diff --git "a/trainer_log.jsonl" "b/trainer_log.jsonl" new file mode 100644--- /dev/null +++ "b/trainer_log.jsonl" @@ -0,0 +1,676 @@ +{"current_steps": 5, "total_steps": 67140, "loss": 7.196, "lr": 2.978850163836759e-08, "epoch": 0.0007447125409591898, "percentage": 0.01, "elapsed_time": "0:00:01", "remaining_time": "6:42:41", "throughput": 1653.81, "total_tokens": 2976} +{"current_steps": 10, "total_steps": 67140, "loss": 7.2587, "lr": 6.702412868632709e-08, "epoch": 0.0014894250819183796, "percentage": 0.01, "elapsed_time": "0:00:02", "remaining_time": "5:28:53", "throughput": 2013.89, "total_tokens": 5920} +{"current_steps": 15, "total_steps": 67140, "loss": 6.546, "lr": 1.0425975573428657e-07, "epoch": 0.002234137622877569, "percentage": 0.02, "elapsed_time": "0:00:04", "remaining_time": "5:04:45", "throughput": 2161.42, "total_tokens": 8832} +{"current_steps": 20, "total_steps": 67140, "loss": 6.6276, "lr": 1.4149538278224606e-07, "epoch": 0.002978850163836759, "percentage": 0.03, "elapsed_time": "0:00:05", "remaining_time": "4:51:31", "throughput": 2234.86, "total_tokens": 11648} +{"current_steps": 25, "total_steps": 67140, "loss": 6.5739, "lr": 1.7873100983020555e-07, "epoch": 0.0037235627047959487, "percentage": 0.04, "elapsed_time": "0:00:06", "remaining_time": "4:42:56", "throughput": 2272.06, "total_tokens": 14368} +{"current_steps": 30, "total_steps": 67140, "loss": 6.138, "lr": 2.1596663687816505e-07, "epoch": 0.004468275245755138, "percentage": 0.04, "elapsed_time": "0:00:07", "remaining_time": "4:37:50", "throughput": 2318.78, "total_tokens": 17280} +{"current_steps": 35, "total_steps": 67140, "loss": 5.3035, "lr": 2.532022639261245e-07, "epoch": 0.005212987786714328, "percentage": 0.05, "elapsed_time": "0:00:08", "remaining_time": "4:34:03", "throughput": 2350.59, "total_tokens": 20160} +{"current_steps": 40, "total_steps": 67140, "loss": 5.5269, "lr": 2.90437890974084e-07, "epoch": 0.005957700327673518, "percentage": 0.06, "elapsed_time": "0:00:09", "remaining_time": "4:31:42", "throughput": 2377.33, "total_tokens": 23104} +{"current_steps": 45, "total_steps": 67140, "loss": 4.9813, "lr": 3.276735180220435e-07, "epoch": 0.006702412868632708, "percentage": 0.07, "elapsed_time": "0:00:10", "remaining_time": "4:29:35", "throughput": 2401.06, "total_tokens": 26048} +{"current_steps": 50, "total_steps": 67140, "loss": 4.6177, "lr": 3.64909145070003e-07, "epoch": 0.0074471254095918975, "percentage": 0.07, "elapsed_time": "0:00:11", "remaining_time": "4:27:45", "throughput": 2416.01, "total_tokens": 28928} +{"current_steps": 55, "total_steps": 67140, "loss": 4.1926, "lr": 4.021447721179625e-07, "epoch": 0.008191837950551088, "percentage": 0.08, "elapsed_time": "0:00:13", "remaining_time": "4:27:50", "throughput": 2448.24, "total_tokens": 32256} +{"current_steps": 60, "total_steps": 67140, "loss": 4.0465, "lr": 4.3938039916592203e-07, "epoch": 0.008936550491510277, "percentage": 0.09, "elapsed_time": "0:00:14", "remaining_time": "4:26:59", "throughput": 2458.91, "total_tokens": 35232} +{"current_steps": 65, "total_steps": 67140, "loss": 3.996, "lr": 4.7661602621388146e-07, "epoch": 0.009681263032469467, "percentage": 0.1, "elapsed_time": "0:00:15", "remaining_time": "4:25:45", "throughput": 2466.5, "total_tokens": 38112} +{"current_steps": 70, "total_steps": 67140, "loss": 3.7153, "lr": 5.13851653261841e-07, "epoch": 0.010425975573428656, "percentage": 0.1, "elapsed_time": "0:00:16", "remaining_time": "4:25:12", "throughput": 2475.94, "total_tokens": 41120} +{"current_steps": 75, "total_steps": 67140, "loss": 3.5405, "lr": 5.510872803098004e-07, "epoch": 0.011170688114387846, "percentage": 0.11, "elapsed_time": "0:00:17", "remaining_time": "4:24:40", "throughput": 2481.22, "total_tokens": 44064} +{"current_steps": 80, "total_steps": 67140, "loss": 3.2765, "lr": 5.8832290735776e-07, "epoch": 0.011915400655347037, "percentage": 0.12, "elapsed_time": "0:00:18", "remaining_time": "4:23:02", "throughput": 2474.68, "total_tokens": 46592} +{"current_steps": 85, "total_steps": 67140, "loss": 3.2172, "lr": 6.255585344057195e-07, "epoch": 0.012660113196306225, "percentage": 0.13, "elapsed_time": "0:00:19", "remaining_time": "4:21:36", "throughput": 2470.23, "total_tokens": 49152} +{"current_steps": 90, "total_steps": 67140, "loss": 3.1597, "lr": 6.627941614536789e-07, "epoch": 0.013404825737265416, "percentage": 0.13, "elapsed_time": "0:00:20", "remaining_time": "4:20:40", "throughput": 2466.16, "total_tokens": 51776} +{"current_steps": 95, "total_steps": 67140, "loss": 2.7179, "lr": 7.000297885016385e-07, "epoch": 0.014149538278224605, "percentage": 0.14, "elapsed_time": "0:00:22", "remaining_time": "4:20:11", "throughput": 2469.32, "total_tokens": 54624} +{"current_steps": 100, "total_steps": 67140, "loss": 2.8843, "lr": 7.372654155495979e-07, "epoch": 0.014894250819183795, "percentage": 0.15, "elapsed_time": "0:00:23", "remaining_time": "4:19:27", "throughput": 2468.05, "total_tokens": 57312} +{"current_steps": 105, "total_steps": 67140, "loss": 2.8324, "lr": 7.745010425975574e-07, "epoch": 0.015638963360142984, "percentage": 0.16, "elapsed_time": "0:00:24", "remaining_time": "4:18:56", "throughput": 2468.19, "total_tokens": 60064} +{"current_steps": 110, "total_steps": 67140, "loss": 2.6194, "lr": 8.11736669645517e-07, "epoch": 0.016383675901102176, "percentage": 0.16, "elapsed_time": "0:00:25", "remaining_time": "4:19:30", "throughput": 2482.13, "total_tokens": 63424} +{"current_steps": 115, "total_steps": 67140, "loss": 2.3547, "lr": 8.489722966934764e-07, "epoch": 0.017128388442061365, "percentage": 0.17, "elapsed_time": "0:00:26", "remaining_time": "4:18:52", "throughput": 2479.46, "total_tokens": 66080} +{"current_steps": 120, "total_steps": 67140, "loss": 2.3412, "lr": 8.862079237414358e-07, "epoch": 0.017873100983020553, "percentage": 0.18, "elapsed_time": "0:00:27", "remaining_time": "4:19:25", "throughput": 2491.52, "total_tokens": 69440} +{"current_steps": 125, "total_steps": 67140, "loss": 2.0561, "lr": 9.234435507893953e-07, "epoch": 0.018617813523979745, "percentage": 0.19, "elapsed_time": "0:00:29", "remaining_time": "4:19:11", "throughput": 2493.17, "total_tokens": 72320} +{"current_steps": 130, "total_steps": 67140, "loss": 1.8618, "lr": 9.606791778373549e-07, "epoch": 0.019362526064938934, "percentage": 0.19, "elapsed_time": "0:00:30", "remaining_time": "4:18:49", "throughput": 2495.07, "total_tokens": 75168} +{"current_steps": 135, "total_steps": 67140, "loss": 1.8099, "lr": 9.979148048853143e-07, "epoch": 0.020107238605898123, "percentage": 0.2, "elapsed_time": "0:00:31", "remaining_time": "4:18:45", "throughput": 2499.23, "total_tokens": 78176} +{"current_steps": 140, "total_steps": 67140, "loss": 1.5512, "lr": 1.035150431933274e-06, "epoch": 0.02085195114685731, "percentage": 0.21, "elapsed_time": "0:00:32", "remaining_time": "4:18:47", "throughput": 2504.06, "total_tokens": 81248} +{"current_steps": 145, "total_steps": 67140, "loss": 1.5942, "lr": 1.0723860589812334e-06, "epoch": 0.021596663687816504, "percentage": 0.22, "elapsed_time": "0:00:33", "remaining_time": "4:18:55", "throughput": 2510.57, "total_tokens": 84416} +{"current_steps": 150, "total_steps": 67140, "loss": 1.4061, "lr": 1.1096216860291928e-06, "epoch": 0.022341376228775692, "percentage": 0.22, "elapsed_time": "0:00:34", "remaining_time": "4:19:02", "throughput": 2516.57, "total_tokens": 87584} +{"current_steps": 155, "total_steps": 67140, "loss": 1.1484, "lr": 1.1468573130771522e-06, "epoch": 0.02308608876973488, "percentage": 0.23, "elapsed_time": "0:00:35", "remaining_time": "4:18:45", "throughput": 2515.52, "total_tokens": 90368} +{"current_steps": 160, "total_steps": 67140, "loss": 1.3229, "lr": 1.1840929401251119e-06, "epoch": 0.023830801310694073, "percentage": 0.24, "elapsed_time": "0:00:37", "remaining_time": "4:18:27", "throughput": 2514.58, "total_tokens": 93152} +{"current_steps": 165, "total_steps": 67140, "loss": 1.0603, "lr": 1.2213285671730713e-06, "epoch": 0.024575513851653262, "percentage": 0.25, "elapsed_time": "0:00:38", "remaining_time": "4:18:37", "throughput": 2521.2, "total_tokens": 96384} +{"current_steps": 170, "total_steps": 67140, "loss": 1.1298, "lr": 1.2585641942210307e-06, "epoch": 0.02532022639261245, "percentage": 0.25, "elapsed_time": "0:00:39", "remaining_time": "4:18:23", "throughput": 2518.96, "total_tokens": 99136} +{"current_steps": 175, "total_steps": 67140, "loss": 1.1053, "lr": 1.2957998212689904e-06, "epoch": 0.026064938933571643, "percentage": 0.26, "elapsed_time": "0:00:40", "remaining_time": "4:18:02", "throughput": 2516.64, "total_tokens": 101824} +{"current_steps": 180, "total_steps": 67140, "loss": 1.0142, "lr": 1.3330354483169498e-06, "epoch": 0.02680965147453083, "percentage": 0.27, "elapsed_time": "0:00:41", "remaining_time": "4:18:02", "throughput": 2518.88, "total_tokens": 104832} +{"current_steps": 185, "total_steps": 67140, "loss": 1.0161, "lr": 1.3702710753649092e-06, "epoch": 0.02755436401549002, "percentage": 0.28, "elapsed_time": "0:00:42", "remaining_time": "4:17:49", "throughput": 2519.29, "total_tokens": 107680} +{"current_steps": 190, "total_steps": 67140, "loss": 0.9298, "lr": 1.4075067024128687e-06, "epoch": 0.02829907655644921, "percentage": 0.28, "elapsed_time": "0:00:43", "remaining_time": "4:17:41", "throughput": 2519.62, "total_tokens": 110560} +{"current_steps": 195, "total_steps": 67140, "loss": 0.9707, "lr": 1.4447423294608283e-06, "epoch": 0.0290437890974084, "percentage": 0.29, "elapsed_time": "0:00:45", "remaining_time": "4:17:43", "throughput": 2524.15, "total_tokens": 113696} +{"current_steps": 200, "total_steps": 67140, "loss": 1.0271, "lr": 1.4819779565087877e-06, "epoch": 0.02978850163836759, "percentage": 0.3, "elapsed_time": "0:00:46", "remaining_time": "4:17:33", "throughput": 2522.73, "total_tokens": 116480} +{"current_steps": 205, "total_steps": 67140, "loss": 0.976, "lr": 1.5192135835567472e-06, "epoch": 0.03053321417932678, "percentage": 0.31, "elapsed_time": "0:00:47", "remaining_time": "4:17:41", "throughput": 2527.99, "total_tokens": 119712} +{"current_steps": 210, "total_steps": 67140, "loss": 0.9068, "lr": 1.5564492106047066e-06, "epoch": 0.03127792672028597, "percentage": 0.31, "elapsed_time": "0:00:48", "remaining_time": "4:17:52", "throughput": 2532.47, "total_tokens": 122944} +{"current_steps": 215, "total_steps": 67140, "loss": 0.7781, "lr": 1.593684837652666e-06, "epoch": 0.032022639261245156, "percentage": 0.32, "elapsed_time": "0:00:49", "remaining_time": "4:17:52", "throughput": 2534.62, "total_tokens": 125984} +{"current_steps": 220, "total_steps": 67140, "loss": 1.0523, "lr": 1.6309204647006257e-06, "epoch": 0.03276735180220435, "percentage": 0.33, "elapsed_time": "0:00:50", "remaining_time": "4:17:59", "throughput": 2539.22, "total_tokens": 129216} +{"current_steps": 225, "total_steps": 67140, "loss": 0.9772, "lr": 1.668156091748585e-06, "epoch": 0.03351206434316354, "percentage": 0.34, "elapsed_time": "0:00:51", "remaining_time": "4:17:39", "throughput": 2535.62, "total_tokens": 131808} +{"current_steps": 230, "total_steps": 67140, "loss": 0.8965, "lr": 1.7053917187965447e-06, "epoch": 0.03425677688412273, "percentage": 0.34, "elapsed_time": "0:00:53", "remaining_time": "4:17:46", "throughput": 2540.0, "total_tokens": 135040} +{"current_steps": 235, "total_steps": 67140, "loss": 0.9434, "lr": 1.7426273458445042e-06, "epoch": 0.03500148942508192, "percentage": 0.35, "elapsed_time": "0:00:54", "remaining_time": "4:17:31", "throughput": 2538.89, "total_tokens": 137792} +{"current_steps": 240, "total_steps": 67140, "loss": 0.9646, "lr": 1.7798629728924636e-06, "epoch": 0.035746201966041107, "percentage": 0.36, "elapsed_time": "0:00:55", "remaining_time": "4:17:30", "throughput": 2540.2, "total_tokens": 140800} +{"current_steps": 245, "total_steps": 67140, "loss": 0.9094, "lr": 1.817098599940423e-06, "epoch": 0.036490914507000295, "percentage": 0.36, "elapsed_time": "0:00:56", "remaining_time": "4:17:23", "throughput": 2539.1, "total_tokens": 143616} +{"current_steps": 250, "total_steps": 67140, "loss": 0.9301, "lr": 1.8543342269883825e-06, "epoch": 0.03723562704795949, "percentage": 0.37, "elapsed_time": "0:00:57", "remaining_time": "4:17:21", "throughput": 2540.04, "total_tokens": 146592} +{"current_steps": 255, "total_steps": 67140, "loss": 1.0944, "lr": 1.8915698540363419e-06, "epoch": 0.03798033958891868, "percentage": 0.38, "elapsed_time": "0:00:58", "remaining_time": "4:17:09", "throughput": 2539.36, "total_tokens": 149376} +{"current_steps": 260, "total_steps": 67140, "loss": 0.9266, "lr": 1.9288054810843013e-06, "epoch": 0.03872505212987787, "percentage": 0.39, "elapsed_time": "0:00:59", "remaining_time": "4:17:00", "throughput": 2539.72, "total_tokens": 152256} +{"current_steps": 265, "total_steps": 67140, "loss": 0.942, "lr": 1.966041108132261e-06, "epoch": 0.03946976467083706, "percentage": 0.39, "elapsed_time": "0:01:01", "remaining_time": "4:16:55", "throughput": 2540.18, "total_tokens": 155168} +{"current_steps": 270, "total_steps": 67140, "loss": 0.9838, "lr": 2.0032767351802206e-06, "epoch": 0.040214477211796246, "percentage": 0.4, "elapsed_time": "0:01:02", "remaining_time": "4:16:50", "throughput": 2539.44, "total_tokens": 158016} +{"current_steps": 275, "total_steps": 67140, "loss": 1.055, "lr": 2.04051236222818e-06, "epoch": 0.040959189752755434, "percentage": 0.41, "elapsed_time": "0:01:03", "remaining_time": "4:16:44", "throughput": 2541.05, "total_tokens": 160992} +{"current_steps": 280, "total_steps": 67140, "loss": 0.7821, "lr": 2.0777479892761395e-06, "epoch": 0.04170390229371462, "percentage": 0.42, "elapsed_time": "0:01:04", "remaining_time": "4:16:33", "throughput": 2538.09, "total_tokens": 163616} +{"current_steps": 285, "total_steps": 67140, "loss": 0.8794, "lr": 2.114983616324099e-06, "epoch": 0.04244861483467382, "percentage": 0.42, "elapsed_time": "0:01:05", "remaining_time": "4:16:29", "throughput": 2537.79, "total_tokens": 166496} +{"current_steps": 290, "total_steps": 67140, "loss": 0.8459, "lr": 2.1522192433720583e-06, "epoch": 0.04319332737563301, "percentage": 0.43, "elapsed_time": "0:01:06", "remaining_time": "4:16:18", "throughput": 2537.03, "total_tokens": 169248} +{"current_steps": 295, "total_steps": 67140, "loss": 0.9928, "lr": 2.1894548704200177e-06, "epoch": 0.043938039916592196, "percentage": 0.44, "elapsed_time": "0:01:07", "remaining_time": "4:16:14", "throughput": 2537.42, "total_tokens": 172160} +{"current_steps": 300, "total_steps": 67140, "loss": 1.0563, "lr": 2.2266904974679776e-06, "epoch": 0.044682752457551385, "percentage": 0.45, "elapsed_time": "0:01:08", "remaining_time": "4:16:06", "throughput": 2535.67, "total_tokens": 174880} +{"current_steps": 305, "total_steps": 67140, "loss": 1.009, "lr": 2.263926124515937e-06, "epoch": 0.045427464998510574, "percentage": 0.45, "elapsed_time": "0:01:10", "remaining_time": "4:15:54", "throughput": 2533.74, "total_tokens": 177536} +{"current_steps": 310, "total_steps": 67140, "loss": 1.0043, "lr": 2.3011617515638965e-06, "epoch": 0.04617217753946976, "percentage": 0.46, "elapsed_time": "0:01:11", "remaining_time": "4:15:50", "throughput": 2533.3, "total_tokens": 180384} +{"current_steps": 315, "total_steps": 67140, "loss": 0.8316, "lr": 2.338397378611856e-06, "epoch": 0.04691689008042895, "percentage": 0.47, "elapsed_time": "0:01:12", "remaining_time": "4:15:41", "throughput": 2531.91, "total_tokens": 183104} +{"current_steps": 320, "total_steps": 67140, "loss": 0.8994, "lr": 2.3756330056598153e-06, "epoch": 0.04766160262138815, "percentage": 0.48, "elapsed_time": "0:01:13", "remaining_time": "4:15:31", "throughput": 2530.39, "total_tokens": 185792} +{"current_steps": 325, "total_steps": 67140, "loss": 0.8567, "lr": 2.4128686327077747e-06, "epoch": 0.048406315162347335, "percentage": 0.48, "elapsed_time": "0:01:14", "remaining_time": "4:15:28", "throughput": 2530.07, "total_tokens": 188640} +{"current_steps": 330, "total_steps": 67140, "loss": 0.9353, "lr": 2.4501042597557346e-06, "epoch": 0.049151027703306524, "percentage": 0.49, "elapsed_time": "0:01:15", "remaining_time": "4:15:18", "throughput": 2528.58, "total_tokens": 191328} +{"current_steps": 335, "total_steps": 67140, "loss": 0.8509, "lr": 2.487339886803694e-06, "epoch": 0.04989574024426571, "percentage": 0.5, "elapsed_time": "0:01:16", "remaining_time": "4:15:24", "throughput": 2530.5, "total_tokens": 194464} +{"current_steps": 340, "total_steps": 67140, "loss": 0.9665, "lr": 2.5245755138516535e-06, "epoch": 0.0506404527852249, "percentage": 0.51, "elapsed_time": "0:01:17", "remaining_time": "4:15:06", "throughput": 2528.11, "total_tokens": 196960} +{"current_steps": 345, "total_steps": 67140, "loss": 0.8715, "lr": 2.561811140899613e-06, "epoch": 0.05138516532618409, "percentage": 0.51, "elapsed_time": "0:01:19", "remaining_time": "4:15:01", "throughput": 2528.58, "total_tokens": 199840} +{"current_steps": 350, "total_steps": 67140, "loss": 0.8209, "lr": 2.5990467679475723e-06, "epoch": 0.052129877867143286, "percentage": 0.52, "elapsed_time": "0:01:20", "remaining_time": "4:14:52", "throughput": 2527.63, "total_tokens": 202560} +{"current_steps": 355, "total_steps": 67140, "loss": 0.8802, "lr": 2.6362823949955317e-06, "epoch": 0.052874590408102475, "percentage": 0.53, "elapsed_time": "0:01:21", "remaining_time": "4:14:56", "throughput": 2528.6, "total_tokens": 205600} +{"current_steps": 360, "total_steps": 67140, "loss": 0.8617, "lr": 2.673518022043491e-06, "epoch": 0.05361930294906166, "percentage": 0.54, "elapsed_time": "0:01:22", "remaining_time": "4:14:59", "throughput": 2530.03, "total_tokens": 208672} +{"current_steps": 365, "total_steps": 67140, "loss": 0.8325, "lr": 2.710753649091451e-06, "epoch": 0.05436401549002085, "percentage": 0.54, "elapsed_time": "0:01:23", "remaining_time": "4:14:56", "throughput": 2529.72, "total_tokens": 211520} +{"current_steps": 370, "total_steps": 67140, "loss": 1.0399, "lr": 2.7479892761394105e-06, "epoch": 0.05510872803098004, "percentage": 0.55, "elapsed_time": "0:01:24", "remaining_time": "4:14:57", "throughput": 2530.28, "total_tokens": 214496} +{"current_steps": 375, "total_steps": 67140, "loss": 0.8416, "lr": 2.78522490318737e-06, "epoch": 0.05585344057193923, "percentage": 0.56, "elapsed_time": "0:01:25", "remaining_time": "4:14:49", "throughput": 2529.42, "total_tokens": 217216} +{"current_steps": 380, "total_steps": 67140, "loss": 0.931, "lr": 2.8224605302353293e-06, "epoch": 0.05659815311289842, "percentage": 0.57, "elapsed_time": "0:01:27", "remaining_time": "4:14:46", "throughput": 2528.48, "total_tokens": 220000} +{"current_steps": 385, "total_steps": 67140, "loss": 1.0547, "lr": 2.8596961572832887e-06, "epoch": 0.057342865653857614, "percentage": 0.57, "elapsed_time": "0:01:28", "remaining_time": "4:14:42", "throughput": 2527.98, "total_tokens": 222816} +{"current_steps": 390, "total_steps": 67140, "loss": 0.841, "lr": 2.896931784331248e-06, "epoch": 0.0580875781948168, "percentage": 0.58, "elapsed_time": "0:01:29", "remaining_time": "4:14:38", "throughput": 2527.99, "total_tokens": 225664} +{"current_steps": 395, "total_steps": 67140, "loss": 0.8392, "lr": 2.9341674113792076e-06, "epoch": 0.05883229073577599, "percentage": 0.59, "elapsed_time": "0:01:30", "remaining_time": "4:14:46", "throughput": 2529.14, "total_tokens": 228800} +{"current_steps": 400, "total_steps": 67140, "loss": 0.8746, "lr": 2.9714030384271675e-06, "epoch": 0.05957700327673518, "percentage": 0.6, "elapsed_time": "0:01:31", "remaining_time": "4:14:55", "throughput": 2531.5, "total_tokens": 232064} +{"current_steps": 405, "total_steps": 67140, "loss": 0.7465, "lr": 3.008638665475127e-06, "epoch": 0.06032171581769437, "percentage": 0.6, "elapsed_time": "0:01:32", "remaining_time": "4:14:50", "throughput": 2531.18, "total_tokens": 234880} +{"current_steps": 410, "total_steps": 67140, "loss": 0.9453, "lr": 3.0458742925230863e-06, "epoch": 0.06106642835865356, "percentage": 0.61, "elapsed_time": "0:01:33", "remaining_time": "4:14:49", "throughput": 2531.98, "total_tokens": 237856} +{"current_steps": 415, "total_steps": 67140, "loss": 0.9598, "lr": 3.0831099195710457e-06, "epoch": 0.06181114089961275, "percentage": 0.62, "elapsed_time": "0:01:35", "remaining_time": "4:14:44", "throughput": 2531.05, "total_tokens": 240608} +{"current_steps": 420, "total_steps": 67140, "loss": 0.8648, "lr": 3.120345546619005e-06, "epoch": 0.06255585344057193, "percentage": 0.63, "elapsed_time": "0:01:36", "remaining_time": "4:14:33", "throughput": 2529.18, "total_tokens": 243168} +{"current_steps": 425, "total_steps": 67140, "loss": 0.8792, "lr": 3.1575811736669646e-06, "epoch": 0.06330056598153112, "percentage": 0.63, "elapsed_time": "0:01:37", "remaining_time": "4:14:36", "throughput": 2530.99, "total_tokens": 246304} +{"current_steps": 430, "total_steps": 67140, "loss": 1.0397, "lr": 3.194816800714924e-06, "epoch": 0.06404527852249031, "percentage": 0.64, "elapsed_time": "0:01:38", "remaining_time": "4:14:30", "throughput": 2529.87, "total_tokens": 249024} +{"current_steps": 435, "total_steps": 67140, "loss": 0.941, "lr": 3.2320524277628835e-06, "epoch": 0.06478999106344951, "percentage": 0.65, "elapsed_time": "0:01:39", "remaining_time": "4:14:32", "throughput": 2532.4, "total_tokens": 252224} +{"current_steps": 440, "total_steps": 67140, "loss": 0.983, "lr": 3.269288054810843e-06, "epoch": 0.0655347036044087, "percentage": 0.66, "elapsed_time": "0:01:40", "remaining_time": "4:14:25", "throughput": 2530.77, "total_tokens": 254848} +{"current_steps": 445, "total_steps": 67140, "loss": 0.9496, "lr": 3.3065236818588023e-06, "epoch": 0.06627941614536789, "percentage": 0.66, "elapsed_time": "0:01:41", "remaining_time": "4:14:24", "throughput": 2530.85, "total_tokens": 257760} +{"current_steps": 450, "total_steps": 67140, "loss": 0.8912, "lr": 3.3437593089067626e-06, "epoch": 0.06702412868632708, "percentage": 0.67, "elapsed_time": "0:01:42", "remaining_time": "4:14:17", "throughput": 2529.21, "total_tokens": 260384} +{"current_steps": 455, "total_steps": 67140, "loss": 0.8947, "lr": 3.380994935954722e-06, "epoch": 0.06776884122728627, "percentage": 0.68, "elapsed_time": "0:01:44", "remaining_time": "4:14:16", "throughput": 2529.88, "total_tokens": 263360} +{"current_steps": 460, "total_steps": 67140, "loss": 0.8604, "lr": 3.4182305630026814e-06, "epoch": 0.06851355376824546, "percentage": 0.69, "elapsed_time": "0:01:45", "remaining_time": "4:14:11", "throughput": 2529.23, "total_tokens": 266112} +{"current_steps": 465, "total_steps": 67140, "loss": 0.8826, "lr": 3.455466190050641e-06, "epoch": 0.06925826630920465, "percentage": 0.69, "elapsed_time": "0:01:46", "remaining_time": "4:14:01", "throughput": 2527.59, "total_tokens": 268672} +{"current_steps": 470, "total_steps": 67140, "loss": 0.8912, "lr": 3.4927018170986003e-06, "epoch": 0.07000297885016384, "percentage": 0.7, "elapsed_time": "0:01:47", "remaining_time": "4:13:55", "throughput": 2526.21, "total_tokens": 271328} +{"current_steps": 475, "total_steps": 67140, "loss": 0.8963, "lr": 3.5299374441465597e-06, "epoch": 0.07074769139112302, "percentage": 0.71, "elapsed_time": "0:01:48", "remaining_time": "4:13:51", "throughput": 2526.0, "total_tokens": 274144} +{"current_steps": 480, "total_steps": 67140, "loss": 0.806, "lr": 3.567173071194519e-06, "epoch": 0.07149240393208221, "percentage": 0.71, "elapsed_time": "0:01:49", "remaining_time": "4:13:48", "throughput": 2526.22, "total_tokens": 277024} +{"current_steps": 485, "total_steps": 67140, "loss": 0.9033, "lr": 3.6044086982424786e-06, "epoch": 0.0722371164730414, "percentage": 0.72, "elapsed_time": "0:01:50", "remaining_time": "4:13:46", "throughput": 2525.81, "total_tokens": 279840} +{"current_steps": 490, "total_steps": 67140, "loss": 0.8872, "lr": 3.641644325290438e-06, "epoch": 0.07298182901400059, "percentage": 0.73, "elapsed_time": "0:01:52", "remaining_time": "4:13:55", "throughput": 2528.3, "total_tokens": 283200} +{"current_steps": 495, "total_steps": 67140, "loss": 0.8645, "lr": 3.6788799523383975e-06, "epoch": 0.07372654155495978, "percentage": 0.74, "elapsed_time": "0:01:53", "remaining_time": "4:13:54", "throughput": 2527.76, "total_tokens": 286016} +{"current_steps": 500, "total_steps": 67140, "loss": 0.8283, "lr": 3.716115579386357e-06, "epoch": 0.07447125409591898, "percentage": 0.74, "elapsed_time": "0:01:54", "remaining_time": "4:13:50", "throughput": 2527.77, "total_tokens": 288864} +{"current_steps": 505, "total_steps": 67140, "loss": 1.0209, "lr": 3.7533512064343163e-06, "epoch": 0.07521596663687817, "percentage": 0.75, "elapsed_time": "0:01:55", "remaining_time": "4:13:50", "throughput": 2528.89, "total_tokens": 291904} +{"current_steps": 510, "total_steps": 67140, "loss": 1.235, "lr": 3.7905868334822757e-06, "epoch": 0.07596067917783736, "percentage": 0.76, "elapsed_time": "0:01:56", "remaining_time": "4:13:45", "throughput": 2528.68, "total_tokens": 294688} +{"current_steps": 515, "total_steps": 67140, "loss": 0.9427, "lr": 3.827822460530236e-06, "epoch": 0.07670539171879655, "percentage": 0.77, "elapsed_time": "0:01:57", "remaining_time": "4:13:48", "throughput": 2529.78, "total_tokens": 297792} +{"current_steps": 520, "total_steps": 67140, "loss": 0.886, "lr": 3.8650580875781954e-06, "epoch": 0.07745010425975574, "percentage": 0.77, "elapsed_time": "0:01:58", "remaining_time": "4:13:45", "throughput": 2530.48, "total_tokens": 300736} +{"current_steps": 525, "total_steps": 67140, "loss": 0.8543, "lr": 3.9022937146261545e-06, "epoch": 0.07819481680071493, "percentage": 0.78, "elapsed_time": "0:01:59", "remaining_time": "4:13:41", "throughput": 2529.9, "total_tokens": 303488} +{"current_steps": 530, "total_steps": 67140, "loss": 0.7119, "lr": 3.939529341674114e-06, "epoch": 0.07893952934167411, "percentage": 0.79, "elapsed_time": "0:02:01", "remaining_time": "4:13:44", "throughput": 2531.18, "total_tokens": 306624} +{"current_steps": 535, "total_steps": 67140, "loss": 0.8965, "lr": 3.976764968722073e-06, "epoch": 0.0796842418826333, "percentage": 0.8, "elapsed_time": "0:02:02", "remaining_time": "4:13:47", "throughput": 2532.69, "total_tokens": 309792} +{"current_steps": 540, "total_steps": 67140, "loss": 0.9347, "lr": 4.014000595770033e-06, "epoch": 0.08042895442359249, "percentage": 0.8, "elapsed_time": "0:02:03", "remaining_time": "4:13:43", "throughput": 2532.34, "total_tokens": 312576} +{"current_steps": 545, "total_steps": 67140, "loss": 0.9361, "lr": 4.051236222817992e-06, "epoch": 0.08117366696455168, "percentage": 0.81, "elapsed_time": "0:02:04", "remaining_time": "4:13:39", "throughput": 2532.01, "total_tokens": 315360} +{"current_steps": 550, "total_steps": 67140, "loss": 1.0087, "lr": 4.088471849865952e-06, "epoch": 0.08191837950551087, "percentage": 0.82, "elapsed_time": "0:02:05", "remaining_time": "4:13:31", "throughput": 2531.15, "total_tokens": 318016} +{"current_steps": 555, "total_steps": 67140, "loss": 0.8295, "lr": 4.125707476913911e-06, "epoch": 0.08266309204647006, "percentage": 0.83, "elapsed_time": "0:02:06", "remaining_time": "4:13:28", "throughput": 2530.44, "total_tokens": 320768} +{"current_steps": 560, "total_steps": 67140, "loss": 0.8625, "lr": 4.162943103961871e-06, "epoch": 0.08340780458742925, "percentage": 0.83, "elapsed_time": "0:02:07", "remaining_time": "4:13:25", "throughput": 2530.85, "total_tokens": 323680} +{"current_steps": 565, "total_steps": 67140, "loss": 0.9651, "lr": 4.20017873100983e-06, "epoch": 0.08415251712838845, "percentage": 0.84, "elapsed_time": "0:02:09", "remaining_time": "4:13:25", "throughput": 2531.14, "total_tokens": 326624} +{"current_steps": 570, "total_steps": 67140, "loss": 0.9424, "lr": 4.23741435805779e-06, "epoch": 0.08489722966934764, "percentage": 0.85, "elapsed_time": "0:02:10", "remaining_time": "4:13:18", "throughput": 2529.87, "total_tokens": 329216} +{"current_steps": 575, "total_steps": 67140, "loss": 0.879, "lr": 4.274649985105749e-06, "epoch": 0.08564194221030683, "percentage": 0.86, "elapsed_time": "0:02:11", "remaining_time": "4:13:12", "throughput": 2529.03, "total_tokens": 331904} +{"current_steps": 580, "total_steps": 67140, "loss": 0.855, "lr": 4.3118856121537094e-06, "epoch": 0.08638665475126601, "percentage": 0.86, "elapsed_time": "0:02:12", "remaining_time": "4:13:10", "throughput": 2528.9, "total_tokens": 334752} +{"current_steps": 585, "total_steps": 67140, "loss": 0.818, "lr": 4.3491212392016685e-06, "epoch": 0.0871313672922252, "percentage": 0.87, "elapsed_time": "0:02:13", "remaining_time": "4:13:15", "throughput": 2530.42, "total_tokens": 337984} +{"current_steps": 590, "total_steps": 67140, "loss": 0.9237, "lr": 4.386356866249628e-06, "epoch": 0.08787607983318439, "percentage": 0.88, "elapsed_time": "0:02:14", "remaining_time": "4:13:11", "throughput": 2530.41, "total_tokens": 340800} +{"current_steps": 595, "total_steps": 67140, "loss": 0.7448, "lr": 4.423592493297587e-06, "epoch": 0.08862079237414358, "percentage": 0.89, "elapsed_time": "0:02:15", "remaining_time": "4:13:05", "throughput": 2529.28, "total_tokens": 343424} +{"current_steps": 600, "total_steps": 67140, "loss": 1.0281, "lr": 4.460828120345547e-06, "epoch": 0.08936550491510277, "percentage": 0.89, "elapsed_time": "0:02:16", "remaining_time": "4:13:11", "throughput": 2531.15, "total_tokens": 346720} +{"current_steps": 605, "total_steps": 67140, "loss": 0.9625, "lr": 4.498063747393506e-06, "epoch": 0.09011021745606196, "percentage": 0.9, "elapsed_time": "0:02:18", "remaining_time": "4:13:11", "throughput": 2531.72, "total_tokens": 349728} +{"current_steps": 610, "total_steps": 67140, "loss": 0.8841, "lr": 4.535299374441466e-06, "epoch": 0.09085492999702115, "percentage": 0.91, "elapsed_time": "0:02:19", "remaining_time": "4:13:05", "throughput": 2530.67, "total_tokens": 352352} +{"current_steps": 615, "total_steps": 67140, "loss": 0.7964, "lr": 4.572535001489425e-06, "epoch": 0.09159964253798034, "percentage": 0.92, "elapsed_time": "0:02:20", "remaining_time": "4:13:02", "throughput": 2530.51, "total_tokens": 355168} +{"current_steps": 620, "total_steps": 67140, "loss": 0.8582, "lr": 4.609770628537385e-06, "epoch": 0.09234435507893952, "percentage": 0.92, "elapsed_time": "0:02:21", "remaining_time": "4:12:58", "throughput": 2530.01, "total_tokens": 357920} +{"current_steps": 625, "total_steps": 67140, "loss": 0.9372, "lr": 4.647006255585344e-06, "epoch": 0.09308906761989871, "percentage": 0.93, "elapsed_time": "0:02:22", "remaining_time": "4:12:56", "throughput": 2529.45, "total_tokens": 360704} +{"current_steps": 630, "total_steps": 67140, "loss": 0.8964, "lr": 4.684241882633304e-06, "epoch": 0.0938337801608579, "percentage": 0.94, "elapsed_time": "0:02:23", "remaining_time": "4:12:58", "throughput": 2530.87, "total_tokens": 363872} +{"current_steps": 635, "total_steps": 67140, "loss": 0.8797, "lr": 4.721477509681263e-06, "epoch": 0.0945784927018171, "percentage": 0.95, "elapsed_time": "0:02:24", "remaining_time": "4:13:00", "throughput": 2531.87, "total_tokens": 366976} +{"current_steps": 640, "total_steps": 67140, "loss": 0.8006, "lr": 4.758713136729223e-06, "epoch": 0.0953232052427763, "percentage": 0.95, "elapsed_time": "0:02:26", "remaining_time": "4:12:58", "throughput": 2531.64, "total_tokens": 369824} +{"current_steps": 645, "total_steps": 67140, "loss": 0.8516, "lr": 4.7959487637771824e-06, "epoch": 0.09606791778373548, "percentage": 0.96, "elapsed_time": "0:02:27", "remaining_time": "4:12:57", "throughput": 2532.47, "total_tokens": 372832} +{"current_steps": 650, "total_steps": 67140, "loss": 0.9315, "lr": 4.833184390825142e-06, "epoch": 0.09681263032469467, "percentage": 0.97, "elapsed_time": "0:02:28", "remaining_time": "4:12:58", "throughput": 2533.18, "total_tokens": 375872} +{"current_steps": 655, "total_steps": 67140, "loss": 0.8474, "lr": 4.870420017873101e-06, "epoch": 0.09755734286565386, "percentage": 0.98, "elapsed_time": "0:02:29", "remaining_time": "4:12:56", "throughput": 2533.14, "total_tokens": 378752} +{"current_steps": 660, "total_steps": 67140, "loss": 0.8887, "lr": 4.907655644921061e-06, "epoch": 0.09830205540661305, "percentage": 0.98, "elapsed_time": "0:02:30", "remaining_time": "4:12:54", "throughput": 2533.18, "total_tokens": 381632} +{"current_steps": 665, "total_steps": 67140, "loss": 0.8347, "lr": 4.94489127196902e-06, "epoch": 0.09904676794757224, "percentage": 0.99, "elapsed_time": "0:02:31", "remaining_time": "4:12:57", "throughput": 2534.54, "total_tokens": 384832} +{"current_steps": 670, "total_steps": 67140, "loss": 0.7682, "lr": 4.98212689901698e-06, "epoch": 0.09979148048853143, "percentage": 1.0, "elapsed_time": "0:02:33", "remaining_time": "4:13:02", "throughput": 2536.59, "total_tokens": 388192} +{"current_steps": 675, "total_steps": 67140, "loss": 0.9034, "lr": 5.019362526064939e-06, "epoch": 0.10053619302949061, "percentage": 1.01, "elapsed_time": "0:02:34", "remaining_time": "4:13:01", "throughput": 2536.56, "total_tokens": 391072} +{"current_steps": 680, "total_steps": 67140, "loss": 1.1481, "lr": 5.056598153112899e-06, "epoch": 0.1012809055704498, "percentage": 1.01, "elapsed_time": "0:02:35", "remaining_time": "4:12:56", "throughput": 2536.06, "total_tokens": 393792} +{"current_steps": 685, "total_steps": 67140, "loss": 0.9595, "lr": 5.093833780160858e-06, "epoch": 0.10202561811140899, "percentage": 1.02, "elapsed_time": "0:02:36", "remaining_time": "4:12:56", "throughput": 2536.56, "total_tokens": 396800} +{"current_steps": 690, "total_steps": 67140, "loss": 0.8885, "lr": 5.131069407208818e-06, "epoch": 0.10277033065236818, "percentage": 1.03, "elapsed_time": "0:02:37", "remaining_time": "4:12:54", "throughput": 2536.33, "total_tokens": 399648} +{"current_steps": 695, "total_steps": 67140, "loss": 0.7986, "lr": 5.168305034256777e-06, "epoch": 0.10351504319332737, "percentage": 1.04, "elapsed_time": "0:02:38", "remaining_time": "4:12:52", "throughput": 2536.38, "total_tokens": 402528} +{"current_steps": 700, "total_steps": 67140, "loss": 0.8624, "lr": 5.205540661304737e-06, "epoch": 0.10425975573428657, "percentage": 1.04, "elapsed_time": "0:02:39", "remaining_time": "4:12:54", "throughput": 2537.54, "total_tokens": 405696} +{"current_steps": 705, "total_steps": 67140, "loss": 0.857, "lr": 5.242776288352696e-06, "epoch": 0.10500446827524576, "percentage": 1.05, "elapsed_time": "0:02:41", "remaining_time": "4:12:56", "throughput": 2538.64, "total_tokens": 408864} +{"current_steps": 710, "total_steps": 67140, "loss": 0.8417, "lr": 5.2800119154006555e-06, "epoch": 0.10574918081620495, "percentage": 1.06, "elapsed_time": "0:02:42", "remaining_time": "4:12:53", "throughput": 2538.17, "total_tokens": 411616} +{"current_steps": 715, "total_steps": 67140, "loss": 0.8854, "lr": 5.317247542448615e-06, "epoch": 0.10649389335716414, "percentage": 1.06, "elapsed_time": "0:02:43", "remaining_time": "4:12:53", "throughput": 2538.08, "total_tokens": 414528} +{"current_steps": 720, "total_steps": 67140, "loss": 0.8461, "lr": 5.354483169496575e-06, "epoch": 0.10723860589812333, "percentage": 1.07, "elapsed_time": "0:02:44", "remaining_time": "4:12:51", "throughput": 2538.25, "total_tokens": 417440} +{"current_steps": 725, "total_steps": 67140, "loss": 0.7645, "lr": 5.391718796544534e-06, "epoch": 0.10798331843908252, "percentage": 1.08, "elapsed_time": "0:02:45", "remaining_time": "4:12:49", "throughput": 2538.11, "total_tokens": 420288} +{"current_steps": 730, "total_steps": 67140, "loss": 0.9127, "lr": 5.428954423592494e-06, "epoch": 0.1087280309800417, "percentage": 1.09, "elapsed_time": "0:02:46", "remaining_time": "4:12:47", "throughput": 2538.06, "total_tokens": 423168} +{"current_steps": 735, "total_steps": 67140, "loss": 0.8004, "lr": 5.466190050640453e-06, "epoch": 0.10947274352100089, "percentage": 1.09, "elapsed_time": "0:02:47", "remaining_time": "4:12:46", "throughput": 2538.68, "total_tokens": 426176} +{"current_steps": 740, "total_steps": 67140, "loss": 0.8383, "lr": 5.503425677688413e-06, "epoch": 0.11021745606196008, "percentage": 1.1, "elapsed_time": "0:02:49", "remaining_time": "4:12:49", "throughput": 2539.69, "total_tokens": 429344} +{"current_steps": 745, "total_steps": 67140, "loss": 0.8357, "lr": 5.540661304736372e-06, "epoch": 0.11096216860291927, "percentage": 1.11, "elapsed_time": "0:02:50", "remaining_time": "4:12:43", "throughput": 2539.15, "total_tokens": 432032} +{"current_steps": 750, "total_steps": 67140, "loss": 0.9268, "lr": 5.577896931784332e-06, "epoch": 0.11170688114387846, "percentage": 1.12, "elapsed_time": "0:02:51", "remaining_time": "4:12:40", "throughput": 2538.66, "total_tokens": 434784} +{"current_steps": 755, "total_steps": 67140, "loss": 0.8091, "lr": 5.615132558832291e-06, "epoch": 0.11245159368483765, "percentage": 1.12, "elapsed_time": "0:02:52", "remaining_time": "4:12:42", "throughput": 2539.71, "total_tokens": 437952} +{"current_steps": 760, "total_steps": 67140, "loss": 0.8245, "lr": 5.652368185880251e-06, "epoch": 0.11319630622579684, "percentage": 1.13, "elapsed_time": "0:02:53", "remaining_time": "4:12:39", "throughput": 2539.01, "total_tokens": 440672} +{"current_steps": 765, "total_steps": 67140, "loss": 0.9108, "lr": 5.68960381292821e-06, "epoch": 0.11394101876675604, "percentage": 1.14, "elapsed_time": "0:02:54", "remaining_time": "4:12:39", "throughput": 2539.36, "total_tokens": 443680} +{"current_steps": 770, "total_steps": 67140, "loss": 0.849, "lr": 5.7268394399761695e-06, "epoch": 0.11468573130771523, "percentage": 1.15, "elapsed_time": "0:02:55", "remaining_time": "4:12:35", "throughput": 2538.87, "total_tokens": 446400} +{"current_steps": 775, "total_steps": 67140, "loss": 0.8606, "lr": 5.7640750670241285e-06, "epoch": 0.11543044384867442, "percentage": 1.15, "elapsed_time": "0:02:56", "remaining_time": "4:12:32", "throughput": 2538.47, "total_tokens": 449184} +{"current_steps": 780, "total_steps": 67140, "loss": 0.8904, "lr": 5.801310694072089e-06, "epoch": 0.1161751563896336, "percentage": 1.16, "elapsed_time": "0:02:58", "remaining_time": "4:12:29", "throughput": 2538.47, "total_tokens": 452032} +{"current_steps": 785, "total_steps": 67140, "loss": 0.9192, "lr": 5.838546321120048e-06, "epoch": 0.1169198689305928, "percentage": 1.17, "elapsed_time": "0:02:59", "remaining_time": "4:12:30", "throughput": 2538.96, "total_tokens": 455072} +{"current_steps": 790, "total_steps": 67140, "loss": 0.8831, "lr": 5.875781948168008e-06, "epoch": 0.11766458147155198, "percentage": 1.18, "elapsed_time": "0:03:00", "remaining_time": "4:12:26", "throughput": 2538.31, "total_tokens": 457760} +{"current_steps": 795, "total_steps": 67140, "loss": 0.8503, "lr": 5.913017575215967e-06, "epoch": 0.11840929401251117, "percentage": 1.18, "elapsed_time": "0:03:01", "remaining_time": "4:12:23", "throughput": 2538.3, "total_tokens": 460608} +{"current_steps": 800, "total_steps": 67140, "loss": 0.7846, "lr": 5.950253202263927e-06, "epoch": 0.11915400655347036, "percentage": 1.19, "elapsed_time": "0:03:02", "remaining_time": "4:12:23", "throughput": 2537.94, "total_tokens": 463456} +{"current_steps": 805, "total_steps": 67140, "loss": 0.8532, "lr": 5.987488829311886e-06, "epoch": 0.11989871909442955, "percentage": 1.2, "elapsed_time": "0:03:03", "remaining_time": "4:12:20", "throughput": 2538.05, "total_tokens": 466336} +{"current_steps": 810, "total_steps": 67140, "loss": 0.8915, "lr": 6.024724456359846e-06, "epoch": 0.12064343163538874, "percentage": 1.21, "elapsed_time": "0:03:04", "remaining_time": "4:12:19", "throughput": 2538.33, "total_tokens": 469280} +{"current_steps": 815, "total_steps": 67140, "loss": 0.8188, "lr": 6.061960083407805e-06, "epoch": 0.12138814417634793, "percentage": 1.21, "elapsed_time": "0:03:06", "remaining_time": "4:12:17", "throughput": 2538.1, "total_tokens": 472096} +{"current_steps": 820, "total_steps": 67140, "loss": 0.8545, "lr": 6.099195710455765e-06, "epoch": 0.12213285671730711, "percentage": 1.22, "elapsed_time": "0:03:07", "remaining_time": "4:12:14", "throughput": 2538.04, "total_tokens": 474944} +{"current_steps": 825, "total_steps": 67140, "loss": 0.8171, "lr": 6.136431337503724e-06, "epoch": 0.1228775692582663, "percentage": 1.23, "elapsed_time": "0:03:08", "remaining_time": "4:12:12", "throughput": 2537.53, "total_tokens": 477696} +{"current_steps": 830, "total_steps": 67140, "loss": 0.8097, "lr": 6.1736669645516834e-06, "epoch": 0.1236222817992255, "percentage": 1.24, "elapsed_time": "0:03:09", "remaining_time": "4:12:12", "throughput": 2537.76, "total_tokens": 480672} +{"current_steps": 835, "total_steps": 67140, "loss": 0.8718, "lr": 6.2109025915996425e-06, "epoch": 0.1243669943401847, "percentage": 1.24, "elapsed_time": "0:03:10", "remaining_time": "4:12:12", "throughput": 2538.18, "total_tokens": 483712} +{"current_steps": 840, "total_steps": 67140, "loss": 0.8227, "lr": 6.248138218647602e-06, "epoch": 0.12511170688114387, "percentage": 1.25, "elapsed_time": "0:03:11", "remaining_time": "4:12:10", "throughput": 2538.06, "total_tokens": 486528} +{"current_steps": 845, "total_steps": 67140, "loss": 0.7903, "lr": 6.285373845695562e-06, "epoch": 0.12585641942210307, "percentage": 1.26, "elapsed_time": "0:03:12", "remaining_time": "4:12:05", "throughput": 2537.44, "total_tokens": 489184} +{"current_steps": 850, "total_steps": 67140, "loss": 0.8724, "lr": 6.322609472743521e-06, "epoch": 0.12660113196306225, "percentage": 1.27, "elapsed_time": "0:03:13", "remaining_time": "4:12:04", "throughput": 2537.42, "total_tokens": 492096} +{"current_steps": 855, "total_steps": 67140, "loss": 0.937, "lr": 6.359845099791481e-06, "epoch": 0.12734584450402145, "percentage": 1.27, "elapsed_time": "0:03:15", "remaining_time": "4:12:06", "throughput": 2537.9, "total_tokens": 495168} +{"current_steps": 860, "total_steps": 67140, "loss": 0.8293, "lr": 6.39708072683944e-06, "epoch": 0.12809055704498062, "percentage": 1.28, "elapsed_time": "0:03:16", "remaining_time": "4:12:04", "throughput": 2538.17, "total_tokens": 498112} +{"current_steps": 865, "total_steps": 67140, "loss": 0.8206, "lr": 6.4343163538874e-06, "epoch": 0.12883526958593983, "percentage": 1.29, "elapsed_time": "0:03:17", "remaining_time": "4:12:07", "throughput": 2538.62, "total_tokens": 501216} +{"current_steps": 870, "total_steps": 67140, "loss": 0.7863, "lr": 6.471551980935359e-06, "epoch": 0.12957998212689903, "percentage": 1.3, "elapsed_time": "0:03:18", "remaining_time": "4:12:04", "throughput": 2538.3, "total_tokens": 504000} +{"current_steps": 875, "total_steps": 67140, "loss": 0.8806, "lr": 6.508787607983319e-06, "epoch": 0.1303246946678582, "percentage": 1.3, "elapsed_time": "0:03:19", "remaining_time": "4:12:02", "throughput": 2538.53, "total_tokens": 506912} +{"current_steps": 880, "total_steps": 67140, "loss": 0.8242, "lr": 6.546023235031279e-06, "epoch": 0.1310694072088174, "percentage": 1.31, "elapsed_time": "0:03:20", "remaining_time": "4:12:00", "throughput": 2538.21, "total_tokens": 509696} +{"current_steps": 885, "total_steps": 67140, "loss": 0.8784, "lr": 6.583258862079238e-06, "epoch": 0.13181411974977658, "percentage": 1.32, "elapsed_time": "0:03:21", "remaining_time": "4:11:58", "throughput": 2538.08, "total_tokens": 512544} +{"current_steps": 890, "total_steps": 67140, "loss": 1.013, "lr": 6.6204944891271974e-06, "epoch": 0.13255883229073578, "percentage": 1.33, "elapsed_time": "0:03:23", "remaining_time": "4:11:55", "throughput": 2538.08, "total_tokens": 515392} +{"current_steps": 895, "total_steps": 67140, "loss": 0.8238, "lr": 6.6577301161751565e-06, "epoch": 0.13330354483169496, "percentage": 1.33, "elapsed_time": "0:03:24", "remaining_time": "4:11:56", "throughput": 2539.08, "total_tokens": 518560} +{"current_steps": 900, "total_steps": 67140, "loss": 0.8272, "lr": 6.694965743223116e-06, "epoch": 0.13404825737265416, "percentage": 1.34, "elapsed_time": "0:03:25", "remaining_time": "4:11:54", "throughput": 2539.2, "total_tokens": 521440} +{"current_steps": 905, "total_steps": 67140, "loss": 0.8323, "lr": 6.732201370271075e-06, "epoch": 0.13479296991361334, "percentage": 1.35, "elapsed_time": "0:03:26", "remaining_time": "4:11:52", "throughput": 2539.32, "total_tokens": 524352} +{"current_steps": 910, "total_steps": 67140, "loss": 1.0111, "lr": 6.769436997319035e-06, "epoch": 0.13553768245457254, "percentage": 1.36, "elapsed_time": "0:03:27", "remaining_time": "4:11:57", "throughput": 2540.97, "total_tokens": 527808} +{"current_steps": 915, "total_steps": 67140, "loss": 1.2627, "lr": 6.806672624366994e-06, "epoch": 0.1362823949955317, "percentage": 1.36, "elapsed_time": "0:03:28", "remaining_time": "4:11:55", "throughput": 2541.06, "total_tokens": 530688} +{"current_steps": 920, "total_steps": 67140, "loss": 0.9499, "lr": 6.843908251414954e-06, "epoch": 0.13702710753649092, "percentage": 1.37, "elapsed_time": "0:03:29", "remaining_time": "4:11:52", "throughput": 2540.51, "total_tokens": 533408} +{"current_steps": 925, "total_steps": 67140, "loss": 0.8445, "lr": 6.881143878462913e-06, "epoch": 0.1377718200774501, "percentage": 1.38, "elapsed_time": "0:03:31", "remaining_time": "4:11:52", "throughput": 2541.08, "total_tokens": 536480} +{"current_steps": 930, "total_steps": 67140, "loss": 0.8811, "lr": 6.918379505510873e-06, "epoch": 0.1385165326184093, "percentage": 1.39, "elapsed_time": "0:03:32", "remaining_time": "4:11:47", "throughput": 2540.3, "total_tokens": 539072} +{"current_steps": 935, "total_steps": 67140, "loss": 1.0344, "lr": 6.955615132558832e-06, "epoch": 0.1392612451593685, "percentage": 1.39, "elapsed_time": "0:03:33", "remaining_time": "4:11:49", "throughput": 2541.02, "total_tokens": 542208} +{"current_steps": 940, "total_steps": 67140, "loss": 0.9861, "lr": 6.992850759606792e-06, "epoch": 0.14000595770032767, "percentage": 1.4, "elapsed_time": "0:03:34", "remaining_time": "4:11:48", "throughput": 2541.2, "total_tokens": 545152} +{"current_steps": 945, "total_steps": 67140, "loss": 0.941, "lr": 7.0300863866547524e-06, "epoch": 0.14075067024128687, "percentage": 1.41, "elapsed_time": "0:03:35", "remaining_time": "4:11:43", "throughput": 2540.55, "total_tokens": 547776} +{"current_steps": 950, "total_steps": 67140, "loss": 0.8363, "lr": 7.067322013702711e-06, "epoch": 0.14149538278224605, "percentage": 1.41, "elapsed_time": "0:03:36", "remaining_time": "4:11:40", "throughput": 2540.65, "total_tokens": 550656} +{"current_steps": 955, "total_steps": 67140, "loss": 0.858, "lr": 7.104557640750671e-06, "epoch": 0.14224009532320525, "percentage": 1.42, "elapsed_time": "0:03:37", "remaining_time": "4:11:37", "throughput": 2540.27, "total_tokens": 553376} +{"current_steps": 960, "total_steps": 67140, "loss": 0.8051, "lr": 7.14179326779863e-06, "epoch": 0.14298480786416443, "percentage": 1.43, "elapsed_time": "0:03:39", "remaining_time": "4:11:38", "throughput": 2540.91, "total_tokens": 556512} +{"current_steps": 965, "total_steps": 67140, "loss": 0.9369, "lr": 7.17902889484659e-06, "epoch": 0.14372952040512363, "percentage": 1.44, "elapsed_time": "0:03:40", "remaining_time": "4:11:39", "throughput": 2541.16, "total_tokens": 559520} +{"current_steps": 970, "total_steps": 67140, "loss": 0.8294, "lr": 7.216264521894549e-06, "epoch": 0.1444742329460828, "percentage": 1.44, "elapsed_time": "0:03:41", "remaining_time": "4:11:37", "throughput": 2541.39, "total_tokens": 562464} +{"current_steps": 975, "total_steps": 67140, "loss": 0.8835, "lr": 7.253500148942509e-06, "epoch": 0.145218945487042, "percentage": 1.45, "elapsed_time": "0:03:42", "remaining_time": "4:11:33", "throughput": 2540.16, "total_tokens": 564960} +{"current_steps": 980, "total_steps": 67140, "loss": 0.8255, "lr": 7.290735775990468e-06, "epoch": 0.14596365802800118, "percentage": 1.46, "elapsed_time": "0:03:43", "remaining_time": "4:11:33", "throughput": 2540.73, "total_tokens": 568032} +{"current_steps": 985, "total_steps": 67140, "loss": 0.8602, "lr": 7.327971403038428e-06, "epoch": 0.14670837056896038, "percentage": 1.47, "elapsed_time": "0:03:44", "remaining_time": "4:11:32", "throughput": 2540.64, "total_tokens": 570912} +{"current_steps": 990, "total_steps": 67140, "loss": 0.8323, "lr": 7.365207030086387e-06, "epoch": 0.14745308310991956, "percentage": 1.47, "elapsed_time": "0:03:45", "remaining_time": "4:11:29", "throughput": 2540.34, "total_tokens": 573696} +{"current_steps": 995, "total_steps": 67140, "loss": 0.8355, "lr": 7.402442657134347e-06, "epoch": 0.14819779565087876, "percentage": 1.48, "elapsed_time": "0:03:46", "remaining_time": "4:11:27", "throughput": 2539.97, "total_tokens": 576480} +{"current_steps": 1000, "total_steps": 67140, "loss": 0.8182, "lr": 7.439678284182306e-06, "epoch": 0.14894250819183796, "percentage": 1.49, "elapsed_time": "0:03:48", "remaining_time": "4:11:27", "throughput": 2540.14, "total_tokens": 579424} +{"current_steps": 1005, "total_steps": 67140, "loss": 0.7963, "lr": 7.476913911230266e-06, "epoch": 0.14968722073279714, "percentage": 1.5, "elapsed_time": "0:03:49", "remaining_time": "4:11:25", "throughput": 2540.42, "total_tokens": 582368} +{"current_steps": 1010, "total_steps": 67140, "loss": 0.8412, "lr": 7.5141495382782254e-06, "epoch": 0.15043193327375634, "percentage": 1.5, "elapsed_time": "0:03:50", "remaining_time": "4:11:25", "throughput": 2540.8, "total_tokens": 585408} +{"current_steps": 1015, "total_steps": 67140, "loss": 0.8297, "lr": 7.5513851653261844e-06, "epoch": 0.15117664581471552, "percentage": 1.51, "elapsed_time": "0:03:51", "remaining_time": "4:11:24", "throughput": 2540.74, "total_tokens": 588288} +{"current_steps": 1020, "total_steps": 67140, "loss": 0.8484, "lr": 7.588620792374144e-06, "epoch": 0.15192135835567472, "percentage": 1.52, "elapsed_time": "0:03:52", "remaining_time": "4:11:22", "throughput": 2540.94, "total_tokens": 591200} +{"current_steps": 1025, "total_steps": 67140, "loss": 0.8566, "lr": 7.625856419422103e-06, "epoch": 0.1526660708966339, "percentage": 1.53, "elapsed_time": "0:03:53", "remaining_time": "4:11:21", "throughput": 2540.76, "total_tokens": 594048} +{"current_steps": 1030, "total_steps": 67140, "loss": 0.8359, "lr": 7.663092046470063e-06, "epoch": 0.1534107834375931, "percentage": 1.53, "elapsed_time": "0:03:54", "remaining_time": "4:11:19", "throughput": 2541.09, "total_tokens": 597024} +{"current_steps": 1035, "total_steps": 67140, "loss": 0.8339, "lr": 7.700327673518021e-06, "epoch": 0.15415549597855227, "percentage": 1.54, "elapsed_time": "0:03:56", "remaining_time": "4:11:18", "throughput": 2540.8, "total_tokens": 599840} +{"current_steps": 1040, "total_steps": 67140, "loss": 0.8462, "lr": 7.737563300565983e-06, "epoch": 0.15490020851951147, "percentage": 1.55, "elapsed_time": "0:03:57", "remaining_time": "4:11:15", "throughput": 2540.73, "total_tokens": 602656} +{"current_steps": 1045, "total_steps": 67140, "loss": 0.8547, "lr": 7.774798927613941e-06, "epoch": 0.15564492106047065, "percentage": 1.56, "elapsed_time": "0:03:58", "remaining_time": "4:11:15", "throughput": 2541.37, "total_tokens": 605760} +{"current_steps": 1050, "total_steps": 67140, "loss": 0.7948, "lr": 7.812034554661901e-06, "epoch": 0.15638963360142985, "percentage": 1.56, "elapsed_time": "0:03:59", "remaining_time": "4:11:12", "throughput": 2540.84, "total_tokens": 608448} +{"current_steps": 1055, "total_steps": 67140, "loss": 0.8331, "lr": 7.84927018170986e-06, "epoch": 0.15713434614238903, "percentage": 1.57, "elapsed_time": "0:04:00", "remaining_time": "4:11:10", "throughput": 2540.78, "total_tokens": 611296} +{"current_steps": 1060, "total_steps": 67140, "loss": 0.8671, "lr": 7.88650580875782e-06, "epoch": 0.15787905868334823, "percentage": 1.58, "elapsed_time": "0:04:01", "remaining_time": "4:11:10", "throughput": 2540.94, "total_tokens": 614272} +{"current_steps": 1065, "total_steps": 67140, "loss": 0.8171, "lr": 7.923741435805779e-06, "epoch": 0.15862377122430743, "percentage": 1.59, "elapsed_time": "0:04:02", "remaining_time": "4:11:12", "throughput": 2541.84, "total_tokens": 617504} +{"current_steps": 1070, "total_steps": 67140, "loss": 0.8654, "lr": 7.960977062853739e-06, "epoch": 0.1593684837652666, "percentage": 1.59, "elapsed_time": "0:04:04", "remaining_time": "4:11:10", "throughput": 2541.9, "total_tokens": 620384} +{"current_steps": 1075, "total_steps": 67140, "loss": 0.8811, "lr": 7.998212689901698e-06, "epoch": 0.1601131963062258, "percentage": 1.6, "elapsed_time": "0:04:05", "remaining_time": "4:11:09", "throughput": 2542.16, "total_tokens": 623360} +{"current_steps": 1080, "total_steps": 67140, "loss": 0.7593, "lr": 8.035448316949658e-06, "epoch": 0.16085790884718498, "percentage": 1.61, "elapsed_time": "0:04:06", "remaining_time": "4:11:09", "throughput": 2542.33, "total_tokens": 626336} +{"current_steps": 1085, "total_steps": 67140, "loss": 0.9517, "lr": 8.072683943997618e-06, "epoch": 0.16160262138814419, "percentage": 1.62, "elapsed_time": "0:04:07", "remaining_time": "4:11:10", "throughput": 2542.88, "total_tokens": 629472} +{"current_steps": 1090, "total_steps": 67140, "loss": 0.8841, "lr": 8.109919571045576e-06, "epoch": 0.16234733392910336, "percentage": 1.62, "elapsed_time": "0:04:08", "remaining_time": "4:11:10", "throughput": 2543.54, "total_tokens": 632608} +{"current_steps": 1095, "total_steps": 67140, "loss": 0.8225, "lr": 8.147155198093536e-06, "epoch": 0.16309204647006256, "percentage": 1.63, "elapsed_time": "0:04:09", "remaining_time": "4:11:10", "throughput": 2544.04, "total_tokens": 635680} +{"current_steps": 1100, "total_steps": 67140, "loss": 0.8263, "lr": 8.184390825141496e-06, "epoch": 0.16383675901102174, "percentage": 1.64, "elapsed_time": "0:04:10", "remaining_time": "4:11:06", "throughput": 2543.43, "total_tokens": 638304} +{"current_steps": 1105, "total_steps": 67140, "loss": 0.809, "lr": 8.221626452189456e-06, "epoch": 0.16458147155198094, "percentage": 1.65, "elapsed_time": "0:04:12", "remaining_time": "4:11:06", "throughput": 2543.79, "total_tokens": 641312} +{"current_steps": 1110, "total_steps": 67140, "loss": 0.8291, "lr": 8.258862079237414e-06, "epoch": 0.16532618409294011, "percentage": 1.65, "elapsed_time": "0:04:13", "remaining_time": "4:11:04", "throughput": 2543.64, "total_tokens": 644160} +{"current_steps": 1115, "total_steps": 67140, "loss": 0.7995, "lr": 8.296097706285374e-06, "epoch": 0.16607089663389932, "percentage": 1.66, "elapsed_time": "0:04:14", "remaining_time": "4:11:02", "throughput": 2543.28, "total_tokens": 646912} +{"current_steps": 1120, "total_steps": 67140, "loss": 0.8182, "lr": 8.333333333333334e-06, "epoch": 0.1668156091748585, "percentage": 1.67, "elapsed_time": "0:04:15", "remaining_time": "4:11:01", "throughput": 2543.43, "total_tokens": 649888} +{"current_steps": 1125, "total_steps": 67140, "loss": 0.8387, "lr": 8.370568960381294e-06, "epoch": 0.1675603217158177, "percentage": 1.68, "elapsed_time": "0:04:16", "remaining_time": "4:10:58", "throughput": 2543.26, "total_tokens": 652672} +{"current_steps": 1130, "total_steps": 67140, "loss": 0.8526, "lr": 8.407804587429252e-06, "epoch": 0.1683050342567769, "percentage": 1.68, "elapsed_time": "0:04:17", "remaining_time": "4:10:52", "throughput": 2542.18, "total_tokens": 655072} +{"current_steps": 1135, "total_steps": 67140, "loss": 0.8242, "lr": 8.445040214477212e-06, "epoch": 0.16904974679773607, "percentage": 1.69, "elapsed_time": "0:04:18", "remaining_time": "4:10:52", "throughput": 2542.53, "total_tokens": 658112} +{"current_steps": 1140, "total_steps": 67140, "loss": 0.8324, "lr": 8.482275841525171e-06, "epoch": 0.16979445933869527, "percentage": 1.7, "elapsed_time": "0:04:19", "remaining_time": "4:10:51", "throughput": 2542.6, "total_tokens": 661024} +{"current_steps": 1145, "total_steps": 67140, "loss": 0.8499, "lr": 8.519511468573131e-06, "epoch": 0.17053917187965445, "percentage": 1.71, "elapsed_time": "0:04:21", "remaining_time": "4:10:49", "throughput": 2542.78, "total_tokens": 663936} +{"current_steps": 1150, "total_steps": 67140, "loss": 0.7932, "lr": 8.556747095621091e-06, "epoch": 0.17128388442061365, "percentage": 1.71, "elapsed_time": "0:04:22", "remaining_time": "4:10:47", "throughput": 2542.73, "total_tokens": 666784} +{"current_steps": 1155, "total_steps": 67140, "loss": 0.8933, "lr": 8.59398272266905e-06, "epoch": 0.17202859696157283, "percentage": 1.72, "elapsed_time": "0:04:23", "remaining_time": "4:10:48", "throughput": 2543.49, "total_tokens": 669984} +{"current_steps": 1160, "total_steps": 67140, "loss": 0.8481, "lr": 8.631218349717011e-06, "epoch": 0.17277330950253203, "percentage": 1.73, "elapsed_time": "0:04:24", "remaining_time": "4:10:46", "throughput": 2542.92, "total_tokens": 672672} +{"current_steps": 1165, "total_steps": 67140, "loss": 0.8239, "lr": 8.668453976764969e-06, "epoch": 0.1735180220434912, "percentage": 1.74, "elapsed_time": "0:04:25", "remaining_time": "4:10:44", "throughput": 2543.05, "total_tokens": 675584} +{"current_steps": 1170, "total_steps": 67140, "loss": 0.8391, "lr": 8.705689603812929e-06, "epoch": 0.1742627345844504, "percentage": 1.74, "elapsed_time": "0:04:26", "remaining_time": "4:10:42", "throughput": 2542.69, "total_tokens": 678336} +{"current_steps": 1175, "total_steps": 67140, "loss": 0.8445, "lr": 8.742925230860887e-06, "epoch": 0.17500744712540958, "percentage": 1.75, "elapsed_time": "0:04:27", "remaining_time": "4:10:40", "throughput": 2542.39, "total_tokens": 681120} +{"current_steps": 1180, "total_steps": 67140, "loss": 0.8338, "lr": 8.780160857908849e-06, "epoch": 0.17575215966636878, "percentage": 1.76, "elapsed_time": "0:04:29", "remaining_time": "4:10:38", "throughput": 2542.12, "total_tokens": 683936} +{"current_steps": 1185, "total_steps": 67140, "loss": 0.8039, "lr": 8.817396484956807e-06, "epoch": 0.17649687220732796, "percentage": 1.76, "elapsed_time": "0:04:30", "remaining_time": "4:10:37", "throughput": 2542.1, "total_tokens": 686816} +{"current_steps": 1190, "total_steps": 67140, "loss": 0.8206, "lr": 8.854632112004767e-06, "epoch": 0.17724158474828716, "percentage": 1.77, "elapsed_time": "0:04:31", "remaining_time": "4:10:35", "throughput": 2542.02, "total_tokens": 689664} +{"current_steps": 1195, "total_steps": 67140, "loss": 0.8445, "lr": 8.891867739052725e-06, "epoch": 0.17798629728924636, "percentage": 1.78, "elapsed_time": "0:04:32", "remaining_time": "4:10:32", "throughput": 2541.49, "total_tokens": 692320} +{"current_steps": 1200, "total_steps": 67140, "loss": 0.7734, "lr": 8.929103366100686e-06, "epoch": 0.17873100983020554, "percentage": 1.79, "elapsed_time": "0:04:33", "remaining_time": "4:10:30", "throughput": 2541.34, "total_tokens": 695136} +{"current_steps": 1205, "total_steps": 67140, "loss": 0.8254, "lr": 8.966338993148644e-06, "epoch": 0.17947572237116474, "percentage": 1.79, "elapsed_time": "0:04:34", "remaining_time": "4:10:29", "throughput": 2541.38, "total_tokens": 698048} +{"current_steps": 1210, "total_steps": 67140, "loss": 0.7267, "lr": 9.003574620196604e-06, "epoch": 0.18022043491212392, "percentage": 1.8, "elapsed_time": "0:04:35", "remaining_time": "4:10:27", "throughput": 2541.22, "total_tokens": 700864} +{"current_steps": 1215, "total_steps": 67140, "loss": 0.8714, "lr": 9.040810247244564e-06, "epoch": 0.18096514745308312, "percentage": 1.81, "elapsed_time": "0:04:36", "remaining_time": "4:10:27", "throughput": 2541.43, "total_tokens": 703872} +{"current_steps": 1220, "total_steps": 67140, "loss": 0.8595, "lr": 9.078045874292524e-06, "epoch": 0.1817098599940423, "percentage": 1.82, "elapsed_time": "0:04:38", "remaining_time": "4:10:24", "throughput": 2540.83, "total_tokens": 706496} +{"current_steps": 1225, "total_steps": 67140, "loss": 0.8288, "lr": 9.115281501340484e-06, "epoch": 0.1824545725350015, "percentage": 1.82, "elapsed_time": "0:04:39", "remaining_time": "4:10:23", "throughput": 2540.86, "total_tokens": 709440} +{"current_steps": 1230, "total_steps": 67140, "loss": 0.7957, "lr": 9.152517128388442e-06, "epoch": 0.18319928507596067, "percentage": 1.83, "elapsed_time": "0:04:40", "remaining_time": "4:10:21", "throughput": 2540.38, "total_tokens": 712128} +{"current_steps": 1235, "total_steps": 67140, "loss": 0.8156, "lr": 9.189752755436402e-06, "epoch": 0.18394399761691987, "percentage": 1.84, "elapsed_time": "0:04:41", "remaining_time": "4:10:19", "throughput": 2540.05, "total_tokens": 714912} +{"current_steps": 1240, "total_steps": 67140, "loss": 0.8507, "lr": 9.226988382484362e-06, "epoch": 0.18468871015787905, "percentage": 1.85, "elapsed_time": "0:04:42", "remaining_time": "4:10:16", "throughput": 2539.49, "total_tokens": 717568} +{"current_steps": 1245, "total_steps": 67140, "loss": 0.8844, "lr": 9.264224009532322e-06, "epoch": 0.18543342269883825, "percentage": 1.85, "elapsed_time": "0:04:43", "remaining_time": "4:10:17", "throughput": 2540.05, "total_tokens": 720704} +{"current_steps": 1250, "total_steps": 67140, "loss": 0.837, "lr": 9.30145963658028e-06, "epoch": 0.18617813523979743, "percentage": 1.86, "elapsed_time": "0:04:44", "remaining_time": "4:10:17", "throughput": 2540.22, "total_tokens": 723680} +{"current_steps": 1255, "total_steps": 67140, "loss": 0.8201, "lr": 9.33869526362824e-06, "epoch": 0.18692284778075663, "percentage": 1.87, "elapsed_time": "0:04:46", "remaining_time": "4:10:15", "throughput": 2540.36, "total_tokens": 726592} +{"current_steps": 1260, "total_steps": 67140, "loss": 0.8252, "lr": 9.3759308906762e-06, "epoch": 0.1876675603217158, "percentage": 1.88, "elapsed_time": "0:04:47", "remaining_time": "4:10:14", "throughput": 2540.51, "total_tokens": 729536} +{"current_steps": 1265, "total_steps": 67140, "loss": 0.8171, "lr": 9.41316651772416e-06, "epoch": 0.188412272862675, "percentage": 1.88, "elapsed_time": "0:04:48", "remaining_time": "4:10:14", "throughput": 2540.67, "total_tokens": 732544} +{"current_steps": 1270, "total_steps": 67140, "loss": 0.7818, "lr": 9.450402144772117e-06, "epoch": 0.1891569854036342, "percentage": 1.89, "elapsed_time": "0:04:49", "remaining_time": "4:10:16", "throughput": 2541.16, "total_tokens": 735712} +{"current_steps": 1275, "total_steps": 67140, "loss": 0.8475, "lr": 9.487637771820077e-06, "epoch": 0.18990169794459338, "percentage": 1.9, "elapsed_time": "0:04:50", "remaining_time": "4:10:12", "throughput": 2540.56, "total_tokens": 738304} +{"current_steps": 1280, "total_steps": 67140, "loss": 0.8415, "lr": 9.524873398868039e-06, "epoch": 0.1906464104855526, "percentage": 1.91, "elapsed_time": "0:04:51", "remaining_time": "4:10:11", "throughput": 2540.63, "total_tokens": 741248} +{"current_steps": 1285, "total_steps": 67140, "loss": 0.847, "lr": 9.562109025915997e-06, "epoch": 0.19139112302651176, "percentage": 1.91, "elapsed_time": "0:04:52", "remaining_time": "4:10:10", "throughput": 2540.89, "total_tokens": 744192} +{"current_steps": 1290, "total_steps": 67140, "loss": 0.804, "lr": 9.599344652963957e-06, "epoch": 0.19213583556747096, "percentage": 1.92, "elapsed_time": "0:04:54", "remaining_time": "4:10:09", "throughput": 2540.9, "total_tokens": 747104} +{"current_steps": 1295, "total_steps": 67140, "loss": 0.819, "lr": 9.636580280011915e-06, "epoch": 0.19288054810843014, "percentage": 1.93, "elapsed_time": "0:04:55", "remaining_time": "4:10:09", "throughput": 2540.87, "total_tokens": 750048} +{"current_steps": 1300, "total_steps": 67140, "loss": 0.7809, "lr": 9.673815907059877e-06, "epoch": 0.19362526064938934, "percentage": 1.94, "elapsed_time": "0:04:56", "remaining_time": "4:10:08", "throughput": 2540.93, "total_tokens": 752992} +{"current_steps": 1305, "total_steps": 67140, "loss": 0.7859, "lr": 9.711051534107835e-06, "epoch": 0.19436997319034852, "percentage": 1.94, "elapsed_time": "0:04:57", "remaining_time": "4:10:06", "throughput": 2541.09, "total_tokens": 755904} +{"current_steps": 1310, "total_steps": 67140, "loss": 0.8247, "lr": 9.748287161155795e-06, "epoch": 0.19511468573130772, "percentage": 1.95, "elapsed_time": "0:04:58", "remaining_time": "4:10:05", "throughput": 2540.96, "total_tokens": 758752} +{"current_steps": 1315, "total_steps": 67140, "loss": 0.8407, "lr": 9.785522788203753e-06, "epoch": 0.1958593982722669, "percentage": 1.96, "elapsed_time": "0:04:59", "remaining_time": "4:10:01", "throughput": 2540.46, "total_tokens": 761344} +{"current_steps": 1320, "total_steps": 67140, "loss": 0.8161, "lr": 9.822758415251714e-06, "epoch": 0.1966041108132261, "percentage": 1.97, "elapsed_time": "0:05:00", "remaining_time": "4:09:59", "throughput": 2540.33, "total_tokens": 764160} +{"current_steps": 1325, "total_steps": 67140, "loss": 0.7901, "lr": 9.859994042299672e-06, "epoch": 0.19734882335418527, "percentage": 1.97, "elapsed_time": "0:05:01", "remaining_time": "4:09:58", "throughput": 2540.48, "total_tokens": 767104} +{"current_steps": 1330, "total_steps": 67140, "loss": 0.8739, "lr": 9.897229669347632e-06, "epoch": 0.19809353589514447, "percentage": 1.98, "elapsed_time": "0:05:03", "remaining_time": "4:09:55", "throughput": 2540.14, "total_tokens": 769824} +{"current_steps": 1335, "total_steps": 67140, "loss": 0.8477, "lr": 9.93446529639559e-06, "epoch": 0.19883824843610368, "percentage": 1.99, "elapsed_time": "0:05:04", "remaining_time": "4:09:53", "throughput": 2539.82, "total_tokens": 772544} +{"current_steps": 1340, "total_steps": 67140, "loss": 0.8241, "lr": 9.971700923443552e-06, "epoch": 0.19958296097706285, "percentage": 2.0, "elapsed_time": "0:05:05", "remaining_time": "4:09:51", "throughput": 2539.69, "total_tokens": 775360} +{"current_steps": 1345, "total_steps": 67140, "loss": 0.8642, "lr": 1.0008936550491512e-05, "epoch": 0.20032767351802205, "percentage": 2.0, "elapsed_time": "0:05:06", "remaining_time": "4:09:48", "throughput": 2539.58, "total_tokens": 778144} +{"current_steps": 1350, "total_steps": 67140, "loss": 0.8101, "lr": 1.004617217753947e-05, "epoch": 0.20107238605898123, "percentage": 2.01, "elapsed_time": "0:05:07", "remaining_time": "4:09:46", "throughput": 2539.21, "total_tokens": 780864} +{"current_steps": 1355, "total_steps": 67140, "loss": 0.7915, "lr": 1.008340780458743e-05, "epoch": 0.20181709859994043, "percentage": 2.02, "elapsed_time": "0:05:08", "remaining_time": "4:09:45", "throughput": 2539.34, "total_tokens": 783776} +{"current_steps": 1360, "total_steps": 67140, "loss": 0.8395, "lr": 1.012064343163539e-05, "epoch": 0.2025618111408996, "percentage": 2.03, "elapsed_time": "0:05:09", "remaining_time": "4:09:44", "throughput": 2539.49, "total_tokens": 786752} +{"current_steps": 1365, "total_steps": 67140, "loss": 0.7894, "lr": 1.015787905868335e-05, "epoch": 0.2033065236818588, "percentage": 2.03, "elapsed_time": "0:05:10", "remaining_time": "4:09:42", "throughput": 2539.3, "total_tokens": 789536} +{"current_steps": 1370, "total_steps": 67140, "loss": 0.9203, "lr": 1.0195114685731308e-05, "epoch": 0.20405123622281798, "percentage": 2.04, "elapsed_time": "0:05:12", "remaining_time": "4:09:39", "throughput": 2538.74, "total_tokens": 792160} +{"current_steps": 1375, "total_steps": 67140, "loss": 0.8656, "lr": 1.0232350312779268e-05, "epoch": 0.20479594876377719, "percentage": 2.05, "elapsed_time": "0:05:13", "remaining_time": "4:09:36", "throughput": 2538.56, "total_tokens": 794912} +{"current_steps": 1380, "total_steps": 67140, "loss": 0.8095, "lr": 1.0269585939827227e-05, "epoch": 0.20554066130473636, "percentage": 2.06, "elapsed_time": "0:05:14", "remaining_time": "4:09:36", "throughput": 2538.59, "total_tokens": 797824} +{"current_steps": 1385, "total_steps": 67140, "loss": 0.8024, "lr": 1.0306821566875187e-05, "epoch": 0.20628537384569556, "percentage": 2.06, "elapsed_time": "0:05:15", "remaining_time": "4:09:38", "throughput": 2539.44, "total_tokens": 801184} +{"current_steps": 1390, "total_steps": 67140, "loss": 0.8168, "lr": 1.0344057193923145e-05, "epoch": 0.20703008638665474, "percentage": 2.07, "elapsed_time": "0:05:16", "remaining_time": "4:09:37", "throughput": 2539.33, "total_tokens": 804032} +{"current_steps": 1395, "total_steps": 67140, "loss": 0.8979, "lr": 1.0381292820971105e-05, "epoch": 0.20777479892761394, "percentage": 2.08, "elapsed_time": "0:05:17", "remaining_time": "4:09:36", "throughput": 2539.27, "total_tokens": 806912} +{"current_steps": 1400, "total_steps": 67140, "loss": 0.9699, "lr": 1.0418528448019065e-05, "epoch": 0.20851951146857314, "percentage": 2.09, "elapsed_time": "0:05:18", "remaining_time": "4:09:32", "throughput": 2538.68, "total_tokens": 809472} +{"current_steps": 1405, "total_steps": 67140, "loss": 0.7895, "lr": 1.0455764075067025e-05, "epoch": 0.20926422400953232, "percentage": 2.09, "elapsed_time": "0:05:19", "remaining_time": "4:09:29", "throughput": 2538.07, "total_tokens": 812064} +{"current_steps": 1410, "total_steps": 67140, "loss": 0.7895, "lr": 1.0492999702114985e-05, "epoch": 0.21000893655049152, "percentage": 2.1, "elapsed_time": "0:05:21", "remaining_time": "4:09:30", "throughput": 2538.6, "total_tokens": 815232} +{"current_steps": 1415, "total_steps": 67140, "loss": 0.7866, "lr": 1.0530235329162943e-05, "epoch": 0.2107536490914507, "percentage": 2.11, "elapsed_time": "0:05:22", "remaining_time": "4:09:28", "throughput": 2538.57, "total_tokens": 818080} +{"current_steps": 1420, "total_steps": 67140, "loss": 0.8694, "lr": 1.0567470956210903e-05, "epoch": 0.2114983616324099, "percentage": 2.11, "elapsed_time": "0:05:23", "remaining_time": "4:09:26", "throughput": 2538.35, "total_tokens": 820832} +{"current_steps": 1425, "total_steps": 67140, "loss": 0.7811, "lr": 1.0604706583258863e-05, "epoch": 0.21224307417336907, "percentage": 2.12, "elapsed_time": "0:05:24", "remaining_time": "4:09:23", "throughput": 2538.25, "total_tokens": 823584} +{"current_steps": 1430, "total_steps": 67140, "loss": 0.828, "lr": 1.0641942210306823e-05, "epoch": 0.21298778671432828, "percentage": 2.13, "elapsed_time": "0:05:25", "remaining_time": "4:09:20", "throughput": 2537.77, "total_tokens": 826240} +{"current_steps": 1435, "total_steps": 67140, "loss": 0.7984, "lr": 1.067917783735478e-05, "epoch": 0.21373249925528745, "percentage": 2.14, "elapsed_time": "0:05:26", "remaining_time": "4:09:17", "throughput": 2537.43, "total_tokens": 828928} +{"current_steps": 1440, "total_steps": 67140, "loss": 0.8251, "lr": 1.071641346440274e-05, "epoch": 0.21447721179624665, "percentage": 2.14, "elapsed_time": "0:05:27", "remaining_time": "4:09:18", "throughput": 2538.07, "total_tokens": 832128} +{"current_steps": 1445, "total_steps": 67140, "loss": 0.8323, "lr": 1.07536490914507e-05, "epoch": 0.21522192433720583, "percentage": 2.15, "elapsed_time": "0:05:29", "remaining_time": "4:09:22", "throughput": 2539.1, "total_tokens": 835616} +{"current_steps": 1450, "total_steps": 67140, "loss": 0.8334, "lr": 1.079088471849866e-05, "epoch": 0.21596663687816503, "percentage": 2.16, "elapsed_time": "0:05:30", "remaining_time": "4:09:21", "throughput": 2539.14, "total_tokens": 838528} +{"current_steps": 1455, "total_steps": 67140, "loss": 0.7766, "lr": 1.0828120345546618e-05, "epoch": 0.2167113494191242, "percentage": 2.17, "elapsed_time": "0:05:31", "remaining_time": "4:09:19", "throughput": 2539.2, "total_tokens": 841440} +{"current_steps": 1460, "total_steps": 67140, "loss": 0.9724, "lr": 1.086535597259458e-05, "epoch": 0.2174560619600834, "percentage": 2.17, "elapsed_time": "0:05:32", "remaining_time": "4:09:19", "throughput": 2539.3, "total_tokens": 844416} +{"current_steps": 1465, "total_steps": 67140, "loss": 0.8614, "lr": 1.0902591599642538e-05, "epoch": 0.2182007745010426, "percentage": 2.18, "elapsed_time": "0:05:33", "remaining_time": "4:09:17", "throughput": 2539.13, "total_tokens": 847168} +{"current_steps": 1470, "total_steps": 67140, "loss": 0.8406, "lr": 1.0939827226690498e-05, "epoch": 0.21894548704200179, "percentage": 2.19, "elapsed_time": "0:05:34", "remaining_time": "4:09:16", "throughput": 2539.32, "total_tokens": 850176} +{"current_steps": 1475, "total_steps": 67140, "loss": 0.8328, "lr": 1.0977062853738458e-05, "epoch": 0.219690199582961, "percentage": 2.2, "elapsed_time": "0:05:35", "remaining_time": "4:09:14", "throughput": 2539.24, "total_tokens": 852992} +{"current_steps": 1480, "total_steps": 67140, "loss": 0.8023, "lr": 1.1014298480786418e-05, "epoch": 0.22043491212392016, "percentage": 2.2, "elapsed_time": "0:05:37", "remaining_time": "4:09:13", "throughput": 2539.55, "total_tokens": 855968} +{"current_steps": 1485, "total_steps": 67140, "loss": 1.3279, "lr": 1.1051534107834378e-05, "epoch": 0.22117962466487937, "percentage": 2.21, "elapsed_time": "0:05:38", "remaining_time": "4:09:14", "throughput": 2540.02, "total_tokens": 859136} +{"current_steps": 1490, "total_steps": 67140, "loss": 0.8657, "lr": 1.1088769734882336e-05, "epoch": 0.22192433720583854, "percentage": 2.22, "elapsed_time": "0:05:39", "remaining_time": "4:09:13", "throughput": 2540.24, "total_tokens": 862144} +{"current_steps": 1495, "total_steps": 67140, "loss": 0.8138, "lr": 1.1126005361930296e-05, "epoch": 0.22266904974679774, "percentage": 2.23, "elapsed_time": "0:05:40", "remaining_time": "4:09:14", "throughput": 2541.07, "total_tokens": 865440} +{"current_steps": 1500, "total_steps": 67140, "loss": 0.8344, "lr": 1.1163240988978255e-05, "epoch": 0.22341376228775692, "percentage": 2.23, "elapsed_time": "0:05:41", "remaining_time": "4:09:15", "throughput": 2541.61, "total_tokens": 868640} +{"current_steps": 1505, "total_steps": 67140, "loss": 0.8112, "lr": 1.1200476616026215e-05, "epoch": 0.22415847482871612, "percentage": 2.24, "elapsed_time": "0:05:42", "remaining_time": "4:09:14", "throughput": 2541.64, "total_tokens": 871520} +{"current_steps": 1510, "total_steps": 67140, "loss": 0.8025, "lr": 1.1237712243074173e-05, "epoch": 0.2249031873696753, "percentage": 2.25, "elapsed_time": "0:05:44", "remaining_time": "4:09:12", "throughput": 2541.7, "total_tokens": 874400} +{"current_steps": 1515, "total_steps": 67140, "loss": 0.8041, "lr": 1.1274947870122133e-05, "epoch": 0.2256478999106345, "percentage": 2.26, "elapsed_time": "0:05:45", "remaining_time": "4:09:13", "throughput": 2542.24, "total_tokens": 877600} +{"current_steps": 1520, "total_steps": 67140, "loss": 0.8462, "lr": 1.1312183497170093e-05, "epoch": 0.22639261245159367, "percentage": 2.26, "elapsed_time": "0:05:46", "remaining_time": "4:09:12", "throughput": 2542.35, "total_tokens": 880544} +{"current_steps": 1525, "total_steps": 67140, "loss": 0.8201, "lr": 1.1349419124218053e-05, "epoch": 0.22713732499255287, "percentage": 2.27, "elapsed_time": "0:05:47", "remaining_time": "4:09:11", "throughput": 2542.44, "total_tokens": 883488} +{"current_steps": 1530, "total_steps": 67140, "loss": 0.8389, "lr": 1.1386654751266011e-05, "epoch": 0.22788203753351208, "percentage": 2.28, "elapsed_time": "0:05:48", "remaining_time": "4:09:09", "throughput": 2542.08, "total_tokens": 886208} +{"current_steps": 1535, "total_steps": 67140, "loss": 0.9066, "lr": 1.1423890378313971e-05, "epoch": 0.22862675007447125, "percentage": 2.29, "elapsed_time": "0:05:49", "remaining_time": "4:09:08", "throughput": 2542.05, "total_tokens": 889088} +{"current_steps": 1540, "total_steps": 67140, "loss": 0.7988, "lr": 1.1461126005361931e-05, "epoch": 0.22937146261543045, "percentage": 2.29, "elapsed_time": "0:05:50", "remaining_time": "4:09:05", "throughput": 2541.67, "total_tokens": 891776} +{"current_steps": 1545, "total_steps": 67140, "loss": 0.8126, "lr": 1.149836163240989e-05, "epoch": 0.23011617515638963, "percentage": 2.3, "elapsed_time": "0:05:52", "remaining_time": "4:09:06", "throughput": 2542.16, "total_tokens": 894944} +{"current_steps": 1550, "total_steps": 67140, "loss": 0.8083, "lr": 1.153559725945785e-05, "epoch": 0.23086088769734883, "percentage": 2.31, "elapsed_time": "0:05:53", "remaining_time": "4:09:05", "throughput": 2542.11, "total_tokens": 897824} +{"current_steps": 1555, "total_steps": 67140, "loss": 0.8044, "lr": 1.1572832886505809e-05, "epoch": 0.231605600238308, "percentage": 2.32, "elapsed_time": "0:05:54", "remaining_time": "4:09:03", "throughput": 2542.02, "total_tokens": 900640} +{"current_steps": 1560, "total_steps": 67140, "loss": 0.8402, "lr": 1.1610068513553769e-05, "epoch": 0.2323503127792672, "percentage": 2.32, "elapsed_time": "0:05:55", "remaining_time": "4:09:01", "throughput": 2541.83, "total_tokens": 903424} +{"current_steps": 1565, "total_steps": 67140, "loss": 0.8316, "lr": 1.1647304140601728e-05, "epoch": 0.23309502532022638, "percentage": 2.33, "elapsed_time": "0:05:56", "remaining_time": "4:08:58", "throughput": 2541.38, "total_tokens": 906048} +{"current_steps": 1570, "total_steps": 67140, "loss": 0.8511, "lr": 1.1684539767649688e-05, "epoch": 0.2338397378611856, "percentage": 2.34, "elapsed_time": "0:05:57", "remaining_time": "4:08:57", "throughput": 2541.24, "total_tokens": 908896} +{"current_steps": 1575, "total_steps": 67140, "loss": 0.7754, "lr": 1.1721775394697646e-05, "epoch": 0.23458445040214476, "percentage": 2.35, "elapsed_time": "0:05:58", "remaining_time": "4:08:56", "throughput": 2541.22, "total_tokens": 911776} +{"current_steps": 1580, "total_steps": 67140, "loss": 0.8293, "lr": 1.1759011021745606e-05, "epoch": 0.23532916294310396, "percentage": 2.35, "elapsed_time": "0:05:59", "remaining_time": "4:08:57", "throughput": 2541.81, "total_tokens": 915040} +{"current_steps": 1585, "total_steps": 67140, "loss": 0.8851, "lr": 1.1796246648793566e-05, "epoch": 0.23607387548406314, "percentage": 2.36, "elapsed_time": "0:06:01", "remaining_time": "4:08:56", "throughput": 2541.84, "total_tokens": 917952} +{"current_steps": 1590, "total_steps": 67140, "loss": 0.8785, "lr": 1.1833482275841526e-05, "epoch": 0.23681858802502234, "percentage": 2.37, "elapsed_time": "0:06:02", "remaining_time": "4:08:53", "throughput": 2541.55, "total_tokens": 920640} +{"current_steps": 1595, "total_steps": 67140, "loss": 0.7781, "lr": 1.1870717902889484e-05, "epoch": 0.23756330056598154, "percentage": 2.38, "elapsed_time": "0:06:03", "remaining_time": "4:08:53", "throughput": 2541.77, "total_tokens": 923680} +{"current_steps": 1600, "total_steps": 67140, "loss": 0.8563, "lr": 1.1907953529937444e-05, "epoch": 0.23830801310694072, "percentage": 2.38, "elapsed_time": "0:06:04", "remaining_time": "4:08:51", "throughput": 2541.82, "total_tokens": 926560} +{"current_steps": 1605, "total_steps": 67140, "loss": 0.8235, "lr": 1.1945189156985404e-05, "epoch": 0.23905272564789992, "percentage": 2.39, "elapsed_time": "0:06:05", "remaining_time": "4:08:50", "throughput": 2541.7, "total_tokens": 929376} +{"current_steps": 1610, "total_steps": 67140, "loss": 0.8091, "lr": 1.1982424784033364e-05, "epoch": 0.2397974381888591, "percentage": 2.4, "elapsed_time": "0:06:06", "remaining_time": "4:08:48", "throughput": 2541.52, "total_tokens": 932160} +{"current_steps": 1615, "total_steps": 67140, "loss": 0.774, "lr": 1.2019660411081324e-05, "epoch": 0.2405421507298183, "percentage": 2.41, "elapsed_time": "0:06:07", "remaining_time": "4:08:47", "throughput": 2541.46, "total_tokens": 935040} +{"current_steps": 1620, "total_steps": 67140, "loss": 0.7916, "lr": 1.2056896038129282e-05, "epoch": 0.24128686327077747, "percentage": 2.41, "elapsed_time": "0:06:09", "remaining_time": "4:08:45", "throughput": 2541.32, "total_tokens": 937824} +{"current_steps": 1625, "total_steps": 67140, "loss": 0.8146, "lr": 1.2094131665177243e-05, "epoch": 0.24203157581173668, "percentage": 2.42, "elapsed_time": "0:06:10", "remaining_time": "4:08:44", "throughput": 2541.57, "total_tokens": 940832} +{"current_steps": 1630, "total_steps": 67140, "loss": 0.8462, "lr": 1.2131367292225201e-05, "epoch": 0.24277628835269585, "percentage": 2.43, "elapsed_time": "0:06:11", "remaining_time": "4:08:42", "throughput": 2541.2, "total_tokens": 943520} +{"current_steps": 1635, "total_steps": 67140, "loss": 0.8411, "lr": 1.2168602919273161e-05, "epoch": 0.24352100089365505, "percentage": 2.44, "elapsed_time": "0:06:12", "remaining_time": "4:08:40", "throughput": 2541.17, "total_tokens": 946400} +{"current_steps": 1640, "total_steps": 67140, "loss": 0.8387, "lr": 1.220583854632112e-05, "epoch": 0.24426571343461423, "percentage": 2.44, "elapsed_time": "0:06:13", "remaining_time": "4:08:40", "throughput": 2541.56, "total_tokens": 949504} +{"current_steps": 1645, "total_steps": 67140, "loss": 0.8387, "lr": 1.2243074173369081e-05, "epoch": 0.24501042597557343, "percentage": 2.45, "elapsed_time": "0:06:14", "remaining_time": "4:08:45", "throughput": 2542.69, "total_tokens": 953184} +{"current_steps": 1650, "total_steps": 67140, "loss": 0.8252, "lr": 1.228030980041704e-05, "epoch": 0.2457551385165326, "percentage": 2.46, "elapsed_time": "0:06:16", "remaining_time": "4:08:45", "throughput": 2542.93, "total_tokens": 956256} +{"current_steps": 1655, "total_steps": 67140, "loss": 0.8003, "lr": 1.2317545427464999e-05, "epoch": 0.2464998510574918, "percentage": 2.46, "elapsed_time": "0:06:17", "remaining_time": "4:08:44", "throughput": 2542.94, "total_tokens": 959168} +{"current_steps": 1660, "total_steps": 67140, "loss": 0.8891, "lr": 1.2354781054512959e-05, "epoch": 0.247244563598451, "percentage": 2.47, "elapsed_time": "0:06:18", "remaining_time": "4:08:43", "throughput": 2542.77, "total_tokens": 962016} +{"current_steps": 1665, "total_steps": 67140, "loss": 0.873, "lr": 1.2392016681560919e-05, "epoch": 0.2479892761394102, "percentage": 2.48, "elapsed_time": "0:06:19", "remaining_time": "4:08:42", "throughput": 2542.68, "total_tokens": 964896} +{"current_steps": 1670, "total_steps": 67140, "loss": 0.8549, "lr": 1.2429252308608877e-05, "epoch": 0.2487339886803694, "percentage": 2.49, "elapsed_time": "0:06:20", "remaining_time": "4:08:41", "throughput": 2542.52, "total_tokens": 967712} +{"current_steps": 1675, "total_steps": 67140, "loss": 0.8274, "lr": 1.2466487935656837e-05, "epoch": 0.24947870122132856, "percentage": 2.49, "elapsed_time": "0:06:21", "remaining_time": "4:08:40", "throughput": 2542.77, "total_tokens": 970752} +{"current_steps": 1680, "total_steps": 67140, "loss": 0.8368, "lr": 1.2503723562704797e-05, "epoch": 0.25022341376228774, "percentage": 2.5, "elapsed_time": "0:06:22", "remaining_time": "4:08:42", "throughput": 2543.44, "total_tokens": 974080} +{"current_steps": 1685, "total_steps": 67140, "loss": 0.832, "lr": 1.2540959189752758e-05, "epoch": 0.25096812630324694, "percentage": 2.51, "elapsed_time": "0:06:24", "remaining_time": "4:08:41", "throughput": 2543.38, "total_tokens": 976960} +{"current_steps": 1690, "total_steps": 67140, "loss": 0.8012, "lr": 1.2578194816800715e-05, "epoch": 0.25171283884420614, "percentage": 2.52, "elapsed_time": "0:06:25", "remaining_time": "4:08:42", "throughput": 2543.94, "total_tokens": 980192} +{"current_steps": 1695, "total_steps": 67140, "loss": 0.7924, "lr": 1.2615430443848674e-05, "epoch": 0.25245755138516535, "percentage": 2.52, "elapsed_time": "0:06:26", "remaining_time": "4:08:40", "throughput": 2543.69, "total_tokens": 982944} +{"current_steps": 1700, "total_steps": 67140, "loss": 0.8289, "lr": 1.2652666070896634e-05, "epoch": 0.2532022639261245, "percentage": 2.53, "elapsed_time": "0:06:27", "remaining_time": "4:08:38", "throughput": 2543.43, "total_tokens": 985696} +{"current_steps": 1705, "total_steps": 67140, "loss": 0.8432, "lr": 1.2689901697944596e-05, "epoch": 0.2539469764670837, "percentage": 2.54, "elapsed_time": "0:06:28", "remaining_time": "4:08:36", "throughput": 2543.2, "total_tokens": 988480} +{"current_steps": 1710, "total_steps": 67140, "loss": 0.8255, "lr": 1.2727137324992552e-05, "epoch": 0.2546916890080429, "percentage": 2.55, "elapsed_time": "0:06:29", "remaining_time": "4:08:35", "throughput": 2543.29, "total_tokens": 991392} +{"current_steps": 1715, "total_steps": 67140, "loss": 0.8194, "lr": 1.2764372952040512e-05, "epoch": 0.2554364015490021, "percentage": 2.55, "elapsed_time": "0:06:30", "remaining_time": "4:08:32", "throughput": 2542.99, "total_tokens": 994048} +{"current_steps": 1720, "total_steps": 67140, "loss": 0.7976, "lr": 1.2801608579088472e-05, "epoch": 0.25618111408996125, "percentage": 2.56, "elapsed_time": "0:06:31", "remaining_time": "4:08:28", "throughput": 2542.41, "total_tokens": 996576} +{"current_steps": 1725, "total_steps": 67140, "loss": 0.8129, "lr": 1.2838844206136434e-05, "epoch": 0.25692582663092045, "percentage": 2.57, "elapsed_time": "0:06:33", "remaining_time": "4:08:28", "throughput": 2542.7, "total_tokens": 999616} +{"current_steps": 1730, "total_steps": 67140, "loss": 0.7758, "lr": 1.287607983318439e-05, "epoch": 0.25767053917187965, "percentage": 2.58, "elapsed_time": "0:06:34", "remaining_time": "4:08:28", "throughput": 2542.97, "total_tokens": 1002720} +{"current_steps": 1735, "total_steps": 67140, "loss": 0.8752, "lr": 1.291331546023235e-05, "epoch": 0.25841525171283886, "percentage": 2.58, "elapsed_time": "0:06:35", "remaining_time": "4:08:26", "throughput": 2542.67, "total_tokens": 1005440} +{"current_steps": 1740, "total_steps": 67140, "loss": 0.7863, "lr": 1.295055108728031e-05, "epoch": 0.25915996425379806, "percentage": 2.59, "elapsed_time": "0:06:36", "remaining_time": "4:08:23", "throughput": 2542.07, "total_tokens": 1007936} +{"current_steps": 1745, "total_steps": 67140, "loss": 0.8869, "lr": 1.2987786714328271e-05, "epoch": 0.2599046767947572, "percentage": 2.6, "elapsed_time": "0:06:37", "remaining_time": "4:08:21", "throughput": 2542.09, "total_tokens": 1010848} +{"current_steps": 1750, "total_steps": 67140, "loss": 0.8411, "lr": 1.3025022341376231e-05, "epoch": 0.2606493893357164, "percentage": 2.61, "elapsed_time": "0:06:38", "remaining_time": "4:08:20", "throughput": 2541.99, "total_tokens": 1013664} +{"current_steps": 1755, "total_steps": 67140, "loss": 0.8157, "lr": 1.3062257968424188e-05, "epoch": 0.2613941018766756, "percentage": 2.61, "elapsed_time": "0:06:39", "remaining_time": "4:08:19", "throughput": 2542.49, "total_tokens": 1016800} +{"current_steps": 1760, "total_steps": 67140, "loss": 0.8327, "lr": 1.3099493595472147e-05, "epoch": 0.2621388144176348, "percentage": 2.62, "elapsed_time": "0:06:41", "remaining_time": "4:08:18", "throughput": 2542.36, "total_tokens": 1019648} +{"current_steps": 1765, "total_steps": 67140, "loss": 0.804, "lr": 1.3136729222520109e-05, "epoch": 0.26288352695859396, "percentage": 2.63, "elapsed_time": "0:06:42", "remaining_time": "4:08:16", "throughput": 2542.29, "total_tokens": 1022432} +{"current_steps": 1770, "total_steps": 67140, "loss": 0.8143, "lr": 1.3173964849568069e-05, "epoch": 0.26362823949955316, "percentage": 2.64, "elapsed_time": "0:06:43", "remaining_time": "4:08:15", "throughput": 2542.52, "total_tokens": 1025472} +{"current_steps": 1775, "total_steps": 67140, "loss": 0.8252, "lr": 1.3211200476616025e-05, "epoch": 0.26437295204051237, "percentage": 2.64, "elapsed_time": "0:06:44", "remaining_time": "4:08:14", "throughput": 2542.41, "total_tokens": 1028288} +{"current_steps": 1780, "total_steps": 67140, "loss": 0.8058, "lr": 1.3248436103663985e-05, "epoch": 0.26511766458147157, "percentage": 2.65, "elapsed_time": "0:06:45", "remaining_time": "4:08:11", "throughput": 2542.23, "total_tokens": 1031040} +{"current_steps": 1785, "total_steps": 67140, "loss": 0.852, "lr": 1.3285671730711947e-05, "epoch": 0.2658623771224307, "percentage": 2.66, "elapsed_time": "0:06:46", "remaining_time": "4:08:10", "throughput": 2541.95, "total_tokens": 1033792} +{"current_steps": 1790, "total_steps": 67140, "loss": 0.8148, "lr": 1.3322907357759907e-05, "epoch": 0.2666070896633899, "percentage": 2.67, "elapsed_time": "0:06:47", "remaining_time": "4:08:08", "throughput": 2541.53, "total_tokens": 1036448} +{"current_steps": 1795, "total_steps": 67140, "loss": 0.7996, "lr": 1.3360142984807863e-05, "epoch": 0.2673518022043491, "percentage": 2.67, "elapsed_time": "0:06:48", "remaining_time": "4:08:05", "throughput": 2541.3, "total_tokens": 1039168} +{"current_steps": 1800, "total_steps": 67140, "loss": 0.7911, "lr": 1.3397378611855823e-05, "epoch": 0.2680965147453083, "percentage": 2.68, "elapsed_time": "0:06:50", "remaining_time": "4:08:04", "throughput": 2541.15, "total_tokens": 1041952} +{"current_steps": 1805, "total_steps": 67140, "loss": 0.8098, "lr": 1.3434614238903784e-05, "epoch": 0.2688412272862675, "percentage": 2.69, "elapsed_time": "0:06:51", "remaining_time": "4:08:01", "throughput": 2540.88, "total_tokens": 1044608} +{"current_steps": 1810, "total_steps": 67140, "loss": 0.9276, "lr": 1.3471849865951744e-05, "epoch": 0.2695859398272267, "percentage": 2.7, "elapsed_time": "0:06:52", "remaining_time": "4:08:00", "throughput": 2540.93, "total_tokens": 1047552} +{"current_steps": 1815, "total_steps": 67140, "loss": 0.8009, "lr": 1.3509085492999704e-05, "epoch": 0.2703306523681859, "percentage": 2.7, "elapsed_time": "0:06:53", "remaining_time": "4:08:04", "throughput": 2541.89, "total_tokens": 1051200} +{"current_steps": 1820, "total_steps": 67140, "loss": 0.8269, "lr": 1.354632112004766e-05, "epoch": 0.2710753649091451, "percentage": 2.71, "elapsed_time": "0:06:54", "remaining_time": "4:08:02", "throughput": 2541.56, "total_tokens": 1053888} +{"current_steps": 1825, "total_steps": 67140, "loss": 0.7616, "lr": 1.3583556747095622e-05, "epoch": 0.2718200774501043, "percentage": 2.72, "elapsed_time": "0:06:55", "remaining_time": "4:07:59", "throughput": 2541.21, "total_tokens": 1056544} +{"current_steps": 1830, "total_steps": 67140, "loss": 0.9282, "lr": 1.3620792374143582e-05, "epoch": 0.2725647899910634, "percentage": 2.73, "elapsed_time": "0:06:56", "remaining_time": "4:07:57", "throughput": 2540.99, "total_tokens": 1059296} +{"current_steps": 1835, "total_steps": 67140, "loss": 0.8151, "lr": 1.3658028001191542e-05, "epoch": 0.27330950253202263, "percentage": 2.73, "elapsed_time": "0:06:58", "remaining_time": "4:07:56", "throughput": 2541.01, "total_tokens": 1062176} +{"current_steps": 1840, "total_steps": 67140, "loss": 0.8991, "lr": 1.3695263628239498e-05, "epoch": 0.27405421507298183, "percentage": 2.74, "elapsed_time": "0:06:59", "remaining_time": "4:07:55", "throughput": 2540.86, "total_tokens": 1064992} +{"current_steps": 1845, "total_steps": 67140, "loss": 0.895, "lr": 1.373249925528746e-05, "epoch": 0.27479892761394104, "percentage": 2.75, "elapsed_time": "0:07:00", "remaining_time": "4:07:53", "throughput": 2540.84, "total_tokens": 1067872} +{"current_steps": 1850, "total_steps": 67140, "loss": 0.8558, "lr": 1.376973488233542e-05, "epoch": 0.2755436401549002, "percentage": 2.76, "elapsed_time": "0:07:01", "remaining_time": "4:07:52", "throughput": 2540.94, "total_tokens": 1070816} +{"current_steps": 1855, "total_steps": 67140, "loss": 0.8051, "lr": 1.380697050938338e-05, "epoch": 0.2762883526958594, "percentage": 2.76, "elapsed_time": "0:07:02", "remaining_time": "4:07:50", "throughput": 2540.85, "total_tokens": 1073600} +{"current_steps": 1860, "total_steps": 67140, "loss": 0.8314, "lr": 1.3844206136431338e-05, "epoch": 0.2770330652368186, "percentage": 2.77, "elapsed_time": "0:07:03", "remaining_time": "4:07:49", "throughput": 2540.89, "total_tokens": 1076512} +{"current_steps": 1865, "total_steps": 67140, "loss": 0.8524, "lr": 1.3881441763479298e-05, "epoch": 0.2777777777777778, "percentage": 2.78, "elapsed_time": "0:07:04", "remaining_time": "4:07:47", "throughput": 2540.66, "total_tokens": 1079264} +{"current_steps": 1870, "total_steps": 67140, "loss": 0.9392, "lr": 1.3918677390527257e-05, "epoch": 0.278522490318737, "percentage": 2.79, "elapsed_time": "0:07:05", "remaining_time": "4:07:46", "throughput": 2540.71, "total_tokens": 1082144} +{"current_steps": 1875, "total_steps": 67140, "loss": 0.8168, "lr": 1.3955913017575217e-05, "epoch": 0.27926720285969614, "percentage": 2.79, "elapsed_time": "0:07:07", "remaining_time": "4:07:44", "throughput": 2540.62, "total_tokens": 1084960} +{"current_steps": 1880, "total_steps": 67140, "loss": 0.8084, "lr": 1.3993148644623177e-05, "epoch": 0.28001191540065534, "percentage": 2.8, "elapsed_time": "0:07:08", "remaining_time": "4:07:44", "throughput": 2540.67, "total_tokens": 1087936} +{"current_steps": 1885, "total_steps": 67140, "loss": 0.8305, "lr": 1.4030384271671135e-05, "epoch": 0.28075662794161454, "percentage": 2.81, "elapsed_time": "0:07:09", "remaining_time": "4:07:44", "throughput": 2540.83, "total_tokens": 1091008} +{"current_steps": 1890, "total_steps": 67140, "loss": 0.9858, "lr": 1.4067619898719095e-05, "epoch": 0.28150134048257375, "percentage": 2.82, "elapsed_time": "0:07:10", "remaining_time": "4:07:41", "throughput": 2540.57, "total_tokens": 1093664} +{"current_steps": 1895, "total_steps": 67140, "loss": 0.8249, "lr": 1.4104855525767055e-05, "epoch": 0.2822460530235329, "percentage": 2.82, "elapsed_time": "0:07:11", "remaining_time": "4:07:40", "throughput": 2540.75, "total_tokens": 1096640} +{"current_steps": 1900, "total_steps": 67140, "loss": 0.754, "lr": 1.4142091152815015e-05, "epoch": 0.2829907655644921, "percentage": 2.83, "elapsed_time": "0:07:12", "remaining_time": "4:07:37", "throughput": 2540.3, "total_tokens": 1099200} +{"current_steps": 1905, "total_steps": 67140, "loss": 0.9017, "lr": 1.4179326779862973e-05, "epoch": 0.2837354781054513, "percentage": 2.84, "elapsed_time": "0:07:13", "remaining_time": "4:07:38", "throughput": 2540.66, "total_tokens": 1102368} +{"current_steps": 1910, "total_steps": 67140, "loss": 0.8283, "lr": 1.4216562406910933e-05, "epoch": 0.2844801906464105, "percentage": 2.84, "elapsed_time": "0:07:15", "remaining_time": "4:07:36", "throughput": 2540.32, "total_tokens": 1105056} +{"current_steps": 1915, "total_steps": 67140, "loss": 0.7989, "lr": 1.4253798033958893e-05, "epoch": 0.28522490318736965, "percentage": 2.85, "elapsed_time": "0:07:16", "remaining_time": "4:07:35", "throughput": 2540.39, "total_tokens": 1108032} +{"current_steps": 1920, "total_steps": 67140, "loss": 0.8267, "lr": 1.4291033661006853e-05, "epoch": 0.28596961572832885, "percentage": 2.86, "elapsed_time": "0:07:17", "remaining_time": "4:07:34", "throughput": 2540.36, "total_tokens": 1110880} +{"current_steps": 1925, "total_steps": 67140, "loss": 0.8895, "lr": 1.432826928805481e-05, "epoch": 0.28671432826928805, "percentage": 2.87, "elapsed_time": "0:07:18", "remaining_time": "4:07:31", "throughput": 2540.16, "total_tokens": 1113568} +{"current_steps": 1930, "total_steps": 67140, "loss": 0.816, "lr": 1.436550491510277e-05, "epoch": 0.28745904081024726, "percentage": 2.87, "elapsed_time": "0:07:19", "remaining_time": "4:07:29", "throughput": 2540.14, "total_tokens": 1116416} +{"current_steps": 1935, "total_steps": 67140, "loss": 0.8171, "lr": 1.440274054215073e-05, "epoch": 0.28820375335120646, "percentage": 2.88, "elapsed_time": "0:07:20", "remaining_time": "4:07:28", "throughput": 2540.04, "total_tokens": 1119232} +{"current_steps": 1940, "total_steps": 67140, "loss": 0.7989, "lr": 1.443997616919869e-05, "epoch": 0.2889484658921656, "percentage": 2.89, "elapsed_time": "0:07:21", "remaining_time": "4:07:27", "throughput": 2540.05, "total_tokens": 1122144} +{"current_steps": 1945, "total_steps": 67140, "loss": 0.8008, "lr": 1.447721179624665e-05, "epoch": 0.2896931784331248, "percentage": 2.9, "elapsed_time": "0:07:22", "remaining_time": "4:07:26", "throughput": 2540.08, "total_tokens": 1125056} +{"current_steps": 1950, "total_steps": 67140, "loss": 0.8327, "lr": 1.4514447423294608e-05, "epoch": 0.290437890974084, "percentage": 2.9, "elapsed_time": "0:07:24", "remaining_time": "4:07:24", "throughput": 2539.79, "total_tokens": 1127744} +{"current_steps": 1955, "total_steps": 67140, "loss": 0.8072, "lr": 1.4551683050342568e-05, "epoch": 0.2911826035150432, "percentage": 2.91, "elapsed_time": "0:07:25", "remaining_time": "4:07:21", "throughput": 2539.55, "total_tokens": 1130432} +{"current_steps": 1960, "total_steps": 67140, "loss": 0.7675, "lr": 1.4588918677390528e-05, "epoch": 0.29192731605600236, "percentage": 2.92, "elapsed_time": "0:07:26", "remaining_time": "4:07:20", "throughput": 2539.3, "total_tokens": 1133184} +{"current_steps": 1965, "total_steps": 67140, "loss": 0.8188, "lr": 1.4626154304438488e-05, "epoch": 0.29267202859696156, "percentage": 2.93, "elapsed_time": "0:07:27", "remaining_time": "4:07:20", "throughput": 2539.5, "total_tokens": 1136256} +{"current_steps": 1970, "total_steps": 67140, "loss": 0.8094, "lr": 1.4663389931486446e-05, "epoch": 0.29341674113792077, "percentage": 2.93, "elapsed_time": "0:07:28", "remaining_time": "4:07:18", "throughput": 2539.49, "total_tokens": 1139104} +{"current_steps": 1975, "total_steps": 67140, "loss": 0.762, "lr": 1.4700625558534406e-05, "epoch": 0.29416145367887997, "percentage": 2.94, "elapsed_time": "0:07:29", "remaining_time": "4:07:18", "throughput": 2539.73, "total_tokens": 1142176} +{"current_steps": 1980, "total_steps": 67140, "loss": 0.8528, "lr": 1.4737861185582366e-05, "epoch": 0.2949061662198391, "percentage": 2.95, "elapsed_time": "0:07:30", "remaining_time": "4:07:16", "throughput": 2539.53, "total_tokens": 1144896} +{"current_steps": 1985, "total_steps": 67140, "loss": 0.7739, "lr": 1.4775096812630326e-05, "epoch": 0.2956508787607983, "percentage": 2.96, "elapsed_time": "0:07:32", "remaining_time": "4:07:17", "throughput": 2540.06, "total_tokens": 1148192} +{"current_steps": 1990, "total_steps": 67140, "loss": 0.8239, "lr": 1.4812332439678284e-05, "epoch": 0.2963955913017575, "percentage": 2.96, "elapsed_time": "0:07:33", "remaining_time": "4:07:15", "throughput": 2539.67, "total_tokens": 1150848} +{"current_steps": 1995, "total_steps": 67140, "loss": 0.8435, "lr": 1.4849568066726244e-05, "epoch": 0.2971403038427167, "percentage": 2.97, "elapsed_time": "0:07:34", "remaining_time": "4:07:14", "throughput": 2539.78, "total_tokens": 1153792} +{"current_steps": 2000, "total_steps": 67140, "loss": 0.8383, "lr": 1.4886803693774203e-05, "epoch": 0.2978850163836759, "percentage": 2.98, "elapsed_time": "0:07:35", "remaining_time": "4:07:12", "throughput": 2539.64, "total_tokens": 1156544} +{"current_steps": 2005, "total_steps": 67140, "loss": 0.8626, "lr": 1.4924039320822163e-05, "epoch": 0.2986297289246351, "percentage": 2.99, "elapsed_time": "0:07:36", "remaining_time": "4:07:10", "throughput": 2539.51, "total_tokens": 1159360} +{"current_steps": 2010, "total_steps": 67140, "loss": 0.8969, "lr": 1.4961274947870125e-05, "epoch": 0.2993744414655943, "percentage": 2.99, "elapsed_time": "0:07:37", "remaining_time": "4:07:09", "throughput": 2539.46, "total_tokens": 1162240} +{"current_steps": 2015, "total_steps": 67140, "loss": 0.8089, "lr": 1.4998510574918081e-05, "epoch": 0.3001191540065535, "percentage": 3.0, "elapsed_time": "0:07:38", "remaining_time": "4:07:07", "throughput": 2539.44, "total_tokens": 1165056} +{"current_steps": 2020, "total_steps": 67140, "loss": 0.8131, "lr": 1.5035746201966041e-05, "epoch": 0.3008638665475127, "percentage": 3.01, "elapsed_time": "0:07:39", "remaining_time": "4:07:05", "throughput": 2538.98, "total_tokens": 1167616} +{"current_steps": 2025, "total_steps": 67140, "loss": 0.8279, "lr": 1.5072981829014001e-05, "epoch": 0.30160857908847183, "percentage": 3.02, "elapsed_time": "0:07:41", "remaining_time": "4:07:04", "throughput": 2538.84, "total_tokens": 1170432} +{"current_steps": 2030, "total_steps": 67140, "loss": 0.7964, "lr": 1.5110217456061963e-05, "epoch": 0.30235329162943103, "percentage": 3.02, "elapsed_time": "0:07:42", "remaining_time": "4:07:02", "throughput": 2538.7, "total_tokens": 1173216} +{"current_steps": 2035, "total_steps": 67140, "loss": 0.7741, "lr": 1.5147453083109919e-05, "epoch": 0.30309800417039023, "percentage": 3.03, "elapsed_time": "0:07:43", "remaining_time": "4:07:02", "throughput": 2538.69, "total_tokens": 1176192} +{"current_steps": 2040, "total_steps": 67140, "loss": 0.8406, "lr": 1.5184688710157879e-05, "epoch": 0.30384271671134944, "percentage": 3.04, "elapsed_time": "0:07:44", "remaining_time": "4:07:02", "throughput": 2539.02, "total_tokens": 1179296} +{"current_steps": 2045, "total_steps": 67140, "loss": 0.8564, "lr": 1.5221924337205839e-05, "epoch": 0.3045874292523086, "percentage": 3.05, "elapsed_time": "0:07:45", "remaining_time": "4:07:01", "throughput": 2539.08, "total_tokens": 1182240} +{"current_steps": 2050, "total_steps": 67140, "loss": 0.8391, "lr": 1.52591599642538e-05, "epoch": 0.3053321417932678, "percentage": 3.05, "elapsed_time": "0:07:46", "remaining_time": "4:07:00", "throughput": 2539.0, "total_tokens": 1185088} +{"current_steps": 2055, "total_steps": 67140, "loss": 0.8133, "lr": 1.529639559130176e-05, "epoch": 0.306076854334227, "percentage": 3.06, "elapsed_time": "0:07:47", "remaining_time": "4:06:59", "throughput": 2539.21, "total_tokens": 1188128} +{"current_steps": 2060, "total_steps": 67140, "loss": 0.8007, "lr": 1.5333631218349718e-05, "epoch": 0.3068215668751862, "percentage": 3.07, "elapsed_time": "0:07:49", "remaining_time": "4:06:57", "throughput": 2539.13, "total_tokens": 1190944} +{"current_steps": 2065, "total_steps": 67140, "loss": 0.8381, "lr": 1.5370866845397678e-05, "epoch": 0.3075662794161454, "percentage": 3.08, "elapsed_time": "0:07:50", "remaining_time": "4:06:56", "throughput": 2539.29, "total_tokens": 1193920} +{"current_steps": 2070, "total_steps": 67140, "loss": 0.8008, "lr": 1.5408102472445638e-05, "epoch": 0.30831099195710454, "percentage": 3.08, "elapsed_time": "0:07:51", "remaining_time": "4:06:54", "throughput": 2539.12, "total_tokens": 1196640} +{"current_steps": 2075, "total_steps": 67140, "loss": 0.859, "lr": 1.5445338099493598e-05, "epoch": 0.30905570449806374, "percentage": 3.09, "elapsed_time": "0:07:52", "remaining_time": "4:06:53", "throughput": 2539.22, "total_tokens": 1199616} +{"current_steps": 2080, "total_steps": 67140, "loss": 0.8235, "lr": 1.5482573726541554e-05, "epoch": 0.30980041703902295, "percentage": 3.1, "elapsed_time": "0:07:53", "remaining_time": "4:06:52", "throughput": 2539.05, "total_tokens": 1202368} +{"current_steps": 2085, "total_steps": 67140, "loss": 0.8023, "lr": 1.5519809353589514e-05, "epoch": 0.31054512957998215, "percentage": 3.11, "elapsed_time": "0:07:54", "remaining_time": "4:06:50", "throughput": 2539.21, "total_tokens": 1205312} +{"current_steps": 2090, "total_steps": 67140, "loss": 0.8231, "lr": 1.5557044980637474e-05, "epoch": 0.3112898421209413, "percentage": 3.11, "elapsed_time": "0:07:55", "remaining_time": "4:06:51", "throughput": 2539.73, "total_tokens": 1208608} +{"current_steps": 2095, "total_steps": 67140, "loss": 0.8268, "lr": 1.5594280607685434e-05, "epoch": 0.3120345546619005, "percentage": 3.12, "elapsed_time": "0:07:57", "remaining_time": "4:06:50", "throughput": 2539.76, "total_tokens": 1211520} +{"current_steps": 2100, "total_steps": 67140, "loss": 0.8107, "lr": 1.5631516234733394e-05, "epoch": 0.3127792672028597, "percentage": 3.13, "elapsed_time": "0:07:58", "remaining_time": "4:06:50", "throughput": 2540.01, "total_tokens": 1214592} +{"current_steps": 2105, "total_steps": 67140, "loss": 0.8254, "lr": 1.5668751861781354e-05, "epoch": 0.3135239797438189, "percentage": 3.14, "elapsed_time": "0:07:59", "remaining_time": "4:06:48", "throughput": 2540.03, "total_tokens": 1217440} +{"current_steps": 2110, "total_steps": 67140, "loss": 0.8137, "lr": 1.5705987488829313e-05, "epoch": 0.31426869228477805, "percentage": 3.14, "elapsed_time": "0:08:00", "remaining_time": "4:06:47", "throughput": 2540.12, "total_tokens": 1220416} +{"current_steps": 2115, "total_steps": 67140, "loss": 0.8132, "lr": 1.5743223115877273e-05, "epoch": 0.31501340482573725, "percentage": 3.15, "elapsed_time": "0:08:01", "remaining_time": "4:06:45", "throughput": 2539.54, "total_tokens": 1222912} +{"current_steps": 2120, "total_steps": 67140, "loss": 0.812, "lr": 1.578045874292523e-05, "epoch": 0.31575811736669646, "percentage": 3.16, "elapsed_time": "0:08:02", "remaining_time": "4:06:44", "throughput": 2539.75, "total_tokens": 1225952} +{"current_steps": 2125, "total_steps": 67140, "loss": 0.8083, "lr": 1.581769436997319e-05, "epoch": 0.31650282990765566, "percentage": 3.17, "elapsed_time": "0:08:03", "remaining_time": "4:06:42", "throughput": 2539.63, "total_tokens": 1228736} +{"current_steps": 2130, "total_steps": 67140, "loss": 0.8249, "lr": 1.585492999702115e-05, "epoch": 0.31724754244861486, "percentage": 3.17, "elapsed_time": "0:08:04", "remaining_time": "4:06:41", "throughput": 2539.6, "total_tokens": 1231584} +{"current_steps": 2135, "total_steps": 67140, "loss": 0.7956, "lr": 1.589216562406911e-05, "epoch": 0.317992254989574, "percentage": 3.18, "elapsed_time": "0:08:06", "remaining_time": "4:06:39", "throughput": 2539.57, "total_tokens": 1234432} +{"current_steps": 2140, "total_steps": 67140, "loss": 0.8012, "lr": 1.5929401251117073e-05, "epoch": 0.3187369675305332, "percentage": 3.19, "elapsed_time": "0:08:07", "remaining_time": "4:06:38", "throughput": 2539.66, "total_tokens": 1237376} +{"current_steps": 2145, "total_steps": 67140, "loss": 0.8011, "lr": 1.596663687816503e-05, "epoch": 0.3194816800714924, "percentage": 3.19, "elapsed_time": "0:08:08", "remaining_time": "4:06:38", "throughput": 2539.72, "total_tokens": 1240352} +{"current_steps": 2150, "total_steps": 67140, "loss": 0.8401, "lr": 1.600387250521299e-05, "epoch": 0.3202263926124516, "percentage": 3.2, "elapsed_time": "0:08:09", "remaining_time": "4:06:35", "throughput": 2539.33, "total_tokens": 1242944} +{"current_steps": 2155, "total_steps": 67140, "loss": 0.8325, "lr": 1.604110813226095e-05, "epoch": 0.32097110515341076, "percentage": 3.21, "elapsed_time": "0:08:10", "remaining_time": "4:06:34", "throughput": 2539.27, "total_tokens": 1245760} +{"current_steps": 2160, "total_steps": 67140, "loss": 1.1421, "lr": 1.607834375930891e-05, "epoch": 0.32171581769436997, "percentage": 3.22, "elapsed_time": "0:08:11", "remaining_time": "4:06:31", "throughput": 2538.91, "total_tokens": 1248352} +{"current_steps": 2165, "total_steps": 67140, "loss": 0.8353, "lr": 1.6115579386356865e-05, "epoch": 0.32246053023532917, "percentage": 3.22, "elapsed_time": "0:08:12", "remaining_time": "4:06:30", "throughput": 2538.62, "total_tokens": 1251072} +{"current_steps": 2170, "total_steps": 67140, "loss": 0.8223, "lr": 1.6152815013404825e-05, "epoch": 0.32320524277628837, "percentage": 3.23, "elapsed_time": "0:08:13", "remaining_time": "4:06:28", "throughput": 2538.38, "total_tokens": 1253792} +{"current_steps": 2175, "total_steps": 67140, "loss": 1.113, "lr": 1.6190050640452785e-05, "epoch": 0.3239499553172475, "percentage": 3.24, "elapsed_time": "0:08:15", "remaining_time": "4:06:26", "throughput": 2538.15, "total_tokens": 1256512} +{"current_steps": 2180, "total_steps": 67140, "loss": 0.8199, "lr": 1.6227286267500748e-05, "epoch": 0.3246946678582067, "percentage": 3.25, "elapsed_time": "0:08:16", "remaining_time": "4:06:24", "throughput": 2537.98, "total_tokens": 1259200} +{"current_steps": 2185, "total_steps": 67140, "loss": 0.8207, "lr": 1.6264521894548704e-05, "epoch": 0.3254393803991659, "percentage": 3.25, "elapsed_time": "0:08:17", "remaining_time": "4:06:23", "throughput": 2538.19, "total_tokens": 1262208} +{"current_steps": 2190, "total_steps": 67140, "loss": 0.8023, "lr": 1.6301757521596664e-05, "epoch": 0.3261840929401251, "percentage": 3.26, "elapsed_time": "0:08:18", "remaining_time": "4:06:21", "throughput": 2538.03, "total_tokens": 1264960} +{"current_steps": 2195, "total_steps": 67140, "loss": 0.7491, "lr": 1.6338993148644624e-05, "epoch": 0.32692880548108433, "percentage": 3.27, "elapsed_time": "0:08:19", "remaining_time": "4:06:20", "throughput": 2538.21, "total_tokens": 1268000} +{"current_steps": 2200, "total_steps": 67140, "loss": 0.8252, "lr": 1.6376228775692584e-05, "epoch": 0.3276735180220435, "percentage": 3.28, "elapsed_time": "0:08:20", "remaining_time": "4:06:21", "throughput": 2538.72, "total_tokens": 1271296} +{"current_steps": 2205, "total_steps": 67140, "loss": 0.821, "lr": 1.6413464402740544e-05, "epoch": 0.3284182305630027, "percentage": 3.28, "elapsed_time": "0:08:21", "remaining_time": "4:06:21", "throughput": 2538.92, "total_tokens": 1274368} +{"current_steps": 2210, "total_steps": 67140, "loss": 0.8159, "lr": 1.64507000297885e-05, "epoch": 0.3291629431039619, "percentage": 3.29, "elapsed_time": "0:08:23", "remaining_time": "4:06:20", "throughput": 2538.86, "total_tokens": 1277216} +{"current_steps": 2215, "total_steps": 67140, "loss": 0.8163, "lr": 1.648793565683646e-05, "epoch": 0.3299076556449211, "percentage": 3.3, "elapsed_time": "0:08:24", "remaining_time": "4:06:18", "throughput": 2538.84, "total_tokens": 1280064} +{"current_steps": 2220, "total_steps": 67140, "loss": 0.7614, "lr": 1.6525171283884423e-05, "epoch": 0.33065236818588023, "percentage": 3.31, "elapsed_time": "0:08:25", "remaining_time": "4:06:17", "throughput": 2538.75, "total_tokens": 1282880} +{"current_steps": 2225, "total_steps": 67140, "loss": 0.8568, "lr": 1.6562406910932383e-05, "epoch": 0.33139708072683943, "percentage": 3.31, "elapsed_time": "0:08:26", "remaining_time": "4:06:16", "throughput": 2538.84, "total_tokens": 1285856} +{"current_steps": 2230, "total_steps": 67140, "loss": 0.7924, "lr": 1.659964253798034e-05, "epoch": 0.33214179326779864, "percentage": 3.32, "elapsed_time": "0:08:27", "remaining_time": "4:06:14", "throughput": 2538.72, "total_tokens": 1288576} +{"current_steps": 2235, "total_steps": 67140, "loss": 0.8141, "lr": 1.66368781650283e-05, "epoch": 0.33288650580875784, "percentage": 3.33, "elapsed_time": "0:08:28", "remaining_time": "4:06:12", "throughput": 2538.61, "total_tokens": 1291360} +{"current_steps": 2240, "total_steps": 67140, "loss": 0.8206, "lr": 1.667411379207626e-05, "epoch": 0.333631218349717, "percentage": 3.34, "elapsed_time": "0:08:29", "remaining_time": "4:06:11", "throughput": 2538.75, "total_tokens": 1294368} +{"current_steps": 2245, "total_steps": 67140, "loss": 0.8092, "lr": 1.671134941912422e-05, "epoch": 0.3343759308906762, "percentage": 3.34, "elapsed_time": "0:08:30", "remaining_time": "4:06:10", "throughput": 2538.65, "total_tokens": 1297152} +{"current_steps": 2250, "total_steps": 67140, "loss": 0.8098, "lr": 1.6748585046172176e-05, "epoch": 0.3351206434316354, "percentage": 3.35, "elapsed_time": "0:08:32", "remaining_time": "4:06:11", "throughput": 2539.37, "total_tokens": 1300640} +{"current_steps": 2255, "total_steps": 67140, "loss": 0.8064, "lr": 1.6785820673220136e-05, "epoch": 0.3358653559725946, "percentage": 3.36, "elapsed_time": "0:08:33", "remaining_time": "4:06:10", "throughput": 2539.3, "total_tokens": 1303488} +{"current_steps": 2260, "total_steps": 67140, "loss": 1.2177, "lr": 1.68230563002681e-05, "epoch": 0.3366100685135538, "percentage": 3.37, "elapsed_time": "0:08:34", "remaining_time": "4:06:10", "throughput": 2539.41, "total_tokens": 1306528} +{"current_steps": 2265, "total_steps": 67140, "loss": 1.0531, "lr": 1.686029192731606e-05, "epoch": 0.33735478105451294, "percentage": 3.37, "elapsed_time": "0:08:35", "remaining_time": "4:06:10", "throughput": 2539.87, "total_tokens": 1309792} +{"current_steps": 2270, "total_steps": 67140, "loss": 0.835, "lr": 1.689752755436402e-05, "epoch": 0.33809949359547214, "percentage": 3.38, "elapsed_time": "0:08:36", "remaining_time": "4:06:08", "throughput": 2539.58, "total_tokens": 1312448} +{"current_steps": 2275, "total_steps": 67140, "loss": 0.8343, "lr": 1.6934763181411975e-05, "epoch": 0.33884420613643135, "percentage": 3.39, "elapsed_time": "0:08:37", "remaining_time": "4:06:06", "throughput": 2539.41, "total_tokens": 1315136} +{"current_steps": 2280, "total_steps": 67140, "loss": 0.8007, "lr": 1.6971998808459935e-05, "epoch": 0.33958891867739055, "percentage": 3.4, "elapsed_time": "0:08:39", "remaining_time": "4:06:05", "throughput": 2539.55, "total_tokens": 1318144} +{"current_steps": 2285, "total_steps": 67140, "loss": 0.8031, "lr": 1.7009234435507895e-05, "epoch": 0.3403336312183497, "percentage": 3.4, "elapsed_time": "0:08:40", "remaining_time": "4:06:03", "throughput": 2539.55, "total_tokens": 1320992} +{"current_steps": 2290, "total_steps": 67140, "loss": 0.8873, "lr": 1.7046470062555855e-05, "epoch": 0.3410783437593089, "percentage": 3.41, "elapsed_time": "0:08:41", "remaining_time": "4:06:02", "throughput": 2539.47, "total_tokens": 1323808} +{"current_steps": 2295, "total_steps": 67140, "loss": 0.8413, "lr": 1.7083705689603814e-05, "epoch": 0.3418230563002681, "percentage": 3.42, "elapsed_time": "0:08:42", "remaining_time": "4:05:59", "throughput": 2539.15, "total_tokens": 1326400} +{"current_steps": 2300, "total_steps": 67140, "loss": 0.8264, "lr": 1.7120941316651774e-05, "epoch": 0.3425677688412273, "percentage": 3.43, "elapsed_time": "0:08:43", "remaining_time": "4:05:58", "throughput": 2539.03, "total_tokens": 1329184} +{"current_steps": 2305, "total_steps": 67140, "loss": 0.794, "lr": 1.7158176943699734e-05, "epoch": 0.34331248138218645, "percentage": 3.43, "elapsed_time": "0:08:44", "remaining_time": "4:05:57", "throughput": 2539.25, "total_tokens": 1332224} +{"current_steps": 2310, "total_steps": 67140, "loss": 0.7891, "lr": 1.7195412570747694e-05, "epoch": 0.34405719392314565, "percentage": 3.44, "elapsed_time": "0:08:45", "remaining_time": "4:05:56", "throughput": 2539.29, "total_tokens": 1335168} +{"current_steps": 2315, "total_steps": 67140, "loss": 0.8767, "lr": 1.723264819779565e-05, "epoch": 0.34480190646410486, "percentage": 3.45, "elapsed_time": "0:08:46", "remaining_time": "4:05:55", "throughput": 2539.27, "total_tokens": 1338016} +{"current_steps": 2320, "total_steps": 67140, "loss": 0.8321, "lr": 1.726988382484361e-05, "epoch": 0.34554661900506406, "percentage": 3.46, "elapsed_time": "0:08:48", "remaining_time": "4:05:52", "throughput": 2538.95, "total_tokens": 1340640} +{"current_steps": 2325, "total_steps": 67140, "loss": 0.8011, "lr": 1.730711945189157e-05, "epoch": 0.34629133154602326, "percentage": 3.46, "elapsed_time": "0:08:49", "remaining_time": "4:05:52", "throughput": 2539.09, "total_tokens": 1343648} +{"current_steps": 2330, "total_steps": 67140, "loss": 0.7867, "lr": 1.734435507893953e-05, "epoch": 0.3470360440869824, "percentage": 3.47, "elapsed_time": "0:08:50", "remaining_time": "4:05:50", "throughput": 2539.08, "total_tokens": 1346464} +{"current_steps": 2335, "total_steps": 67140, "loss": 0.7928, "lr": 1.738159070598749e-05, "epoch": 0.3477807566279416, "percentage": 3.48, "elapsed_time": "0:08:51", "remaining_time": "4:05:49", "throughput": 2539.22, "total_tokens": 1349408} +{"current_steps": 2340, "total_steps": 67140, "loss": 0.8558, "lr": 1.741882633303545e-05, "epoch": 0.3485254691689008, "percentage": 3.49, "elapsed_time": "0:08:52", "remaining_time": "4:05:47", "throughput": 2539.22, "total_tokens": 1352288} +{"current_steps": 2345, "total_steps": 67140, "loss": 0.7812, "lr": 1.745606196008341e-05, "epoch": 0.34927018170986, "percentage": 3.49, "elapsed_time": "0:08:53", "remaining_time": "4:05:45", "throughput": 2538.93, "total_tokens": 1354944} +{"current_steps": 2350, "total_steps": 67140, "loss": 0.8045, "lr": 1.749329758713137e-05, "epoch": 0.35001489425081916, "percentage": 3.5, "elapsed_time": "0:08:54", "remaining_time": "4:05:45", "throughput": 2539.26, "total_tokens": 1358048} +{"current_steps": 2355, "total_steps": 67140, "loss": 0.8376, "lr": 1.753053321417933e-05, "epoch": 0.35075960679177837, "percentage": 3.51, "elapsed_time": "0:08:55", "remaining_time": "4:05:42", "throughput": 2539.04, "total_tokens": 1360704} +{"current_steps": 2360, "total_steps": 67140, "loss": 0.8094, "lr": 1.7567768841227286e-05, "epoch": 0.35150431933273757, "percentage": 3.52, "elapsed_time": "0:08:56", "remaining_time": "4:05:40", "throughput": 2538.63, "total_tokens": 1363232} +{"current_steps": 2365, "total_steps": 67140, "loss": 0.7936, "lr": 1.7605004468275246e-05, "epoch": 0.35224903187369677, "percentage": 3.52, "elapsed_time": "0:08:58", "remaining_time": "4:05:39", "throughput": 2538.76, "total_tokens": 1366272} +{"current_steps": 2370, "total_steps": 67140, "loss": 0.8107, "lr": 1.7642240095323205e-05, "epoch": 0.3529937444146559, "percentage": 3.53, "elapsed_time": "0:08:59", "remaining_time": "4:05:37", "throughput": 2538.64, "total_tokens": 1369024} +{"current_steps": 2375, "total_steps": 67140, "loss": 0.7999, "lr": 1.7679475722371165e-05, "epoch": 0.3537384569556151, "percentage": 3.54, "elapsed_time": "0:09:00", "remaining_time": "4:05:36", "throughput": 2538.67, "total_tokens": 1371936} +{"current_steps": 2380, "total_steps": 67140, "loss": 0.8048, "lr": 1.7716711349419125e-05, "epoch": 0.3544831694965743, "percentage": 3.54, "elapsed_time": "0:09:01", "remaining_time": "4:05:35", "throughput": 2538.9, "total_tokens": 1374976} +{"current_steps": 2385, "total_steps": 67140, "loss": 0.811, "lr": 1.7753946976467085e-05, "epoch": 0.3552278820375335, "percentage": 3.55, "elapsed_time": "0:09:02", "remaining_time": "4:05:35", "throughput": 2539.37, "total_tokens": 1378208} +{"current_steps": 2390, "total_steps": 67140, "loss": 0.8175, "lr": 1.7791182603515045e-05, "epoch": 0.35597259457849273, "percentage": 3.56, "elapsed_time": "0:09:03", "remaining_time": "4:05:34", "throughput": 2539.29, "total_tokens": 1381056} +{"current_steps": 2395, "total_steps": 67140, "loss": 0.8096, "lr": 1.7828418230563005e-05, "epoch": 0.3567173071194519, "percentage": 3.57, "elapsed_time": "0:09:05", "remaining_time": "4:05:35", "throughput": 2539.8, "total_tokens": 1384384} +{"current_steps": 2400, "total_steps": 67140, "loss": 0.865, "lr": 1.786565385761096e-05, "epoch": 0.3574620196604111, "percentage": 3.57, "elapsed_time": "0:09:06", "remaining_time": "4:05:33", "throughput": 2539.69, "total_tokens": 1387200} +{"current_steps": 2405, "total_steps": 67140, "loss": 0.8289, "lr": 1.790288948465892e-05, "epoch": 0.3582067322013703, "percentage": 3.58, "elapsed_time": "0:09:07", "remaining_time": "4:05:33", "throughput": 2539.83, "total_tokens": 1390272} +{"current_steps": 2410, "total_steps": 67140, "loss": 0.8108, "lr": 1.794012511170688e-05, "epoch": 0.3589514447423295, "percentage": 3.59, "elapsed_time": "0:09:08", "remaining_time": "4:05:33", "throughput": 2540.09, "total_tokens": 1393408} +{"current_steps": 2415, "total_steps": 67140, "loss": 0.8332, "lr": 1.797736073875484e-05, "epoch": 0.35969615728328863, "percentage": 3.6, "elapsed_time": "0:09:09", "remaining_time": "4:05:32", "throughput": 2540.22, "total_tokens": 1396352} +{"current_steps": 2420, "total_steps": 67140, "loss": 0.8087, "lr": 1.80145963658028e-05, "epoch": 0.36044086982424783, "percentage": 3.6, "elapsed_time": "0:09:10", "remaining_time": "4:05:31", "throughput": 2540.35, "total_tokens": 1399328} +{"current_steps": 2425, "total_steps": 67140, "loss": 0.8944, "lr": 1.805183199285076e-05, "epoch": 0.36118558236520704, "percentage": 3.61, "elapsed_time": "0:09:11", "remaining_time": "4:05:29", "throughput": 2540.24, "total_tokens": 1402080} +{"current_steps": 2430, "total_steps": 67140, "loss": 0.7992, "lr": 1.808906761989872e-05, "epoch": 0.36193029490616624, "percentage": 3.62, "elapsed_time": "0:09:13", "remaining_time": "4:05:26", "throughput": 2539.82, "total_tokens": 1404576} +{"current_steps": 2435, "total_steps": 67140, "loss": 0.8077, "lr": 1.812630324694668e-05, "epoch": 0.3626750074471254, "percentage": 3.63, "elapsed_time": "0:09:14", "remaining_time": "4:05:26", "throughput": 2539.89, "total_tokens": 1407552} +{"current_steps": 2440, "total_steps": 67140, "loss": 0.7669, "lr": 1.816353887399464e-05, "epoch": 0.3634197199880846, "percentage": 3.63, "elapsed_time": "0:09:15", "remaining_time": "4:05:24", "throughput": 2539.68, "total_tokens": 1410272} +{"current_steps": 2445, "total_steps": 67140, "loss": 0.8473, "lr": 1.8200774501042596e-05, "epoch": 0.3641644325290438, "percentage": 3.64, "elapsed_time": "0:09:16", "remaining_time": "4:05:22", "throughput": 2539.54, "total_tokens": 1412992} +{"current_steps": 2450, "total_steps": 67140, "loss": 0.8161, "lr": 1.8238010128090556e-05, "epoch": 0.364909145070003, "percentage": 3.65, "elapsed_time": "0:09:17", "remaining_time": "4:05:21", "throughput": 2539.48, "total_tokens": 1415840} +{"current_steps": 2455, "total_steps": 67140, "loss": 0.7825, "lr": 1.8275245755138516e-05, "epoch": 0.3656538576109622, "percentage": 3.66, "elapsed_time": "0:09:18", "remaining_time": "4:05:19", "throughput": 2539.3, "total_tokens": 1418560} +{"current_steps": 2460, "total_steps": 67140, "loss": 0.7928, "lr": 1.8312481382186476e-05, "epoch": 0.36639857015192134, "percentage": 3.66, "elapsed_time": "0:09:19", "remaining_time": "4:05:19", "throughput": 2539.53, "total_tokens": 1421664} +{"current_steps": 2465, "total_steps": 67140, "loss": 0.8028, "lr": 1.8349717009234436e-05, "epoch": 0.36714328269288055, "percentage": 3.67, "elapsed_time": "0:09:20", "remaining_time": "4:05:17", "throughput": 2539.53, "total_tokens": 1424512} +{"current_steps": 2470, "total_steps": 67140, "loss": 0.7821, "lr": 1.8386952636282396e-05, "epoch": 0.36788799523383975, "percentage": 3.68, "elapsed_time": "0:09:22", "remaining_time": "4:05:16", "throughput": 2539.51, "total_tokens": 1427392} +{"current_steps": 2475, "total_steps": 67140, "loss": 0.7836, "lr": 1.8424188263330356e-05, "epoch": 0.36863270777479895, "percentage": 3.69, "elapsed_time": "0:09:23", "remaining_time": "4:05:14", "throughput": 2539.22, "total_tokens": 1430048} +{"current_steps": 2480, "total_steps": 67140, "loss": 0.8589, "lr": 1.8461423890378315e-05, "epoch": 0.3693774203157581, "percentage": 3.69, "elapsed_time": "0:09:24", "remaining_time": "4:05:12", "throughput": 2538.98, "total_tokens": 1432704} +{"current_steps": 2485, "total_steps": 67140, "loss": 0.8221, "lr": 1.8498659517426275e-05, "epoch": 0.3701221328567173, "percentage": 3.7, "elapsed_time": "0:09:25", "remaining_time": "4:05:10", "throughput": 2538.89, "total_tokens": 1435488} +{"current_steps": 2490, "total_steps": 67140, "loss": 0.8163, "lr": 1.8535895144474232e-05, "epoch": 0.3708668453976765, "percentage": 3.71, "elapsed_time": "0:09:26", "remaining_time": "4:05:08", "throughput": 2538.64, "total_tokens": 1438176} +{"current_steps": 2495, "total_steps": 67140, "loss": 0.8527, "lr": 1.857313077152219e-05, "epoch": 0.3716115579386357, "percentage": 3.72, "elapsed_time": "0:09:27", "remaining_time": "4:05:06", "throughput": 2538.39, "total_tokens": 1440800} +{"current_steps": 2500, "total_steps": 67140, "loss": 0.8082, "lr": 1.8610366398570155e-05, "epoch": 0.37235627047959485, "percentage": 3.72, "elapsed_time": "0:09:28", "remaining_time": "4:05:05", "throughput": 2538.52, "total_tokens": 1443808} +{"current_steps": 2505, "total_steps": 67140, "loss": 0.802, "lr": 1.8647602025618115e-05, "epoch": 0.37310098302055406, "percentage": 3.73, "elapsed_time": "0:09:29", "remaining_time": "4:05:04", "throughput": 2538.6, "total_tokens": 1446752} +{"current_steps": 2510, "total_steps": 67140, "loss": 0.791, "lr": 1.868483765266607e-05, "epoch": 0.37384569556151326, "percentage": 3.74, "elapsed_time": "0:09:31", "remaining_time": "4:05:04", "throughput": 2538.74, "total_tokens": 1449792} +{"current_steps": 2515, "total_steps": 67140, "loss": 0.79, "lr": 1.872207327971403e-05, "epoch": 0.37459040810247246, "percentage": 3.75, "elapsed_time": "0:09:32", "remaining_time": "4:05:03", "throughput": 2538.73, "total_tokens": 1452672} +{"current_steps": 2520, "total_steps": 67140, "loss": 0.8412, "lr": 1.875930890676199e-05, "epoch": 0.3753351206434316, "percentage": 3.75, "elapsed_time": "0:09:33", "remaining_time": "4:05:01", "throughput": 2538.67, "total_tokens": 1455456} +{"current_steps": 2525, "total_steps": 67140, "loss": 0.8189, "lr": 1.879654453380995e-05, "epoch": 0.3760798331843908, "percentage": 3.76, "elapsed_time": "0:09:34", "remaining_time": "4:04:59", "throughput": 2538.55, "total_tokens": 1458208} +{"current_steps": 2530, "total_steps": 67140, "loss": 0.8245, "lr": 1.8833780160857907e-05, "epoch": 0.37682454572535, "percentage": 3.77, "elapsed_time": "0:09:35", "remaining_time": "4:04:58", "throughput": 2538.47, "total_tokens": 1461024} +{"current_steps": 2535, "total_steps": 67140, "loss": 0.8051, "lr": 1.8871015787905867e-05, "epoch": 0.3775692582663092, "percentage": 3.78, "elapsed_time": "0:09:36", "remaining_time": "4:04:56", "throughput": 2538.33, "total_tokens": 1463776} +{"current_steps": 2540, "total_steps": 67140, "loss": 0.8204, "lr": 1.890825141495383e-05, "epoch": 0.3783139708072684, "percentage": 3.78, "elapsed_time": "0:09:37", "remaining_time": "4:04:55", "throughput": 2538.36, "total_tokens": 1466688} +{"current_steps": 2545, "total_steps": 67140, "loss": 0.7153, "lr": 1.894548704200179e-05, "epoch": 0.37905868334822757, "percentage": 3.79, "elapsed_time": "0:09:38", "remaining_time": "4:04:54", "throughput": 2538.3, "total_tokens": 1469536} +{"current_steps": 2550, "total_steps": 67140, "loss": 0.9849, "lr": 1.898272266904975e-05, "epoch": 0.37980339588918677, "percentage": 3.8, "elapsed_time": "0:09:40", "remaining_time": "4:04:51", "throughput": 2537.94, "total_tokens": 1472096} +{"current_steps": 2555, "total_steps": 67140, "loss": 1.1735, "lr": 1.9019958296097706e-05, "epoch": 0.38054810843014597, "percentage": 3.81, "elapsed_time": "0:09:41", "remaining_time": "4:04:51", "throughput": 2537.95, "total_tokens": 1475008} +{"current_steps": 2560, "total_steps": 67140, "loss": 0.9002, "lr": 1.9057193923145666e-05, "epoch": 0.3812928209711052, "percentage": 3.81, "elapsed_time": "0:09:42", "remaining_time": "4:04:49", "throughput": 2537.66, "total_tokens": 1477664} +{"current_steps": 2565, "total_steps": 67140, "loss": 0.8423, "lr": 1.9094429550193626e-05, "epoch": 0.3820375335120643, "percentage": 3.82, "elapsed_time": "0:09:43", "remaining_time": "4:04:47", "throughput": 2537.73, "total_tokens": 1480576} +{"current_steps": 2570, "total_steps": 67140, "loss": 0.8087, "lr": 1.9131665177241586e-05, "epoch": 0.3827822460530235, "percentage": 3.83, "elapsed_time": "0:09:44", "remaining_time": "4:04:46", "throughput": 2537.82, "total_tokens": 1483488} +{"current_steps": 2575, "total_steps": 67140, "loss": 0.8138, "lr": 1.9168900804289542e-05, "epoch": 0.3835269585939827, "percentage": 3.84, "elapsed_time": "0:09:45", "remaining_time": "4:04:45", "throughput": 2537.86, "total_tokens": 1486368} +{"current_steps": 2580, "total_steps": 67140, "loss": 0.818, "lr": 1.9206136431337506e-05, "epoch": 0.38427167113494193, "percentage": 3.84, "elapsed_time": "0:09:46", "remaining_time": "4:04:44", "throughput": 2537.78, "total_tokens": 1489216} +{"current_steps": 2585, "total_steps": 67140, "loss": 0.8128, "lr": 1.9243372058385466e-05, "epoch": 0.3850163836759011, "percentage": 3.85, "elapsed_time": "0:09:47", "remaining_time": "4:04:42", "throughput": 2537.74, "total_tokens": 1492032} +{"current_steps": 2590, "total_steps": 67140, "loss": 0.7771, "lr": 1.9280607685433425e-05, "epoch": 0.3857610962168603, "percentage": 3.86, "elapsed_time": "0:09:49", "remaining_time": "4:04:40", "throughput": 2537.59, "total_tokens": 1494784} +{"current_steps": 2595, "total_steps": 67140, "loss": 0.7263, "lr": 1.9317843312481382e-05, "epoch": 0.3865058087578195, "percentage": 3.87, "elapsed_time": "0:09:50", "remaining_time": "4:04:40", "throughput": 2537.82, "total_tokens": 1497856} +{"current_steps": 2600, "total_steps": 67140, "loss": 1.0673, "lr": 1.9355078939529342e-05, "epoch": 0.3872505212987787, "percentage": 3.87, "elapsed_time": "0:09:51", "remaining_time": "4:04:38", "throughput": 2537.55, "total_tokens": 1500512} +{"current_steps": 2605, "total_steps": 67140, "loss": 1.0956, "lr": 1.93923145665773e-05, "epoch": 0.3879952338397379, "percentage": 3.88, "elapsed_time": "0:09:52", "remaining_time": "4:04:36", "throughput": 2537.53, "total_tokens": 1503328} +{"current_steps": 2610, "total_steps": 67140, "loss": 1.0844, "lr": 1.942955019362526e-05, "epoch": 0.38873994638069703, "percentage": 3.89, "elapsed_time": "0:09:53", "remaining_time": "4:04:35", "throughput": 2537.29, "total_tokens": 1506016} +{"current_steps": 2615, "total_steps": 67140, "loss": 1.2134, "lr": 1.946678582067322e-05, "epoch": 0.38948465892165623, "percentage": 3.89, "elapsed_time": "0:09:54", "remaining_time": "4:04:33", "throughput": 2537.15, "total_tokens": 1508736} +{"current_steps": 2620, "total_steps": 67140, "loss": 0.8445, "lr": 1.950402144772118e-05, "epoch": 0.39022937146261544, "percentage": 3.9, "elapsed_time": "0:09:56", "remaining_time": "4:04:38", "throughput": 2538.24, "total_tokens": 1512896} +{"current_steps": 2625, "total_steps": 67140, "loss": 0.8305, "lr": 1.954125707476914e-05, "epoch": 0.39097408400357464, "percentage": 3.91, "elapsed_time": "0:09:57", "remaining_time": "4:04:36", "throughput": 2538.18, "total_tokens": 1515712} +{"current_steps": 2630, "total_steps": 67140, "loss": 0.8257, "lr": 1.95784927018171e-05, "epoch": 0.3917187965445338, "percentage": 3.92, "elapsed_time": "0:09:58", "remaining_time": "4:04:35", "throughput": 2538.17, "total_tokens": 1518560} +{"current_steps": 2635, "total_steps": 67140, "loss": 0.8286, "lr": 1.961572832886506e-05, "epoch": 0.392463509085493, "percentage": 3.92, "elapsed_time": "0:09:59", "remaining_time": "4:04:34", "throughput": 2538.25, "total_tokens": 1521536} +{"current_steps": 2640, "total_steps": 67140, "loss": 0.824, "lr": 1.9652963955913017e-05, "epoch": 0.3932082216264522, "percentage": 3.93, "elapsed_time": "0:10:00", "remaining_time": "4:04:34", "throughput": 2538.31, "total_tokens": 1524544} +{"current_steps": 2645, "total_steps": 67140, "loss": 0.8159, "lr": 1.9690199582960977e-05, "epoch": 0.3939529341674114, "percentage": 3.94, "elapsed_time": "0:10:01", "remaining_time": "4:04:34", "throughput": 2538.65, "total_tokens": 1527744} +{"current_steps": 2650, "total_steps": 67140, "loss": 0.8089, "lr": 1.9727435210008937e-05, "epoch": 0.39469764670837054, "percentage": 3.95, "elapsed_time": "0:10:02", "remaining_time": "4:04:32", "throughput": 2538.61, "total_tokens": 1530592} +{"current_steps": 2655, "total_steps": 67140, "loss": 0.8022, "lr": 1.9764670837056897e-05, "epoch": 0.39544235924932974, "percentage": 3.95, "elapsed_time": "0:10:04", "remaining_time": "4:04:31", "throughput": 2538.69, "total_tokens": 1533568} +{"current_steps": 2660, "total_steps": 67140, "loss": 0.8653, "lr": 1.9801906464104857e-05, "epoch": 0.39618707179028895, "percentage": 3.96, "elapsed_time": "0:10:05", "remaining_time": "4:04:30", "throughput": 2538.79, "total_tokens": 1536512} +{"current_steps": 2665, "total_steps": 67140, "loss": 0.8423, "lr": 1.9839142091152816e-05, "epoch": 0.39693178433124815, "percentage": 3.97, "elapsed_time": "0:10:06", "remaining_time": "4:04:30", "throughput": 2538.91, "total_tokens": 1539520} +{"current_steps": 2670, "total_steps": 67140, "loss": 0.8154, "lr": 1.9876377718200776e-05, "epoch": 0.39767649687220735, "percentage": 3.98, "elapsed_time": "0:10:07", "remaining_time": "4:04:29", "throughput": 2538.98, "total_tokens": 1542464} +{"current_steps": 2675, "total_steps": 67140, "loss": 0.7289, "lr": 1.9913613345248736e-05, "epoch": 0.3984212094131665, "percentage": 3.98, "elapsed_time": "0:10:08", "remaining_time": "4:04:27", "throughput": 2539.02, "total_tokens": 1545344} +{"current_steps": 2680, "total_steps": 67140, "loss": 0.7757, "lr": 1.9950848972296696e-05, "epoch": 0.3991659219541257, "percentage": 3.99, "elapsed_time": "0:10:09", "remaining_time": "4:04:26", "throughput": 2539.06, "total_tokens": 1548256} +{"current_steps": 2685, "total_steps": 67140, "loss": 0.8067, "lr": 1.9988084599344652e-05, "epoch": 0.3999106344950849, "percentage": 4.0, "elapsed_time": "0:10:10", "remaining_time": "4:04:26", "throughput": 2539.22, "total_tokens": 1551328} +{"current_steps": 2690, "total_steps": 67140, "loss": 0.9948, "lr": 2.0025320226392612e-05, "epoch": 0.4006553470360441, "percentage": 4.01, "elapsed_time": "0:10:12", "remaining_time": "4:04:24", "throughput": 2539.07, "total_tokens": 1554048} +{"current_steps": 2695, "total_steps": 67140, "loss": 0.8306, "lr": 2.0062555853440572e-05, "epoch": 0.40140005957700325, "percentage": 4.01, "elapsed_time": "0:10:13", "remaining_time": "4:04:22", "throughput": 2538.81, "total_tokens": 1556704} +{"current_steps": 2700, "total_steps": 67140, "loss": 0.8198, "lr": 2.0099791480488532e-05, "epoch": 0.40214477211796246, "percentage": 4.02, "elapsed_time": "0:10:14", "remaining_time": "4:04:21", "throughput": 2538.9, "total_tokens": 1559680} +{"current_steps": 2705, "total_steps": 67140, "loss": 0.8041, "lr": 2.0137027107536492e-05, "epoch": 0.40288948465892166, "percentage": 4.03, "elapsed_time": "0:10:15", "remaining_time": "4:04:20", "throughput": 2538.77, "total_tokens": 1562464} +{"current_steps": 2710, "total_steps": 67140, "loss": 0.8012, "lr": 2.0174262734584452e-05, "epoch": 0.40363419719988086, "percentage": 4.04, "elapsed_time": "0:10:16", "remaining_time": "4:04:19", "throughput": 2538.82, "total_tokens": 1565376} +{"current_steps": 2715, "total_steps": 67140, "loss": 0.7979, "lr": 2.021149836163241e-05, "epoch": 0.40437890974084, "percentage": 4.04, "elapsed_time": "0:10:17", "remaining_time": "4:04:17", "throughput": 2538.81, "total_tokens": 1568256} +{"current_steps": 2720, "total_steps": 67140, "loss": 0.8219, "lr": 2.024873398868037e-05, "epoch": 0.4051236222817992, "percentage": 4.05, "elapsed_time": "0:10:18", "remaining_time": "4:04:17", "throughput": 2539.09, "total_tokens": 1571424} +{"current_steps": 2725, "total_steps": 67140, "loss": 0.7847, "lr": 2.0285969615728328e-05, "epoch": 0.4058683348227584, "percentage": 4.06, "elapsed_time": "0:10:19", "remaining_time": "4:04:15", "throughput": 2538.96, "total_tokens": 1574112} +{"current_steps": 2730, "total_steps": 67140, "loss": 0.8211, "lr": 2.0323205242776288e-05, "epoch": 0.4066130473637176, "percentage": 4.07, "elapsed_time": "0:10:21", "remaining_time": "4:04:14", "throughput": 2538.97, "total_tokens": 1577024} +{"current_steps": 2735, "total_steps": 67140, "loss": 0.7901, "lr": 2.0360440869824248e-05, "epoch": 0.4073577599046768, "percentage": 4.07, "elapsed_time": "0:10:22", "remaining_time": "4:04:13", "throughput": 2538.84, "total_tokens": 1579808} +{"current_steps": 2740, "total_steps": 67140, "loss": 0.83, "lr": 2.0397676496872207e-05, "epoch": 0.40810247244563597, "percentage": 4.08, "elapsed_time": "0:10:23", "remaining_time": "4:04:12", "throughput": 2538.91, "total_tokens": 1582752} +{"current_steps": 2745, "total_steps": 67140, "loss": 0.7893, "lr": 2.043491212392017e-05, "epoch": 0.40884718498659517, "percentage": 4.09, "elapsed_time": "0:10:24", "remaining_time": "4:04:11", "throughput": 2539.0, "total_tokens": 1585728} +{"current_steps": 2750, "total_steps": 67140, "loss": 0.8043, "lr": 2.0472147750968127e-05, "epoch": 0.40959189752755437, "percentage": 4.1, "elapsed_time": "0:10:25", "remaining_time": "4:04:09", "throughput": 2538.91, "total_tokens": 1588480} +{"current_steps": 2755, "total_steps": 67140, "loss": 0.8264, "lr": 2.0509383378016087e-05, "epoch": 0.4103366100685136, "percentage": 4.1, "elapsed_time": "0:10:26", "remaining_time": "4:04:09", "throughput": 2539.18, "total_tokens": 1591680} +{"current_steps": 2760, "total_steps": 67140, "loss": 0.8289, "lr": 2.0546619005064047e-05, "epoch": 0.4110813226094727, "percentage": 4.11, "elapsed_time": "0:10:27", "remaining_time": "4:04:08", "throughput": 2539.13, "total_tokens": 1594496} +{"current_steps": 2765, "total_steps": 67140, "loss": 0.8149, "lr": 2.0583854632112007e-05, "epoch": 0.4118260351504319, "percentage": 4.12, "elapsed_time": "0:10:29", "remaining_time": "4:04:06", "throughput": 2539.17, "total_tokens": 1597408} +{"current_steps": 2770, "total_steps": 67140, "loss": 0.818, "lr": 2.0621090259159963e-05, "epoch": 0.4125707476913911, "percentage": 4.13, "elapsed_time": "0:10:30", "remaining_time": "4:04:05", "throughput": 2539.16, "total_tokens": 1600288} +{"current_steps": 2775, "total_steps": 67140, "loss": 0.8214, "lr": 2.0658325886207923e-05, "epoch": 0.41331546023235033, "percentage": 4.13, "elapsed_time": "0:10:31", "remaining_time": "4:04:04", "throughput": 2539.18, "total_tokens": 1603200} +{"current_steps": 2780, "total_steps": 67140, "loss": 0.7981, "lr": 2.0695561513255883e-05, "epoch": 0.4140601727733095, "percentage": 4.14, "elapsed_time": "0:10:32", "remaining_time": "4:04:03", "throughput": 2539.25, "total_tokens": 1606144} +{"current_steps": 2785, "total_steps": 67140, "loss": 0.7929, "lr": 2.0732797140303846e-05, "epoch": 0.4148048853142687, "percentage": 4.15, "elapsed_time": "0:10:33", "remaining_time": "4:04:02", "throughput": 2539.38, "total_tokens": 1609152} +{"current_steps": 2790, "total_steps": 67140, "loss": 0.7985, "lr": 2.0770032767351803e-05, "epoch": 0.4155495978552279, "percentage": 4.16, "elapsed_time": "0:10:34", "remaining_time": "4:04:01", "throughput": 2539.57, "total_tokens": 1612192} +{"current_steps": 2795, "total_steps": 67140, "loss": 0.8087, "lr": 2.0807268394399762e-05, "epoch": 0.4162943103961871, "percentage": 4.16, "elapsed_time": "0:10:35", "remaining_time": "4:04:00", "throughput": 2539.47, "total_tokens": 1614944} +{"current_steps": 2800, "total_steps": 67140, "loss": 0.7982, "lr": 2.0844504021447722e-05, "epoch": 0.4170390229371463, "percentage": 4.17, "elapsed_time": "0:10:37", "remaining_time": "4:03:58", "throughput": 2539.53, "total_tokens": 1617856} +{"current_steps": 2805, "total_steps": 67140, "loss": 0.7835, "lr": 2.0881739648495682e-05, "epoch": 0.41778373547810543, "percentage": 4.18, "elapsed_time": "0:10:38", "remaining_time": "4:03:58", "throughput": 2539.72, "total_tokens": 1620928} +{"current_steps": 2810, "total_steps": 67140, "loss": 0.7978, "lr": 2.0918975275543642e-05, "epoch": 0.41852844801906464, "percentage": 4.19, "elapsed_time": "0:10:39", "remaining_time": "4:03:56", "throughput": 2539.69, "total_tokens": 1623744} +{"current_steps": 2815, "total_steps": 67140, "loss": 0.8482, "lr": 2.09562109025916e-05, "epoch": 0.41927316056002384, "percentage": 4.19, "elapsed_time": "0:10:40", "remaining_time": "4:03:55", "throughput": 2539.77, "total_tokens": 1626720} +{"current_steps": 2820, "total_steps": 67140, "loss": 0.8709, "lr": 2.099344652963956e-05, "epoch": 0.42001787310098304, "percentage": 4.2, "elapsed_time": "0:10:41", "remaining_time": "4:03:55", "throughput": 2539.82, "total_tokens": 1629696} +{"current_steps": 2825, "total_steps": 67140, "loss": 0.843, "lr": 2.103068215668752e-05, "epoch": 0.4207625856419422, "percentage": 4.21, "elapsed_time": "0:10:42", "remaining_time": "4:03:53", "throughput": 2539.66, "total_tokens": 1632416} +{"current_steps": 2830, "total_steps": 67140, "loss": 0.7854, "lr": 2.106791778373548e-05, "epoch": 0.4215072981829014, "percentage": 4.22, "elapsed_time": "0:10:43", "remaining_time": "4:03:51", "throughput": 2539.54, "total_tokens": 1635168} +{"current_steps": 2835, "total_steps": 67140, "loss": 0.7903, "lr": 2.1105153410783438e-05, "epoch": 0.4222520107238606, "percentage": 4.22, "elapsed_time": "0:10:44", "remaining_time": "4:03:49", "throughput": 2539.26, "total_tokens": 1637760} +{"current_steps": 2840, "total_steps": 67140, "loss": 0.8039, "lr": 2.1142389037831398e-05, "epoch": 0.4229967232648198, "percentage": 4.23, "elapsed_time": "0:10:46", "remaining_time": "4:03:47", "throughput": 2539.13, "total_tokens": 1640480} +{"current_steps": 2845, "total_steps": 67140, "loss": 0.8519, "lr": 2.1179624664879358e-05, "epoch": 0.42374143580577894, "percentage": 4.24, "elapsed_time": "0:10:47", "remaining_time": "4:03:46", "throughput": 2539.01, "total_tokens": 1643232} +{"current_steps": 2850, "total_steps": 67140, "loss": 0.7222, "lr": 2.1216860291927317e-05, "epoch": 0.42448614834673815, "percentage": 4.24, "elapsed_time": "0:10:48", "remaining_time": "4:03:44", "throughput": 2539.16, "total_tokens": 1646208} +{"current_steps": 2855, "total_steps": 67140, "loss": 0.978, "lr": 2.1254095918975274e-05, "epoch": 0.42523086088769735, "percentage": 4.25, "elapsed_time": "0:10:49", "remaining_time": "4:03:43", "throughput": 2538.91, "total_tokens": 1648864} +{"current_steps": 2860, "total_steps": 67140, "loss": 0.8888, "lr": 2.1291331546023234e-05, "epoch": 0.42597557342865655, "percentage": 4.26, "elapsed_time": "0:10:50", "remaining_time": "4:03:41", "throughput": 2538.82, "total_tokens": 1651648} +{"current_steps": 2865, "total_steps": 67140, "loss": 0.8909, "lr": 2.1328567173071197e-05, "epoch": 0.42672028596961575, "percentage": 4.27, "elapsed_time": "0:10:51", "remaining_time": "4:03:39", "throughput": 2538.58, "total_tokens": 1654272} +{"current_steps": 2870, "total_steps": 67140, "loss": 0.8107, "lr": 2.1365802800119157e-05, "epoch": 0.4274649985105749, "percentage": 4.27, "elapsed_time": "0:10:52", "remaining_time": "4:03:38", "throughput": 2538.74, "total_tokens": 1657280} +{"current_steps": 2875, "total_steps": 67140, "loss": 0.8155, "lr": 2.1403038427167117e-05, "epoch": 0.4282097110515341, "percentage": 4.28, "elapsed_time": "0:10:53", "remaining_time": "4:03:36", "throughput": 2538.62, "total_tokens": 1660000} +{"current_steps": 2880, "total_steps": 67140, "loss": 0.772, "lr": 2.1440274054215073e-05, "epoch": 0.4289544235924933, "percentage": 4.29, "elapsed_time": "0:10:55", "remaining_time": "4:03:35", "throughput": 2538.61, "total_tokens": 1662880} +{"current_steps": 2885, "total_steps": 67140, "loss": 0.7775, "lr": 2.1477509681263033e-05, "epoch": 0.4296991361334525, "percentage": 4.3, "elapsed_time": "0:10:56", "remaining_time": "4:03:34", "throughput": 2538.64, "total_tokens": 1665760} +{"current_steps": 2890, "total_steps": 67140, "loss": 0.939, "lr": 2.1514745308310993e-05, "epoch": 0.43044384867441166, "percentage": 4.3, "elapsed_time": "0:10:57", "remaining_time": "4:03:33", "throughput": 2538.62, "total_tokens": 1668640} +{"current_steps": 2895, "total_steps": 67140, "loss": 0.887, "lr": 2.1551980935358953e-05, "epoch": 0.43118856121537086, "percentage": 4.31, "elapsed_time": "0:10:58", "remaining_time": "4:03:32", "throughput": 2538.62, "total_tokens": 1671552} +{"current_steps": 2900, "total_steps": 67140, "loss": 1.0482, "lr": 2.1589216562406913e-05, "epoch": 0.43193327375633006, "percentage": 4.32, "elapsed_time": "0:10:59", "remaining_time": "4:03:31", "throughput": 2538.6, "total_tokens": 1674432} +{"current_steps": 2905, "total_steps": 67140, "loss": 0.8411, "lr": 2.1626452189454872e-05, "epoch": 0.43267798629728926, "percentage": 4.33, "elapsed_time": "0:11:00", "remaining_time": "4:03:29", "throughput": 2538.5, "total_tokens": 1677248} +{"current_steps": 2910, "total_steps": 67140, "loss": 0.8101, "lr": 2.1663687816502832e-05, "epoch": 0.4334226988382484, "percentage": 4.33, "elapsed_time": "0:11:01", "remaining_time": "4:03:28", "throughput": 2538.46, "total_tokens": 1680064} +{"current_steps": 2915, "total_steps": 67140, "loss": 0.819, "lr": 2.1700923443550792e-05, "epoch": 0.4341674113792076, "percentage": 4.34, "elapsed_time": "0:11:02", "remaining_time": "4:03:27", "throughput": 2538.33, "total_tokens": 1682848} +{"current_steps": 2920, "total_steps": 67140, "loss": 0.8216, "lr": 2.173815907059875e-05, "epoch": 0.4349121239201668, "percentage": 4.35, "elapsed_time": "0:11:04", "remaining_time": "4:03:26", "throughput": 2538.35, "total_tokens": 1685792} +{"current_steps": 2925, "total_steps": 67140, "loss": 0.8134, "lr": 2.177539469764671e-05, "epoch": 0.435656836461126, "percentage": 4.36, "elapsed_time": "0:11:05", "remaining_time": "4:03:24", "throughput": 2538.15, "total_tokens": 1688448} +{"current_steps": 2930, "total_steps": 67140, "loss": 0.8206, "lr": 2.1812630324694668e-05, "epoch": 0.4364015490020852, "percentage": 4.36, "elapsed_time": "0:11:06", "remaining_time": "4:03:23", "throughput": 2538.13, "total_tokens": 1691328} +{"current_steps": 2935, "total_steps": 67140, "loss": 0.8053, "lr": 2.1849865951742628e-05, "epoch": 0.43714626154304437, "percentage": 4.37, "elapsed_time": "0:11:07", "remaining_time": "4:03:22", "throughput": 2538.3, "total_tokens": 1694336} +{"current_steps": 2940, "total_steps": 67140, "loss": 0.8074, "lr": 2.1887101578790588e-05, "epoch": 0.43789097408400357, "percentage": 4.38, "elapsed_time": "0:11:08", "remaining_time": "4:03:20", "throughput": 2538.14, "total_tokens": 1697056} +{"current_steps": 2945, "total_steps": 67140, "loss": 0.8099, "lr": 2.1924337205838548e-05, "epoch": 0.4386356866249628, "percentage": 4.39, "elapsed_time": "0:11:09", "remaining_time": "4:03:18", "throughput": 2538.02, "total_tokens": 1699808} +{"current_steps": 2950, "total_steps": 67140, "loss": 0.7736, "lr": 2.1961572832886508e-05, "epoch": 0.439380399165922, "percentage": 4.39, "elapsed_time": "0:11:10", "remaining_time": "4:03:18", "throughput": 2538.11, "total_tokens": 1702848} +{"current_steps": 2955, "total_steps": 67140, "loss": 0.7975, "lr": 2.1998808459934468e-05, "epoch": 0.4401251117068811, "percentage": 4.4, "elapsed_time": "0:11:12", "remaining_time": "4:03:17", "throughput": 2538.06, "total_tokens": 1705696} +{"current_steps": 2960, "total_steps": 67140, "loss": 0.7947, "lr": 2.2036044086982427e-05, "epoch": 0.4408698242478403, "percentage": 4.41, "elapsed_time": "0:11:13", "remaining_time": "4:03:16", "throughput": 2538.09, "total_tokens": 1708576} +{"current_steps": 2965, "total_steps": 67140, "loss": 0.7549, "lr": 2.2073279714030384e-05, "epoch": 0.4416145367887995, "percentage": 4.42, "elapsed_time": "0:11:14", "remaining_time": "4:03:14", "throughput": 2538.01, "total_tokens": 1711328} +{"current_steps": 2970, "total_steps": 67140, "loss": 0.8116, "lr": 2.2110515341078344e-05, "epoch": 0.44235924932975873, "percentage": 4.42, "elapsed_time": "0:11:15", "remaining_time": "4:03:13", "throughput": 2538.19, "total_tokens": 1714368} +{"current_steps": 2975, "total_steps": 67140, "loss": 0.8477, "lr": 2.2147750968126304e-05, "epoch": 0.4431039618707179, "percentage": 4.43, "elapsed_time": "0:11:16", "remaining_time": "4:03:12", "throughput": 2538.21, "total_tokens": 1717248} +{"current_steps": 2980, "total_steps": 67140, "loss": 0.8349, "lr": 2.2184986595174263e-05, "epoch": 0.4438486744116771, "percentage": 4.44, "elapsed_time": "0:11:17", "remaining_time": "4:03:11", "throughput": 2538.47, "total_tokens": 1720384} +{"current_steps": 2985, "total_steps": 67140, "loss": 0.802, "lr": 2.2222222222222223e-05, "epoch": 0.4445933869526363, "percentage": 4.45, "elapsed_time": "0:11:18", "remaining_time": "4:03:10", "throughput": 2538.63, "total_tokens": 1723360} +{"current_steps": 2990, "total_steps": 67140, "loss": 0.8091, "lr": 2.2259457849270183e-05, "epoch": 0.4453380994935955, "percentage": 4.45, "elapsed_time": "0:11:19", "remaining_time": "4:03:08", "throughput": 2538.3, "total_tokens": 1725920} +{"current_steps": 2995, "total_steps": 67140, "loss": 0.7513, "lr": 2.2296693476318143e-05, "epoch": 0.4460828120345547, "percentage": 4.46, "elapsed_time": "0:11:21", "remaining_time": "4:03:06", "throughput": 2538.23, "total_tokens": 1728672} +{"current_steps": 3000, "total_steps": 67140, "loss": 0.825, "lr": 2.2333929103366103e-05, "epoch": 0.44682752457551383, "percentage": 4.47, "elapsed_time": "0:11:22", "remaining_time": "4:03:04", "throughput": 2538.17, "total_tokens": 1731488} +{"current_steps": 3005, "total_steps": 67140, "loss": 0.851, "lr": 2.2371164730414063e-05, "epoch": 0.44757223711647304, "percentage": 4.48, "elapsed_time": "0:11:23", "remaining_time": "4:03:04", "throughput": 2538.28, "total_tokens": 1734496} +{"current_steps": 3010, "total_steps": 67140, "loss": 0.8375, "lr": 2.240840035746202e-05, "epoch": 0.44831694965743224, "percentage": 4.48, "elapsed_time": "0:11:24", "remaining_time": "4:03:03", "throughput": 2538.25, "total_tokens": 1737408} +{"current_steps": 3015, "total_steps": 67140, "loss": 0.7872, "lr": 2.244563598450998e-05, "epoch": 0.44906166219839144, "percentage": 4.49, "elapsed_time": "0:11:25", "remaining_time": "4:03:01", "throughput": 2538.1, "total_tokens": 1740096} +{"current_steps": 3020, "total_steps": 67140, "loss": 0.7825, "lr": 2.248287161155794e-05, "epoch": 0.4498063747393506, "percentage": 4.5, "elapsed_time": "0:11:26", "remaining_time": "4:02:59", "throughput": 2537.88, "total_tokens": 1742688} +{"current_steps": 3025, "total_steps": 67140, "loss": 0.8149, "lr": 2.25201072386059e-05, "epoch": 0.4505510872803098, "percentage": 4.51, "elapsed_time": "0:11:27", "remaining_time": "4:02:58", "throughput": 2538.03, "total_tokens": 1745760} +{"current_steps": 3030, "total_steps": 67140, "loss": 0.8057, "lr": 2.255734286565386e-05, "epoch": 0.451295799821269, "percentage": 4.51, "elapsed_time": "0:11:28", "remaining_time": "4:02:58", "throughput": 2538.13, "total_tokens": 1748768} +{"current_steps": 3035, "total_steps": 67140, "loss": 0.8026, "lr": 2.259457849270182e-05, "epoch": 0.4520405123622282, "percentage": 4.52, "elapsed_time": "0:11:30", "remaining_time": "4:02:57", "throughput": 2538.12, "total_tokens": 1751680} +{"current_steps": 3040, "total_steps": 67140, "loss": 0.8169, "lr": 2.2631814119749778e-05, "epoch": 0.45278522490318734, "percentage": 4.53, "elapsed_time": "0:11:31", "remaining_time": "4:02:56", "throughput": 2538.03, "total_tokens": 1754496} +{"current_steps": 3045, "total_steps": 67140, "loss": 0.8415, "lr": 2.2669049746797738e-05, "epoch": 0.45352993744414655, "percentage": 4.54, "elapsed_time": "0:11:32", "remaining_time": "4:02:53", "throughput": 2537.71, "total_tokens": 1757024} +{"current_steps": 3050, "total_steps": 67140, "loss": 0.7941, "lr": 2.2706285373845695e-05, "epoch": 0.45427464998510575, "percentage": 4.54, "elapsed_time": "0:11:33", "remaining_time": "4:02:52", "throughput": 2537.78, "total_tokens": 1759936} +{"current_steps": 3055, "total_steps": 67140, "loss": 0.7864, "lr": 2.2743521000893654e-05, "epoch": 0.45501936252606495, "percentage": 4.55, "elapsed_time": "0:11:34", "remaining_time": "4:02:51", "throughput": 2537.89, "total_tokens": 1762880} +{"current_steps": 3060, "total_steps": 67140, "loss": 0.7976, "lr": 2.2780756627941614e-05, "epoch": 0.45576407506702415, "percentage": 4.56, "elapsed_time": "0:11:35", "remaining_time": "4:02:51", "throughput": 2537.99, "total_tokens": 1765952} +{"current_steps": 3065, "total_steps": 67140, "loss": 0.7689, "lr": 2.2817992254989574e-05, "epoch": 0.4565087876079833, "percentage": 4.57, "elapsed_time": "0:11:36", "remaining_time": "4:02:49", "throughput": 2537.9, "total_tokens": 1768704} +{"current_steps": 3070, "total_steps": 67140, "loss": 0.7909, "lr": 2.2855227882037537e-05, "epoch": 0.4572535001489425, "percentage": 4.57, "elapsed_time": "0:11:38", "remaining_time": "4:02:47", "throughput": 2537.83, "total_tokens": 1771488} +{"current_steps": 3075, "total_steps": 67140, "loss": 0.8151, "lr": 2.2892463509085494e-05, "epoch": 0.4579982126899017, "percentage": 4.58, "elapsed_time": "0:11:39", "remaining_time": "4:02:47", "throughput": 2538.04, "total_tokens": 1774624} +{"current_steps": 3080, "total_steps": 67140, "loss": 0.8575, "lr": 2.2929699136133454e-05, "epoch": 0.4587429252308609, "percentage": 4.59, "elapsed_time": "0:11:40", "remaining_time": "4:02:47", "throughput": 2538.21, "total_tokens": 1777728} +{"current_steps": 3085, "total_steps": 67140, "loss": 0.8042, "lr": 2.2966934763181414e-05, "epoch": 0.45948763777182006, "percentage": 4.59, "elapsed_time": "0:11:41", "remaining_time": "4:02:45", "throughput": 2538.26, "total_tokens": 1780640} +{"current_steps": 3090, "total_steps": 67140, "loss": 0.8787, "lr": 2.3004170390229373e-05, "epoch": 0.46023235031277926, "percentage": 4.6, "elapsed_time": "0:11:42", "remaining_time": "4:02:44", "throughput": 2538.29, "total_tokens": 1783520} +{"current_steps": 3095, "total_steps": 67140, "loss": 0.785, "lr": 2.304140601727733e-05, "epoch": 0.46097706285373846, "percentage": 4.61, "elapsed_time": "0:11:43", "remaining_time": "4:02:42", "throughput": 2538.17, "total_tokens": 1786240} +{"current_steps": 3100, "total_steps": 67140, "loss": 0.8045, "lr": 2.307864164432529e-05, "epoch": 0.46172177539469766, "percentage": 4.62, "elapsed_time": "0:11:44", "remaining_time": "4:02:41", "throughput": 2538.23, "total_tokens": 1789184} +{"current_steps": 3105, "total_steps": 67140, "loss": 0.8292, "lr": 2.3115877271373253e-05, "epoch": 0.4624664879356568, "percentage": 4.62, "elapsed_time": "0:11:46", "remaining_time": "4:02:40", "throughput": 2538.16, "total_tokens": 1791968} +{"current_steps": 3110, "total_steps": 67140, "loss": 0.8058, "lr": 2.3153112898421213e-05, "epoch": 0.463211200476616, "percentage": 4.63, "elapsed_time": "0:11:47", "remaining_time": "4:02:39", "throughput": 2538.1, "total_tokens": 1794816} +{"current_steps": 3115, "total_steps": 67140, "loss": 0.8127, "lr": 2.319034852546917e-05, "epoch": 0.4639559130175752, "percentage": 4.64, "elapsed_time": "0:11:48", "remaining_time": "4:02:37", "throughput": 2538.14, "total_tokens": 1797696} +{"current_steps": 3120, "total_steps": 67140, "loss": 0.8214, "lr": 2.322758415251713e-05, "epoch": 0.4647006255585344, "percentage": 4.65, "elapsed_time": "0:11:49", "remaining_time": "4:02:36", "throughput": 2538.21, "total_tokens": 1800640} +{"current_steps": 3125, "total_steps": 67140, "loss": 0.8343, "lr": 2.326481977956509e-05, "epoch": 0.4654453380994936, "percentage": 4.65, "elapsed_time": "0:11:50", "remaining_time": "4:02:35", "throughput": 2538.24, "total_tokens": 1803552} +{"current_steps": 3130, "total_steps": 67140, "loss": 0.8078, "lr": 2.330205540661305e-05, "epoch": 0.46619005064045277, "percentage": 4.66, "elapsed_time": "0:11:51", "remaining_time": "4:02:34", "throughput": 2538.42, "total_tokens": 1806624} +{"current_steps": 3135, "total_steps": 67140, "loss": 0.7926, "lr": 2.333929103366101e-05, "epoch": 0.46693476318141197, "percentage": 4.67, "elapsed_time": "0:11:52", "remaining_time": "4:02:34", "throughput": 2538.66, "total_tokens": 1809760} +{"current_steps": 3140, "total_steps": 67140, "loss": 0.8006, "lr": 2.3376526660708965e-05, "epoch": 0.4676794757223712, "percentage": 4.68, "elapsed_time": "0:11:53", "remaining_time": "4:02:32", "throughput": 2538.61, "total_tokens": 1812544} +{"current_steps": 3145, "total_steps": 67140, "loss": 0.8171, "lr": 2.341376228775693e-05, "epoch": 0.4684241882633304, "percentage": 4.68, "elapsed_time": "0:11:55", "remaining_time": "4:02:30", "throughput": 2538.32, "total_tokens": 1815072} +{"current_steps": 3150, "total_steps": 67140, "loss": 0.8089, "lr": 2.3450997914804888e-05, "epoch": 0.4691689008042895, "percentage": 4.69, "elapsed_time": "0:11:56", "remaining_time": "4:02:28", "throughput": 2538.16, "total_tokens": 1817760} +{"current_steps": 3155, "total_steps": 67140, "loss": 0.8073, "lr": 2.3488233541852848e-05, "epoch": 0.4699136133452487, "percentage": 4.7, "elapsed_time": "0:11:57", "remaining_time": "4:02:27", "throughput": 2538.04, "total_tokens": 1820512} +{"current_steps": 3160, "total_steps": 67140, "loss": 0.81, "lr": 2.3525469168900805e-05, "epoch": 0.47065832588620793, "percentage": 4.71, "elapsed_time": "0:11:58", "remaining_time": "4:02:26", "throughput": 2538.45, "total_tokens": 1823808} +{"current_steps": 3165, "total_steps": 67140, "loss": 0.7948, "lr": 2.3562704795948764e-05, "epoch": 0.47140303842716713, "percentage": 4.71, "elapsed_time": "0:11:59", "remaining_time": "4:02:25", "throughput": 2538.48, "total_tokens": 1826656} +{"current_steps": 3170, "total_steps": 67140, "loss": 0.8306, "lr": 2.3599940422996724e-05, "epoch": 0.4721477509681263, "percentage": 4.72, "elapsed_time": "0:12:00", "remaining_time": "4:02:26", "throughput": 2539.12, "total_tokens": 1830304} +{"current_steps": 3175, "total_steps": 67140, "loss": 0.8011, "lr": 2.3637176050044684e-05, "epoch": 0.4728924635090855, "percentage": 4.73, "elapsed_time": "0:12:02", "remaining_time": "4:02:25", "throughput": 2539.33, "total_tokens": 1833408} +{"current_steps": 3180, "total_steps": 67140, "loss": 0.7885, "lr": 2.367441167709264e-05, "epoch": 0.4736371760500447, "percentage": 4.74, "elapsed_time": "0:12:03", "remaining_time": "4:02:24", "throughput": 2539.13, "total_tokens": 1836096} +{"current_steps": 3185, "total_steps": 67140, "loss": 0.8015, "lr": 2.3711647304140604e-05, "epoch": 0.4743818885910039, "percentage": 4.74, "elapsed_time": "0:12:04", "remaining_time": "4:02:22", "throughput": 2539.12, "total_tokens": 1838912} +{"current_steps": 3190, "total_steps": 67140, "loss": 0.7958, "lr": 2.3748882931188564e-05, "epoch": 0.4751266011319631, "percentage": 4.75, "elapsed_time": "0:12:05", "remaining_time": "4:02:21", "throughput": 2539.14, "total_tokens": 1841824} +{"current_steps": 3195, "total_steps": 67140, "loss": 0.8026, "lr": 2.3786118558236524e-05, "epoch": 0.47587131367292224, "percentage": 4.76, "elapsed_time": "0:12:06", "remaining_time": "4:02:20", "throughput": 2539.2, "total_tokens": 1844800} +{"current_steps": 3200, "total_steps": 67140, "loss": 0.8187, "lr": 2.3823354185284483e-05, "epoch": 0.47661602621388144, "percentage": 4.77, "elapsed_time": "0:12:07", "remaining_time": "4:02:19", "throughput": 2539.2, "total_tokens": 1847648} +{"current_steps": 3205, "total_steps": 67140, "loss": 0.7782, "lr": 2.386058981233244e-05, "epoch": 0.47736073875484064, "percentage": 4.77, "elapsed_time": "0:12:08", "remaining_time": "4:02:17", "throughput": 2539.19, "total_tokens": 1850464} +{"current_steps": 3210, "total_steps": 67140, "loss": 0.7974, "lr": 2.38978254393804e-05, "epoch": 0.47810545129579984, "percentage": 4.78, "elapsed_time": "0:12:09", "remaining_time": "4:02:15", "throughput": 2539.15, "total_tokens": 1853248} +{"current_steps": 3215, "total_steps": 67140, "loss": 0.792, "lr": 2.393506106642836e-05, "epoch": 0.478850163836759, "percentage": 4.79, "elapsed_time": "0:12:10", "remaining_time": "4:02:14", "throughput": 2539.0, "total_tokens": 1856000} +{"current_steps": 3220, "total_steps": 67140, "loss": 0.8005, "lr": 2.397229669347632e-05, "epoch": 0.4795948763777182, "percentage": 4.8, "elapsed_time": "0:12:12", "remaining_time": "4:02:13", "throughput": 2539.04, "total_tokens": 1858944} +{"current_steps": 3225, "total_steps": 67140, "loss": 0.7765, "lr": 2.400953232052428e-05, "epoch": 0.4803395889186774, "percentage": 4.8, "elapsed_time": "0:12:13", "remaining_time": "4:02:13", "throughput": 2539.24, "total_tokens": 1862080} +{"current_steps": 3230, "total_steps": 67140, "loss": 0.7977, "lr": 2.404676794757224e-05, "epoch": 0.4810843014596366, "percentage": 4.81, "elapsed_time": "0:12:14", "remaining_time": "4:02:12", "throughput": 2539.32, "total_tokens": 1865088} +{"current_steps": 3235, "total_steps": 67140, "loss": 0.798, "lr": 2.40840035746202e-05, "epoch": 0.48182901400059575, "percentage": 4.82, "elapsed_time": "0:12:15", "remaining_time": "4:02:10", "throughput": 2538.94, "total_tokens": 1867552} +{"current_steps": 3240, "total_steps": 67140, "loss": 0.8523, "lr": 2.412123920166816e-05, "epoch": 0.48257372654155495, "percentage": 4.83, "elapsed_time": "0:12:16", "remaining_time": "4:02:10", "throughput": 2539.24, "total_tokens": 1870784} +{"current_steps": 3245, "total_steps": 67140, "loss": 0.8352, "lr": 2.4158474828716115e-05, "epoch": 0.48331843908251415, "percentage": 4.83, "elapsed_time": "0:12:17", "remaining_time": "4:02:09", "throughput": 2539.45, "total_tokens": 1873920} +{"current_steps": 3250, "total_steps": 67140, "loss": 0.7789, "lr": 2.4195710455764075e-05, "epoch": 0.48406315162347335, "percentage": 4.84, "elapsed_time": "0:12:19", "remaining_time": "4:02:09", "throughput": 2539.68, "total_tokens": 1877056} +{"current_steps": 3255, "total_steps": 67140, "loss": 0.817, "lr": 2.4232946082812035e-05, "epoch": 0.48480786416443256, "percentage": 4.85, "elapsed_time": "0:12:20", "remaining_time": "4:02:08", "throughput": 2539.85, "total_tokens": 1880160} +{"current_steps": 3260, "total_steps": 67140, "loss": 0.824, "lr": 2.4270181709859995e-05, "epoch": 0.4855525767053917, "percentage": 4.86, "elapsed_time": "0:12:21", "remaining_time": "4:02:07", "throughput": 2539.73, "total_tokens": 1882912} +{"current_steps": 3265, "total_steps": 67140, "loss": 0.8139, "lr": 2.4307417336907955e-05, "epoch": 0.4862972892463509, "percentage": 4.86, "elapsed_time": "0:12:22", "remaining_time": "4:02:05", "throughput": 2539.55, "total_tokens": 1885536} +{"current_steps": 3270, "total_steps": 67140, "loss": 0.8198, "lr": 2.4344652963955915e-05, "epoch": 0.4870420017873101, "percentage": 4.87, "elapsed_time": "0:12:23", "remaining_time": "4:02:04", "throughput": 2539.55, "total_tokens": 1888416} +{"current_steps": 3275, "total_steps": 67140, "loss": 0.8168, "lr": 2.4381888591003874e-05, "epoch": 0.4877867143282693, "percentage": 4.88, "elapsed_time": "0:12:24", "remaining_time": "4:02:03", "throughput": 2539.68, "total_tokens": 1891456} +{"current_steps": 3280, "total_steps": 67140, "loss": 0.8166, "lr": 2.4419124218051834e-05, "epoch": 0.48853142686922846, "percentage": 4.89, "elapsed_time": "0:12:25", "remaining_time": "4:02:01", "throughput": 2539.6, "total_tokens": 1894240} +{"current_steps": 3285, "total_steps": 67140, "loss": 0.8086, "lr": 2.4456359845099794e-05, "epoch": 0.48927613941018766, "percentage": 4.89, "elapsed_time": "0:12:27", "remaining_time": "4:02:00", "throughput": 2539.55, "total_tokens": 1897088} +{"current_steps": 3290, "total_steps": 67140, "loss": 0.8148, "lr": 2.449359547214775e-05, "epoch": 0.49002085195114686, "percentage": 4.9, "elapsed_time": "0:12:28", "remaining_time": "4:02:00", "throughput": 2539.76, "total_tokens": 1900192} +{"current_steps": 3295, "total_steps": 67140, "loss": 0.8207, "lr": 2.453083109919571e-05, "epoch": 0.49076556449210607, "percentage": 4.91, "elapsed_time": "0:12:29", "remaining_time": "4:01:59", "throughput": 2539.78, "total_tokens": 1903136} +{"current_steps": 3300, "total_steps": 67140, "loss": 0.7766, "lr": 2.456806672624367e-05, "epoch": 0.4915102770330652, "percentage": 4.92, "elapsed_time": "0:12:30", "remaining_time": "4:01:57", "throughput": 2539.8, "total_tokens": 1906016} +{"current_steps": 3305, "total_steps": 67140, "loss": 0.8123, "lr": 2.460530235329163e-05, "epoch": 0.4922549895740244, "percentage": 4.92, "elapsed_time": "0:12:31", "remaining_time": "4:01:57", "throughput": 2540.05, "total_tokens": 1909184} +{"current_steps": 3310, "total_steps": 67140, "loss": 0.8203, "lr": 2.464253798033959e-05, "epoch": 0.4929997021149836, "percentage": 4.93, "elapsed_time": "0:12:32", "remaining_time": "4:01:55", "throughput": 2539.88, "total_tokens": 1911872} +{"current_steps": 3315, "total_steps": 67140, "loss": 1.0299, "lr": 2.467977360738755e-05, "epoch": 0.4937444146559428, "percentage": 4.94, "elapsed_time": "0:12:33", "remaining_time": "4:01:55", "throughput": 2539.89, "total_tokens": 1914848} +{"current_steps": 3320, "total_steps": 67140, "loss": 0.7773, "lr": 2.471700923443551e-05, "epoch": 0.494489127196902, "percentage": 4.94, "elapsed_time": "0:12:35", "remaining_time": "4:01:54", "throughput": 2540.04, "total_tokens": 1917920} +{"current_steps": 3325, "total_steps": 67140, "loss": 0.84, "lr": 2.475424486148347e-05, "epoch": 0.49523383973786117, "percentage": 4.95, "elapsed_time": "0:12:36", "remaining_time": "4:01:53", "throughput": 2540.0, "total_tokens": 1920704} +{"current_steps": 3330, "total_steps": 67140, "loss": 0.8743, "lr": 2.4791480488531426e-05, "epoch": 0.4959785522788204, "percentage": 4.96, "elapsed_time": "0:12:37", "remaining_time": "4:01:50", "throughput": 2539.74, "total_tokens": 1923264} +{"current_steps": 3335, "total_steps": 67140, "loss": 3.2495, "lr": 2.4828716115579386e-05, "epoch": 0.4967232648197796, "percentage": 4.97, "elapsed_time": "0:12:38", "remaining_time": "4:01:49", "throughput": 2539.67, "total_tokens": 1926048} +{"current_steps": 3340, "total_steps": 67140, "loss": 0.8086, "lr": 2.4865951742627346e-05, "epoch": 0.4974679773607388, "percentage": 4.97, "elapsed_time": "0:12:39", "remaining_time": "4:01:48", "throughput": 2539.63, "total_tokens": 1928896} +{"current_steps": 3345, "total_steps": 67140, "loss": 0.8048, "lr": 2.4903187369675306e-05, "epoch": 0.4982126899016979, "percentage": 4.98, "elapsed_time": "0:12:40", "remaining_time": "4:01:47", "throughput": 2539.61, "total_tokens": 1931776} +{"current_steps": 3350, "total_steps": 67140, "loss": 0.7965, "lr": 2.494042299672327e-05, "epoch": 0.4989574024426571, "percentage": 4.99, "elapsed_time": "0:12:41", "remaining_time": "4:01:45", "throughput": 2539.6, "total_tokens": 1934624} +{"current_steps": 3355, "total_steps": 67140, "loss": 0.8057, "lr": 2.4977658623771225e-05, "epoch": 0.49970211498361633, "percentage": 5.0, "elapsed_time": "0:12:42", "remaining_time": "4:01:44", "throughput": 2539.67, "total_tokens": 1937600} +{"current_steps": 3357, "total_steps": 67140, "eval_loss": 0.8055608868598938, "epoch": 0.5, "percentage": 5.0, "elapsed_time": "0:13:57", "remaining_time": "4:25:14", "throughput": 2314.59, "total_tokens": 1938656} +{"current_steps": 3360, "total_steps": 67140, "loss": 0.825, "lr": 2.501489425081919e-05, "epoch": 0.5004468275245755, "percentage": 5.0, "elapsed_time": "0:13:59", "remaining_time": "4:25:37", "throughput": 2310.81, "total_tokens": 1940192} +{"current_steps": 3365, "total_steps": 67140, "loss": 0.7827, "lr": 2.505212987786714e-05, "epoch": 0.5011915400655347, "percentage": 5.01, "elapsed_time": "0:14:00", "remaining_time": "4:25:33", "throughput": 2310.97, "total_tokens": 1942912} +{"current_steps": 3370, "total_steps": 67140, "loss": 0.8375, "lr": 2.50893655049151e-05, "epoch": 0.5019362526064939, "percentage": 5.02, "elapsed_time": "0:14:01", "remaining_time": "4:25:29", "throughput": 2311.07, "total_tokens": 1945504} +{"current_steps": 3375, "total_steps": 67140, "loss": 0.8303, "lr": 2.512660113196306e-05, "epoch": 0.5026809651474531, "percentage": 5.03, "elapsed_time": "0:14:02", "remaining_time": "4:25:26", "throughput": 2311.44, "total_tokens": 1948512}