| {"current_steps": 10, "total_steps": 1500, "loss": 0.9315, "accuracy": 0.574999988079071, "learning_rate": 4.999451708687114e-06, "epoch": 0.008880994671403197, "percentage": 0.67, "elapsed_time": "0:01:23", "remaining_time": "3:26:19", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 20, "total_steps": 1500, "loss": 0.9318, "accuracy": 0.5249999761581421, "learning_rate": 4.997807075247147e-06, "epoch": 0.017761989342806393, "percentage": 1.33, "elapsed_time": "0:02:40", "remaining_time": "3:18:28", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 30, "total_steps": 1500, "loss": 0.9211, "accuracy": 0.6625000238418579, "learning_rate": 4.9950668210706795e-06, "epoch": 0.02664298401420959, "percentage": 2.0, "elapsed_time": "0:03:59", "remaining_time": "3:15:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 40, "total_steps": 1500, "loss": 0.941, "accuracy": 0.5375000238418579, "learning_rate": 4.9912321481237616e-06, "epoch": 0.035523978685612786, "percentage": 2.67, "elapsed_time": "0:05:15", "remaining_time": "3:11:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "loss": 0.929, "accuracy": 0.44999998807907104, "learning_rate": 4.986304738420684e-06, "epoch": 0.04440497335701599, "percentage": 3.33, "elapsed_time": "0:06:32", "remaining_time": "3:09:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9458721876144409, "epoch": 0.04440497335701599, "percentage": 3.33, "elapsed_time": "0:07:00", "remaining_time": "3:23:16", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 60, "total_steps": 1500, "loss": 0.9335, "accuracy": 0.5, "learning_rate": 4.980286753286196e-06, "epoch": 0.05328596802841918, "percentage": 4.0, "elapsed_time": "0:08:28", "remaining_time": "3:23:30", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 70, "total_steps": 1500, "loss": 0.9234, "accuracy": 0.6499999761581421, "learning_rate": 4.973180832407471e-06, "epoch": 0.06216696269982238, "percentage": 4.67, "elapsed_time": "0:09:46", "remaining_time": "3:19:45", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 80, "total_steps": 1500, "loss": 0.9317, "accuracy": 0.550000011920929, "learning_rate": 4.964990092676263e-06, "epoch": 0.07104795737122557, "percentage": 5.33, "elapsed_time": "0:11:06", "remaining_time": "3:17:03", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 90, "total_steps": 1500, "loss": 0.9276, "accuracy": 0.5625, "learning_rate": 4.9557181268217225e-06, "epoch": 0.07992895204262877, "percentage": 6.0, "elapsed_time": "0:12:23", "remaining_time": "3:14:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "loss": 0.9448, "accuracy": 0.5249999761581421, "learning_rate": 4.9453690018345144e-06, "epoch": 0.08880994671403197, "percentage": 6.67, "elapsed_time": "0:13:44", "remaining_time": "3:12:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 100, "total_steps": 1500, "eval_loss": 0.9382757544517517, "epoch": 0.08880994671403197, "percentage": 6.67, "elapsed_time": "0:14:11", "remaining_time": "3:18:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 110, "total_steps": 1500, "loss": 0.9307, "accuracy": 0.5874999761581421, "learning_rate": 4.933947257182901e-06, "epoch": 0.09769094138543517, "percentage": 7.33, "elapsed_time": "0:15:33", "remaining_time": "3:16:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 120, "total_steps": 1500, "loss": 0.9046, "accuracy": 0.574999988079071, "learning_rate": 4.921457902821578e-06, "epoch": 0.10657193605683836, "percentage": 8.0, "elapsed_time": "0:16:52", "remaining_time": "3:14:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 130, "total_steps": 1500, "loss": 0.9151, "accuracy": 0.6000000238418579, "learning_rate": 4.907906416994146e-06, "epoch": 0.11545293072824156, "percentage": 8.67, "elapsed_time": "0:18:11", "remaining_time": "3:11:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 140, "total_steps": 1500, "loss": 0.9053, "accuracy": 0.6000000238418579, "learning_rate": 4.893298743830168e-06, "epoch": 0.12433392539964476, "percentage": 9.33, "elapsed_time": "0:19:26", "remaining_time": "3:08:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "loss": 0.9097, "accuracy": 0.5375000238418579, "learning_rate": 4.8776412907378845e-06, "epoch": 0.13321492007104796, "percentage": 10.0, "elapsed_time": "0:20:41", "remaining_time": "3:06:15", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.9194123148918152, "epoch": 0.13321492007104796, "percentage": 10.0, "elapsed_time": "0:21:08", "remaining_time": "3:10:17", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 160, "total_steps": 1500, "loss": 0.8929, "accuracy": 0.6000000238418579, "learning_rate": 4.860940925593703e-06, "epoch": 0.14209591474245115, "percentage": 10.67, "elapsed_time": "0:22:35", "remaining_time": "3:09:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 170, "total_steps": 1500, "loss": 0.895, "accuracy": 0.625, "learning_rate": 4.84320497372973e-06, "epoch": 0.15097690941385436, "percentage": 11.33, "elapsed_time": "0:23:53", "remaining_time": "3:06:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 180, "total_steps": 1500, "loss": 0.8801, "accuracy": 0.5625, "learning_rate": 4.824441214720629e-06, "epoch": 0.15985790408525755, "percentage": 12.0, "elapsed_time": "0:25:08", "remaining_time": "3:04:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 190, "total_steps": 1500, "loss": 0.8776, "accuracy": 0.6499999761581421, "learning_rate": 4.804657878971252e-06, "epoch": 0.16873889875666073, "percentage": 12.67, "elapsed_time": "0:26:22", "remaining_time": "3:01:53", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "loss": 0.8596, "accuracy": 0.5874999761581421, "learning_rate": 4.783863644106502e-06, "epoch": 0.17761989342806395, "percentage": 13.33, "elapsed_time": "0:27:39", "remaining_time": "2:59:49", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8602121472358704, "epoch": 0.17761989342806395, "percentage": 13.33, "elapsed_time": "0:28:06", "remaining_time": "3:02:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 210, "total_steps": 1500, "loss": 0.8553, "accuracy": 0.625, "learning_rate": 4.762067631165049e-06, "epoch": 0.18650088809946713, "percentage": 14.0, "elapsed_time": "0:29:28", "remaining_time": "3:01:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 220, "total_steps": 1500, "loss": 0.8204, "accuracy": 0.574999988079071, "learning_rate": 4.7392794005985324e-06, "epoch": 0.19538188277087035, "percentage": 14.67, "elapsed_time": "0:30:46", "remaining_time": "2:59:05", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 230, "total_steps": 1500, "loss": 0.7884, "accuracy": 0.612500011920929, "learning_rate": 4.715508948078037e-06, "epoch": 0.20426287744227353, "percentage": 15.33, "elapsed_time": "0:32:01", "remaining_time": "2:56:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 240, "total_steps": 1500, "loss": 0.7919, "accuracy": 0.612500011920929, "learning_rate": 4.690766700109659e-06, "epoch": 0.21314387211367672, "percentage": 16.0, "elapsed_time": "0:33:17", "remaining_time": "2:54:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "loss": 0.7456, "accuracy": 0.675000011920929, "learning_rate": 4.665063509461098e-06, "epoch": 0.22202486678507993, "percentage": 16.67, "elapsed_time": "0:34:33", "remaining_time": "2:52:46", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7499477863311768, "epoch": 0.22202486678507993, "percentage": 16.67, "elapsed_time": "0:35:00", "remaining_time": "2:55:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 260, "total_steps": 1500, "loss": 0.6853, "accuracy": 0.7749999761581421, "learning_rate": 4.638410650401267e-06, "epoch": 0.23090586145648312, "percentage": 17.33, "elapsed_time": "0:36:25", "remaining_time": "2:53:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 270, "total_steps": 1500, "loss": 0.6514, "accuracy": 0.7124999761581421, "learning_rate": 4.610819813755038e-06, "epoch": 0.23978685612788633, "percentage": 18.0, "elapsed_time": "0:37:40", "remaining_time": "2:51:37", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 280, "total_steps": 1500, "loss": 0.6447, "accuracy": 0.612500011920929, "learning_rate": 4.582303101775249e-06, "epoch": 0.24866785079928952, "percentage": 18.67, "elapsed_time": "0:38:58", "remaining_time": "2:49:51", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 290, "total_steps": 1500, "loss": 0.5863, "accuracy": 0.6875, "learning_rate": 4.55287302283426e-06, "epoch": 0.25754884547069273, "percentage": 19.33, "elapsed_time": "0:40:15", "remaining_time": "2:47:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "loss": 0.5354, "accuracy": 0.75, "learning_rate": 4.522542485937369e-06, "epoch": 0.2664298401420959, "percentage": 20.0, "elapsed_time": "0:41:27", "remaining_time": "2:45:50", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 300, "total_steps": 1500, "eval_loss": 0.5640697479248047, "epoch": 0.2664298401420959, "percentage": 20.0, "elapsed_time": "0:41:54", "remaining_time": "2:47:38", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 310, "total_steps": 1500, "loss": 0.5357, "accuracy": 0.6875, "learning_rate": 4.491324795060491e-06, "epoch": 0.2753108348134991, "percentage": 20.67, "elapsed_time": "0:43:16", "remaining_time": "2:46:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 320, "total_steps": 1500, "loss": 0.5412, "accuracy": 0.6625000238418579, "learning_rate": 4.4592336433146e-06, "epoch": 0.2841918294849023, "percentage": 21.33, "elapsed_time": "0:44:30", "remaining_time": "2:44:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 330, "total_steps": 1500, "loss": 0.5502, "accuracy": 0.675000011920929, "learning_rate": 4.426283106939474e-06, "epoch": 0.29307282415630553, "percentage": 22.0, "elapsed_time": "0:45:44", "remaining_time": "2:42:09", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 340, "total_steps": 1500, "loss": 0.5519, "accuracy": 0.637499988079071, "learning_rate": 4.3924876391293915e-06, "epoch": 0.3019538188277087, "percentage": 22.67, "elapsed_time": "0:47:01", "remaining_time": "2:40:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "loss": 0.4806, "accuracy": 0.7124999761581421, "learning_rate": 4.357862063693486e-06, "epoch": 0.3108348134991119, "percentage": 23.33, "elapsed_time": "0:48:18", "remaining_time": "2:38:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 350, "total_steps": 1500, "eval_loss": 0.4698469638824463, "epoch": 0.3108348134991119, "percentage": 23.33, "elapsed_time": "0:48:45", "remaining_time": "2:40:11", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 360, "total_steps": 1500, "loss": 0.472, "accuracy": 0.7875000238418579, "learning_rate": 4.322421568553529e-06, "epoch": 0.3197158081705151, "percentage": 24.0, "elapsed_time": "0:50:07", "remaining_time": "2:38:43", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 370, "total_steps": 1500, "loss": 0.4169, "accuracy": 0.8374999761581421, "learning_rate": 4.286181699082008e-06, "epoch": 0.3285968028419183, "percentage": 24.67, "elapsed_time": "0:51:22", "remaining_time": "2:36:54", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 380, "total_steps": 1500, "loss": 0.4156, "accuracy": 0.8500000238418579, "learning_rate": 4.249158351283414e-06, "epoch": 0.33747779751332146, "percentage": 25.33, "elapsed_time": "0:52:43", "remaining_time": "2:35:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 390, "total_steps": 1500, "loss": 0.4085, "accuracy": 0.862500011920929, "learning_rate": 4.211367764821722e-06, "epoch": 0.3463587921847247, "percentage": 26.0, "elapsed_time": "0:53:59", "remaining_time": "2:33:39", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "loss": 0.3723, "accuracy": 0.887499988079071, "learning_rate": 4.172826515897146e-06, "epoch": 0.3552397868561279, "percentage": 26.67, "elapsed_time": "0:55:19", "remaining_time": "2:32:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.38738909363746643, "epoch": 0.3552397868561279, "percentage": 26.67, "elapsed_time": "0:55:46", "remaining_time": "2:33:22", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 410, "total_steps": 1500, "loss": 0.4031, "accuracy": 0.8999999761581421, "learning_rate": 4.133551509975264e-06, "epoch": 0.3641207815275311, "percentage": 27.33, "elapsed_time": "0:57:11", "remaining_time": "2:32:02", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 420, "total_steps": 1500, "loss": 0.3609, "accuracy": 0.862500011920929, "learning_rate": 4.093559974371725e-06, "epoch": 0.37300177619893427, "percentage": 28.0, "elapsed_time": "0:58:30", "remaining_time": "2:30:26", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 430, "total_steps": 1500, "loss": 0.3669, "accuracy": 0.8500000238418579, "learning_rate": 4.052869450695776e-06, "epoch": 0.38188277087033745, "percentage": 28.67, "elapsed_time": "0:59:51", "remaining_time": "2:28:56", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 440, "total_steps": 1500, "loss": 0.3428, "accuracy": 0.925000011920929, "learning_rate": 4.011497787155938e-06, "epoch": 0.3907637655417407, "percentage": 29.33, "elapsed_time": "1:01:09", "remaining_time": "2:27:21", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "loss": 0.3589, "accuracy": 0.8500000238418579, "learning_rate": 3.969463130731183e-06, "epoch": 0.3996447602131439, "percentage": 30.0, "elapsed_time": "1:02:22", "remaining_time": "2:25:32", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.35665163397789, "epoch": 0.3996447602131439, "percentage": 30.0, "elapsed_time": "1:02:49", "remaining_time": "2:26:35", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 460, "total_steps": 1500, "loss": 0.3338, "accuracy": 0.875, "learning_rate": 3.92678391921108e-06, "epoch": 0.40852575488454707, "percentage": 30.67, "elapsed_time": "1:04:12", "remaining_time": "2:25:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 470, "total_steps": 1500, "loss": 0.3348, "accuracy": 0.925000011920929, "learning_rate": 3.88347887310836e-06, "epoch": 0.41740674955595025, "percentage": 31.33, "elapsed_time": "1:05:35", "remaining_time": "2:23:44", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 480, "total_steps": 1500, "loss": 0.3171, "accuracy": 0.862500011920929, "learning_rate": 3.839566987447492e-06, "epoch": 0.42628774422735344, "percentage": 32.0, "elapsed_time": "1:06:53", "remaining_time": "2:22:08", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 490, "total_steps": 1500, "loss": 0.3238, "accuracy": 0.925000011920929, "learning_rate": 3.795067523432826e-06, "epoch": 0.4351687388987567, "percentage": 32.67, "elapsed_time": "1:08:15", "remaining_time": "2:20:41", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "loss": 0.3052, "accuracy": 0.875, "learning_rate": 3.7500000000000005e-06, "epoch": 0.44404973357015987, "percentage": 33.33, "elapsed_time": "1:09:35", "remaining_time": "2:19:10", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.324949711561203, "epoch": 0.44404973357015987, "percentage": 33.33, "elapsed_time": "1:10:02", "remaining_time": "2:20:04", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 510, "total_steps": 1500, "loss": 0.3185, "accuracy": 0.862500011920929, "learning_rate": 3.7043841852542884e-06, "epoch": 0.45293072824156305, "percentage": 34.0, "elapsed_time": "1:11:24", "remaining_time": "2:18:36", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 520, "total_steps": 1500, "loss": 0.3148, "accuracy": 0.875, "learning_rate": 3.658240087799655e-06, "epoch": 0.46181172291296624, "percentage": 34.67, "elapsed_time": "1:12:44", "remaining_time": "2:17:06", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 530, "total_steps": 1500, "loss": 0.3191, "accuracy": 0.9375, "learning_rate": 3.611587947962319e-06, "epoch": 0.4706927175843694, "percentage": 35.33, "elapsed_time": "1:14:02", "remaining_time": "2:15:31", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 540, "total_steps": 1500, "loss": 0.276, "accuracy": 0.8999999761581421, "learning_rate": 3.564448228912682e-06, "epoch": 0.47957371225577267, "percentage": 36.0, "elapsed_time": "1:15:23", "remaining_time": "2:14:01", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "loss": 0.3257, "accuracy": 0.9375, "learning_rate": 3.516841607689501e-06, "epoch": 0.48845470692717585, "percentage": 36.67, "elapsed_time": "1:16:40", "remaining_time": "2:12:25", "throughput": "0.00", "total_tokens": 0} | |
| {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.30456680059432983, "epoch": 0.48845470692717585, "percentage": 36.67, "elapsed_time": "1:17:07", "remaining_time": "2:13:12", "throughput": "0.00", "total_tokens": 0} | |