Files
sft_qwen32b/trainer_log.jsonl

49 lines
8.8 KiB
Plaintext
Raw Permalink Normal View History

{"current_steps": 10, "total_steps": 470, "loss": 0.8989, "lr": 9.574468085106384e-07, "epoch": 0.10666666666666667, "percentage": 2.13, "elapsed_time": "0:11:23", "remaining_time": "8:44:12"}
{"current_steps": 20, "total_steps": 470, "loss": 0.802, "lr": 2.021276595744681e-06, "epoch": 0.21333333333333335, "percentage": 4.26, "elapsed_time": "0:23:26", "remaining_time": "8:47:28"}
{"current_steps": 30, "total_steps": 470, "loss": 0.6301, "lr": 3.0851063829787237e-06, "epoch": 0.32, "percentage": 6.38, "elapsed_time": "0:35:12", "remaining_time": "8:36:16"}
{"current_steps": 40, "total_steps": 470, "loss": 0.5338, "lr": 4.148936170212766e-06, "epoch": 0.4266666666666667, "percentage": 8.51, "elapsed_time": "0:47:51", "remaining_time": "8:34:33"}
{"current_steps": 50, "total_steps": 470, "loss": 0.4672, "lr": 4.999724208402901e-06, "epoch": 0.5333333333333333, "percentage": 10.64, "elapsed_time": "0:59:09", "remaining_time": "8:16:56"}
{"current_steps": 60, "total_steps": 470, "loss": 0.4331, "lr": 4.990077890125364e-06, "epoch": 0.64, "percentage": 12.77, "elapsed_time": "1:11:09", "remaining_time": "8:06:12"}
{"current_steps": 70, "total_steps": 470, "loss": 0.397, "lr": 4.9667027804779025e-06, "epoch": 0.7466666666666667, "percentage": 14.89, "elapsed_time": "1:23:06", "remaining_time": "7:54:53"}
{"current_steps": 80, "total_steps": 470, "loss": 0.3799, "lr": 4.9297277557518455e-06, "epoch": 0.8533333333333334, "percentage": 17.02, "elapsed_time": "1:35:46", "remaining_time": "7:46:53"}
{"current_steps": 90, "total_steps": 470, "loss": 0.3661, "lr": 4.8793566739880894e-06, "epoch": 0.96, "percentage": 19.15, "elapsed_time": "1:47:51", "remaining_time": "7:35:23"}
{"current_steps": 100, "total_steps": 470, "loss": 0.3395, "lr": 4.81586725102651e-06, "epoch": 1.064, "percentage": 21.28, "elapsed_time": "1:59:18", "remaining_time": "7:21:26"}
{"current_steps": 110, "total_steps": 470, "loss": 0.3106, "lr": 4.739609529347905e-06, "epoch": 1.1706666666666667, "percentage": 23.4, "elapsed_time": "2:10:31", "remaining_time": "7:07:11"}
{"current_steps": 120, "total_steps": 470, "loss": 0.3117, "lr": 4.651003948150349e-06, "epoch": 1.2773333333333334, "percentage": 25.53, "elapsed_time": "2:22:36", "remaining_time": "6:55:55"}
{"current_steps": 130, "total_steps": 470, "loss": 0.3129, "lr": 4.5505390253004116e-06, "epoch": 1.384, "percentage": 27.66, "elapsed_time": "2:35:05", "remaining_time": "6:45:37"}
{"current_steps": 140, "total_steps": 470, "loss": 0.3192, "lr": 4.4387686639395435e-06, "epoch": 1.4906666666666666, "percentage": 29.79, "elapsed_time": "2:48:03", "remaining_time": "6:36:09"}
{"current_steps": 150, "total_steps": 470, "loss": 0.2955, "lr": 4.3163090985954085e-06, "epoch": 1.5973333333333333, "percentage": 31.91, "elapsed_time": "2:59:48", "remaining_time": "6:23:35"}
{"current_steps": 160, "total_steps": 470, "loss": 0.2965, "lr": 4.1838354976354416e-06, "epoch": 1.704, "percentage": 34.04, "elapsed_time": "3:10:53", "remaining_time": "6:09:51"}
{"current_steps": 170, "total_steps": 470, "loss": 0.2963, "lr": 4.042078240794675e-06, "epoch": 1.8106666666666666, "percentage": 36.17, "elapsed_time": "3:23:36", "remaining_time": "5:59:19"}
{"current_steps": 180, "total_steps": 470, "loss": 0.2941, "lr": 3.891818892301304e-06, "epoch": 1.9173333333333333, "percentage": 38.3, "elapsed_time": "3:35:15", "remaining_time": "5:46:48"}
{"current_steps": 190, "total_steps": 470, "loss": 0.2989, "lr": 3.733885891801746e-06, "epoch": 2.021333333333333, "percentage": 40.43, "elapsed_time": "3:47:17", "remaining_time": "5:34:56"}
{"current_steps": 200, "total_steps": 470, "loss": 0.2455, "lr": 3.569149986842847e-06, "epoch": 2.128, "percentage": 42.55, "elapsed_time": "3:59:57", "remaining_time": "5:23:56"}
{"current_steps": 210, "total_steps": 470, "loss": 0.2395, "lr": 3.398519432093782e-06, "epoch": 2.2346666666666666, "percentage": 44.68, "elapsed_time": "4:11:37", "remaining_time": "5:11:31"}
{"current_steps": 220, "total_steps": 470, "loss": 0.245, "lr": 3.222934981776248e-06, "epoch": 2.3413333333333335, "percentage": 46.81, "elapsed_time": "4:23:52", "remaining_time": "4:59:51"}
{"current_steps": 230, "total_steps": 470, "loss": 0.2349, "lr": 3.0433647029116675e-06, "epoch": 2.448, "percentage": 48.94, "elapsed_time": "4:36:02", "remaining_time": "4:48:02"}
{"current_steps": 240, "total_steps": 470, "loss": 0.2415, "lr": 2.8607986379820668e-06, "epoch": 2.554666666666667, "percentage": 51.06, "elapsed_time": "4:48:25", "remaining_time": "4:36:24"}
{"current_steps": 250, "total_steps": 470, "loss": 0.2476, "lr": 2.676243346431463e-06, "epoch": 2.6613333333333333, "percentage": 53.19, "elapsed_time": "5:01:09", "remaining_time": "4:25:00"}
{"current_steps": 260, "total_steps": 470, "loss": 0.2403, "lr": 2.4907163551026755e-06, "epoch": 2.768, "percentage": 55.32, "elapsed_time": "5:12:59", "remaining_time": "4:12:47"}
{"current_steps": 270, "total_steps": 470, "loss": 0.2343, "lr": 2.3052405482064923e-06, "epoch": 2.8746666666666667, "percentage": 57.45, "elapsed_time": "5:24:43", "remaining_time": "4:00:32"}
{"current_steps": 280, "total_steps": 470, "loss": 0.2366, "lr": 2.1208385277535355e-06, "epoch": 2.981333333333333, "percentage": 59.57, "elapsed_time": "5:36:39", "remaining_time": "3:48:27"}
{"current_steps": 290, "total_steps": 470, "loss": 0.2041, "lr": 1.938526975542005e-06, "epoch": 3.0853333333333333, "percentage": 61.7, "elapsed_time": "5:48:48", "remaining_time": "3:36:30"}
{"current_steps": 300, "total_steps": 470, "loss": 0.1954, "lr": 1.7593110477859155e-06, "epoch": 3.192, "percentage": 63.83, "elapsed_time": "6:00:47", "remaining_time": "3:24:26"}
{"current_steps": 310, "total_steps": 470, "loss": 0.1967, "lr": 1.5841788332884672e-06, "epoch": 3.2986666666666666, "percentage": 65.96, "elapsed_time": "6:12:44", "remaining_time": "3:12:22"}
{"current_steps": 320, "total_steps": 470, "loss": 0.1978, "lr": 1.4140959057148545e-06, "epoch": 3.405333333333333, "percentage": 68.09, "elapsed_time": "6:25:17", "remaining_time": "3:00:36"}
{"current_steps": 330, "total_steps": 470, "loss": 0.1939, "lr": 1.2500000000000007e-06, "epoch": 3.512, "percentage": 70.21, "elapsed_time": "6:36:25", "remaining_time": "2:48:10"}
{"current_steps": 340, "total_steps": 470, "loss": 0.1898, "lr": 1.0927958422422913e-06, "epoch": 3.618666666666667, "percentage": 72.34, "elapsed_time": "6:47:13", "remaining_time": "2:35:42"}
{"current_steps": 350, "total_steps": 470, "loss": 0.1966, "lr": 9.433501615881924e-07, "epoch": 3.7253333333333334, "percentage": 74.47, "elapsed_time": "7:00:01", "remaining_time": "2:24:00"}
{"current_steps": 360, "total_steps": 470, "loss": 0.2024, "lr": 8.02486911609188e-07, "epoch": 3.832, "percentage": 76.6, "elapsed_time": "7:12:22", "remaining_time": "2:12:06"}
{"current_steps": 370, "total_steps": 470, "loss": 0.1979, "lr": 6.709827275174994e-07, "epoch": 3.9386666666666668, "percentage": 78.72, "elapsed_time": "7:24:12", "remaining_time": "2:00:03"}
{"current_steps": 380, "total_steps": 470, "loss": 0.1862, "lr": 5.495626442667826e-07, "epoch": 4.042666666666666, "percentage": 80.85, "elapsed_time": "7:36:29", "remaining_time": "1:48:07"}
{"current_steps": 390, "total_steps": 470, "loss": 0.176, "lr": 4.388960991455998e-07, "epoch": 4.149333333333334, "percentage": 82.98, "elapsed_time": "7:48:36", "remaining_time": "1:36:07"}
{"current_steps": 400, "total_steps": 470, "loss": 0.1813, "lr": 3.3959324090295897e-07, "epoch": 4.256, "percentage": 85.11, "elapsed_time": "8:01:10", "remaining_time": "1:24:12"}
{"current_steps": 410, "total_steps": 470, "loss": 0.1694, "lr": 2.522015657552068e-07, "epoch": 4.362666666666667, "percentage": 87.23, "elapsed_time": "8:12:35", "remaining_time": "1:12:05"}
{"current_steps": 420, "total_steps": 470, "loss": 0.1701, "lr": 1.7720289882128095e-07, "epoch": 4.469333333333333, "percentage": 89.36, "elapsed_time": "8:24:30", "remaining_time": "1:00:03"}
{"current_steps": 430, "total_steps": 470, "loss": 0.1702, "lr": 1.1501073762888559e-07, "epoch": 4.576, "percentage": 91.49, "elapsed_time": "8:36:55", "remaining_time": "0:48:05"}
{"current_steps": 440, "total_steps": 470, "loss": 0.1687, "lr": 6.596797233789865e-08, "epoch": 4.682666666666667, "percentage": 93.62, "elapsed_time": "8:48:59", "remaining_time": "0:36:04"}
{"current_steps": 450, "total_steps": 470, "loss": 0.1728, "lr": 3.034499525032625e-08, "epoch": 4.789333333333333, "percentage": 95.74, "elapsed_time": "9:01:18", "remaining_time": "0:24:03"}
{"current_steps": 460, "total_steps": 470, "loss": 0.1709, "lr": 8.338210029824878e-09, "epoch": 4.896, "percentage": 97.87, "elapsed_time": "9:12:30", "remaining_time": "0:12:00"}
{"current_steps": 470, "total_steps": 470, "loss": 0.1789, "lr": 6.894885006381025e-11, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "9:24:18", "remaining_time": "0:00:00"}
{"current_steps": 470, "total_steps": 470, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "9:25:13", "remaining_time": "0:00:00"}