ckpt probe_log.jsonl
Browse files- probe_log.jsonl +100 -0
probe_log.jsonl
CHANGED
|
@@ -3899,3 +3899,103 @@
|
|
| 3899 |
{"type": "train", "step": 3898, "loss": 1.30462, "gnorm": 0.2695, "lr": 5.075906515436321e-05, "tokens": 9904, "L": 837, "bl2": 11209104, "ckpt_on": false, "samples_seen": 62368, "step_ms": 2121.7, "ts": 1790085974.5, "ema_loss": 1.07109}
|
| 3900 |
{"type": "train", "step": 3899, "loss": 1.18425, "gnorm": 0.25, "lr": 5.074426265352636e-05, "tokens": 10477, "L": 745, "bl2": 8880400, "ckpt_on": false, "samples_seen": 62384, "step_ms": 2106.7, "ts": 1790085976.7, "ema_loss": 1.07335}
|
| 3901 |
{"type": "train", "step": 3900, "loss": 1.57635, "gnorm": 0.5039, "lr": 5.0729605669802765e-05, "tokens": 13669, "L": 1028, "bl2": 16908544, "ckpt_on": false, "samples_seen": 62400, "step_ms": 2340.0, "ts": 1790085990.7, "mem_alloc_gb": 3.71, "mem_reserved_gb": 93.48, "ema_loss": 1.08341}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3899 |
{"type": "train", "step": 3898, "loss": 1.30462, "gnorm": 0.2695, "lr": 5.075906515436321e-05, "tokens": 9904, "L": 837, "bl2": 11209104, "ckpt_on": false, "samples_seen": 62368, "step_ms": 2121.7, "ts": 1790085974.5, "ema_loss": 1.07109}
|
| 3900 |
{"type": "train", "step": 3899, "loss": 1.18425, "gnorm": 0.25, "lr": 5.074426265352636e-05, "tokens": 10477, "L": 745, "bl2": 8880400, "ckpt_on": false, "samples_seen": 62384, "step_ms": 2106.7, "ts": 1790085976.7, "ema_loss": 1.07335}
|
| 3901 |
{"type": "train", "step": 3900, "loss": 1.57635, "gnorm": 0.5039, "lr": 5.0729605669802765e-05, "tokens": 13669, "L": 1028, "bl2": 16908544, "ckpt_on": false, "samples_seen": 62400, "step_ms": 2340.0, "ts": 1790085990.7, "mem_alloc_gb": 3.71, "mem_reserved_gb": 93.48, "ema_loss": 1.08341}
|
| 3902 |
+
{"type": "train", "step": 3901, "loss": 1.50726, "gnorm": 0.5352, "lr": 5.0715094212703175e-05, "tokens": 13480, "L": 1030, "bl2": 16974400, "ckpt_on": false, "samples_seen": 62416, "step_ms": 2833.8, "ts": 1790086010.9, "ema_loss": 1.09189}
|
| 3903 |
+
{"type": "train", "step": 3902, "loss": 2.29598, "gnorm": 0.8906, "lr": 5.070072829164393e-05, "tokens": 12964, "L": 1037, "bl2": 17205904, "ckpt_on": false, "samples_seen": 62432, "step_ms": 2299.3, "ts": 1790086013.3, "ema_loss": 1.11597}
|
| 3904 |
+
{"type": "train", "step": 3903, "loss": 1.30275, "gnorm": 0.3828, "lr": 5.06865079159469e-05, "tokens": 13919, "L": 1035, "bl2": 17139600, "ckpt_on": false, "samples_seen": 62448, "step_ms": 2424.5, "ts": 1790086017.1, "ema_loss": 1.11971}
|
| 3905 |
+
{"type": "train", "step": 3904, "loss": 1.51226, "gnorm": 0.5234, "lr": 5.067243309483958e-05, "tokens": 14342, "L": 1008, "bl2": 16257024, "ckpt_on": false, "samples_seen": 62464, "step_ms": 2150.7, "ts": 1790086026.7, "ema_loss": 1.12756}
|
| 3906 |
+
{"type": "train", "step": 3905, "loss": 1.43846, "gnorm": 0.498, "lr": 5.06585038374549e-05, "tokens": 13871, "L": 1026, "bl2": 16842816, "ckpt_on": false, "samples_seen": 62480, "step_ms": 2276.8999999999996, "ts": 1790086029.1, "ema_loss": 1.13378}
|
| 3907 |
+
{"type": "train", "step": 3906, "loss": 1.24955, "gnorm": 0.4902, "lr": 5.064472015283145e-05, "tokens": 12618, "L": 1032, "bl2": 17040384, "ckpt_on": false, "samples_seen": 62496, "step_ms": 2294.5, "ts": 1790086039.6, "ema_loss": 1.13609}
|
| 3908 |
+
{"type": "train", "step": 3907, "loss": 1.60828, "gnorm": 0.4258, "lr": 5.0631082049913335e-05, "tokens": 13313, "L": 1062, "bl2": 18045504, "ckpt_on": false, "samples_seen": 62512, "step_ms": 2451.3, "ts": 1790086043.3, "ema_loss": 1.14554}
|
| 3909 |
+
{"type": "train", "step": 3908, "loss": 1.19841, "gnorm": 0.3652, "lr": 5.06175895375501e-05, "tokens": 14028, "L": 998, "bl2": 15936064, "ckpt_on": false, "samples_seen": 62528, "step_ms": 2220.3999999999996, "ts": 1790086045.7, "ema_loss": 1.14659}
|
| 3910 |
+
{"type": "train", "step": 3909, "loss": 1.28421, "gnorm": 0.4805, "lr": 5.0604242624496935e-05, "tokens": 12992, "L": 1033, "bl2": 17073424, "ckpt_on": false, "samples_seen": 62544, "step_ms": 2289.4, "ts": 1790086055.4, "ema_loss": 1.14935}
|
| 3911 |
+
{"type": "train", "step": 3910, "loss": 1.16869, "gnorm": 0.4199, "lr": 5.059104131941452e-05, "tokens": 13822, "L": 1020, "bl2": 16646400, "ckpt_on": false, "samples_seen": 62560, "step_ms": 2164.5, "ts": 1790086065.9, "ema_loss": 1.14973}
|
| 3912 |
+
{"type": "train", "step": 3911, "loss": 1.73296, "gnorm": 0.4004, "lr": 5.057798563086898e-05, "tokens": 13401, "L": 992, "bl2": 15745024, "ckpt_on": false, "samples_seen": 62576, "step_ms": 2128.5, "ts": 1790086068.3, "ema_loss": 1.1614}
|
| 3913 |
+
{"type": "train", "step": 3912, "loss": 1.47763, "gnorm": 0.3906, "lr": 5.056507556733207e-05, "tokens": 14185, "L": 1033, "bl2": 17073424, "ckpt_on": false, "samples_seen": 62592, "step_ms": 2306.9, "ts": 1790086072.3, "ema_loss": 1.16772}
|
| 3914 |
+
{"type": "train", "step": 3913, "loss": 1.21182, "gnorm": 0.4082, "lr": 5.0552311137180995e-05, "tokens": 13928, "L": 1041, "bl2": 17338896, "ckpt_on": false, "samples_seen": 62608, "step_ms": 2315.3, "ts": 1790086074.7, "ema_loss": 1.1686}
|
| 3915 |
+
{"type": "train", "step": 3914, "loss": 1.20343, "gnorm": 0.3477, "lr": 5.053969234869841e-05, "tokens": 13799, "L": 1048, "bl2": 17572864, "ckpt_on": false, "samples_seen": 62624, "step_ms": 2791.1, "ts": 1790086092.6, "ema_loss": 1.1693}
|
| 3916 |
+
{"type": "train", "step": 3915, "loss": 0.80854, "gnorm": 0.1914, "lr": 5.052721921007253e-05, "tokens": 9276, "L": 798, "bl2": 10188864, "ckpt_on": false, "samples_seen": 62640, "step_ms": 1940.7, "ts": 1790086094.6, "ema_loss": 1.16209}
|
| 3917 |
+
{"type": "train", "step": 3916, "loss": 0.99131, "gnorm": 0.2158, "lr": 5.051489172939702e-05, "tokens": 10456, "L": 801, "bl2": 10265616, "ckpt_on": false, "samples_seen": 62656, "step_ms": 2359.1000000000004, "ts": 1790086097.1, "ema_loss": 1.15867}
|
| 3918 |
+
{"type": "train", "step": 3917, "loss": 1.03485, "gnorm": 0.2412, "lr": 5.0502709914671094e-05, "tokens": 9593, "L": 787, "bl2": 9909904, "ckpt_on": false, "samples_seen": 62672, "step_ms": 2238.8, "ts": 1790086099.9, "ema_loss": 1.15619}
|
| 3919 |
+
{"type": "train", "step": 3918, "loss": 0.97585, "gnorm": 0.1934, "lr": 5.0490673773799374e-05, "tokens": 9592, "L": 809, "bl2": 10471696, "ckpt_on": false, "samples_seen": 62688, "step_ms": 1748.5, "ts": 1790086101.7, "ema_loss": 1.15259}
|
| 3920 |
+
{"type": "train", "step": 3919, "loss": 0.94484, "gnorm": 0.2051, "lr": 5.047878331459195e-05, "tokens": 10274, "L": 833, "bl2": 11102224, "ckpt_on": false, "samples_seen": 62704, "step_ms": 2343.6, "ts": 1790086109.3, "ema_loss": 1.14843}
|
| 3921 |
+
{"type": "train", "step": 3920, "loss": 1.02443, "gnorm": 0.2275, "lr": 5.046703854476447e-05, "tokens": 10089, "L": 801, "bl2": 10265616, "ckpt_on": false, "samples_seen": 62720, "step_ms": 1820.4, "ts": 1790086111.2, "mem_alloc_gb": 3.71, "mem_reserved_gb": 71.52, "ema_loss": 1.14595}
|
| 3922 |
+
{"type": "train", "step": 3921, "loss": 0.91284, "gnorm": 0.3652, "lr": 5.045543947193795e-05, "tokens": 10221, "L": 818, "bl2": 10705984, "ckpt_on": false, "samples_seen": 62736, "step_ms": 1668.0, "ts": 1790086113.0, "ema_loss": 1.14129}
|
| 3923 |
+
{"type": "train", "step": 3922, "loss": 0.94298, "gnorm": 0.3164, "lr": 5.04439861036389e-05, "tokens": 9814, "L": 762, "bl2": 9290304, "ckpt_on": false, "samples_seen": 62752, "step_ms": 2089.3, "ts": 1790086120.4, "ema_loss": 1.13732}
|
| 3924 |
+
{"type": "train", "step": 3923, "loss": 0.94287, "gnorm": 0.2109, "lr": 5.0432678447299304e-05, "tokens": 10832, "L": 799, "bl2": 10214416, "ckpt_on": false, "samples_seen": 62768, "step_ms": 2269.1, "ts": 1790086122.7, "ema_loss": 1.13343}
|
| 3925 |
+
{"type": "train", "step": 3924, "loss": 0.92767, "gnorm": 0.1924, "lr": 5.042151651025658e-05, "tokens": 9757, "L": 765, "bl2": 9363600, "ckpt_on": false, "samples_seen": 62784, "step_ms": 1817.4, "ts": 1790086124.6, "ema_loss": 1.12932}
|
| 3926 |
+
{"type": "train", "step": 3925, "loss": 1.04506, "gnorm": 0.2363, "lr": 5.041050029975357e-05, "tokens": 8898, "L": 796, "bl2": 10137856, "ckpt_on": false, "samples_seen": 62800, "step_ms": 2467.5, "ts": 1790086127.7, "ema_loss": 1.12763}
|
| 3927 |
+
{"type": "train", "step": 3926, "loss": 0.98136, "gnorm": 0.1426, "lr": 5.03996298229386e-05, "tokens": 10509, "L": 810, "bl2": 10497600, "ckpt_on": false, "samples_seen": 62816, "step_ms": 2196.3, "ts": 1790086130.0, "ema_loss": 1.12471}
|
| 3928 |
+
{"type": "train", "step": 3927, "loss": 1.06156, "gnorm": 0.209, "lr": 5.038890508686535e-05, "tokens": 10215, "L": 824, "bl2": 10863616, "ckpt_on": false, "samples_seen": 62832, "step_ms": 2506.2, "ts": 1790086133.2, "ema_loss": 1.12345}
|
| 3929 |
+
{"type": "train", "step": 3928, "loss": 0.98608, "gnorm": 0.2871, "lr": 5.037832609849304e-05, "tokens": 9417, "L": 838, "bl2": 11235904, "ckpt_on": false, "samples_seen": 62848, "step_ms": 2848.3, "ts": 1790086136.1, "ema_loss": 1.1207}
|
| 3930 |
+
{"type": "train", "step": 3929, "loss": 1.05244, "gnorm": 0.208, "lr": 5.0367892864686273e-05, "tokens": 11051, "L": 836, "bl2": 11182336, "ckpt_on": false, "samples_seen": 62864, "step_ms": 2231.4, "ts": 1790086139.0, "ema_loss": 1.11933}
|
| 3931 |
+
{"type": "train", "step": 3930, "loss": 1.01887, "gnorm": 0.1738, "lr": 5.0357605392215e-05, "tokens": 9630, "L": 814, "bl2": 10601536, "ckpt_on": false, "samples_seen": 62880, "step_ms": 2435.8, "ts": 1790086141.5, "ema_loss": 1.11732}
|
| 3932 |
+
{"type": "train", "step": 3931, "loss": 0.90539, "gnorm": 0.25, "lr": 5.034746368775467e-05, "tokens": 10428, "L": 759, "bl2": 9217296, "ckpt_on": false, "samples_seen": 62896, "step_ms": 2298.0, "ts": 1790086145.0, "ema_loss": 1.11308}
|
| 3933 |
+
{"type": "train", "step": 3932, "loss": 1.01138, "gnorm": 0.2637, "lr": 5.033746775788616e-05, "tokens": 10899, "L": 832, "bl2": 11075584, "ckpt_on": false, "samples_seen": 62912, "step_ms": 1717.0, "ts": 1790086147.4, "ema_loss": 1.11105}
|
| 3934 |
+
{"type": "train", "step": 3933, "loss": 0.95219, "gnorm": 0.2461, "lr": 5.032761760909569e-05, "tokens": 10140, "L": 850, "bl2": 11560000, "ckpt_on": false, "samples_seen": 62928, "step_ms": 2819.6, "ts": 1790086150.3, "ema_loss": 1.10787}
|
| 3935 |
+
{"type": "train", "step": 3934, "loss": 0.90646, "gnorm": 0.2773, "lr": 5.031791324777491e-05, "tokens": 8706, "L": 794, "bl2": 10086976, "ckpt_on": false, "samples_seen": 62944, "step_ms": 2705.5, "ts": 1790086153.7, "ema_loss": 1.10385}
|
| 3936 |
+
{"type": "train", "step": 3935, "loss": 1.09518, "gnorm": 0.7461, "lr": 5.0308354680220896e-05, "tokens": 8820, "L": 760, "bl2": 9241600, "ckpt_on": false, "samples_seen": 62960, "step_ms": 1887.4, "ts": 1790086155.6, "ema_loss": 1.10367}
|
| 3937 |
+
{"type": "train", "step": 3936, "loss": 1.06153, "gnorm": 0.2637, "lr": 5.029894191263607e-05, "tokens": 10620, "L": 798, "bl2": 10188864, "ckpt_on": false, "samples_seen": 62976, "step_ms": 2551.2, "ts": 1790086159.6, "ema_loss": 1.10283}
|
| 3938 |
+
{"type": "train", "step": 3937, "loss": 0.81385, "gnorm": 0.334, "lr": 5.0289674951128305e-05, "tokens": 9465, "L": 827, "bl2": 10942864, "ckpt_on": false, "samples_seen": 62992, "step_ms": 2826.2, "ts": 1790086163.1, "ema_loss": 1.09705}
|
| 3939 |
+
{"type": "train", "step": 3938, "loss": 1.201, "gnorm": 0.1914, "lr": 5.028055380171083e-05, "tokens": 8946, "L": 765, "bl2": 9363600, "ckpt_on": false, "samples_seen": 63008, "step_ms": 2157.6, "ts": 1790086165.3, "ema_loss": 1.09913}
|
| 3940 |
+
{"type": "train", "step": 3939, "loss": 1.1361, "gnorm": 0.2988, "lr": 5.027157847030221e-05, "tokens": 9698, "L": 829, "bl2": 10995856, "ckpt_on": false, "samples_seen": 63024, "step_ms": 1735.0, "ts": 1790086173.3, "ema_loss": 1.09987}
|
| 3941 |
+
{"type": "train", "step": 3940, "loss": 1.06343, "gnorm": 0.5195, "lr": 5.026274896272651e-05, "tokens": 10582, "L": 807, "bl2": 10419984, "ckpt_on": false, "samples_seen": 63040, "step_ms": 1652.1, "ts": 1790086175.0, "mem_alloc_gb": 3.71, "mem_reserved_gb": 93.43, "ema_loss": 1.09914}
|
| 3942 |
+
{"type": "train", "step": 3941, "loss": 1.07614, "gnorm": 0.4668, "lr": 5.0254065284713084e-05, "tokens": 9272, "L": 853, "bl2": 11641744, "ckpt_on": false, "samples_seen": 63056, "step_ms": 1781.0, "ts": 1790086176.9, "ema_loss": 1.09868}
|
| 3943 |
+
{"type": "train", "step": 3942, "loss": 1.04578, "gnorm": 0.1826, "lr": 5.024552744189664e-05, "tokens": 9699, "L": 680, "bl2": 7398400, "ckpt_on": false, "samples_seen": 63072, "step_ms": 1740.7, "ts": 1790086185.5, "ema_loss": 1.09762}
|
| 3944 |
+
{"type": "train", "step": 3943, "loss": 1.01267, "gnorm": 0.3164, "lr": 5.023713543981732e-05, "tokens": 9403, "L": 811, "bl2": 10523536, "ckpt_on": false, "samples_seen": 63088, "step_ms": 1794.7, "ts": 1790086187.4, "ema_loss": 1.09592}
|
| 3945 |
+
{"type": "train", "step": 3944, "loss": 1.15427, "gnorm": 0.2002, "lr": 5.0228889283920605e-05, "tokens": 10056, "L": 773, "bl2": 9560464, "ckpt_on": false, "samples_seen": 63104, "step_ms": 2150.7, "ts": 1790086190.1, "ema_loss": 1.09709}
|
| 3946 |
+
{"type": "train", "step": 3945, "loss": 0.98623, "gnorm": 0.2617, "lr": 5.0220788979557336e-05, "tokens": 10586, "L": 832, "bl2": 11075584, "ckpt_on": false, "samples_seen": 63120, "step_ms": 1820.2, "ts": 1790086192.0, "ema_loss": 1.09487}
|
| 3947 |
+
{"type": "train", "step": 3946, "loss": 1.23555, "gnorm": 0.2578, "lr": 5.0212834531983685e-05, "tokens": 9146, "L": 726, "bl2": 8433216, "ckpt_on": false, "samples_seen": 63136, "step_ms": 1936.4, "ts": 1790086194.1, "ema_loss": 1.09769}
|
| 3948 |
+
{"type": "train", "step": 3947, "loss": 1.01676, "gnorm": 0.2275, "lr": 5.0205025946361234e-05, "tokens": 8825, "L": 786, "bl2": 9884736, "ckpt_on": false, "samples_seen": 63152, "step_ms": 2061.3, "ts": 1790086196.8, "ema_loss": 1.09607}
|
| 3949 |
+
{"type": "train", "step": 3948, "loss": 1.00834, "gnorm": 0.1797, "lr": 5.019736322775687e-05, "tokens": 10418, "L": 791, "bl2": 10010896, "ckpt_on": false, "samples_seen": 63168, "step_ms": 2310.2, "ts": 1790086207.4, "ema_loss": 1.09431}
|
| 3950 |
+
{"type": "train", "step": 3949, "loss": 1.11269, "gnorm": 0.2734, "lr": 5.018984638114289e-05, "tokens": 9202, "L": 827, "bl2": 10942864, "ckpt_on": false, "samples_seen": 63184, "step_ms": 2018.4, "ts": 1790086209.5, "ema_loss": 1.09468}
|
| 3951 |
+
{"type": "train", "step": 3950, "loss": 0.8816, "gnorm": 0.1641, "lr": 5.018247541139684e-05, "tokens": 10455, "L": 826, "bl2": 10916416, "ckpt_on": false, "samples_seen": 63200, "step_ms": 2386.8, "ts": 1790086212.0, "ema_loss": 1.09042}
|
| 3952 |
+
{"type": "train", "step": 3951, "loss": 0.9973, "gnorm": 0.2363, "lr": 5.017525032330169e-05, "tokens": 10054, "L": 780, "bl2": 9734400, "ckpt_on": false, "samples_seen": 63216, "step_ms": 2234.1, "ts": 1790086214.8, "ema_loss": 1.08856}
|
| 3953 |
+
{"type": "train", "step": 3952, "loss": 0.97467, "gnorm": 0.3613, "lr": 5.016817112154572e-05, "tokens": 10100, "L": 804, "bl2": 10342656, "ckpt_on": false, "samples_seen": 63232, "step_ms": 1787.5, "ts": 1790086216.8, "ema_loss": 1.08628}
|
| 3954 |
+
{"type": "train", "step": 3953, "loss": 1.18672, "gnorm": 0.2539, "lr": 5.016123781072255e-05, "tokens": 9387, "L": 741, "bl2": 8785296, "ckpt_on": false, "samples_seen": 63248, "step_ms": 2000.6, "ts": 1790086219.4, "ema_loss": 1.08829}
|
| 3955 |
+
{"type": "train", "step": 3954, "loss": 1.18838, "gnorm": 0.2207, "lr": 5.015445039533112e-05, "tokens": 10101, "L": 818, "bl2": 10705984, "ckpt_on": false, "samples_seen": 63264, "step_ms": 1839.7, "ts": 1790086221.4, "ema_loss": 1.09029}
|
| 3956 |
+
{"type": "train", "step": 3955, "loss": 0.98523, "gnorm": 0.248, "lr": 5.014780887977573e-05, "tokens": 10050, "L": 747, "bl2": 8928144, "ckpt_on": false, "samples_seen": 63280, "step_ms": 1973.1, "ts": 1790086223.4, "ema_loss": 1.08819}
|
| 3957 |
+
{"type": "train", "step": 3956, "loss": 1.00619, "gnorm": 0.4336, "lr": 5.0141313268365946e-05, "tokens": 9526, "L": 818, "bl2": 10705984, "ckpt_on": false, "samples_seen": 63296, "step_ms": 1813.5, "ts": 1790086225.9, "ema_loss": 1.08655}
|
| 3958 |
+
{"type": "train", "step": 3957, "loss": 1.01996, "gnorm": 0.3145, "lr": 5.013496356531674e-05, "tokens": 9958, "L": 807, "bl2": 10419984, "ckpt_on": false, "samples_seen": 63312, "step_ms": 2473.2, "ts": 1790086228.5, "ema_loss": 1.08522}
|
| 3959 |
+
{"type": "train", "step": 3958, "loss": 1.02288, "gnorm": 0.2207, "lr": 5.0128759774748356e-05, "tokens": 10252, "L": 804, "bl2": 10342656, "ckpt_on": false, "samples_seen": 63328, "step_ms": 2043.8, "ts": 1790086236.7, "ema_loss": 1.08397}
|
| 3960 |
+
{"type": "train", "step": 3959, "loss": 0.98149, "gnorm": 0.3066, "lr": 5.012270190068635e-05, "tokens": 9386, "L": 822, "bl2": 10810944, "ckpt_on": false, "samples_seen": 63344, "step_ms": 2381.0, "ts": 1790086239.2, "ema_loss": 1.08192}
|
| 3961 |
+
{"type": "train", "step": 3960, "loss": 1.08065, "gnorm": 0.2021, "lr": 5.0116789947061654e-05, "tokens": 9749, "L": 780, "bl2": 9734400, "ckpt_on": false, "samples_seen": 63360, "step_ms": 2207.3, "ts": 1790086247.4, "mem_alloc_gb": 3.71, "mem_reserved_gb": 86.28, "ema_loss": 1.08189}
|
| 3962 |
+
{"type": "train", "step": 3961, "loss": 1.23369, "gnorm": 0.2109, "lr": 5.011102391771039e-05, "tokens": 10198, "L": 793, "bl2": 10061584, "ckpt_on": false, "samples_seen": 63376, "step_ms": 1664.9, "ts": 1790086249.2, "ema_loss": 1.08493}
|
| 3963 |
+
{"type": "train", "step": 3962, "loss": 1.14498, "gnorm": 0.2314, "lr": 5.0105403816374154e-05, "tokens": 10150, "L": 795, "bl2": 10112400, "ckpt_on": false, "samples_seen": 63392, "step_ms": 1650.3000000000002, "ts": 1790086250.9, "ema_loss": 1.08613}
|
| 3964 |
+
{"type": "train", "step": 3963, "loss": 1.25354, "gnorm": 0.2812, "lr": 5.009992964669975e-05, "tokens": 10230, "L": 782, "bl2": 9784384, "ckpt_on": false, "samples_seen": 63408, "step_ms": 2202.8, "ts": 1790086253.7, "ema_loss": 1.08948}
|
| 3965 |
+
{"type": "train", "step": 3964, "loss": 0.91087, "gnorm": 0.1924, "lr": 5.0094601412239256e-05, "tokens": 9678, "L": 779, "bl2": 9709456, "ckpt_on": false, "samples_seen": 63424, "step_ms": 2016.3, "ts": 1790086255.8, "ema_loss": 1.08591}
|
| 3966 |
+
{"type": "train", "step": 3965, "loss": 0.96863, "gnorm": 0.3848, "lr": 5.008941911645016e-05, "tokens": 10679, "L": 841, "bl2": 11316496, "ckpt_on": false, "samples_seen": 63440, "step_ms": 2403.5, "ts": 1790086261.8, "ema_loss": 1.08356}
|
| 3967 |
+
{"type": "train", "step": 3966, "loss": 1.10474, "gnorm": 0.2852, "lr": 5.008438276269519e-05, "tokens": 9942, "L": 774, "bl2": 9585216, "ckpt_on": false, "samples_seen": 63456, "step_ms": 1998.5, "ts": 1790086269.8, "ema_loss": 1.08399}
|
| 3968 |
+
{"type": "train", "step": 3967, "loss": 1.18354, "gnorm": 0.2236, "lr": 5.007949235424235e-05, "tokens": 10330, "L": 748, "bl2": 8952064, "ckpt_on": false, "samples_seen": 63472, "step_ms": 2133.3, "ts": 1790086272.0, "ema_loss": 1.08598}
|
| 3969 |
+
{"type": "train", "step": 3968, "loss": 1.02366, "gnorm": 0.2393, "lr": 5.007474789426501e-05, "tokens": 9504, "L": 770, "bl2": 9486400, "ckpt_on": false, "samples_seen": 63488, "step_ms": 2193.5, "ts": 1790086275.2, "ema_loss": 1.08473}
|
| 3970 |
+
{"type": "train", "step": 3969, "loss": 0.94188, "gnorm": 0.3809, "lr": 5.0070149385841784e-05, "tokens": 10757, "L": 804, "bl2": 10342656, "ckpt_on": false, "samples_seen": 63504, "step_ms": 2508.3, "ts": 1790086277.8, "ema_loss": 1.08187}
|
| 3971 |
+
{"type": "train", "step": 3970, "loss": 1.26713, "gnorm": 0.2266, "lr": 5.0065696831956594e-05, "tokens": 10180, "L": 809, "bl2": 10471696, "ckpt_on": false, "samples_seen": 63520, "step_ms": 2113.1000000000004, "ts": 1790086280.0, "ema_loss": 1.08558}
|
| 3972 |
+
{"type": "train", "step": 3971, "loss": 0.97674, "gnorm": 0.2471, "lr": 5.006139023549865e-05, "tokens": 9754, "L": 764, "bl2": 9339136, "ckpt_on": false, "samples_seen": 63536, "step_ms": 2177.3, "ts": 1790086282.9, "ema_loss": 1.0834}
|
| 3973 |
+
{"type": "train", "step": 3972, "loss": 1.29552, "gnorm": 0.3535, "lr": 5.005722959926245e-05, "tokens": 10630, "L": 785, "bl2": 9859600, "ckpt_on": false, "samples_seen": 63552, "step_ms": 2304.4, "ts": 1790086285.3, "ema_loss": 1.08764}
|
| 3974 |
+
{"type": "train", "step": 3973, "loss": 1.03487, "gnorm": 0.1768, "lr": 5.005321492594779e-05, "tokens": 10599, "L": 791, "bl2": 10010896, "ckpt_on": false, "samples_seen": 63568, "step_ms": 2374.7, "ts": 1790086292.3, "ema_loss": 1.08659}
|
| 3975 |
+
{"type": "train", "step": 3974, "loss": 1.06457, "gnorm": 0.3867, "lr": 5.004934621815976e-05, "tokens": 10087, "L": 847, "bl2": 11478544, "ckpt_on": false, "samples_seen": 63584, "step_ms": 2643.3999999999996, "ts": 1790086295.0, "ema_loss": 1.08615}
|
| 3976 |
+
{"type": "train", "step": 3975, "loss": 1.05213, "gnorm": 0.2656, "lr": 5.0045623478408725e-05, "tokens": 10480, "L": 787, "bl2": 9909904, "ckpt_on": false, "samples_seen": 63600, "step_ms": 2432.6, "ts": 1790086297.5, "ema_loss": 1.08547}
|
| 3977 |
+
{"type": "train", "step": 3976, "loss": 1.03213, "gnorm": 0.418, "lr": 5.004204670911031e-05, "tokens": 9948, "L": 786, "bl2": 9884736, "ckpt_on": false, "samples_seen": 63616, "step_ms": 2201.9, "ts": 1790086306.5, "ema_loss": 1.0844}
|
| 3978 |
+
{"type": "train", "step": 3977, "loss": 0.99998, "gnorm": 0.2295, "lr": 5.0038615912585464e-05, "tokens": 9367, "L": 713, "bl2": 8133904, "ckpt_on": false, "samples_seen": 63632, "step_ms": 1787.6, "ts": 1790086308.4, "ema_loss": 1.08271}
|
| 3979 |
+
{"type": "train", "step": 3978, "loss": 1.09588, "gnorm": 0.3691, "lr": 5.0035331091060375e-05, "tokens": 10418, "L": 825, "bl2": 10890000, "ckpt_on": false, "samples_seen": 63648, "step_ms": 1870.9, "ts": 1790086310.9, "ema_loss": 1.08298}
|
| 3980 |
+
{"type": "train", "step": 3979, "loss": 1.16271, "gnorm": 0.3457, "lr": 5.003219224666653e-05, "tokens": 10131, "L": 807, "bl2": 10419984, "ckpt_on": false, "samples_seen": 63664, "step_ms": 2572.3, "ts": 1790086313.5, "ema_loss": 1.08457}
|
| 3981 |
+
{"type": "train", "step": 3980, "loss": 1.12458, "gnorm": 0.2344, "lr": 5.0029199381440704e-05, "tokens": 9522, "L": 797, "bl2": 10163344, "ckpt_on": false, "samples_seen": 63680, "step_ms": 2664.3999999999996, "ts": 1790086316.3, "mem_alloc_gb": 3.71, "mem_reserved_gb": 44.39, "ema_loss": 1.08537}
|
| 3982 |
+
{"type": "train", "step": 3981, "loss": 0.97083, "gnorm": 0.2285, "lr": 5.00263524973249e-05, "tokens": 11165, "L": 820, "bl2": 10758400, "ckpt_on": false, "samples_seen": 63696, "step_ms": 2118.0, "ts": 1790086319.1, "ema_loss": 1.08308}
|
| 3983 |
+
{"type": "train", "step": 3982, "loss": 1.00179, "gnorm": 0.2695, "lr": 5.002365159616648e-05, "tokens": 9586, "L": 746, "bl2": 8904256, "ckpt_on": false, "samples_seen": 63712, "step_ms": 2201.2, "ts": 1790086321.4, "ema_loss": 1.08145}
|
| 3984 |
+
{"type": "train", "step": 3983, "loss": 1.05172, "gnorm": 0.2754, "lr": 5.002109667971802e-05, "tokens": 9303, "L": 795, "bl2": 10112400, "ckpt_on": false, "samples_seen": 63728, "step_ms": 2483.0, "ts": 1790086328.2, "ema_loss": 1.08086}
|
| 3985 |
+
{"type": "train", "step": 3984, "loss": 1.01682, "gnorm": 0.252, "lr": 5.001868774963734e-05, "tokens": 9737, "L": 874, "bl2": 12222016, "ckpt_on": false, "samples_seen": 63744, "step_ms": 2114.6, "ts": 1790086330.4, "ema_loss": 1.07958}
|
| 3986 |
+
{"type": "train", "step": 3985, "loss": 1.14844, "gnorm": 0.1787, "lr": 5.00164248074876e-05, "tokens": 10112, "L": 786, "bl2": 9884736, "ckpt_on": false, "samples_seen": 63760, "step_ms": 2147.2, "ts": 1790086337.9, "ema_loss": 1.08096}
|
| 3987 |
+
{"type": "train", "step": 3986, "loss": 1.16397, "gnorm": 0.2188, "lr": 5.00143078547372e-05, "tokens": 10100, "L": 782, "bl2": 9784384, "ckpt_on": false, "samples_seen": 63776, "step_ms": 2075.6, "ts": 1790086340.0, "ema_loss": 1.08262}
|
| 3988 |
+
{"type": "train", "step": 3987, "loss": 1.25704, "gnorm": 0.2139, "lr": 5.001233689275978e-05, "tokens": 10216, "L": 761, "bl2": 9265936, "ckpt_on": false, "samples_seen": 63792, "step_ms": 1899.3, "ts": 1790086342.0, "ema_loss": 1.0861}
|
| 3989 |
+
{"type": "train", "step": 3988, "loss": 1.0066, "gnorm": 0.291, "lr": 5.001051192283429e-05, "tokens": 9885, "L": 770, "bl2": 9486400, "ckpt_on": false, "samples_seen": 63808, "step_ms": 2094.1, "ts": 1790086344.8, "ema_loss": 1.08451}
|
| 3990 |
+
{"type": "train", "step": 3989, "loss": 1.01821, "gnorm": 0.2676, "lr": 5.0008832946144966e-05, "tokens": 11021, "L": 782, "bl2": 9784384, "ckpt_on": false, "samples_seen": 63824, "step_ms": 2037.4, "ts": 1790086346.9, "ema_loss": 1.08319}
|
| 3991 |
+
{"type": "train", "step": 3990, "loss": 1.00159, "gnorm": 0.2617, "lr": 5.0007299963781215e-05, "tokens": 10848, "L": 834, "bl2": 11128896, "ckpt_on": false, "samples_seen": 63840, "step_ms": 1785.3, "ts": 1790086353.7, "ema_loss": 1.08156}
|
| 3992 |
+
{"type": "train", "step": 3991, "loss": 1.02743, "gnorm": 0.2041, "lr": 5.000591297673782e-05, "tokens": 9202, "L": 753, "bl2": 9072144, "ckpt_on": false, "samples_seen": 63856, "step_ms": 2006.7, "ts": 1790086355.9, "ema_loss": 1.08047}
|
| 3993 |
+
{"type": "train", "step": 3992, "loss": 0.98413, "gnorm": 0.2227, "lr": 5.000467198591479e-05, "tokens": 10381, "L": 837, "bl2": 11209104, "ckpt_on": false, "samples_seen": 63872, "step_ms": 1856.8, "ts": 1790086357.8, "ema_loss": 1.07855}
|
| 3994 |
+
{"type": "train", "step": 3993, "loss": 1.00116, "gnorm": 0.293, "lr": 5.0003576992117356e-05, "tokens": 11261, "L": 812, "bl2": 10549504, "ckpt_on": false, "samples_seen": 63888, "step_ms": 2399.3, "ts": 1790086368.0, "ema_loss": 1.077}
|
| 3995 |
+
{"type": "train", "step": 3994, "loss": 1.04811, "gnorm": 0.2578, "lr": 5.000262799605605e-05, "tokens": 10050, "L": 762, "bl2": 9290304, "ckpt_on": false, "samples_seen": 63904, "step_ms": 2033.2, "ts": 1790086370.1, "ema_loss": 1.07642}
|
| 3996 |
+
{"type": "train", "step": 3995, "loss": 1.19142, "gnorm": 0.2334, "lr": 5.000182499834667e-05, "tokens": 10756, "L": 836, "bl2": 11182336, "ckpt_on": false, "samples_seen": 63920, "step_ms": 1865.7, "ts": 1790086372.7, "ema_loss": 1.07872}
|
| 3997 |
+
{"type": "train", "step": 3996, "loss": 1.00728, "gnorm": 0.165, "lr": 5.000116799951032e-05, "tokens": 10166, "L": 806, "bl2": 10394176, "ckpt_on": false, "samples_seen": 63936, "step_ms": 2559.4, "ts": 1790086375.4, "ema_loss": 1.07729}
|
| 3998 |
+
{"type": "train", "step": 3997, "loss": 0.97126, "gnorm": 0.2617, "lr": 5.0000656999973227e-05, "tokens": 9361, "L": 822, "bl2": 10810944, "ckpt_on": false, "samples_seen": 63952, "step_ms": 2040.0, "ts": 1790086378.2, "ema_loss": 1.07517}
|
| 3999 |
+
{"type": "train", "step": 3998, "loss": 1.07612, "gnorm": 0.2471, "lr": 5.000029200006705e-05, "tokens": 10458, "L": 853, "bl2": 11641744, "ckpt_on": false, "samples_seen": 63968, "step_ms": 2565.4, "ts": 1790086380.8, "ema_loss": 1.07519}
|
| 4000 |
+
{"type": "train", "step": 3999, "loss": 1.1112, "gnorm": 0.2188, "lr": 5.0000073000028605e-05, "tokens": 11265, "L": 802, "bl2": 10291264, "ckpt_on": false, "samples_seen": 63984, "step_ms": 2559.2, "ts": 1790086383.4, "ema_loss": 1.07591}
|
| 4001 |
+
{"type": "train", "step": 4000, "loss": 1.18898, "gnorm": 0.2617, "lr": 5e-05, "tokens": 10950, "L": 807, "bl2": 10419984, "ckpt_on": false, "samples_seen": 64000, "step_ms": 2900.2, "ts": 1790086391.4, "mem_alloc_gb": 3.71, "mem_reserved_gb": 44.18, "ema_loss": 1.07817}
|