Files
llama3.2-1b-gsm8k-full/trainer_log.jsonl
ModelHub XC dd42342cca 初始化项目,由ModelHub XC社区提供模型
Model: SidhaarthMurali/llama3.2-1b-gsm8k-full
Source: Original Platform
2026-05-15 15:08:49 +08:00

165 lines
31 KiB
JSON

{"current_steps": 10, "total_steps": 1632, "loss": 1.2036, "lr": 6.097560975609757e-07, "epoch": 0.01838235294117647, "percentage": 0.61, "elapsed_time": "0:00:06", "remaining_time": "0:17:09"}
{"current_steps": 20, "total_steps": 1632, "loss": 1.2064, "lr": 1.2195121951219514e-06, "epoch": 0.03676470588235294, "percentage": 1.23, "elapsed_time": "0:00:11", "remaining_time": "0:15:49"}
{"current_steps": 30, "total_steps": 1632, "loss": 1.2741, "lr": 1.8292682926829268e-06, "epoch": 0.05514705882352941, "percentage": 1.84, "elapsed_time": "0:00:17", "remaining_time": "0:15:16"}
{"current_steps": 40, "total_steps": 1632, "loss": 0.7596, "lr": 2.4390243902439027e-06, "epoch": 0.07352941176470588, "percentage": 2.45, "elapsed_time": "0:00:22", "remaining_time": "0:14:58"}
{"current_steps": 50, "total_steps": 1632, "loss": 0.6171, "lr": 3.0487804878048782e-06, "epoch": 0.09191176470588236, "percentage": 3.06, "elapsed_time": "0:00:27", "remaining_time": "0:14:44"}
{"current_steps": 60, "total_steps": 1632, "loss": 0.794, "lr": 3.6585365853658537e-06, "epoch": 0.11029411764705882, "percentage": 3.68, "elapsed_time": "0:00:33", "remaining_time": "0:14:33"}
{"current_steps": 70, "total_steps": 1632, "loss": 0.6233, "lr": 4.268292682926829e-06, "epoch": 0.12867647058823528, "percentage": 4.29, "elapsed_time": "0:00:38", "remaining_time": "0:14:25"}
{"current_steps": 80, "total_steps": 1632, "loss": 0.5441, "lr": 4.8780487804878055e-06, "epoch": 0.14705882352941177, "percentage": 4.9, "elapsed_time": "0:00:44", "remaining_time": "0:14:16"}
{"current_steps": 90, "total_steps": 1632, "loss": 0.5784, "lr": 5.487804878048781e-06, "epoch": 0.16544117647058823, "percentage": 5.51, "elapsed_time": "0:00:49", "remaining_time": "0:14:08"}
{"current_steps": 100, "total_steps": 1632, "loss": 0.4844, "lr": 6.0975609756097564e-06, "epoch": 0.18382352941176472, "percentage": 6.13, "elapsed_time": "0:00:54", "remaining_time": "0:14:00"}
{"current_steps": 110, "total_steps": 1632, "loss": 0.6535, "lr": 6.707317073170733e-06, "epoch": 0.20220588235294118, "percentage": 6.74, "elapsed_time": "0:01:00", "remaining_time": "0:13:53"}
{"current_steps": 120, "total_steps": 1632, "loss": 0.6897, "lr": 7.317073170731707e-06, "epoch": 0.22058823529411764, "percentage": 7.35, "elapsed_time": "0:01:05", "remaining_time": "0:13:47"}
{"current_steps": 130, "total_steps": 1632, "loss": 0.4217, "lr": 7.926829268292685e-06, "epoch": 0.23897058823529413, "percentage": 7.97, "elapsed_time": "0:01:11", "remaining_time": "0:13:41"}
{"current_steps": 140, "total_steps": 1632, "loss": 0.5868, "lr": 8.536585365853658e-06, "epoch": 0.25735294117647056, "percentage": 8.58, "elapsed_time": "0:01:16", "remaining_time": "0:13:35"}
{"current_steps": 150, "total_steps": 1632, "loss": 0.53, "lr": 9.146341463414635e-06, "epoch": 0.2757352941176471, "percentage": 9.19, "elapsed_time": "0:01:21", "remaining_time": "0:13:29"}
{"current_steps": 160, "total_steps": 1632, "loss": 0.5538, "lr": 9.756097560975611e-06, "epoch": 0.29411764705882354, "percentage": 9.8, "elapsed_time": "0:01:27", "remaining_time": "0:13:23"}
{"current_steps": 170, "total_steps": 1632, "loss": 0.4616, "lr": 9.999587822598768e-06, "epoch": 0.3125, "percentage": 10.42, "elapsed_time": "0:01:32", "remaining_time": "0:13:17"}
{"current_steps": 180, "total_steps": 1632, "loss": 0.5633, "lr": 9.997069206794246e-06, "epoch": 0.33088235294117646, "percentage": 11.03, "elapsed_time": "0:01:38", "remaining_time": "0:13:11"}
{"current_steps": 190, "total_steps": 1632, "loss": 0.6035, "lr": 9.992262114666653e-06, "epoch": 0.3492647058823529, "percentage": 11.64, "elapsed_time": "0:01:43", "remaining_time": "0:13:05"}
{"current_steps": 200, "total_steps": 1632, "loss": 0.5822, "lr": 9.985168747689706e-06, "epoch": 0.36764705882352944, "percentage": 12.25, "elapsed_time": "0:01:48", "remaining_time": "0:13:00"}
{"current_steps": 210, "total_steps": 1632, "loss": 0.3755, "lr": 9.975792354368019e-06, "epoch": 0.3860294117647059, "percentage": 12.87, "elapsed_time": "0:01:54", "remaining_time": "0:12:54"}
{"current_steps": 220, "total_steps": 1632, "loss": 0.4914, "lr": 9.964137228749409e-06, "epoch": 0.40441176470588236, "percentage": 13.48, "elapsed_time": "0:01:59", "remaining_time": "0:12:49"}
{"current_steps": 230, "total_steps": 1632, "loss": 0.4604, "lr": 9.950208708458371e-06, "epoch": 0.4227941176470588, "percentage": 14.09, "elapsed_time": "0:02:05", "remaining_time": "0:12:43"}
{"current_steps": 240, "total_steps": 1632, "loss": 0.5029, "lr": 9.934013172251654e-06, "epoch": 0.4411764705882353, "percentage": 14.71, "elapsed_time": "0:02:10", "remaining_time": "0:12:37"}
{"current_steps": 250, "total_steps": 1632, "loss": 0.5404, "lr": 9.915558037097003e-06, "epoch": 0.45955882352941174, "percentage": 15.32, "elapsed_time": "0:02:16", "remaining_time": "0:12:32"}
{"current_steps": 260, "total_steps": 1632, "loss": 0.3555, "lr": 9.894851754776473e-06, "epoch": 0.47794117647058826, "percentage": 15.93, "elapsed_time": "0:02:21", "remaining_time": "0:12:26"}
{"current_steps": 270, "total_steps": 1632, "loss": 0.4092, "lr": 9.871903808015812e-06, "epoch": 0.4963235294117647, "percentage": 16.54, "elapsed_time": "0:02:26", "remaining_time": "0:12:21"}
{"current_steps": 280, "total_steps": 1632, "loss": 0.4489, "lr": 9.846724706141718e-06, "epoch": 0.5147058823529411, "percentage": 17.16, "elapsed_time": "0:02:32", "remaining_time": "0:12:15"}
{"current_steps": 290, "total_steps": 1632, "loss": 0.5297, "lr": 9.819325980268946e-06, "epoch": 0.5330882352941176, "percentage": 17.77, "elapsed_time": "0:02:37", "remaining_time": "0:12:10"}
{"current_steps": 300, "total_steps": 1632, "loss": 0.4301, "lr": 9.789720178019483e-06, "epoch": 0.5514705882352942, "percentage": 18.38, "elapsed_time": "0:02:43", "remaining_time": "0:12:04"}
{"current_steps": 310, "total_steps": 1632, "loss": 0.5499, "lr": 9.757920857776188e-06, "epoch": 0.5698529411764706, "percentage": 19.0, "elapsed_time": "0:02:48", "remaining_time": "0:11:59"}
{"current_steps": 320, "total_steps": 1632, "loss": 0.3723, "lr": 9.723942582473545e-06, "epoch": 0.5882352941176471, "percentage": 19.61, "elapsed_time": "0:02:54", "remaining_time": "0:11:54"}
{"current_steps": 330, "total_steps": 1632, "loss": 0.6103, "lr": 9.687800912928362e-06, "epoch": 0.6066176470588235, "percentage": 20.22, "elapsed_time": "0:02:59", "remaining_time": "0:11:48"}
{"current_steps": 340, "total_steps": 1632, "loss": 0.5561, "lr": 9.649512400713497e-06, "epoch": 0.625, "percentage": 20.83, "elapsed_time": "0:03:04", "remaining_time": "0:11:42"}
{"current_steps": 350, "total_steps": 1632, "loss": 0.4384, "lr": 9.609094580577825e-06, "epoch": 0.6433823529411765, "percentage": 21.45, "elapsed_time": "0:03:10", "remaining_time": "0:11:37"}
{"current_steps": 360, "total_steps": 1632, "loss": 0.492, "lr": 9.566565962415958e-06, "epoch": 0.6617647058823529, "percentage": 22.06, "elapsed_time": "0:03:15", "remaining_time": "0:11:31"}
{"current_steps": 370, "total_steps": 1632, "loss": 0.5596, "lr": 9.521946022791402e-06, "epoch": 0.6801470588235294, "percentage": 22.67, "elapsed_time": "0:03:21", "remaining_time": "0:11:26"}
{"current_steps": 380, "total_steps": 1632, "loss": 0.4657, "lr": 9.475255196016972e-06, "epoch": 0.6985294117647058, "percentage": 23.28, "elapsed_time": "0:03:26", "remaining_time": "0:11:20"}
{"current_steps": 390, "total_steps": 1632, "loss": 0.547, "lr": 9.426514864796648e-06, "epoch": 0.7169117647058824, "percentage": 23.9, "elapsed_time": "0:03:32", "remaining_time": "0:11:15"}
{"current_steps": 400, "total_steps": 1632, "loss": 0.4821, "lr": 9.375747350433044e-06, "epoch": 0.7352941176470589, "percentage": 24.51, "elapsed_time": "0:03:37", "remaining_time": "0:11:09"}
{"current_steps": 410, "total_steps": 1632, "loss": 0.3627, "lr": 9.322975902605082e-06, "epoch": 0.7536764705882353, "percentage": 25.12, "elapsed_time": "0:03:42", "remaining_time": "0:11:04"}
{"current_steps": 420, "total_steps": 1632, "loss": 0.2779, "lr": 9.268224688720475e-06, "epoch": 0.7720588235294118, "percentage": 25.74, "elapsed_time": "0:03:48", "remaining_time": "0:10:58"}
{"current_steps": 430, "total_steps": 1632, "loss": 0.684, "lr": 9.211518782847932e-06, "epoch": 0.7904411764705882, "percentage": 26.35, "elapsed_time": "0:03:53", "remaining_time": "0:10:53"}
{"current_steps": 440, "total_steps": 1632, "loss": 0.3829, "lr": 9.152884154234147e-06, "epoch": 0.8088235294117647, "percentage": 26.96, "elapsed_time": "0:03:59", "remaining_time": "0:10:47"}
{"current_steps": 450, "total_steps": 1632, "loss": 0.409, "lr": 9.092347655410818e-06, "epoch": 0.8272058823529411, "percentage": 27.57, "elapsed_time": "0:04:04", "remaining_time": "0:10:42"}
{"current_steps": 460, "total_steps": 1632, "loss": 0.4189, "lr": 9.029937009897176e-06, "epoch": 0.8455882352941176, "percentage": 28.19, "elapsed_time": "0:04:09", "remaining_time": "0:10:36"}
{"current_steps": 470, "total_steps": 1632, "loss": 0.4846, "lr": 8.96568079950361e-06, "epoch": 0.8639705882352942, "percentage": 28.8, "elapsed_time": "0:04:15", "remaining_time": "0:10:31"}
{"current_steps": 480, "total_steps": 1632, "loss": 0.4869, "lr": 8.899608451242233e-06, "epoch": 0.8823529411764706, "percentage": 29.41, "elapsed_time": "0:04:20", "remaining_time": "0:10:25"}
{"current_steps": 490, "total_steps": 1632, "loss": 0.368, "lr": 8.83175022385039e-06, "epoch": 0.9007352941176471, "percentage": 30.02, "elapsed_time": "0:04:26", "remaining_time": "0:10:20"}
{"current_steps": 500, "total_steps": 1632, "loss": 0.3489, "lr": 8.762137193933241e-06, "epoch": 0.9191176470588235, "percentage": 30.64, "elapsed_time": "0:04:31", "remaining_time": "0:10:14"}
{"current_steps": 510, "total_steps": 1632, "loss": 0.4095, "lr": 8.690801241731818e-06, "epoch": 0.9375, "percentage": 31.25, "elapsed_time": "0:04:52", "remaining_time": "0:10:42"}
{"current_steps": 520, "total_steps": 1632, "loss": 0.4641, "lr": 8.617775036523014e-06, "epoch": 0.9558823529411765, "percentage": 31.86, "elapsed_time": "0:04:57", "remaining_time": "0:10:36"}
{"current_steps": 530, "total_steps": 1632, "loss": 0.3311, "lr": 8.543092021658259e-06, "epoch": 0.9742647058823529, "percentage": 32.48, "elapsed_time": "0:05:03", "remaining_time": "0:10:30"}
{"current_steps": 540, "total_steps": 1632, "loss": 0.3561, "lr": 8.466786399247663e-06, "epoch": 0.9926470588235294, "percentage": 33.09, "elapsed_time": "0:05:08", "remaining_time": "0:10:23"}
{"current_steps": 550, "total_steps": 1632, "loss": 0.3474, "lr": 8.388893114496706e-06, "epoch": 1.0110294117647058, "percentage": 33.7, "elapsed_time": "0:05:13", "remaining_time": "0:10:17"}
{"current_steps": 560, "total_steps": 1632, "loss": 0.2188, "lr": 8.309447839702583e-06, "epoch": 1.0294117647058822, "percentage": 34.31, "elapsed_time": "0:05:19", "remaining_time": "0:10:11"}
{"current_steps": 570, "total_steps": 1632, "loss": 0.2178, "lr": 8.228486957917608e-06, "epoch": 1.0477941176470589, "percentage": 34.93, "elapsed_time": "0:05:24", "remaining_time": "0:10:05"}
{"current_steps": 580, "total_steps": 1632, "loss": 0.2783, "lr": 8.146047546287077e-06, "epoch": 1.0661764705882353, "percentage": 35.54, "elapsed_time": "0:05:30", "remaining_time": "0:09:58"}
{"current_steps": 590, "total_steps": 1632, "loss": 0.2463, "lr": 8.062167359069301e-06, "epoch": 1.0845588235294117, "percentage": 36.15, "elapsed_time": "0:05:35", "remaining_time": "0:09:52"}
{"current_steps": 600, "total_steps": 1632, "loss": 0.2634, "lr": 7.97688481034551e-06, "epoch": 1.1029411764705883, "percentage": 36.76, "elapsed_time": "0:05:41", "remaining_time": "0:09:46"}
{"current_steps": 610, "total_steps": 1632, "loss": 0.294, "lr": 7.8902389564276e-06, "epoch": 1.1213235294117647, "percentage": 37.38, "elapsed_time": "0:05:46", "remaining_time": "0:09:40"}
{"current_steps": 620, "total_steps": 1632, "loss": 0.273, "lr": 7.802269477971771e-06, "epoch": 1.1397058823529411, "percentage": 37.99, "elapsed_time": "0:05:51", "remaining_time": "0:09:34"}
{"current_steps": 630, "total_steps": 1632, "loss": 0.2975, "lr": 7.713016661806213e-06, "epoch": 1.1580882352941178, "percentage": 38.6, "elapsed_time": "0:05:57", "remaining_time": "0:09:28"}
{"current_steps": 640, "total_steps": 1632, "loss": 0.2831, "lr": 7.622521382481208e-06, "epoch": 1.1764705882352942, "percentage": 39.22, "elapsed_time": "0:06:02", "remaining_time": "0:09:22"}
{"current_steps": 650, "total_steps": 1632, "loss": 0.3548, "lr": 7.530825083550073e-06, "epoch": 1.1948529411764706, "percentage": 39.83, "elapsed_time": "0:06:08", "remaining_time": "0:09:16"}
{"current_steps": 660, "total_steps": 1632, "loss": 0.2454, "lr": 7.437969758589508e-06, "epoch": 1.213235294117647, "percentage": 40.44, "elapsed_time": "0:06:13", "remaining_time": "0:09:10"}
{"current_steps": 670, "total_steps": 1632, "loss": 0.2694, "lr": 7.343997931968068e-06, "epoch": 1.2316176470588236, "percentage": 41.05, "elapsed_time": "0:06:19", "remaining_time": "0:09:04"}
{"current_steps": 680, "total_steps": 1632, "loss": 0.3091, "lr": 7.248952639371543e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "0:06:24", "remaining_time": "0:08:58"}
{"current_steps": 690, "total_steps": 1632, "loss": 0.2305, "lr": 7.152877408094179e-06, "epoch": 1.2683823529411764, "percentage": 42.28, "elapsed_time": "0:06:29", "remaining_time": "0:08:52"}
{"current_steps": 700, "total_steps": 1632, "loss": 0.3002, "lr": 7.055816237104753e-06, "epoch": 1.2867647058823528, "percentage": 42.89, "elapsed_time": "0:06:35", "remaining_time": "0:08:46"}
{"current_steps": 710, "total_steps": 1632, "loss": 0.2868, "lr": 6.957813576896647e-06, "epoch": 1.3051470588235294, "percentage": 43.5, "elapsed_time": "0:06:40", "remaining_time": "0:08:40"}
{"current_steps": 720, "total_steps": 1632, "loss": 0.2342, "lr": 6.858914309131131e-06, "epoch": 1.3235294117647058, "percentage": 44.12, "elapsed_time": "0:06:45", "remaining_time": "0:08:34"}
{"current_steps": 730, "total_steps": 1632, "loss": 0.2143, "lr": 6.7591637260831925e-06, "epoch": 1.3419117647058822, "percentage": 44.73, "elapsed_time": "0:06:51", "remaining_time": "0:08:28"}
{"current_steps": 740, "total_steps": 1632, "loss": 0.3071, "lr": 6.6586075098993196e-06, "epoch": 1.3602941176470589, "percentage": 45.34, "elapsed_time": "0:06:56", "remaining_time": "0:08:22"}
{"current_steps": 750, "total_steps": 1632, "loss": 0.2977, "lr": 6.557291711676738e-06, "epoch": 1.3786764705882353, "percentage": 45.96, "elapsed_time": "0:07:02", "remaining_time": "0:08:16"}
{"current_steps": 760, "total_steps": 1632, "loss": 0.2326, "lr": 6.455262730373673e-06, "epoch": 1.3970588235294117, "percentage": 46.57, "elapsed_time": "0:07:07", "remaining_time": "0:08:10"}
{"current_steps": 770, "total_steps": 1632, "loss": 0.3158, "lr": 6.352567291560319e-06, "epoch": 1.4154411764705883, "percentage": 47.18, "elapsed_time": "0:07:12", "remaining_time": "0:08:04"}
{"current_steps": 780, "total_steps": 1632, "loss": 0.3301, "lr": 6.249252426020217e-06, "epoch": 1.4338235294117647, "percentage": 47.79, "elapsed_time": "0:07:18", "remaining_time": "0:07:58"}
{"current_steps": 790, "total_steps": 1632, "loss": 0.2937, "lr": 6.145365448211866e-06, "epoch": 1.4522058823529411, "percentage": 48.41, "elapsed_time": "0:07:23", "remaining_time": "0:07:53"}
{"current_steps": 800, "total_steps": 1632, "loss": 0.2229, "lr": 6.040953934600425e-06, "epoch": 1.4705882352941178, "percentage": 49.02, "elapsed_time": "0:07:29", "remaining_time": "0:07:47"}
{"current_steps": 810, "total_steps": 1632, "loss": 0.3169, "lr": 5.936065701869404e-06, "epoch": 1.4889705882352942, "percentage": 49.63, "elapsed_time": "0:07:34", "remaining_time": "0:07:41"}
{"current_steps": 820, "total_steps": 1632, "loss": 0.257, "lr": 5.830748785022369e-06, "epoch": 1.5073529411764706, "percentage": 50.25, "elapsed_time": "0:07:40", "remaining_time": "0:07:35"}
{"current_steps": 830, "total_steps": 1632, "loss": 0.2766, "lr": 5.725051415384657e-06, "epoch": 1.5257352941176472, "percentage": 50.86, "elapsed_time": "0:07:45", "remaining_time": "0:07:29"}
{"current_steps": 840, "total_steps": 1632, "loss": 0.2385, "lr": 5.619021998515165e-06, "epoch": 1.5441176470588234, "percentage": 51.47, "elapsed_time": "0:07:50", "remaining_time": "0:07:23"}
{"current_steps": 850, "total_steps": 1632, "loss": 0.2844, "lr": 5.51270909203838e-06, "epoch": 1.5625, "percentage": 52.08, "elapsed_time": "0:07:56", "remaining_time": "0:07:18"}
{"current_steps": 860, "total_steps": 1632, "loss": 0.2924, "lr": 5.40616138340673e-06, "epoch": 1.5808823529411766, "percentage": 52.7, "elapsed_time": "0:08:01", "remaining_time": "0:07:12"}
{"current_steps": 870, "total_steps": 1632, "loss": 0.2826, "lr": 5.299427667603516e-06, "epoch": 1.5992647058823528, "percentage": 53.31, "elapsed_time": "0:08:07", "remaining_time": "0:07:06"}
{"current_steps": 880, "total_steps": 1632, "loss": 0.2106, "lr": 5.1925568247965686e-06, "epoch": 1.6176470588235294, "percentage": 53.92, "elapsed_time": "0:08:12", "remaining_time": "0:07:00"}
{"current_steps": 890, "total_steps": 1632, "loss": 0.3306, "lr": 5.085597797952906e-06, "epoch": 1.6360294117647058, "percentage": 54.53, "elapsed_time": "0:08:18", "remaining_time": "0:06:55"}
{"current_steps": 900, "total_steps": 1632, "loss": 0.2227, "lr": 4.97859957042464e-06, "epoch": 1.6544117647058822, "percentage": 55.15, "elapsed_time": "0:08:23", "remaining_time": "0:06:49"}
{"current_steps": 910, "total_steps": 1632, "loss": 0.2275, "lr": 4.871611143516367e-06, "epoch": 1.6727941176470589, "percentage": 55.76, "elapsed_time": "0:08:28", "remaining_time": "0:06:43"}
{"current_steps": 920, "total_steps": 1632, "loss": 0.2966, "lr": 4.7646815140443625e-06, "epoch": 1.6911764705882353, "percentage": 56.37, "elapsed_time": "0:08:34", "remaining_time": "0:06:38"}
{"current_steps": 930, "total_steps": 1632, "loss": 0.228, "lr": 4.657859651897807e-06, "epoch": 1.7095588235294117, "percentage": 56.99, "elapsed_time": "0:08:39", "remaining_time": "0:06:32"}
{"current_steps": 940, "total_steps": 1632, "loss": 0.2694, "lr": 4.551194477612351e-06, "epoch": 1.7279411764705883, "percentage": 57.6, "elapsed_time": "0:08:45", "remaining_time": "0:06:26"}
{"current_steps": 950, "total_steps": 1632, "loss": 0.1944, "lr": 4.444734839966306e-06, "epoch": 1.7463235294117647, "percentage": 58.21, "elapsed_time": "0:08:50", "remaining_time": "0:06:20"}
{"current_steps": 960, "total_steps": 1632, "loss": 0.2479, "lr": 4.338529493609647e-06, "epoch": 1.7647058823529411, "percentage": 58.82, "elapsed_time": "0:08:55", "remaining_time": "0:06:15"}
{"current_steps": 970, "total_steps": 1632, "loss": 0.1819, "lr": 4.232627076736181e-06, "epoch": 1.7830882352941178, "percentage": 59.44, "elapsed_time": "0:09:01", "remaining_time": "0:06:09"}
{"current_steps": 980, "total_steps": 1632, "loss": 0.2514, "lr": 4.127076088809e-06, "epoch": 1.8014705882352942, "percentage": 60.05, "elapsed_time": "0:09:06", "remaining_time": "0:06:03"}
{"current_steps": 990, "total_steps": 1632, "loss": 0.24, "lr": 4.021924868349493e-06, "epoch": 1.8198529411764706, "percentage": 60.66, "elapsed_time": "0:09:12", "remaining_time": "0:05:57"}
{"current_steps": 1000, "total_steps": 1632, "loss": 0.2477, "lr": 3.9172215708000655e-06, "epoch": 1.8382352941176472, "percentage": 61.27, "elapsed_time": "0:09:17", "remaining_time": "0:05:52"}
{"current_steps": 1010, "total_steps": 1632, "loss": 0.2207, "lr": 3.8130141464706806e-06, "epoch": 1.8566176470588234, "percentage": 61.89, "elapsed_time": "0:09:36", "remaining_time": "0:05:55"}
{"current_steps": 1020, "total_steps": 1632, "loss": 0.2634, "lr": 3.709350318579371e-06, "epoch": 1.875, "percentage": 62.5, "elapsed_time": "0:09:41", "remaining_time": "0:05:49"}
{"current_steps": 1030, "total_steps": 1632, "loss": 0.236, "lr": 3.606277561396726e-06, "epoch": 1.8933823529411766, "percentage": 63.11, "elapsed_time": "0:09:47", "remaining_time": "0:05:43"}
{"current_steps": 1040, "total_steps": 1632, "loss": 0.2132, "lr": 3.503843078504405e-06, "epoch": 1.9117647058823528, "percentage": 63.73, "elapsed_time": "0:09:52", "remaining_time": "0:05:37"}
{"current_steps": 1050, "total_steps": 1632, "loss": 0.2088, "lr": 3.4020937811776154e-06, "epoch": 1.9301470588235294, "percentage": 64.34, "elapsed_time": "0:09:58", "remaining_time": "0:05:31"}
{"current_steps": 1060, "total_steps": 1632, "loss": 0.2413, "lr": 3.301076266901435e-06, "epoch": 1.9485294117647058, "percentage": 64.95, "elapsed_time": "0:10:03", "remaining_time": "0:05:25"}
{"current_steps": 1070, "total_steps": 1632, "loss": 0.2271, "lr": 3.2008367980308737e-06, "epoch": 1.9669117647058822, "percentage": 65.56, "elapsed_time": "0:10:08", "remaining_time": "0:05:19"}
{"current_steps": 1080, "total_steps": 1632, "loss": 0.2285, "lr": 3.1014212806043794e-06, "epoch": 1.9852941176470589, "percentage": 66.18, "elapsed_time": "0:10:14", "remaining_time": "0:05:13"}
{"current_steps": 1090, "total_steps": 1632, "loss": 0.1852, "lr": 3.0028752433205475e-06, "epoch": 2.0036764705882355, "percentage": 66.79, "elapsed_time": "0:10:19", "remaining_time": "0:05:08"}
{"current_steps": 1100, "total_steps": 1632, "loss": 0.1519, "lr": 2.9052438166876305e-06, "epoch": 2.0220588235294117, "percentage": 67.4, "elapsed_time": "0:10:25", "remaining_time": "0:05:02"}
{"current_steps": 1110, "total_steps": 1632, "loss": 0.1601, "lr": 2.808571712355389e-06, "epoch": 2.0404411764705883, "percentage": 68.01, "elapsed_time": "0:10:30", "remaining_time": "0:04:56"}
{"current_steps": 1120, "total_steps": 1632, "loss": 0.1264, "lr": 2.7129032026388046e-06, "epoch": 2.0588235294117645, "percentage": 68.63, "elapsed_time": "0:10:35", "remaining_time": "0:04:50"}
{"current_steps": 1130, "total_steps": 1632, "loss": 0.137, "lr": 2.618282100242935e-06, "epoch": 2.077205882352941, "percentage": 69.24, "elapsed_time": "0:10:41", "remaining_time": "0:04:44"}
{"current_steps": 1140, "total_steps": 1632, "loss": 0.1085, "lr": 2.5247517381983137e-06, "epoch": 2.0955882352941178, "percentage": 69.85, "elapsed_time": "0:10:46", "remaining_time": "0:04:39"}
{"current_steps": 1150, "total_steps": 1632, "loss": 0.1258, "lr": 2.4323549500159806e-06, "epoch": 2.113970588235294, "percentage": 70.47, "elapsed_time": "0:10:52", "remaining_time": "0:04:33"}
{"current_steps": 1160, "total_steps": 1632, "loss": 0.1046, "lr": 2.3411340500712833e-06, "epoch": 2.1323529411764706, "percentage": 71.08, "elapsed_time": "0:10:57", "remaining_time": "0:04:27"}
{"current_steps": 1170, "total_steps": 1632, "loss": 0.092, "lr": 2.251130814225449e-06, "epoch": 2.150735294117647, "percentage": 71.69, "elapsed_time": "0:11:03", "remaining_time": "0:04:21"}
{"current_steps": 1180, "total_steps": 1632, "loss": 0.0868, "lr": 2.16238646069373e-06, "epoch": 2.1691176470588234, "percentage": 72.3, "elapsed_time": "0:11:08", "remaining_time": "0:04:16"}
{"current_steps": 1190, "total_steps": 1632, "loss": 0.1059, "lr": 2.0749416311689845e-06, "epoch": 2.1875, "percentage": 72.92, "elapsed_time": "0:11:13", "remaining_time": "0:04:10"}
{"current_steps": 1200, "total_steps": 1632, "loss": 0.098, "lr": 1.9888363722092376e-06, "epoch": 2.2058823529411766, "percentage": 73.53, "elapsed_time": "0:11:19", "remaining_time": "0:04:04"}
{"current_steps": 1210, "total_steps": 1632, "loss": 0.108, "lr": 1.9041101168978094e-06, "epoch": 2.224264705882353, "percentage": 74.14, "elapsed_time": "0:11:24", "remaining_time": "0:03:58"}
{"current_steps": 1220, "total_steps": 1632, "loss": 0.1039, "lr": 1.8208016667844153e-06, "epoch": 2.2426470588235294, "percentage": 74.75, "elapsed_time": "0:11:30", "remaining_time": "0:03:53"}
{"current_steps": 1230, "total_steps": 1632, "loss": 0.1132, "lr": 1.7389491741154373e-06, "epoch": 2.261029411764706, "percentage": 75.37, "elapsed_time": "0:11:35", "remaining_time": "0:03:47"}
{"current_steps": 1240, "total_steps": 1632, "loss": 0.0999, "lr": 1.6585901243616044e-06, "epoch": 2.2794117647058822, "percentage": 75.98, "elapsed_time": "0:11:41", "remaining_time": "0:03:41"}
{"current_steps": 1250, "total_steps": 1632, "loss": 0.1059, "lr": 1.5797613190509908e-06, "epoch": 2.297794117647059, "percentage": 76.59, "elapsed_time": "0:11:46", "remaining_time": "0:03:35"}
{"current_steps": 1260, "total_steps": 1632, "loss": 0.1186, "lr": 1.502498858915254e-06, "epoch": 2.3161764705882355, "percentage": 77.21, "elapsed_time": "0:11:51", "remaining_time": "0:03:30"}
{"current_steps": 1270, "total_steps": 1632, "loss": 0.1018, "lr": 1.4268381273568232e-06, "epoch": 2.3345588235294117, "percentage": 77.82, "elapsed_time": "0:11:57", "remaining_time": "0:03:24"}
{"current_steps": 1280, "total_steps": 1632, "loss": 0.0953, "lr": 1.352813774244565e-06, "epoch": 2.3529411764705883, "percentage": 78.43, "elapsed_time": "0:12:02", "remaining_time": "0:03:18"}
{"current_steps": 1290, "total_steps": 1632, "loss": 0.1211, "lr": 1.2804597000454217e-06, "epoch": 2.3713235294117645, "percentage": 79.04, "elapsed_time": "0:12:08", "remaining_time": "0:03:13"}
{"current_steps": 1300, "total_steps": 1632, "loss": 0.1821, "lr": 1.2098090402992085e-06, "epoch": 2.389705882352941, "percentage": 79.66, "elapsed_time": "0:12:13", "remaining_time": "0:03:07"}
{"current_steps": 1310, "total_steps": 1632, "loss": 0.1263, "lr": 1.1408941504437533e-06, "epoch": 2.4080882352941178, "percentage": 80.27, "elapsed_time": "0:12:18", "remaining_time": "0:03:01"}
{"current_steps": 1320, "total_steps": 1632, "loss": 0.0792, "lr": 1.0737465909972778e-06, "epoch": 2.426470588235294, "percentage": 80.88, "elapsed_time": "0:12:24", "remaining_time": "0:02:55"}
{"current_steps": 1330, "total_steps": 1632, "loss": 0.1395, "lr": 1.0083971131048158e-06, "epoch": 2.4448529411764706, "percentage": 81.5, "elapsed_time": "0:12:29", "remaining_time": "0:02:50"}
{"current_steps": 1340, "total_steps": 1632, "loss": 0.1168, "lr": 9.448756444553226e-07, "epoch": 2.463235294117647, "percentage": 82.11, "elapsed_time": "0:12:35", "remaining_time": "0:02:44"}
{"current_steps": 1350, "total_steps": 1632, "loss": 0.0876, "lr": 8.832112755758598e-07, "epoch": 2.4816176470588234, "percentage": 82.72, "elapsed_time": "0:12:40", "remaining_time": "0:02:38"}
{"current_steps": 1360, "total_steps": 1632, "loss": 0.1019, "lr": 8.234322465092049e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:12:46", "remaining_time": "0:02:33"}
{"current_steps": 1370, "total_steps": 1632, "loss": 0.1377, "lr": 7.655659338809329e-07, "epoch": 2.5183823529411766, "percentage": 83.95, "elapsed_time": "0:12:51", "remaining_time": "0:02:27"}
{"current_steps": 1380, "total_steps": 1632, "loss": 0.0879, "lr": 7.09638838361908e-07, "epoch": 2.536764705882353, "percentage": 84.56, "elapsed_time": "0:12:56", "remaining_time": "0:02:21"}
{"current_steps": 1390, "total_steps": 1632, "loss": 0.0958, "lr": 6.556765725319525e-07, "epoch": 2.5551470588235294, "percentage": 85.17, "elapsed_time": "0:13:02", "remaining_time": "0:02:16"}
{"current_steps": 1400, "total_steps": 1632, "loss": 0.0994, "lr": 6.037038491501978e-07, "epoch": 2.5735294117647056, "percentage": 85.78, "elapsed_time": "0:13:07", "remaining_time": "0:02:10"}
{"current_steps": 1410, "total_steps": 1632, "loss": 0.0818, "lr": 5.53744469837551e-07, "epoch": 2.5919117647058822, "percentage": 86.4, "elapsed_time": "0:13:13", "remaining_time": "0:02:04"}
{"current_steps": 1420, "total_steps": 1632, "loss": 0.1018, "lr": 5.058213141764151e-07, "epoch": 2.610294117647059, "percentage": 87.01, "elapsed_time": "0:13:18", "remaining_time": "0:01:59"}
{"current_steps": 1430, "total_steps": 1632, "loss": 0.0874, "lr": 4.599563292326592e-07, "epoch": 2.6286764705882355, "percentage": 87.62, "elapsed_time": "0:13:23", "remaining_time": "0:01:53"}
{"current_steps": 1440, "total_steps": 1632, "loss": 0.1395, "lr": 4.1617051950467613e-07, "epoch": 2.6470588235294117, "percentage": 88.24, "elapsed_time": "0:13:29", "remaining_time": "0:01:47"}
{"current_steps": 1450, "total_steps": 1632, "loss": 0.1316, "lr": 3.744839373040682e-07, "epoch": 2.6654411764705883, "percentage": 88.85, "elapsed_time": "0:13:34", "remaining_time": "0:01:42"}
{"current_steps": 1460, "total_steps": 1632, "loss": 0.1149, "lr": 3.3491567357242736e-07, "epoch": 2.6838235294117645, "percentage": 89.46, "elapsed_time": "0:13:40", "remaining_time": "0:01:36"}
{"current_steps": 1470, "total_steps": 1632, "loss": 0.0907, "lr": 2.9748384913837525e-07, "epoch": 2.702205882352941, "percentage": 90.07, "elapsed_time": "0:13:45", "remaining_time": "0:01:30"}
{"current_steps": 1480, "total_steps": 1632, "loss": 0.1253, "lr": 2.6220560641887385e-07, "epoch": 2.7205882352941178, "percentage": 90.69, "elapsed_time": "0:13:50", "remaining_time": "0:01:25"}
{"current_steps": 1490, "total_steps": 1632, "loss": 0.098, "lr": 2.2909710156863275e-07, "epoch": 2.7389705882352944, "percentage": 91.3, "elapsed_time": "0:13:56", "remaining_time": "0:01:19"}
{"current_steps": 1500, "total_steps": 1632, "loss": 0.1071, "lr": 1.981734970811644e-07, "epoch": 2.7573529411764706, "percentage": 91.91, "elapsed_time": "0:14:01", "remaining_time": "0:01:14"}
{"current_steps": 1510, "total_steps": 1632, "loss": 0.097, "lr": 1.6944895484492075e-07, "epoch": 2.775735294117647, "percentage": 92.52, "elapsed_time": "0:14:21", "remaining_time": "0:01:09"}
{"current_steps": 1520, "total_steps": 1632, "loss": 0.0984, "lr": 1.429366296576623e-07, "epoch": 2.7941176470588234, "percentage": 93.14, "elapsed_time": "0:14:26", "remaining_time": "0:01:03"}
{"current_steps": 1530, "total_steps": 1632, "loss": 0.0858, "lr": 1.1864866320203116e-07, "epoch": 2.8125, "percentage": 93.75, "elapsed_time": "0:14:32", "remaining_time": "0:00:58"}
{"current_steps": 1540, "total_steps": 1632, "loss": 0.1211, "lr": 9.659617848510883e-08, "epoch": 2.8308823529411766, "percentage": 94.36, "elapsed_time": "0:14:37", "remaining_time": "0:00:52"}
{"current_steps": 1550, "total_steps": 1632, "loss": 0.1214, "lr": 7.678927474447817e-08, "epoch": 2.849264705882353, "percentage": 94.98, "elapsed_time": "0:14:43", "remaining_time": "0:00:46"}
{"current_steps": 1560, "total_steps": 1632, "loss": 0.0839, "lr": 5.9237022823140924e-08, "epoch": 2.8676470588235294, "percentage": 95.59, "elapsed_time": "0:14:48", "remaining_time": "0:00:41"}
{"current_steps": 1570, "total_steps": 1632, "loss": 0.1084, "lr": 4.394746101540115e-08, "epoch": 2.8860294117647056, "percentage": 96.2, "elapsed_time": "0:14:54", "remaining_time": "0:00:35"}
{"current_steps": 1580, "total_steps": 1632, "loss": 0.109, "lr": 3.092759138561607e-08, "epoch": 2.9044117647058822, "percentage": 96.81, "elapsed_time": "0:14:59", "remaining_time": "0:00:29"}
{"current_steps": 1590, "total_steps": 1632, "loss": 0.0956, "lr": 2.0183376561507263e-08, "epoch": 2.922794117647059, "percentage": 97.43, "elapsed_time": "0:15:04", "remaining_time": "0:00:23"}
{"current_steps": 1600, "total_steps": 1632, "loss": 0.119, "lr": 1.171973700349216e-08, "epoch": 2.9411764705882355, "percentage": 98.04, "elapsed_time": "0:15:10", "remaining_time": "0:00:18"}
{"current_steps": 1610, "total_steps": 1632, "loss": 0.1018, "lr": 5.540548751292174e-09, "epoch": 2.9595588235294117, "percentage": 98.65, "elapsed_time": "0:15:15", "remaining_time": "0:00:12"}
{"current_steps": 1620, "total_steps": 1632, "loss": 0.0922, "lr": 1.6486416488459279e-09, "epoch": 2.9779411764705883, "percentage": 99.26, "elapsed_time": "0:15:21", "remaining_time": "0:00:06"}
{"current_steps": 1630, "total_steps": 1632, "loss": 0.0803, "lr": 4.579804834703438e-11, "epoch": 2.9963235294117645, "percentage": 99.88, "elapsed_time": "0:15:26", "remaining_time": "0:00:01"}
{"current_steps": 1632, "total_steps": 1632, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:15:43", "remaining_time": "0:00:00"}