Upload 4 files

trainer_log.jsonl

@@ -0,0 +1,87 @@
+{"current_steps": 10, "total_steps": 860, "loss": 1.0627, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.998999272555359e-05, "epoch": 0.05, "percentage": 1.16, "elapsed_time": "0:06:38", "remaining_time": "9:24:32"}
+{"current_steps": 20, "total_steps": 860, "loss": 0.9782, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9959984254953276e-05, "epoch": 0.09, "percentage": 2.33, "elapsed_time": "0:13:15", "remaining_time": "9:17:05"}
+{"current_steps": 30, "total_steps": 860, "loss": 0.9571, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9910014628599188e-05, "epoch": 0.14, "percentage": 3.49, "elapsed_time": "0:19:53", "remaining_time": "9:10:14"}
+{"current_steps": 40, "total_steps": 860, "loss": 0.9545, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9840150521126656e-05, "epoch": 0.19, "percentage": 4.65, "elapsed_time": "0:26:30", "remaining_time": "9:03:27"}
+{"current_steps": 50, "total_steps": 860, "loss": 0.9367, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.975048515244199e-05, "epoch": 0.23, "percentage": 5.81, "elapsed_time": "0:33:07", "remaining_time": "8:56:41"}
+{"current_steps": 60, "total_steps": 860, "loss": 0.9475, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.964113816333891e-05, "epoch": 0.28, "percentage": 6.98, "elapsed_time": "0:39:44", "remaining_time": "8:49:54"}
+{"current_steps": 70, "total_steps": 860, "loss": 0.9201, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9512255455861378e-05, "epoch": 0.32, "percentage": 8.14, "elapsed_time": "0:46:22", "remaining_time": "8:43:21"}
+{"current_steps": 80, "total_steps": 860, "loss": 0.9139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.936400899862609e-05, "epoch": 0.37, "percentage": 9.3, "elapsed_time": "0:52:59", "remaining_time": "8:36:41"}
+{"current_steps": 90, "total_steps": 860, "loss": 0.9289, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.919659659736414e-05, "epoch": 0.42, "percentage": 10.47, "elapsed_time": "0:59:36", "remaining_time": "8:30:02"}
+{"current_steps": 100, "total_steps": 860, "loss": 0.9073, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.901024163098822e-05, "epoch": 0.46, "percentage": 11.63, "elapsed_time": "1:06:15", "remaining_time": "8:23:31"}
+{"current_steps": 110, "total_steps": 860, "loss": 0.9186, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.880519275353739e-05, "epoch": 0.51, "percentage": 12.79, "elapsed_time": "1:12:52", "remaining_time": "8:16:52"}
+{"current_steps": 120, "total_steps": 860, "loss": 0.88, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8581723562397203e-05, "epoch": 0.56, "percentage": 13.95, "elapsed_time": "1:19:29", "remaining_time": "8:10:14"}
+{"current_steps": 130, "total_steps": 860, "loss": 0.8877, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8340132233237784e-05, "epoch": 0.6, "percentage": 15.12, "elapsed_time": "1:26:07", "remaining_time": "8:03:35"}
+{"current_steps": 140, "total_steps": 860, "loss": 0.9036, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8080741122157116e-05, "epoch": 0.65, "percentage": 16.28, "elapsed_time": "1:32:44", "remaining_time": "7:56:59"}
+{"current_steps": 150, "total_steps": 860, "loss": 0.8827, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.78038963355602e-05, "epoch": 0.7, "percentage": 17.44, "elapsed_time": "1:39:22", "remaining_time": "7:50:22"}
+{"current_steps": 160, "total_steps": 860, "loss": 0.8985, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7509967268348168e-05, "epoch": 0.74, "percentage": 18.6, "elapsed_time": "1:46:00", "remaining_time": "7:43:48"}
+{"current_steps": 170, "total_steps": 860, "loss": 0.8883, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.719934611103348e-05, "epoch": 0.79, "percentage": 19.77, "elapsed_time": "1:52:38", "remaining_time": "7:37:10"}
+{"current_steps": 180, "total_steps": 860, "loss": 0.8711, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6872447326438813e-05, "epoch": 0.84, "percentage": 20.93, "elapsed_time": "1:59:16", "remaining_time": "7:30:34"}
+{"current_steps": 190, "total_steps": 860, "loss": 0.8941, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.652970709667798e-05, "epoch": 0.88, "percentage": 22.09, "elapsed_time": "2:05:54", "remaining_time": "7:23:58"}
+{"current_steps": 200, "total_steps": 860, "loss": 0.8909, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.617158274115673e-05, "epoch": 0.93, "percentage": 23.26, "elapsed_time": "2:12:32", "remaining_time": "7:17:21"}
+{"current_steps": 210, "total_steps": 860, "loss": 0.8901, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.579855210636994e-05, "epoch": 0.97, "percentage": 24.42, "elapsed_time": "2:19:09", "remaining_time": "7:10:42"}
+{"current_steps": 220, "total_steps": 860, "loss": 0.8664, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.541111292830951e-05, "epoch": 1.02, "percentage": 25.58, "elapsed_time": "2:25:46", "remaining_time": "7:04:04"}
+{"current_steps": 230, "total_steps": 860, "loss": 0.8718, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.500978216833359e-05, "epoch": 1.07, "percentage": 26.74, "elapsed_time": "2:32:24", "remaining_time": "6:57:27"}
+{"current_steps": 240, "total_steps": 860, "loss": 0.8489, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.459509532338337e-05, "epoch": 1.11, "percentage": 27.91, "elapsed_time": "2:39:02", "remaining_time": "6:50:50"}
+{"current_steps": 250, "total_steps": 860, "loss": 0.851, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.416760571146774e-05, "epoch": 1.16, "percentage": 29.07, "elapsed_time": "2:45:39", "remaining_time": "6:44:13"}
+{"current_steps": 260, "total_steps": 860, "loss": 0.8481, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3727883733369295e-05, "epoch": 1.21, "percentage": 30.23, "elapsed_time": "2:52:17", "remaining_time": "6:37:35"}
+{"current_steps": 270, "total_steps": 860, "loss": 0.8605, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.327651611155669e-05, "epoch": 1.25, "percentage": 31.4, "elapsed_time": "2:58:55", "remaining_time": "6:30:59"}
+{"current_steps": 280, "total_steps": 860, "loss": 0.8586, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2814105107318955e-05, "epoch": 1.3, "percentage": 32.56, "elapsed_time": "3:05:32", "remaining_time": "6:24:20"}
+{"current_steps": 290, "total_steps": 860, "loss": 0.8642, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2341267717166285e-05, "epoch": 1.35, "percentage": 33.72, "elapsed_time": "3:12:10", "remaining_time": "6:17:42"}
+{"current_steps": 300, "total_steps": 860, "loss": 0.8676, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1858634849569578e-05, "epoch": 1.39, "percentage": 34.88, "elapsed_time": "3:18:48", "remaining_time": "6:11:06"}
+{"current_steps": 310, "total_steps": 860, "loss": 0.8443, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.136685048313723e-05, "epoch": 1.44, "percentage": 36.05, "elapsed_time": "3:25:26", "remaining_time": "6:04:28"}
+{"current_steps": 320, "total_steps": 860, "loss": 0.842, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.086657080735234e-05, "epoch": 1.48, "percentage": 37.21, "elapsed_time": "3:32:03", "remaining_time": "5:57:51"}
+{"current_steps": 330, "total_steps": 860, "loss": 0.8432, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.035846334701699e-05, "epoch": 1.53, "percentage": 38.37, "elapsed_time": "3:38:40", "remaining_time": "5:51:12"}
+{"current_steps": 340, "total_steps": 860, "loss": 0.8451, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9843206071571692e-05, "epoch": 1.58, "percentage": 39.53, "elapsed_time": "3:45:18", "remaining_time": "5:44:34"}
+{"current_steps": 350, "total_steps": 860, "loss": 0.8645, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9321486490478565e-05, "epoch": 1.62, "percentage": 40.7, "elapsed_time": "3:51:55", "remaining_time": "5:37:57"}
+{"current_steps": 360, "total_steps": 860, "loss": 0.8377, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.879400073587521e-05, "epoch": 1.67, "percentage": 41.86, "elapsed_time": "3:58:33", "remaining_time": "5:31:19"}
+{"current_steps": 370, "total_steps": 860, "loss": 0.8374, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8261452633723356e-05, "epoch": 1.72, "percentage": 43.02, "elapsed_time": "4:05:10", "remaining_time": "5:24:41"}
+{"current_steps": 380, "total_steps": 860, "loss": 0.8491, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7724552764691545e-05, "epoch": 1.76, "percentage": 44.19, "elapsed_time": "4:11:48", "remaining_time": "5:18:04"}
+{"current_steps": 390, "total_steps": 860, "loss": 0.8391, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7184017516025075e-05, "epoch": 1.81, "percentage": 45.35, "elapsed_time": "4:18:26", "remaining_time": "5:11:27"}
+{"current_steps": 400, "total_steps": 860, "loss": 0.8521, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.664056812566812e-05, "epoch": 1.86, "percentage": 46.51, "elapsed_time": "4:25:03", "remaining_time": "5:04:49"}
+{"current_steps": 410, "total_steps": 860, "loss": 0.846, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6094929719913614e-05, "epoch": 1.9, "percentage": 47.67, "elapsed_time": "4:31:40", "remaining_time": "4:58:10"}
+{"current_steps": 420, "total_steps": 860, "loss": 0.8759, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5547830345864887e-05, "epoch": 1.95, "percentage": 48.84, "elapsed_time": "4:38:17", "remaining_time": "4:51:32"}
+{"current_steps": 430, "total_steps": 860, "loss": 0.8411, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5e-05, "epoch": 2.0, "percentage": 50.0, "elapsed_time": "4:44:55", "remaining_time": "4:44:55"}
+{"current_steps": 440, "total_steps": 860, "loss": 0.8106, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4452169654135116e-05, "epoch": 2.04, "percentage": 51.16, "elapsed_time": "4:51:33", "remaining_time": "4:38:18"}
+{"current_steps": 450, "total_steps": 860, "loss": 0.8265, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3905070280086387e-05, "epoch": 2.09, "percentage": 52.33, "elapsed_time": "4:58:11", "remaining_time": "4:31:41"}
+{"current_steps": 460, "total_steps": 860, "loss": 0.8261, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3359431874331888e-05, "epoch": 2.13, "percentage": 53.49, "elapsed_time": "5:04:49", "remaining_time": "4:25:03"}
+{"current_steps": 470, "total_steps": 860, "loss": 0.8107, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.281598248397493e-05, "epoch": 2.18, "percentage": 54.65, "elapsed_time": "5:11:26", "remaining_time": "4:18:25"}
+{"current_steps": 480, "total_steps": 860, "loss": 0.7914, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2275447235308454e-05, "epoch": 2.23, "percentage": 55.81, "elapsed_time": "5:18:03", "remaining_time": "4:11:47"}
+{"current_steps": 490, "total_steps": 860, "loss": 0.7966, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1738547366276648e-05, "epoch": 2.27, "percentage": 56.98, "elapsed_time": "5:24:40", "remaining_time": "4:05:10"}
+{"current_steps": 500, "total_steps": 860, "loss": 0.8102, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1205999264124788e-05, "epoch": 2.32, "percentage": 58.14, "elapsed_time": "5:31:18", "remaining_time": "3:58:32"}
+{"current_steps": 510, "total_steps": 860, "loss": 0.794, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0678513509521436e-05, "epoch": 2.37, "percentage": 59.3, "elapsed_time": "5:37:56", "remaining_time": "3:51:54"}
+{"current_steps": 520, "total_steps": 860, "loss": 0.7862, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.015679392842831e-05, "epoch": 2.41, "percentage": 60.47, "elapsed_time": "5:44:33", "remaining_time": "3:45:17"}
+{"current_steps": 530, "total_steps": 860, "loss": 0.8126, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.64153665298301e-06, "epoch": 2.46, "percentage": 61.63, "elapsed_time": "5:51:11", "remaining_time": "3:38:40"}
+{"current_steps": 540, "total_steps": 860, "loss": 0.8134, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.133429192647661e-06, "epoch": 2.51, "percentage": 62.79, "elapsed_time": "5:57:49", "remaining_time": "3:32:02"}
+{"current_steps": 550, "total_steps": 860, "loss": 0.8136, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.633149516862777e-06, "epoch": 2.55, "percentage": 63.95, "elapsed_time": "6:04:27", "remaining_time": "3:25:25"}
+{"current_steps": 560, "total_steps": 860, "loss": 0.7995, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.141365150430423e-06, "epoch": 2.6, "percentage": 65.12, "elapsed_time": "6:11:04", "remaining_time": "3:18:47"}
+{"current_steps": 570, "total_steps": 860, "loss": 0.7874, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.658732282833721e-06, "epoch": 2.65, "percentage": 66.28, "elapsed_time": "6:17:42", "remaining_time": "3:12:10"}
+{"current_steps": 580, "total_steps": 860, "loss": 0.7907, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.185894892681048e-06, "epoch": 2.69, "percentage": 67.44, "elapsed_time": "6:24:20", "remaining_time": "3:05:32"}
+{"current_steps": 590, "total_steps": 860, "loss": 0.7957, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.72348388844331e-06, "epoch": 2.74, "percentage": 68.6, "elapsed_time": "6:30:58", "remaining_time": "2:58:55"}
+{"current_steps": 600, "total_steps": 860, "loss": 0.8031, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.27211626663071e-06, "epoch": 2.78, "percentage": 69.77, "elapsed_time": "6:37:36", "remaining_time": "2:52:17"}
+{"current_steps": 610, "total_steps": 860, "loss": 0.8071, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.832394288532261e-06, "epoch": 2.83, "percentage": 70.93, "elapsed_time": "6:44:14", "remaining_time": "2:45:40"}
+{"current_steps": 620, "total_steps": 860, "loss": 0.7953, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.404904676616634e-06, "epoch": 2.88, "percentage": 72.09, "elapsed_time": "6:50:51", "remaining_time": "2:39:02"}
+{"current_steps": 630, "total_steps": 860, "loss": 0.8028, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.99021783166641e-06, "epoch": 2.92, "percentage": 73.26, "elapsed_time": "6:57:29", "remaining_time": "2:32:25"}
+{"current_steps": 640, "total_steps": 860, "loss": 0.8043, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.588887071690491e-06, "epoch": 2.97, "percentage": 74.42, "elapsed_time": "7:04:07", "remaining_time": "2:25:47"}
+{"current_steps": 650, "total_steps": 860, "loss": 0.7826, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.201447893630065e-06, "epoch": 3.02, "percentage": 75.58, "elapsed_time": "7:10:45", "remaining_time": "2:19:10"}
+{"current_steps": 660, "total_steps": 860, "loss": 0.7723, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.828417258843272e-06, "epoch": 3.06, "percentage": 76.74, "elapsed_time": "7:17:23", "remaining_time": "2:12:32"}
+{"current_steps": 670, "total_steps": 860, "loss": 0.7734, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.4702929033220176e-06, "epoch": 3.11, "percentage": 77.91, "elapsed_time": "7:24:00", "remaining_time": "2:05:54"}
+{"current_steps": 680, "total_steps": 860, "loss": 0.7834, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.12755267356119e-06, "epoch": 3.16, "percentage": 79.07, "elapsed_time": "7:30:37", "remaining_time": "1:59:17"}
+{"current_steps": 690, "total_steps": 860, "loss": 0.7712, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8006538889665194e-06, "epoch": 3.2, "percentage": 80.23, "elapsed_time": "7:37:15", "remaining_time": "1:52:39"}
+{"current_steps": 700, "total_steps": 860, "loss": 0.7634, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.490032731651833e-06, "epoch": 3.25, "percentage": 81.4, "elapsed_time": "7:43:53", "remaining_time": "1:46:01"}
+{"current_steps": 710, "total_steps": 860, "loss": 0.754, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1961036644398034e-06, "epoch": 3.29, "percentage": 82.56, "elapsed_time": "7:50:30", "remaining_time": "1:39:24"}
+{"current_steps": 720, "total_steps": 860, "loss": 0.7738, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9192588778428844e-06, "epoch": 3.34, "percentage": 83.72, "elapsed_time": "7:57:08", "remaining_time": "1:32:46"}
+{"current_steps": 730, "total_steps": 860, "loss": 0.7776, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6598677667622176e-06, "epoch": 3.39, "percentage": 84.88, "elapsed_time": "8:03:46", "remaining_time": "1:26:09"}
+{"current_steps": 740, "total_steps": 860, "loss": 0.7706, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4182764376028007e-06, "epoch": 3.43, "percentage": 86.05, "elapsed_time": "8:10:23", "remaining_time": "1:19:31"}
+{"current_steps": 750, "total_steps": 860, "loss": 0.7699, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1948072464626102e-06, "epoch": 3.48, "percentage": 87.21, "elapsed_time": "8:17:00", "remaining_time": "1:12:53"}
+{"current_steps": 760, "total_steps": 860, "loss": 0.7867, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.897583690117813e-07, "epoch": 3.53, "percentage": 88.37, "elapsed_time": "8:23:38", "remaining_time": "1:06:16"}
+{"current_steps": 770, "total_steps": 860, "loss": 0.766, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.034034026358589e-07, "epoch": 3.57, "percentage": 89.53, "elapsed_time": "8:30:16", "remaining_time": "0:59:38"}
+{"current_steps": 780, "total_steps": 860, "loss": 0.7704, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.359910013739123e-07, "epoch": 3.62, "percentage": 90.7, "elapsed_time": "8:36:54", "remaining_time": "0:53:00"}
+{"current_steps": 790, "total_steps": 860, "loss": 0.7601, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.877445441386219e-07, "epoch": 3.67, "percentage": 91.86, "elapsed_time": "8:43:31", "remaining_time": "0:46:23"}
+{"current_steps": 800, "total_steps": 860, "loss": 0.7838, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.588618366610941e-07, "epoch": 3.71, "percentage": 93.02, "elapsed_time": "8:50:09", "remaining_time": "0:39:45"}
+{"current_steps": 810, "total_steps": 860, "loss": 0.7715, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.495148475580089e-07, "epoch": 3.76, "percentage": 94.19, "elapsed_time": "8:56:47", "remaining_time": "0:33:08"}
+{"current_steps": 820, "total_steps": 860, "loss": 0.7726, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5984947887334622e-07, "epoch": 3.81, "percentage": 95.35, "elapsed_time": "9:03:25", "remaining_time": "0:26:30"}
+{"current_steps": 830, "total_steps": 860, "loss": 0.7796, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.998537140081143e-08, "epoch": 3.85, "percentage": 96.51, "elapsed_time": "9:10:02", "remaining_time": "0:19:52"}
+{"current_steps": 840, "total_steps": 860, "loss": 0.786, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.0015745046725336e-08, "epoch": 3.9, "percentage": 97.67, "elapsed_time": "9:16:40", "remaining_time": "0:13:15"}
+{"current_steps": 850, "total_steps": 860, "loss": 0.7874, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0007274446409143e-08, "epoch": 3.94, "percentage": 98.84, "elapsed_time": "9:23:19", "remaining_time": "0:06:37"}
+{"current_steps": 860, "total_steps": 860, "loss": 0.7847, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 3.99, "percentage": 100.0, "elapsed_time": "9:29:57", "remaining_time": "0:00:00"}
+{"current_steps": 860, "total_steps": 860, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.99, "percentage": 100.0, "elapsed_time": "9:29:57", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,546 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.9907192575406034,
+  "eval_steps": 500,
+  "global_step": 860,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.998999272555359e-05,
+      "loss": 1.0627,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.9959984254953276e-05,
+      "loss": 0.9782,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.9910014628599188e-05,
+      "loss": 0.9571,
+      "step": 30
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.9840150521126656e-05,
+      "loss": 0.9545,
+      "step": 40
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.975048515244199e-05,
+      "loss": 0.9367,
+      "step": 50
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.964113816333891e-05,
+      "loss": 0.9475,
+      "step": 60
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.9512255455861378e-05,
+      "loss": 0.9201,
+      "step": 70
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.936400899862609e-05,
+      "loss": 0.9139,
+      "step": 80
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.919659659736414e-05,
+      "loss": 0.9289,
+      "step": 90
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.901024163098822e-05,
+      "loss": 0.9073,
+      "step": 100
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.880519275353739e-05,
+      "loss": 0.9186,
+      "step": 110
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.8581723562397203e-05,
+      "loss": 0.88,
+      "step": 120
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2.8340132233237784e-05,
+      "loss": 0.8877,
+      "step": 130
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2.8080741122157116e-05,
+      "loss": 0.9036,
+      "step": 140
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.78038963355602e-05,
+      "loss": 0.8827,
+      "step": 150
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.7509967268348168e-05,
+      "loss": 0.8985,
+      "step": 160
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.719934611103348e-05,
+      "loss": 0.8883,
+      "step": 170
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.6872447326438813e-05,
+      "loss": 0.8711,
+      "step": 180
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.652970709667798e-05,
+      "loss": 0.8941,
+      "step": 190
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.617158274115673e-05,
+      "loss": 0.8909,
+      "step": 200
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.579855210636994e-05,
+      "loss": 0.8901,
+      "step": 210
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.541111292830951e-05,
+      "loss": 0.8664,
+      "step": 220
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.500978216833359e-05,
+      "loss": 0.8718,
+      "step": 230
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.459509532338337e-05,
+      "loss": 0.8489,
+      "step": 240
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 2.416760571146774e-05,
+      "loss": 0.851,
+      "step": 250
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 2.3727883733369295e-05,
+      "loss": 0.8481,
+      "step": 260
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.327651611155669e-05,
+      "loss": 0.8605,
+      "step": 270
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 2.2814105107318955e-05,
+      "loss": 0.8586,
+      "step": 280
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2.2341267717166285e-05,
+      "loss": 0.8642,
+      "step": 290
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2.1858634849569578e-05,
+      "loss": 0.8676,
+      "step": 300
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 2.136685048313723e-05,
+      "loss": 0.8443,
+      "step": 310
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 2.086657080735234e-05,
+      "loss": 0.842,
+      "step": 320
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.035846334701699e-05,
+      "loss": 0.8432,
+      "step": 330
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.9843206071571692e-05,
+      "loss": 0.8451,
+      "step": 340
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.9321486490478565e-05,
+      "loss": 0.8645,
+      "step": 350
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.879400073587521e-05,
+      "loss": 0.8377,
+      "step": 360
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.8261452633723356e-05,
+      "loss": 0.8374,
+      "step": 370
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.7724552764691545e-05,
+      "loss": 0.8491,
+      "step": 380
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.7184017516025075e-05,
+      "loss": 0.8391,
+      "step": 390
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.664056812566812e-05,
+      "loss": 0.8521,
+      "step": 400
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.6094929719913614e-05,
+      "loss": 0.846,
+      "step": 410
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.5547830345864887e-05,
+      "loss": 0.8759,
+      "step": 420
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.5e-05,
+      "loss": 0.8411,
+      "step": 430
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.4452169654135116e-05,
+      "loss": 0.8106,
+      "step": 440
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1.3905070280086387e-05,
+      "loss": 0.8265,
+      "step": 450
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.3359431874331888e-05,
+      "loss": 0.8261,
+      "step": 460
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 1.281598248397493e-05,
+      "loss": 0.8107,
+      "step": 470
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 1.2275447235308454e-05,
+      "loss": 0.7914,
+      "step": 480
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1.1738547366276648e-05,
+      "loss": 0.7966,
+      "step": 490
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 1.1205999264124788e-05,
+      "loss": 0.8102,
+      "step": 500
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.0678513509521436e-05,
+      "loss": 0.794,
+      "step": 510
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.015679392842831e-05,
+      "loss": 0.7862,
+      "step": 520
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 9.64153665298301e-06,
+      "loss": 0.8126,
+      "step": 530
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 9.133429192647661e-06,
+      "loss": 0.8134,
+      "step": 540
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 8.633149516862777e-06,
+      "loss": 0.8136,
+      "step": 550
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 8.141365150430423e-06,
+      "loss": 0.7995,
+      "step": 560
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 7.658732282833721e-06,
+      "loss": 0.7874,
+      "step": 570
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 7.185894892681048e-06,
+      "loss": 0.7907,
+      "step": 580
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 6.72348388844331e-06,
+      "loss": 0.7957,
+      "step": 590
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 6.27211626663071e-06,
+      "loss": 0.8031,
+      "step": 600
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 5.832394288532261e-06,
+      "loss": 0.8071,
+      "step": 610
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 5.404904676616634e-06,
+      "loss": 0.7953,
+      "step": 620
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 4.99021783166641e-06,
+      "loss": 0.8028,
+      "step": 630
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 4.588887071690491e-06,
+      "loss": 0.8043,
+      "step": 640
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 4.201447893630065e-06,
+      "loss": 0.7826,
+      "step": 650
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 3.828417258843272e-06,
+      "loss": 0.7723,
+      "step": 660
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 3.4702929033220176e-06,
+      "loss": 0.7734,
+      "step": 670
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 3.12755267356119e-06,
+      "loss": 0.7834,
+      "step": 680
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 2.8006538889665194e-06,
+      "loss": 0.7712,
+      "step": 690
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 2.490032731651833e-06,
+      "loss": 0.7634,
+      "step": 700
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 2.1961036644398034e-06,
+      "loss": 0.754,
+      "step": 710
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 1.9192588778428844e-06,
+      "loss": 0.7738,
+      "step": 720
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 1.6598677667622176e-06,
+      "loss": 0.7776,
+      "step": 730
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 1.4182764376028007e-06,
+      "loss": 0.7706,
+      "step": 740
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 1.1948072464626102e-06,
+      "loss": 0.7699,
+      "step": 750
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 9.897583690117813e-07,
+      "loss": 0.7867,
+      "step": 760
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 8.034034026358589e-07,
+      "loss": 0.766,
+      "step": 770
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 6.359910013739123e-07,
+      "loss": 0.7704,
+      "step": 780
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 4.877445441386219e-07,
+      "loss": 0.7601,
+      "step": 790
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 3.588618366610941e-07,
+      "loss": 0.7838,
+      "step": 800
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 2.495148475580089e-07,
+      "loss": 0.7715,
+      "step": 810
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 1.5984947887334622e-07,
+      "loss": 0.7726,
+      "step": 820
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 8.998537140081143e-08,
+      "loss": 0.7796,
+      "step": 830
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 4.0015745046725336e-08,
+      "loss": 0.786,
+      "step": 840
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 1.0007274446409143e-08,
+      "loss": 0.7874,
+      "step": 850
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 0.0,
+      "loss": 0.7847,
+      "step": 860
+    },
+    {
+      "epoch": 3.99,
+      "step": 860,
+      "total_flos": 1017528113430528.0,
+      "train_loss": 0.8370421792185584,
+      "train_runtime": 34197.088,
+      "train_samples_per_second": 5.644,
+      "train_steps_per_second": 0.025
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 860,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 1000,
+  "total_flos": 1017528113430528.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47d0716f07137cfe0ff2a2a9e839e9b7b130149e13de87c02a3f44edf688764c
+size 6008