foamQwen3-8B / trainer_log.jsonl
finalform's picture
Upload folder using huggingface_hub
8d8fce4 verified
{"current_steps": 10, "total_steps": 369, "loss": 1.4338, "lr": 7.500000000000001e-05, "epoch": 0.23952095808383234, "percentage": 2.71, "elapsed_time": "0:01:07", "remaining_time": "0:40:22"}
{"current_steps": 20, "total_steps": 369, "loss": 0.8267, "lr": 9.990516643685222e-05, "epoch": 0.47904191616766467, "percentage": 5.42, "elapsed_time": "0:02:13", "remaining_time": "0:38:44"}
{"current_steps": 30, "total_steps": 369, "loss": 0.4881, "lr": 9.944154131125642e-05, "epoch": 0.718562874251497, "percentage": 8.13, "elapsed_time": "0:03:20", "remaining_time": "0:37:42"}
{"current_steps": 40, "total_steps": 369, "loss": 0.3591, "lr": 9.859528969650738e-05, "epoch": 0.9580838323353293, "percentage": 10.84, "elapsed_time": "0:04:27", "remaining_time": "0:36:39"}
{"current_steps": 42, "total_steps": 369, "eval_loss": 0.39884674549102783, "epoch": 1.0, "percentage": 11.38, "elapsed_time": "0:05:09", "remaining_time": "0:40:08"}
{"current_steps": 50, "total_steps": 369, "loss": 0.4172, "lr": 9.737296070648186e-05, "epoch": 1.1916167664670658, "percentage": 13.55, "elapsed_time": "0:06:04", "remaining_time": "0:38:44"}
{"current_steps": 60, "total_steps": 369, "loss": 0.3893, "lr": 9.57840139057007e-05, "epoch": 1.4311377245508983, "percentage": 16.26, "elapsed_time": "0:07:10", "remaining_time": "0:36:58"}
{"current_steps": 70, "total_steps": 369, "loss": 0.3658, "lr": 9.384074610206495e-05, "epoch": 1.6706586826347305, "percentage": 18.97, "elapsed_time": "0:08:19", "remaining_time": "0:35:35"}
{"current_steps": 80, "total_steps": 369, "loss": 0.2673, "lr": 9.155819618225708e-05, "epoch": 1.910179640718563, "percentage": 21.68, "elapsed_time": "0:09:27", "remaining_time": "0:34:09"}
{"current_steps": 84, "total_steps": 369, "eval_loss": 0.325968861579895, "epoch": 2.0, "percentage": 22.76, "elapsed_time": "0:10:21", "remaining_time": "0:35:08"}
{"current_steps": 90, "total_steps": 369, "loss": 0.3165, "lr": 8.895402872628352e-05, "epoch": 2.143712574850299, "percentage": 24.39, "elapsed_time": "0:11:02", "remaining_time": "0:34:12"}
{"current_steps": 100, "total_steps": 369, "loss": 0.336, "lr": 8.604839730186125e-05, "epoch": 2.3832335329341316, "percentage": 27.1, "elapsed_time": "0:12:09", "remaining_time": "0:32:42"}
{"current_steps": 110, "total_steps": 369, "loss": 0.288, "lr": 8.286378849660896e-05, "epoch": 2.622754491017964, "percentage": 29.81, "elapsed_time": "0:13:17", "remaining_time": "0:31:17"}
{"current_steps": 120, "total_steps": 369, "loss": 0.2425, "lr": 7.942484789507283e-05, "epoch": 2.8622754491017965, "percentage": 32.52, "elapsed_time": "0:14:25", "remaining_time": "0:29:55"}
{"current_steps": 126, "total_steps": 369, "eval_loss": 0.289765864610672, "epoch": 3.0, "percentage": 34.15, "elapsed_time": "0:15:33", "remaining_time": "0:29:59"}
{"current_steps": 130, "total_steps": 369, "loss": 0.2304, "lr": 7.57581893473448e-05, "epoch": 3.095808383233533, "percentage": 35.23, "elapsed_time": "0:15:59", "remaining_time": "0:29:24"}
{"current_steps": 140, "total_steps": 369, "loss": 0.2905, "lr": 7.18921890053375e-05, "epoch": 3.3353293413173652, "percentage": 37.94, "elapsed_time": "0:17:08", "remaining_time": "0:28:03"}
{"current_steps": 150, "total_steps": 369, "loss": 0.2336, "lr": 6.785676572066225e-05, "epoch": 3.5748502994011977, "percentage": 40.65, "elapsed_time": "0:18:15", "remaining_time": "0:26:38"}
{"current_steps": 160, "total_steps": 369, "loss": 0.2069, "lr": 6.368314950360415e-05, "epoch": 3.81437125748503, "percentage": 43.36, "elapsed_time": "0:19:24", "remaining_time": "0:25:20"}
{"current_steps": 168, "total_steps": 369, "eval_loss": 0.2659221291542053, "epoch": 4.0, "percentage": 45.53, "elapsed_time": "0:20:44", "remaining_time": "0:24:49"}
{"current_steps": 170, "total_steps": 369, "loss": 0.1815, "lr": 5.940363983508257e-05, "epoch": 4.047904191616767, "percentage": 46.07, "elapsed_time": "0:20:58", "remaining_time": "0:24:33"}
{"current_steps": 180, "total_steps": 369, "loss": 0.2426, "lr": 5.5051355702012893e-05, "epoch": 4.287425149700598, "percentage": 48.78, "elapsed_time": "0:22:07", "remaining_time": "0:23:14"}
{"current_steps": 190, "total_steps": 369, "loss": 0.1998, "lr": 5.0659979290537954e-05, "epoch": 4.526946107784431, "percentage": 51.49, "elapsed_time": "0:23:13", "remaining_time": "0:21:52"}
{"current_steps": 200, "total_steps": 369, "loss": 0.1713, "lr": 4.626349532067879e-05, "epoch": 4.766467065868263, "percentage": 54.2, "elapsed_time": "0:24:21", "remaining_time": "0:20:35"}
{"current_steps": 210, "total_steps": 369, "loss": 0.138, "lr": 4.189592803968563e-05, "epoch": 5.0, "percentage": 56.91, "elapsed_time": "0:25:26", "remaining_time": "0:19:15"}
{"current_steps": 210, "total_steps": 369, "eval_loss": 0.2524815797805786, "epoch": 5.0, "percentage": 56.91, "elapsed_time": "0:25:56", "remaining_time": "0:19:38"}
{"current_steps": 220, "total_steps": 369, "loss": 0.199, "lr": 3.759107790948882e-05, "epoch": 5.2395209580838324, "percentage": 59.62, "elapsed_time": "0:27:06", "remaining_time": "0:18:21"}
{"current_steps": 230, "total_steps": 369, "loss": 0.1654, "lr": 3.338226002601703e-05, "epoch": 5.479041916167665, "percentage": 62.33, "elapsed_time": "0:28:12", "remaining_time": "0:17:02"}
{"current_steps": 240, "total_steps": 369, "loss": 0.1459, "lr": 2.9302046294747497e-05, "epoch": 5.718562874251497, "percentage": 65.04, "elapsed_time": "0:29:19", "remaining_time": "0:15:45"}
{"current_steps": 250, "total_steps": 369, "loss": 0.1251, "lr": 2.5382013357782893e-05, "epoch": 5.95808383233533, "percentage": 67.75, "elapsed_time": "0:30:26", "remaining_time": "0:14:29"}
{"current_steps": 252, "total_steps": 369, "eval_loss": 0.24969537556171417, "epoch": 6.0, "percentage": 68.29, "elapsed_time": "0:31:08", "remaining_time": "0:14:27"}
{"current_steps": 260, "total_steps": 369, "loss": 0.1486, "lr": 2.1652498223239427e-05, "epoch": 6.191616766467066, "percentage": 70.46, "elapsed_time": "0:32:03", "remaining_time": "0:13:26"}
{"current_steps": 270, "total_steps": 369, "loss": 0.1527, "lr": 1.814236348812211e-05, "epoch": 6.431137724550898, "percentage": 73.17, "elapsed_time": "0:33:10", "remaining_time": "0:12:09"}
{"current_steps": 280, "total_steps": 369, "loss": 0.1344, "lr": 1.4878773971620074e-05, "epoch": 6.6706586826347305, "percentage": 75.88, "elapsed_time": "0:34:19", "remaining_time": "0:10:54"}
{"current_steps": 290, "total_steps": 369, "loss": 0.1072, "lr": 1.1886986487449475e-05, "epoch": 6.910179640718563, "percentage": 78.59, "elapsed_time": "0:35:26", "remaining_time": "0:09:39"}
{"current_steps": 294, "total_steps": 369, "eval_loss": 0.24749523401260376, "epoch": 7.0, "percentage": 79.67, "elapsed_time": "0:36:20", "remaining_time": "0:09:16"}
{"current_steps": 300, "total_steps": 369, "loss": 0.1224, "lr": 9.190154382188921e-06, "epoch": 7.1437125748503, "percentage": 81.3, "elapsed_time": "0:37:01", "remaining_time": "0:08:30"}
{"current_steps": 310, "total_steps": 369, "loss": 0.1493, "lr": 6.809148352279182e-06, "epoch": 7.383233532934132, "percentage": 84.01, "elapsed_time": "0:38:08", "remaining_time": "0:07:15"}
{"current_steps": 320, "total_steps": 369, "loss": 0.1126, "lr": 4.762394926378477e-06, "epoch": 7.6227544910179645, "percentage": 86.72, "elapsed_time": "0:39:16", "remaining_time": "0:06:00"}
{"current_steps": 330, "total_steps": 369, "loss": 0.1059, "lr": 3.065733863053072e-06, "epoch": 7.862275449101796, "percentage": 89.43, "elapsed_time": "0:40:24", "remaining_time": "0:04:46"}
{"current_steps": 336, "total_steps": 369, "eval_loss": 0.2483372986316681, "epoch": 8.0, "percentage": 91.06, "elapsed_time": "0:41:32", "remaining_time": "0:04:04"}
{"current_steps": 340, "total_steps": 369, "loss": 0.0986, "lr": 1.7322955673980678e-06, "epoch": 8.095808383233534, "percentage": 92.14, "elapsed_time": "0:41:58", "remaining_time": "0:03:34"}
{"current_steps": 350, "total_steps": 369, "loss": 0.1465, "lr": 7.723994752570462e-07, "epoch": 8.335329341317365, "percentage": 94.85, "elapsed_time": "0:43:08", "remaining_time": "0:02:20"}
{"current_steps": 360, "total_steps": 369, "loss": 0.1073, "lr": 1.9347419144180035e-07, "epoch": 8.574850299401197, "percentage": 97.56, "elapsed_time": "0:44:14", "remaining_time": "0:01:06"}
{"current_steps": 369, "total_steps": 369, "eval_loss": 0.24962204694747925, "epoch": 8.790419161676647, "percentage": 100.0, "elapsed_time": "0:45:48", "remaining_time": "0:00:00"}
{"current_steps": 369, "total_steps": 369, "epoch": 8.790419161676647, "percentage": 100.0, "elapsed_time": "0:45:48", "remaining_time": "0:00:00"}
{"current_steps": 5, "total_steps": 65, "percentage": 7.69, "elapsed_time": "0:00:01", "remaining_time": "0:00:16"}
{"current_steps": 10, "total_steps": 65, "percentage": 15.38, "elapsed_time": "0:00:03", "remaining_time": "0:00:16"}
{"current_steps": 15, "total_steps": 65, "percentage": 23.08, "elapsed_time": "0:00:04", "remaining_time": "0:00:15"}
{"current_steps": 20, "total_steps": 65, "percentage": 30.77, "elapsed_time": "0:00:06", "remaining_time": "0:00:14"}
{"current_steps": 25, "total_steps": 65, "percentage": 38.46, "elapsed_time": "0:00:07", "remaining_time": "0:00:12"}
{"current_steps": 30, "total_steps": 65, "percentage": 46.15, "elapsed_time": "0:00:09", "remaining_time": "0:00:11"}
{"current_steps": 35, "total_steps": 65, "percentage": 53.85, "elapsed_time": "0:00:11", "remaining_time": "0:00:09"}
{"current_steps": 40, "total_steps": 65, "percentage": 61.54, "elapsed_time": "0:00:12", "remaining_time": "0:00:08"}
{"current_steps": 45, "total_steps": 65, "percentage": 69.23, "elapsed_time": "0:00:14", "remaining_time": "0:00:06"}
{"current_steps": 50, "total_steps": 65, "percentage": 76.92, "elapsed_time": "0:00:16", "remaining_time": "0:00:04"}
{"current_steps": 55, "total_steps": 65, "percentage": 84.62, "elapsed_time": "0:00:18", "remaining_time": "0:00:03"}
{"current_steps": 60, "total_steps": 65, "percentage": 92.31, "elapsed_time": "0:00:20", "remaining_time": "0:00:01"}
{"current_steps": 65, "total_steps": 65, "percentage": 100.0, "elapsed_time": "0:00:22", "remaining_time": "0:00:00"}
{"current_steps": 0, "total_steps": 65, "eval_loss": 1.6609941720962524, "percentage": 0.0, "elapsed_time": "0:00:22", "remaining_time": "0:00:00"}
{"current_steps": 5, "total_steps": 65, "percentage": 7.69, "elapsed_time": "0:00:01", "remaining_time": "0:00:16"}
{"current_steps": 10, "total_steps": 65, "percentage": 15.38, "elapsed_time": "0:00:03", "remaining_time": "0:00:16"}
{"current_steps": 15, "total_steps": 65, "percentage": 23.08, "elapsed_time": "0:00:04", "remaining_time": "0:00:15"}
{"current_steps": 20, "total_steps": 65, "percentage": 30.77, "elapsed_time": "0:00:06", "remaining_time": "0:00:14"}
{"current_steps": 25, "total_steps": 65, "percentage": 38.46, "elapsed_time": "0:00:07", "remaining_time": "0:00:12"}
{"current_steps": 30, "total_steps": 65, "percentage": 46.15, "elapsed_time": "0:00:09", "remaining_time": "0:00:11"}
{"current_steps": 35, "total_steps": 65, "percentage": 53.85, "elapsed_time": "0:00:11", "remaining_time": "0:00:09"}
{"current_steps": 40, "total_steps": 65, "percentage": 61.54, "elapsed_time": "0:00:12", "remaining_time": "0:00:08"}
{"current_steps": 45, "total_steps": 65, "percentage": 69.23, "elapsed_time": "0:00:14", "remaining_time": "0:00:06"}
{"current_steps": 50, "total_steps": 65, "percentage": 76.92, "elapsed_time": "0:00:16", "remaining_time": "0:00:04"}
{"current_steps": 55, "total_steps": 65, "percentage": 84.62, "elapsed_time": "0:00:18", "remaining_time": "0:00:03"}
{"current_steps": 60, "total_steps": 65, "percentage": 92.31, "elapsed_time": "0:00:20", "remaining_time": "0:00:01"}
{"current_steps": 65, "total_steps": 65, "percentage": 100.0, "elapsed_time": "0:00:21", "remaining_time": "0:00:00"}
{"current_steps": 0, "total_steps": 65, "eval_loss": 1.6609941720962524, "percentage": 0.0, "elapsed_time": "0:00:21", "remaining_time": "0:00:00"}