tokens": 5711456}
|
| 2798 |
+
{"current_steps": 13945, "total_steps": 14680, "loss": 0.0, "lr": 7.637469806944798e-08, "epoch": 18.998637602179837, "percentage": 94.99, "elapsed_time": "0:26:25", "remaining_time": "0:01:23", "throughput": 3603.78, "total_tokens": 5713408}
|
| 2799 |
+
{"current_steps": 13950, "total_steps": 14680, "loss": 0.0, "lr": 7.534312834372726e-08, "epoch": 19.005449591280655, "percentage": 95.03, "elapsed_time": "0:26:25", "remaining_time": "0:01:22", "throughput": 3603.51, "total_tokens": 5715120}
|
| 2800 |
+
{"current_steps": 13955, "total_steps": 14680, "loss": 0.0, "lr": 7.431851972884651e-08, "epoch": 19.01226158038147, "percentage": 95.06, "elapsed_time": "0:26:26", "remaining_time": "0:01:22", "throughput": 3603.61, "total_tokens": 5717296}
|
| 2801 |
+
{"current_steps": 13960, "total_steps": 14680, "loss": 0.0, "lr": 7.330087367311389e-08, "epoch": 19.019073569482288, "percentage": 95.1, "elapsed_time": "0:26:27", "remaining_time": "0:01:21", "throughput": 3603.67, "total_tokens": 5719408}
|
| 2802 |
+
{"current_steps": 13965, "total_steps": 14680, "loss": 0.0, "lr": 7.229019161499374e-08, "epoch": 19.025885558583106, "percentage": 95.13, "elapsed_time": "0:26:27", "remaining_time": "0:01:21", "throughput": 3603.77, "total_tokens": 5721488}
|
| 2803 |
+
{"current_steps": 13970, "total_steps": 14680, "loss": 0.0, "lr": 7.12864749831077e-08, "epoch": 19.032697547683924, "percentage": 95.16, "elapsed_time": "0:26:28", "remaining_time": "0:01:20", "throughput": 3603.83, "total_tokens": 5723600}
|
| 2804 |
+
{"current_steps": 13975, "total_steps": 14680, "loss": 0.0, "lr": 7.0289725196232e-08, "epoch": 19.039509536784742, "percentage": 95.2, "elapsed_time": "0:26:28", "remaining_time": "0:01:20", "throughput": 3603.89, "total_tokens": 5725616}
|
| 2805 |
+
{"current_steps": 13980, "total_steps": 14680, "loss": 0.0, "lr": 6.929994366329296e-08, "epoch": 19.04632152588556, "percentage": 95.23, "elapsed_time": "0:26:29", "remaining_time": "0:01:19", "throughput": 3603.97, "total_tokens": 5727760}
|
| 2806 |
+
{"current_steps": 13985, "total_steps": 14680, "loss": 0.0, "lr": 6.831713178336918e-08, "epoch": 19.053133514986374, "percentage": 95.27, "elapsed_time": "0:26:29", "remaining_time": "0:01:19", "throughput": 3604.05, "total_tokens": 5729808}
|
| 2807 |
+
{"current_steps": 13990, "total_steps": 14680, "loss": 0.0, "lr": 6.734129094568775e-08, "epoch": 19.059945504087192, "percentage": 95.3, "elapsed_time": "0:26:30", "remaining_time": "0:01:18", "throughput": 3604.15, "total_tokens": 5731888}
|
| 2808 |
+
{"current_steps": 13995, "total_steps": 14680, "loss": 0.0, "lr": 6.637242252961973e-08, "epoch": 19.06675749318801, "percentage": 95.33, "elapsed_time": "0:26:30", "remaining_time": "0:01:17", "throughput": 3604.18, "total_tokens": 5734032}
|
| 2809 |
+
{"current_steps": 14000, "total_steps": 14680, "loss": 0.0, "lr": 6.541052790468294e-08, "epoch": 19.07356948228883, "percentage": 95.37, "elapsed_time": "0:26:31", "remaining_time": "0:01:17", "throughput": 3604.24, "total_tokens": 5736048}
|
| 2810 |
+
{"current_steps": 14005, "total_steps": 14680, "loss": 0.0, "lr": 6.445560843053644e-08, "epoch": 19.080381471389646, "percentage": 95.4, "elapsed_time": "0:26:32", "remaining_time": "0:01:16", "throughput": 3604.32, "total_tokens": 5738096}
|
| 2811 |
+
{"current_steps": 14010, "total_steps": 14680, "loss": 0.0, "lr": 6.35076654569794e-08, "epoch": 19.087193460490465, "percentage": 95.44, "elapsed_time": "0:26:32", "remaining_time": "0:01:16", "throughput": 3604.35, "total_tokens": 5740240}
|
| 2812 |
+
{"current_steps": 14015, "total_steps": 14680, "loss": 0.0, "lr": 6.256670032395051e-08, "epoch": 19.09400544959128, "percentage": 95.47, "elapsed_time": "0:26:33", "remaining_time": "0:01:15", "throughput": 3604.44, "total_tokens": 5742192}
|
| 2813 |
+
{"current_steps": 14020, "total_steps": 14680, "loss": 0.0, "lr": 6.163271436152474e-08, "epoch": 19.100817438692097, "percentage": 95.5, "elapsed_time": "0:26:33", "remaining_time": "0:01:15", "throughput": 3604.58, "total_tokens": 5744368}
|
| 2814 |
+
{"current_steps": 14025, "total_steps": 14680, "loss": 0.0, "lr": 6.070570888991157e-08, "epoch": 19.107629427792915, "percentage": 95.54, "elapsed_time": "0:26:34", "remaining_time": "0:01:14", "throughput": 3604.64, "total_tokens": 5746384}
|
| 2815 |
+
{"current_steps": 14030, "total_steps": 14680, "loss": 0.0, "lr": 5.978568521945338e-08, "epoch": 19.114441416893733, "percentage": 95.57, "elapsed_time": "0:26:34", "remaining_time": "0:01:13", "throughput": 3604.76, "total_tokens": 5748400}
|
| 2816 |
+
{"current_steps": 14035, "total_steps": 14680, "loss": 0.0, "lr": 5.887264465062437e-08, "epoch": 19.12125340599455, "percentage": 95.61, "elapsed_time": "0:26:35", "remaining_time": "0:01:13", "throughput": 3604.85, "total_tokens": 5750352}
|
| 2817 |
+
{"current_steps": 14040, "total_steps": 14680, "loss": 0.0, "lr": 5.7966588474027695e-08, "epoch": 19.12806539509537, "percentage": 95.64, "elapsed_time": "0:26:35", "remaining_time": "0:01:12", "throughput": 3604.97, "total_tokens": 5752368}
|
| 2818 |
+
{"current_steps": 14045, "total_steps": 14680, "loss": 0.0, "lr": 5.706751797039334e-08, "epoch": 19.134877384196184, "percentage": 95.67, "elapsed_time": "0:26:36", "remaining_time": "0:01:12", "throughput": 3605.0, "total_tokens": 5754416}
|
| 2819 |
+
{"current_steps": 14050, "total_steps": 14680, "loss": 0.0, "lr": 5.617543441057638e-08, "epoch": 19.141689373297, "percentage": 95.71, "elapsed_time": "0:26:36", "remaining_time": "0:01:11", "throughput": 3605.04, "total_tokens": 5756592}
|
| 2820 |
+
{"current_steps": 14055, "total_steps": 14680, "loss": 0.0, "lr": 5.52903390555587e-08, "epoch": 19.14850136239782, "percentage": 95.74, "elapsed_time": "0:26:37", "remaining_time": "0:01:11", "throughput": 3605.07, "total_tokens": 5758544}
|
| 2821 |
+
{"current_steps": 14060, "total_steps": 14680, "loss": 0.0, "lr": 5.441223315643951e-08, "epoch": 19.155313351498638, "percentage": 95.78, "elapsed_time": "0:26:37", "remaining_time": "0:01:10", "throughput": 3605.16, "total_tokens": 5760720}
|
| 2822 |
+
{"current_steps": 14065, "total_steps": 14680, "loss": 0.0, "lr": 5.354111795444261e-08, "epoch": 19.162125340599456, "percentage": 95.81, "elapsed_time": "0:26:38", "remaining_time": "0:01:09", "throughput": 3605.27, "total_tokens": 5762832}
|
| 2823 |
+
{"current_steps": 14070, "total_steps": 14680, "loss": 0.0, "lr": 5.2676994680908035e-08, "epoch": 19.168937329700274, "percentage": 95.84, "elapsed_time": "0:26:39", "remaining_time": "0:01:09", "throughput": 3605.37, "total_tokens": 5765008}
|
| 2824 |
+
{"current_steps": 14075, "total_steps": 14680, "loss": 0.0, "lr": 5.1819864557292595e-08, "epoch": 19.17574931880109, "percentage": 95.88, "elapsed_time": "0:26:39", "remaining_time": "0:01:08", "throughput": 3605.45, "total_tokens": 5767056}
|
| 2825 |
+
{"current_steps": 14080, "total_steps": 14680, "loss": 0.0, "lr": 5.096972879516937e-08, "epoch": 19.182561307901906, "percentage": 95.91, "elapsed_time": "0:26:40", "remaining_time": "0:01:08", "throughput": 3605.53, "total_tokens": 5769200}
|
| 2826 |
+
{"current_steps": 14085, "total_steps": 14680, "loss": 0.0, "lr": 5.012658859622321e-08, "epoch": 19.189373297002724, "percentage": 95.95, "elapsed_time": "0:26:40", "remaining_time": "0:01:07", "throughput": 3605.63, "total_tokens": 5771280}
|
| 2827 |
+
{"current_steps": 14090, "total_steps": 14680, "loss": 0.0, "lr": 4.9290445152251895e-08, "epoch": 19.196185286103542, "percentage": 95.98, "elapsed_time": "0:26:41", "remaining_time": "0:01:07", "throughput": 3605.67, "total_tokens": 5773360}
|
| 2828 |
+
{"current_steps": 14095, "total_steps": 14680, "loss": 0.0, "lr": 4.846129964516222e-08, "epoch": 19.20299727520436, "percentage": 96.01, "elapsed_time": "0:26:41", "remaining_time": "0:01:06", "throughput": 3605.76, "total_tokens": 5775632}
|
| 2829 |
+
{"current_steps": 14100, "total_steps": 14680, "loss": 0.0, "lr": 4.7639153246969436e-08, "epoch": 19.20980926430518, "percentage": 96.05, "elapsed_time": "0:26:42", "remaining_time": "0:01:05", "throughput": 3605.79, "total_tokens": 5777584}
|
| 2830 |
+
{"current_steps": 14105, "total_steps": 14680, "loss": 0.0, "lr": 4.6824007119796176e-08, "epoch": 19.216621253405993, "percentage": 96.08, "elapsed_time": "0:26:42", "remaining_time": "0:01:05", "throughput": 3605.91, "total_tokens": 5779504}
|
| 2831 |
+
{"current_steps": 14110, "total_steps": 14680, "loss": 0.0, "lr": 4.601586241586964e-08, "epoch": 19.22343324250681, "percentage": 96.12, "elapsed_time": "0:26:43", "remaining_time": "0:01:04", "throughput": 3606.0, "total_tokens": 5781584}
|
| 2832 |
+
{"current_steps": 14115, "total_steps": 14680, "loss": 0.0, "lr": 4.521472027751883e-08, "epoch": 19.23024523160763, "percentage": 96.15, "elapsed_time": "0:26:43", "remaining_time": "0:01:04", "throughput": 3606.12, "total_tokens": 5783600}
|
| 2833 |
+
{"current_steps": 14120, "total_steps": 14680, "loss": 0.0, "lr": 4.442058183717679e-08, "epoch": 19.237057220708447, "percentage": 96.19, "elapsed_time": "0:26:44", "remaining_time": "0:01:03", "throughput": 3606.21, "total_tokens": 5785712}
|
| 2834 |
+
{"current_steps": 14125, "total_steps": 14680, "loss": 0.0, "lr": 4.363344821737558e-08, "epoch": 19.243869209809265, "percentage": 96.22, "elapsed_time": "0:26:44", "remaining_time": "0:01:03", "throughput": 3606.27, "total_tokens": 5787824}
|
| 2835 |
+
{"current_steps": 14130, "total_steps": 14680, "loss": 0.0, "lr": 4.285332053074576e-08, "epoch": 19.250681198910083, "percentage": 96.25, "elapsed_time": "0:26:45", "remaining_time": "0:01:02", "throughput": 3606.37, "total_tokens": 5789712}
|
| 2836 |
+
{"current_steps": 14135, "total_steps": 14680, "loss": 0.0, "lr": 4.2080199880015217e-08, "epoch": 19.257493188010898, "percentage": 96.29, "elapsed_time": "0:26:45", "remaining_time": "0:01:01", "throughput": 3606.44, "total_tokens": 5791760}
|
| 2837 |
+
{"current_steps": 14140, "total_steps": 14680, "loss": 0.0, "lr": 4.131408735800646e-08, "epoch": 19.264305177111716, "percentage": 96.32, "elapsed_time": "0:26:46", "remaining_time": "0:01:01", "throughput": 3606.43, "total_tokens": 5793840}
|
| 2838 |
+
{"current_steps": 14145, "total_steps": 14680, "loss": 0.0, "lr": 4.055498404763658e-08, "epoch": 19.271117166212534, "percentage": 96.36, "elapsed_time": "0:26:47", "remaining_time": "0:01:00", "throughput": 3606.52, "total_tokens": 5795824}
|
| 2839 |
+
{"current_steps": 14150, "total_steps": 14680, "loss": 0.0, "lr": 3.9802891021915036e-08, "epoch": 19.277929155313352, "percentage": 96.39, "elapsed_time": "0:26:47", "remaining_time": "0:01:00", "throughput": 3606.66, "total_tokens": 5797776}
|
| 2840 |
+
{"current_steps": 14155, "total_steps": 14680, "loss": 0.0, "lr": 3.905780934394199e-08, "epoch": 19.28474114441417, "percentage": 96.42, "elapsed_time": "0:26:48", "remaining_time": "0:00:59", "throughput": 3606.7, "total_tokens": 5799760}
|
| 2841 |
+
{"current_steps": 14160, "total_steps": 14680, "loss": 0.0, "lr": 3.831974006690664e-08, "epoch": 19.291553133514988, "percentage": 96.46, "elapsed_time": "0:26:48", "remaining_time": "0:00:59", "throughput": 3606.77, "total_tokens": 5801776}
|
| 2842 |
+
{"current_steps": 14165, "total_steps": 14680, "loss": 0.0, "lr": 3.7588684234085574e-08, "epoch": 19.298365122615802, "percentage": 96.49, "elapsed_time": "0:26:49", "remaining_time": "0:00:58", "throughput": 3606.82, "total_tokens": 5803664}
|
| 2843 |
+
{"current_steps": 14170, "total_steps": 14680, "loss": 0.0, "lr": 3.6864642878842725e-08, "epoch": 19.30517711171662, "percentage": 96.53, "elapsed_time": "0:26:49", "remaining_time": "0:00:57", "throughput": 3606.86, "total_tokens": 5805648}
|
| 2844 |
+
{"current_steps": 14175, "total_steps": 14680, "loss": 0.0, "lr": 3.614761702462721e-08, "epoch": 19.31198910081744, "percentage": 96.56, "elapsed_time": "0:26:50", "remaining_time": "0:00:57", "throughput": 3606.95, "total_tokens": 5807600}
|
| 2845 |
+
{"current_steps": 14180, "total_steps": 14680, "loss": 0.0, "lr": 3.5437607684969955e-08, "epoch": 19.318801089918257, "percentage": 96.59, "elapsed_time": "0:26:50", "remaining_time": "0:00:56", "throughput": 3607.0, "total_tokens": 5809488}
|
| 2846 |
+
{"current_steps": 14185, "total_steps": 14680, "loss": 0.0, "lr": 3.473461586348481e-08, "epoch": 19.325613079019075, "percentage": 96.63, "elapsed_time": "0:26:51", "remaining_time": "0:00:56", "throughput": 3607.11, "total_tokens": 5811600}
|
| 2847 |
+
{"current_steps": 14190, "total_steps": 14680, "loss": 0.0, "lr": 3.4038642553866906e-08, "epoch": 19.332425068119893, "percentage": 96.66, "elapsed_time": "0:26:51", "remaining_time": "0:00:55", "throughput": 3607.18, "total_tokens": 5813840}
|
| 2848 |
+
{"current_steps": 14195, "total_steps": 14680, "loss": 0.0, "lr": 3.334968873988875e-08, "epoch": 19.339237057220707, "percentage": 96.7, "elapsed_time": "0:26:52", "remaining_time": "0:00:55", "throughput": 3607.24, "total_tokens": 5815856}
|
| 2849 |
+
{"current_steps": 14200, "total_steps": 14680, "loss": 0.0, "lr": 3.2667755395402454e-08, "epoch": 19.346049046321525, "percentage": 96.73, "elapsed_time": "0:26:52", "remaining_time": "0:00:54", "throughput": 3607.33, "total_tokens": 5817936}
|
| 2850 |
+
{"current_steps": 14205, "total_steps": 14680, "loss": 0.0, "lr": 3.199284348433584e-08, "epoch": 19.352861035422343, "percentage": 96.76, "elapsed_time": "0:26:53", "remaining_time": "0:00:53", "throughput": 3607.46, "total_tokens": 5819984}
|
| 2851 |
+
{"current_steps": 14210, "total_steps": 14680, "loss": 0.0, "lr": 3.1324953960691354e-08, "epoch": 19.35967302452316, "percentage": 96.8, "elapsed_time": "0:26:53", "remaining_time": "0:00:53", "throughput": 3607.61, "total_tokens": 5822064}
|
| 2852 |
+
{"current_steps": 14215, "total_steps": 14680, "loss": 0.0, "lr": 3.066408776854546e-08, "epoch": 19.36648501362398, "percentage": 96.83, "elapsed_time": "0:26:54", "remaining_time": "0:00:52", "throughput": 3607.71, "total_tokens": 5824272}
|
| 2853 |
+
{"current_steps": 14220, "total_steps": 14680, "loss": 0.0, "lr": 3.001024584204815e-08, "epoch": 19.373297002724797, "percentage": 96.87, "elapsed_time": "0:26:54", "remaining_time": "0:00:52", "throughput": 3607.77, "total_tokens": 5826384}
|
| 2854 |
+
{"current_steps": 14225, "total_steps": 14680, "loss": 0.0, "lr": 2.9363429105417896e-08, "epoch": 19.38010899182561, "percentage": 96.9, "elapsed_time": "0:26:55", "remaining_time": "0:00:51", "throughput": 3607.88, "total_tokens": 5828400}
|
| 2855 |
+
{"current_steps": 14230, "total_steps": 14680, "loss": 0.0, "lr": 2.8723638472945015e-08, "epoch": 19.38692098092643, "percentage": 96.93, "elapsed_time": "0:26:55", "remaining_time": "0:00:51", "throughput": 3607.96, "total_tokens": 5830448}
|
| 2856 |
+
{"current_steps": 14235, "total_steps": 14680, "loss": 0.0, "lr": 2.809087484898776e-08, "epoch": 19.393732970027248, "percentage": 96.97, "elapsed_time": "0:26:56", "remaining_time": "0:00:50", "throughput": 3608.04, "total_tokens": 5832496}
|
| 2857 |
+
{"current_steps": 14240, "total_steps": 14680, "loss": 0.0, "lr": 2.746513912797122e-08, "epoch": 19.400544959128066, "percentage": 97.0, "elapsed_time": "0:26:57", "remaining_time": "0:00:49", "throughput": 3608.06, "total_tokens": 5834640}
|
| 2858 |
+
{"current_steps": 14245, "total_steps": 14680, "loss": 0.0, "lr": 2.6846432194386762e-08, "epoch": 19.407356948228884, "percentage": 97.04, "elapsed_time": "0:26:57", "remaining_time": "0:00:49", "throughput": 3608.08, "total_tokens": 5836688}
|
| 2859 |
+
{"current_steps": 14250, "total_steps": 14680, "loss": 0.0, "lr": 2.6234754922790374e-08, "epoch": 19.414168937329702, "percentage": 97.07, "elapsed_time": "0:26:58", "remaining_time": "0:00:48", "throughput": 3608.18, "total_tokens": 5838864}
|
| 2860 |
+
{"current_steps": 14255, "total_steps": 14680, "loss": 0.0, "lr": 2.5630108177800984e-08, "epoch": 19.420980926430516, "percentage": 97.1, "elapsed_time": "0:26:58", "remaining_time": "0:00:48", "throughput": 3608.22, "total_tokens": 5840848}
|
| 2861 |
+
{"current_steps": 14260, "total_steps": 14680, "loss": 0.0, "lr": 2.5032492814100472e-08, "epoch": 19.427792915531334, "percentage": 97.14, "elapsed_time": "0:26:59", "remaining_time": "0:00:47", "throughput": 3608.33, "total_tokens": 5842864}
|
| 2862 |
+
{"current_steps": 14265, "total_steps": 14680, "loss": 0.0, "lr": 2.44419096764309e-08, "epoch": 19.434604904632153, "percentage": 97.17, "elapsed_time": "0:26:59", "remaining_time": "0:00:47", "throughput": 3608.4, "total_tokens": 5844880}
|
| 2863 |
+
{"current_steps": 14270, "total_steps": 14680, "loss": 0.0, "lr": 2.3858359599594483e-08, "epoch": 19.44141689373297, "percentage": 97.21, "elapsed_time": "0:27:00", "remaining_time": "0:00:46", "throughput": 3608.44, "total_tokens": 5846960}
|
| 2864 |
+
{"current_steps": 14275, "total_steps": 14680, "loss": 0.0, "lr": 2.3281843408453074e-08, "epoch": 19.44822888283379, "percentage": 97.24, "elapsed_time": "0:27:00", "remaining_time": "0:00:45", "throughput": 3608.46, "total_tokens": 5849104}
|
| 2865 |
+
{"current_steps": 14280, "total_steps": 14680, "loss": 0.0, "lr": 2.2712361917923697e-08, "epoch": 19.455040871934607, "percentage": 97.28, "elapsed_time": "0:27:01", "remaining_time": "0:00:45", "throughput": 3608.53, "total_tokens": 5851024}
|
| 2866 |
+
{"current_steps": 14285, "total_steps": 14680, "loss": 0.0, "lr": 2.2149915932981327e-08, "epoch": 19.46185286103542, "percentage": 97.31, "elapsed_time": "0:27:01", "remaining_time": "0:00:44", "throughput": 3608.59, "total_tokens": 5853040}
|
| 2867 |
+
{"current_steps": 14290, "total_steps": 14680, "loss": 0.0, "lr": 2.159450624865611e-08, "epoch": 19.46866485013624, "percentage": 97.34, "elapsed_time": "0:27:02", "remaining_time": "0:00:44", "throughput": 3608.71, "total_tokens": 5855088}
|
| 2868 |
+
{"current_steps": 14295, "total_steps": 14680, "loss": 0.0, "lr": 2.104613365003172e-08, "epoch": 19.475476839237057, "percentage": 97.38, "elapsed_time": "0:27:02", "remaining_time": "0:00:43", "throughput": 3608.79, "total_tokens": 5857040}
|
| 2869 |
+
{"current_steps": 14300, "total_steps": 14680, "loss": 0.0, "lr": 2.0504798912245328e-08, "epoch": 19.482288828337875, "percentage": 97.41, "elapsed_time": "0:27:03", "remaining_time": "0:00:43", "throughput": 3608.87, "total_tokens": 5859184}
|
| 2870 |
+
{"current_steps": 14305, "total_steps": 14680, "loss": 0.0, "lr": 1.9970502800484292e-08, "epoch": 19.489100817438693, "percentage": 97.45, "elapsed_time": "0:27:04", "remaining_time": "0:00:42", "throughput": 3608.92, "total_tokens": 5861168}
|
| 2871 |
+
{"current_steps": 14310, "total_steps": 14680, "loss": 0.0, "lr": 1.944324606998893e-08, "epoch": 19.495912806539508, "percentage": 97.48, "elapsed_time": "0:27:04", "remaining_time": "0:00:42", "throughput": 3608.99, "total_tokens": 5863312}
|
| 2872 |
+
{"current_steps": 14315, "total_steps": 14680, "loss": 0.0, "lr": 1.8923029466048072e-08, "epoch": 19.502724795640326, "percentage": 97.51, "elapsed_time": "0:27:05", "remaining_time": "0:00:41", "throughput": 3609.08, "total_tokens": 5865488}
|
| 2873 |
+
{"current_steps": 14320, "total_steps": 14680, "loss": 0.0, "lr": 1.840985372399906e-08, "epoch": 19.509536784741144, "percentage": 97.55, "elapsed_time": "0:27:05", "remaining_time": "0:00:40", "throughput": 3609.18, "total_tokens": 5867472}
|
| 2874 |
+
{"current_steps": 14325, "total_steps": 14680, "loss": 0.0, "lr": 1.7903719569227206e-08, "epoch": 19.516348773841962, "percentage": 97.58, "elapsed_time": "0:27:06", "remaining_time": "0:00:40", "throughput": 3609.28, "total_tokens": 5869552}
|
| 2875 |
+
{"current_steps": 14330, "total_steps": 14680, "loss": 0.0, "lr": 1.740462771716411e-08, "epoch": 19.52316076294278, "percentage": 97.62, "elapsed_time": "0:27:06", "remaining_time": "0:00:39", "throughput": 3609.32, "total_tokens": 5871632}
|
| 2876 |
+
{"current_steps": 14335, "total_steps": 14680, "loss": 0.0, "lr": 1.6912578873287678e-08, "epoch": 19.529972752043598, "percentage": 97.65, "elapsed_time": "0:27:07", "remaining_time": "0:00:39", "throughput": 3609.47, "total_tokens": 5873616}
|
| 2877 |
+
{"current_steps": 14340, "total_steps": 14680, "loss": 0.0, "lr": 1.6427573733119317e-08, "epoch": 19.536784741144416, "percentage": 97.68, "elapsed_time": "0:27:07", "remaining_time": "0:00:38", "throughput": 3609.54, "total_tokens": 5875632}
|
| 2878 |
+
{"current_steps": 14345, "total_steps": 14680, "loss": 0.0, "lr": 1.5949612982224527e-08, "epoch": 19.54359673024523, "percentage": 97.72, "elapsed_time": "0:27:08", "remaining_time": "0:00:38", "throughput": 3609.62, "total_tokens": 5877680}
|
| 2879 |
+
{"current_steps": 14350, "total_steps": 14680, "loss": 0.0, "lr": 1.547869729621121e-08, "epoch": 19.55040871934605, "percentage": 97.75, "elapsed_time": "0:27:08", "remaining_time": "0:00:37", "throughput": 3609.65, "total_tokens": 5879728}
|
| 2880 |
+
{"current_steps": 14355, "total_steps": 14680, "loss": 0.0, "lr": 1.501482734072912e-08, "epoch": 19.557220708446867, "percentage": 97.79, "elapsed_time": "0:27:09", "remaining_time": "0:00:36", "throughput": 3609.78, "total_tokens": 5882064}
|
| 2881 |
+
{"current_steps": 14360, "total_steps": 14680, "loss": 0.0, "lr": 1.4558003771468765e-08, "epoch": 19.564032697547685, "percentage": 97.82, "elapsed_time": "0:27:10", "remaining_time": "0:00:36", "throughput": 3609.86, "total_tokens": 5884112}
|
| 2882 |
+
{"current_steps": 14365, "total_steps": 14680, "loss": 0.0, "lr": 1.4108227234160277e-08, "epoch": 19.570844686648503, "percentage": 97.85, "elapsed_time": "0:27:10", "remaining_time": "0:00:35", "throughput": 3609.86, "total_tokens": 5886128}
|
| 2883 |
+
{"current_steps": 14370, "total_steps": 14680, "loss": 0.0, "lr": 1.366549836457287e-08, "epoch": 19.577656675749317, "percentage": 97.89, "elapsed_time": "0:27:11", "remaining_time": "0:00:35", "throughput": 3610.0, "total_tokens": 5888176}
|
| 2884 |
+
{"current_steps": 14375, "total_steps": 14680, "loss": 0.0, "lr": 1.3229817788513178e-08, "epoch": 19.584468664850135, "percentage": 97.92, "elapsed_time": "0:27:11", "remaining_time": "0:00:34", "throughput": 3610.05, "total_tokens": 5890288}
|
| 2885 |
+
{"current_steps": 14380, "total_steps": 14680, "loss": 0.0, "lr": 1.2801186121825238e-08, "epoch": 19.591280653950953, "percentage": 97.96, "elapsed_time": "0:27:12", "remaining_time": "0:00:34", "throughput": 3610.17, "total_tokens": 5892304}
|
| 2886 |
+
{"current_steps": 14385, "total_steps": 14680, "loss": 0.0, "lr": 1.2379603970389953e-08, "epoch": 19.59809264305177, "percentage": 97.99, "elapsed_time": "0:27:12", "remaining_time": "0:00:33", "throughput": 3610.3, "total_tokens": 5894448}
|
| 2887 |
+
{"current_steps": 14390, "total_steps": 14680, "loss": 0.0, "lr": 1.1965071930122308e-08, "epoch": 19.60490463215259, "percentage": 98.02, "elapsed_time": "0:27:13", "remaining_time": "0:00:32", "throughput": 3610.34, "total_tokens": 5896624}
|
| 2888 |
+
{"current_steps": 14395, "total_steps": 14680, "loss": 0.0, "lr": 1.1557590586973034e-08, "epoch": 19.611716621253407, "percentage": 98.06, "elapsed_time": "0:27:13", "remaining_time": "0:00:32", "throughput": 3610.44, "total_tokens": 5898832}
|
| 2889 |
+
{"current_steps": 14400, "total_steps": 14680, "loss": 0.0, "lr": 1.115716051692528e-08, "epoch": 19.618528610354222, "percentage": 98.09, "elapsed_time": "0:27:14", "remaining_time": "0:00:31", "throughput": 3610.49, "total_tokens": 5901040}
|
| 2890 |
+
{"current_steps": 14405, "total_steps": 14680, "loss": 0.0, "lr": 1.0763782285996282e-08, "epoch": 19.62534059945504, "percentage": 98.13, "elapsed_time": "0:27:14", "remaining_time": "0:00:31", "throughput": 3610.53, "total_tokens": 5903120}
|
| 2891 |
+
{"current_steps": 14410, "total_steps": 14680, "loss": 0.0, "lr": 1.037745645023458e-08, "epoch": 19.632152588555858, "percentage": 98.16, "elapsed_time": "0:27:15", "remaining_time": "0:00:30", "throughput": 3610.56, "total_tokens": 5905168}
|
| 2892 |
+
{"current_steps": 14415, "total_steps": 14680, "loss": 0.0, "lr": 9.998183555720575e-09, "epoch": 19.638964577656676, "percentage": 98.19, "elapsed_time": "0:27:16", "remaining_time": "0:00:30", "throughput": 3610.6, "total_tokens": 5907152}
|
| 2893 |
+
{"current_steps": 14420, "total_steps": 14680, "loss": 0.0, "lr": 9.625964138564315e-09, "epoch": 19.645776566757494, "percentage": 98.23, "elapsed_time": "0:27:16", "remaining_time": "0:00:29", "throughput": 3610.67, "total_tokens": 5909072}
|
| 2894 |
+
{"current_steps": 14425, "total_steps": 14680, "loss": 0.0, "lr": 9.260798724906595e-09, "epoch": 19.652588555858312, "percentage": 98.26, "elapsed_time": "0:27:17", "remaining_time": "0:00:28", "throughput": 3610.73, "total_tokens": 5911088}
|
| 2895 |
+
{"current_steps": 14430, "total_steps": 14680, "loss": 0.0, "lr": 8.902687830916746e-09, "epoch": 19.659400544959126, "percentage": 98.3, "elapsed_time": "0:27:17", "remaining_time": "0:00:28", "throughput": 3610.81, "total_tokens": 5913136}
|
| 2896 |
+
{"current_steps": 14435, "total_steps": 14680, "loss": 0.0, "lr": 8.551631962792072e-09, "epoch": 19.666212534059945, "percentage": 98.33, "elapsed_time": "0:27:18", "remaining_time": "0:00:27", "throughput": 3610.92, "total_tokens": 5915056}
|
| 2897 |
+
{"current_steps": 14440, "total_steps": 14680, "loss": 0.0, "lr": 8.20763161675786e-09, "epoch": 19.673024523160763, "percentage": 98.37, "elapsed_time": "0:27:18", "remaining_time": "0:00:27", "throughput": 3611.05, "total_tokens": 5917104}
|
| 2898 |
+
{"current_steps": 14445, "total_steps": 14680, "loss": 0.0, "lr": 7.870687279066258e-09, "epoch": 19.67983651226158, "percentage": 98.4, "elapsed_time": "0:27:19", "remaining_time": "0:00:26", "throughput": 3611.12, "total_tokens": 5918928}
|
| 2899 |
+
{"current_steps": 14450, "total_steps": 14680, "loss": 0.0, "lr": 7.540799425995726e-09, "epoch": 19.6866485013624, "percentage": 98.43, "elapsed_time": "0:27:19", "remaining_time": "0:00:26", "throughput": 3611.21, "total_tokens": 5920912}
|
| 2900 |
+
{"current_steps": 14455, "total_steps": 14680, "loss": 0.0, "lr": 7.217968523849928e-09, "epoch": 19.693460490463217, "percentage": 98.47, "elapsed_time": "0:27:20", "remaining_time": "0:00:25", "throughput": 3611.3, "total_tokens": 5922768}
|
| 2901 |
+
{"current_steps": 14460, "total_steps": 14680, "loss": 0.0, "lr": 6.90219502895717e-09, "epoch": 19.70027247956403, "percentage": 98.5, "elapsed_time": "0:27:20", "remaining_time": "0:00:24", "throughput": 3611.45, "total_tokens": 5924848}
|
| 2902 |
+
{"current_steps": 14465, "total_steps": 14680, "loss": 0.0, "lr": 6.593479387669854e-09, "epoch": 19.70708446866485, "percentage": 98.54, "elapsed_time": "0:27:21", "remaining_time": "0:00:24", "throughput": 3611.54, "total_tokens": 5926832}
|
| 2903 |
+
{"current_steps": 14470, "total_steps": 14680, "loss": 0.0, "lr": 6.29182203636558e-09, "epoch": 19.713896457765667, "percentage": 98.57, "elapsed_time": "0:27:21", "remaining_time": "0:00:23", "throughput": 3611.62, "total_tokens": 5928880}
|
| 2904 |
+
{"current_steps": 14475, "total_steps": 14680, "loss": 0.0, "lr": 5.997223401442154e-09, "epoch": 19.720708446866485, "percentage": 98.6, "elapsed_time": "0:27:22", "remaining_time": "0:00:23", "throughput": 3611.61, "total_tokens": 5930960}
|
| 2905 |
+
{"current_steps": 14480, "total_steps": 14680, "loss": 0.0, "lr": 5.7096838993225826e-09, "epoch": 19.727520435967303, "percentage": 98.64, "elapsed_time": "0:27:22", "remaining_time": "0:00:22", "throughput": 3611.64, "total_tokens": 5932944}
|
| 2906 |
+
{"current_steps": 14485, "total_steps": 14680, "loss": 0.0, "lr": 5.429203936449523e-09, "epoch": 19.73433242506812, "percentage": 98.67, "elapsed_time": "0:27:23", "remaining_time": "0:00:22", "throughput": 3611.72, "total_tokens": 5934992}
|
| 2907 |
+
{"current_steps": 14490, "total_steps": 14680, "loss": 0.0, "lr": 5.155783909288059e-09, "epoch": 19.741144414168936, "percentage": 98.71, "elapsed_time": "0:27:23", "remaining_time": "0:00:21", "throughput": 3611.79, "total_tokens": 5936912}
|
| 2908 |
+
{"current_steps": 14495, "total_steps": 14680, "loss": 0.0, "lr": 4.889424204322368e-09, "epoch": 19.747956403269754, "percentage": 98.74, "elapsed_time": "0:27:24", "remaining_time": "0:00:20", "throughput": 3611.81, "total_tokens": 5939056}
|
| 2909 |
+
{"current_steps": 14500, "total_steps": 14680, "loss": 0.0, "lr": 4.630125198059055e-09, "epoch": 19.754768392370572, "percentage": 98.77, "elapsed_time": "0:27:24", "remaining_time": "0:00:20", "throughput": 3611.9, "total_tokens": 5941040}
|
| 2910 |
+
{"current_steps": 14505, "total_steps": 14680, "loss": 0.0, "lr": 4.377887257022151e-09, "epoch": 19.76158038147139, "percentage": 98.81, "elapsed_time": "0:27:25", "remaining_time": "0:00:19", "throughput": 3611.96, "total_tokens": 5943152}
|
| 2911 |
+
{"current_steps": 14510, "total_steps": 14680, "loss": 0.0, "lr": 4.1327107377558965e-09, "epoch": 19.768392370572208, "percentage": 98.84, "elapsed_time": "0:27:25", "remaining_time": "0:00:19", "throughput": 3612.03, "total_tokens": 5945296}
|
| 2912 |
+
{"current_steps": 14515, "total_steps": 14680, "loss": 0.0, "lr": 3.894595986821959e-09, "epoch": 19.775204359673026, "percentage": 98.88, "elapsed_time": "0:27:26", "remaining_time": "0:00:18", "throughput": 3612.1, "total_tokens": 5947216}
|
| 2913 |
+
{"current_steps": 14520, "total_steps": 14680, "loss": 0.0, "lr": 3.6635433408022113e-09, "epoch": 19.78201634877384, "percentage": 98.91, "elapsed_time": "0:27:26", "remaining_time": "0:00:18", "throughput": 3612.2, "total_tokens": 5949200}
|
| 2914 |
+
{"current_steps": 14525, "total_steps": 14680, "loss": 0.0, "lr": 3.4395531262937377e-09, "epoch": 19.78882833787466, "percentage": 98.94, "elapsed_time": "0:27:27", "remaining_time": "0:00:17", "throughput": 3612.29, "total_tokens": 5951376}
|
| 2915 |
+
{"current_steps": 14530, "total_steps": 14680, "loss": 0.0, "lr": 3.2226256599110493e-09, "epoch": 19.795640326975477, "percentage": 98.98, "elapsed_time": "0:27:28", "remaining_time": "0:00:17", "throughput": 3612.34, "total_tokens": 5953488}
|
| 2916 |
+
{"current_steps": 14535, "total_steps": 14680, "loss": 0.0, "lr": 3.012761248287199e-09, "epoch": 19.802452316076295, "percentage": 99.01, "elapsed_time": "0:27:28", "remaining_time": "0:00:16", "throughput": 3612.45, "total_tokens": 5955600}
|
| 2917 |
+
{"current_steps": 14540, "total_steps": 14680, "loss": 0.0, "lr": 2.8099601880693384e-09, "epoch": 19.809264305177113, "percentage": 99.05, "elapsed_time": "0:27:29", "remaining_time": "0:00:15", "throughput": 3612.46, "total_tokens": 5957712}
|
| 2918 |
+
{"current_steps": 14545, "total_steps": 14680, "loss": 0.0, "lr": 2.6142227659214923e-09, "epoch": 19.81607629427793, "percentage": 99.08, "elapsed_time": "0:27:29", "remaining_time": "0:00:15", "throughput": 3612.51, "total_tokens": 5959824}
|
| 2919 |
+
{"current_steps": 14550, "total_steps": 14680, "loss": 0.0, "lr": 2.4255492585228967e-09, "epoch": 19.822888283378745, "percentage": 99.11, "elapsed_time": "0:27:30", "remaining_time": "0:00:14", "throughput": 3612.67, "total_tokens": 5961712}
|
| 2920 |
+
{"current_steps": 14555, "total_steps": 14680, "loss": 0.0, "lr": 2.2439399325668853e-09, "epoch": 19.829700272479563, "percentage": 99.15, "elapsed_time": "0:27:30", "remaining_time": "0:00:14", "throughput": 3612.83, "total_tokens": 5963632}
|
| 2921 |
+
{"current_steps": 14560, "total_steps": 14680, "loss": 0.0, "lr": 2.0693950447636667e-09, "epoch": 19.83651226158038, "percentage": 99.18, "elapsed_time": "0:27:31", "remaining_time": "0:00:13", "throughput": 3612.95, "total_tokens": 5965776}
|
| 2922 |
+
{"current_steps": 14565, "total_steps": 14680, "loss": 0.0, "lr": 1.9019148418353282e-09, "epoch": 19.8433242506812, "percentage": 99.22, "elapsed_time": "0:27:31", "remaining_time": "0:00:13", "throughput": 3613.04, "total_tokens": 5967856}
|
| 2923 |
+
{"current_steps": 14570, "total_steps": 14680, "loss": 0.0, "lr": 1.7414995605186114e-09, "epoch": 19.850136239782017, "percentage": 99.25, "elapsed_time": "0:27:32", "remaining_time": "0:00:12", "throughput": 3613.09, "total_tokens": 5969840}
|
| 2924 |
+
{"current_steps": 14575, "total_steps": 14680, "loss": 0.0, "lr": 1.5881494275649113e-09, "epoch": 19.856948228882835, "percentage": 99.28, "elapsed_time": "0:27:32", "remaining_time": "0:00:11", "throughput": 3613.2, "total_tokens": 5971952}
|
| 2925 |
+
{"current_steps": 14580, "total_steps": 14680, "loss": 0.0, "lr": 1.4418646597369467e-09, "epoch": 19.86376021798365, "percentage": 99.32, "elapsed_time": "0:27:33", "remaining_time": "0:00:11", "throughput": 3613.28, "total_tokens": 5973904}
|
| 2926 |
+
{"current_steps": 14585, "total_steps": 14680, "loss": 0.0, "lr": 1.3026454638126461e-09, "epoch": 19.870572207084468, "percentage": 99.35, "elapsed_time": "0:27:33", "remaining_time": "0:00:10", "throughput": 3613.36, "total_tokens": 5976080}
|
| 2927 |
+
{"current_steps": 14590, "total_steps": 14680, "loss": 0.0, "lr": 1.170492036580706e-09, "epoch": 19.877384196185286, "percentage": 99.39, "elapsed_time": "0:27:34", "remaining_time": "0:00:10", "throughput": 3613.47, "total_tokens": 5978096}
|
| 2928 |
+
{"current_steps": 14595, "total_steps": 14680, "loss": 0.0, "lr": 1.0454045648428112e-09, "epoch": 19.884196185286104, "percentage": 99.42, "elapsed_time": "0:27:34", "remaining_time": "0:00:09", "throughput": 3613.57, "total_tokens": 5980080}
|
| 2929 |
+
{"current_steps": 14600, "total_steps": 14680, "loss": 0.0, "lr": 9.27383225413081e-10, "epoch": 19.891008174386922, "percentage": 99.46, "elapsed_time": "0:27:35", "remaining_time": "0:00:09", "throughput": 3613.64, "total_tokens": 5982128}
|
| 2930 |
+
{"current_steps": 14605, "total_steps": 14680, "loss": 0.0, "lr": 8.164281851169576e-10, "epoch": 19.89782016348774, "percentage": 99.49, "elapsed_time": "0:27:35", "remaining_time": "0:00:08", "throughput": 3613.65, "total_tokens": 5984144}
|
| 2931 |
+
{"current_steps": 14610, "total_steps": 14680, "loss": 0.0, "lr": 7.125396007923169e-10, "epoch": 19.904632152588555, "percentage": 99.52, "elapsed_time": "0:27:36", "remaining_time": "0:00:07", "throughput": 3613.77, "total_tokens": 5986064}
|
| 2932 |
+
{"current_steps": 14615, "total_steps": 14680, "loss": 0.0, "lr": 6.157176192878034e-10, "epoch": 19.911444141689373, "percentage": 99.56, "elapsed_time": "0:27:36", "remaining_time": "0:00:07", "throughput": 3613.86, "total_tokens": 5988144}
|
| 2933 |
+
{"current_steps": 14620, "total_steps": 14680, "loss": 0.0, "lr": 5.259623774633849e-10, "epoch": 19.91825613079019, "percentage": 99.59, "elapsed_time": "0:27:37", "remaining_time": "0:00:06", "throughput": 3613.92, "total_tokens": 5990160}
|
| 2934 |
+
{"current_steps": 14625, "total_steps": 14680, "loss": 0.0, "lr": 4.4327400219035254e-10, "epoch": 19.92506811989101, "percentage": 99.63, "elapsed_time": "0:27:38", "remaining_time": "0:00:06", "throughput": 3614.02, "total_tokens": 5992272}
|
| 2935 |
+
{"current_steps": 14630, "total_steps": 14680, "loss": 0.0, "lr": 3.676526103502109e-10, "epoch": 19.931880108991827, "percentage": 99.66, "elapsed_time": "0:27:38", "remaining_time": "0:00:05", "throughput": 3614.09, "total_tokens": 5994192}
|
| 2936 |
+
{"current_steps": 14635, "total_steps": 14680, "loss": 0.0, "lr": 2.990983088352328e-10, "epoch": 19.938692098092645, "percentage": 99.69, "elapsed_time": "0:27:39", "remaining_time": "0:00:05", "throughput": 3614.1, "total_tokens": 5996208}
|
| 2937 |
+
{"current_steps": 14640, "total_steps": 14680, "loss": 0.0, "lr": 2.376111945484594e-10, "epoch": 19.94550408719346, "percentage": 99.73, "elapsed_time": "0:27:39", "remaining_time": "0:00:04", "throughput": 3614.17, "total_tokens": 5998256}
|
| 2938 |
+
{"current_steps": 14645, "total_steps": 14680, "loss": 0.0, "lr": 1.8319135440425517e-10, "epoch": 19.952316076294277, "percentage": 99.76, "elapsed_time": "0:27:40", "remaining_time": "0:00:03", "throughput": 3614.25, "total_tokens": 6000208}
|
| 2939 |
+
{"current_steps": 14650, "total_steps": 14680, "loss": 0.0, "lr": 1.3583886532497758e-10, "epoch": 19.959128065395095, "percentage": 99.8, "elapsed_time": "0:27:40", "remaining_time": "0:00:03", "throughput": 3614.31, "total_tokens": 6002480}
|
| 2940 |
+
{"current_steps": 14655, "total_steps": 14680, "loss": 0.0, "lr": 9.555379424486255e-11, "epoch": 19.965940054495913, "percentage": 99.83, "elapsed_time": "0:27:41", "remaining_time": "0:00:02", "throughput": 3614.35, "total_tokens": 6004560}
|
| 2941 |
+
{"current_steps": 14660, "total_steps": 14680, "loss": 0.0, "lr": 6.233619810835923e-11, "epoch": 19.97275204359673, "percentage": 99.86, "elapsed_time": "0:27:41", "remaining_time": "0:00:02", "throughput": 3614.4, "total_tokens": 6006672}
|
| 2942 |
+
{"current_steps": 14665, "total_steps": 14680, "loss": 0.0, "lr": 3.618612386846465e-11, "epoch": 19.979564032697546, "percentage": 99.9, "elapsed_time": "0:27:42", "remaining_time": "0:00:01", "throughput": 3614.47, "total_tokens": 6008592}
|
| 2943 |
+
{"current_steps": 14670, "total_steps": 14680, "loss": 0.0, "lr": 1.710360848894421e-11, "epoch": 19.986376021798364, "percentage": 99.93, "elapsed_time": "0:27:42", "remaining_time": "0:00:01", "throughput": 3614.51, "total_tokens": 6010672}
|
| 2944 |
+
{"current_steps": 14675, "total_steps": 14680, "loss": 0.0, "lr": 5.088678943776515e-12, "epoch": 19.993188010899182, "percentage": 99.97, "elapsed_time": "0:27:43", "remaining_time": "0:00:00", "throughput": 3614.57, "total_tokens": 6012688}
|
| 2945 |
+
{"current_steps": 14680, "total_steps": 14680, "loss": 0.0, "lr": 1.4135221604316685e-13, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:27:44", "remaining_time": "0:00:00", "throughput": 3614.44, "total_tokens": 6014512}
|
| 2946 |
+
{"current_steps": 14680, "total_steps": 14680, "eval_loss": 0.9237494468688965, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:27:52", "remaining_time": "0:00:00", "throughput": 3595.25, "total_tokens": 6014512}
|
| 2947 |
+
{"current_steps": 14680, "total_steps": 14680, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:27:56", "remaining_time": "0:00:00", "throughput": 3588.36, "total_tokens": 6014512}
|