openthoughts_30000 / trainer_log.jsonl
ryanmarten's picture
Upload folder using huggingface_hub
1ecdc1f verified
{"current_steps": 1, "total_steps": 72, "loss": 0.8792, "lr": 1e-05, "epoch": 0.041237113402061855, "percentage": 1.39, "elapsed_time": "0:04:17", "remaining_time": "5:04:36"}
{"current_steps": 2, "total_steps": 72, "loss": 0.8614, "lr": 2e-05, "epoch": 0.08247422680412371, "percentage": 2.78, "elapsed_time": "0:07:53", "remaining_time": "4:36:07"}
{"current_steps": 3, "total_steps": 72, "loss": 0.7805, "lr": 3.0000000000000004e-05, "epoch": 0.12371134020618557, "percentage": 4.17, "elapsed_time": "0:11:31", "remaining_time": "4:25:09"}
{"current_steps": 4, "total_steps": 72, "loss": 0.814, "lr": 4e-05, "epoch": 0.16494845360824742, "percentage": 5.56, "elapsed_time": "0:15:09", "remaining_time": "4:17:40"}
{"current_steps": 5, "total_steps": 72, "loss": 0.9298, "lr": 5e-05, "epoch": 0.20618556701030927, "percentage": 6.94, "elapsed_time": "0:18:46", "remaining_time": "4:11:30"}
{"current_steps": 6, "total_steps": 72, "loss": 0.8568, "lr": 6.000000000000001e-05, "epoch": 0.24742268041237114, "percentage": 8.33, "elapsed_time": "0:22:23", "remaining_time": "4:06:14"}
{"current_steps": 7, "total_steps": 72, "loss": 0.7715, "lr": 7.000000000000001e-05, "epoch": 0.28865979381443296, "percentage": 9.72, "elapsed_time": "0:26:00", "remaining_time": "4:01:32"}
{"current_steps": 8, "total_steps": 72, "loss": 0.7178, "lr": 8e-05, "epoch": 0.32989690721649484, "percentage": 11.11, "elapsed_time": "0:29:38", "remaining_time": "3:57:10"}
{"current_steps": 9, "total_steps": 72, "loss": 0.7012, "lr": 7.99518182482069e-05, "epoch": 0.3711340206185567, "percentage": 12.5, "elapsed_time": "0:33:17", "remaining_time": "3:53:00"}
{"current_steps": 10, "total_steps": 72, "loss": 0.7192, "lr": 7.980738906688788e-05, "epoch": 0.41237113402061853, "percentage": 13.89, "elapsed_time": "0:36:55", "remaining_time": "3:48:53"}
{"current_steps": 11, "total_steps": 72, "loss": 0.668, "lr": 7.956706039859124e-05, "epoch": 0.4536082474226804, "percentage": 15.28, "elapsed_time": "0:40:33", "remaining_time": "3:44:55"}
{"current_steps": 12, "total_steps": 72, "loss": 0.6467, "lr": 7.923141121612922e-05, "epoch": 0.4948453608247423, "percentage": 16.67, "elapsed_time": "0:44:01", "remaining_time": "3:40:08"}
{"current_steps": 13, "total_steps": 72, "loss": 0.6382, "lr": 7.880125012778177e-05, "epoch": 0.5360824742268041, "percentage": 18.06, "elapsed_time": "0:47:25", "remaining_time": "3:35:12"}
{"current_steps": 14, "total_steps": 72, "loss": 0.6351, "lr": 7.827761342928836e-05, "epoch": 0.5773195876288659, "percentage": 19.44, "elapsed_time": "0:51:04", "remaining_time": "3:31:34"}
{"current_steps": 15, "total_steps": 72, "loss": 0.6166, "lr": 7.766176260732084e-05, "epoch": 0.6185567010309279, "percentage": 20.83, "elapsed_time": "0:54:42", "remaining_time": "3:27:52"}
{"current_steps": 16, "total_steps": 72, "loss": 0.6185, "lr": 7.695518130045147e-05, "epoch": 0.6597938144329897, "percentage": 22.22, "elapsed_time": "0:58:19", "remaining_time": "3:24:08"}
{"current_steps": 17, "total_steps": 72, "loss": 0.5974, "lr": 7.615957172493774e-05, "epoch": 0.7010309278350515, "percentage": 23.61, "elapsed_time": "1:01:56", "remaining_time": "3:20:23"}
{"current_steps": 18, "total_steps": 72, "loss": 0.6219, "lr": 7.52768505739342e-05, "epoch": 0.7422680412371134, "percentage": 25.0, "elapsed_time": "1:05:33", "remaining_time": "3:16:39"}
{"current_steps": 19, "total_steps": 72, "loss": 0.5906, "lr": 7.430914440001089e-05, "epoch": 0.7835051546391752, "percentage": 26.39, "elapsed_time": "1:09:11", "remaining_time": "3:13:00"}
{"current_steps": 20, "total_steps": 72, "loss": 0.5944, "lr": 7.325878449210182e-05, "epoch": 0.8247422680412371, "percentage": 27.78, "elapsed_time": "1:12:48", "remaining_time": "3:09:18"}
{"current_steps": 21, "total_steps": 72, "loss": 0.5681, "lr": 7.21283012592258e-05, "epoch": 0.865979381443299, "percentage": 29.17, "elapsed_time": "1:16:28", "remaining_time": "3:05:42"}
{"current_steps": 22, "total_steps": 72, "loss": 0.569, "lr": 7.092041813450948e-05, "epoch": 0.9072164948453608, "percentage": 30.56, "elapsed_time": "1:20:07", "remaining_time": "3:02:06"}
{"current_steps": 23, "total_steps": 72, "loss": 0.5688, "lr": 6.963804501419837e-05, "epoch": 0.9484536082474226, "percentage": 31.94, "elapsed_time": "1:23:46", "remaining_time": "2:58:28"}
{"current_steps": 24, "total_steps": 72, "loss": 0.5538, "lr": 6.828427124746191e-05, "epoch": 0.9896907216494846, "percentage": 33.33, "elapsed_time": "1:27:21", "remaining_time": "2:54:42"}
{"current_steps": 25, "total_steps": 72, "loss": 0.5439, "lr": 6.686235819388075e-05, "epoch": 1.0309278350515463, "percentage": 34.72, "elapsed_time": "1:31:50", "remaining_time": "2:52:40"}
{"current_steps": 26, "total_steps": 72, "loss": 0.5383, "lr": 6.537573136654582e-05, "epoch": 1.0721649484536082, "percentage": 36.11, "elapsed_time": "1:35:24", "remaining_time": "2:48:47"}
{"current_steps": 27, "total_steps": 72, "loss": 0.5447, "lr": 6.382797217969734e-05, "epoch": 1.1134020618556701, "percentage": 37.5, "elapsed_time": "1:39:01", "remaining_time": "2:45:02"}
{"current_steps": 28, "total_steps": 72, "loss": 0.5319, "lr": 6.22228093207841e-05, "epoch": 1.1546391752577319, "percentage": 38.89, "elapsed_time": "1:42:39", "remaining_time": "2:41:19"}
{"current_steps": 29, "total_steps": 72, "loss": 0.537, "lr": 6.056410976772887e-05, "epoch": 1.1958762886597938, "percentage": 40.28, "elapsed_time": "1:46:21", "remaining_time": "2:37:41"}
{"current_steps": 30, "total_steps": 72, "loss": 0.5224, "lr": 5.8855869473039924e-05, "epoch": 1.2371134020618557, "percentage": 41.67, "elapsed_time": "1:50:00", "remaining_time": "2:34:00"}
{"current_steps": 31, "total_steps": 72, "loss": 0.511, "lr": 5.710220373721129e-05, "epoch": 1.2783505154639174, "percentage": 43.06, "elapsed_time": "1:53:39", "remaining_time": "2:30:18"}
{"current_steps": 32, "total_steps": 72, "loss": 0.518, "lr": 5.5307337294603595e-05, "epoch": 1.3195876288659794, "percentage": 44.44, "elapsed_time": "1:57:18", "remaining_time": "2:26:37"}
{"current_steps": 33, "total_steps": 72, "loss": 0.5119, "lr": 5.347559413568881e-05, "epoch": 1.3608247422680413, "percentage": 45.83, "elapsed_time": "2:00:55", "remaining_time": "2:22:54"}
{"current_steps": 34, "total_steps": 72, "loss": 0.5117, "lr": 5.16113870901785e-05, "epoch": 1.402061855670103, "percentage": 47.22, "elapsed_time": "2:04:33", "remaining_time": "2:19:13"}
{"current_steps": 35, "total_steps": 72, "loss": 0.5076, "lr": 4.971920719613056e-05, "epoch": 1.443298969072165, "percentage": 48.61, "elapsed_time": "2:08:11", "remaining_time": "2:15:31"}
{"current_steps": 36, "total_steps": 72, "loss": 0.503, "lr": 4.780361288064514e-05, "epoch": 1.4845360824742269, "percentage": 50.0, "elapsed_time": "2:11:53", "remaining_time": "2:11:53"}
{"current_steps": 37, "total_steps": 72, "loss": 0.5098, "lr": 4.586921897821447e-05, "epoch": 1.5257731958762886, "percentage": 51.39, "elapsed_time": "2:15:23", "remaining_time": "2:08:04"}
{"current_steps": 38, "total_steps": 72, "loss": 0.4945, "lr": 4.392068561318244e-05, "epoch": 1.5670103092783505, "percentage": 52.78, "elapsed_time": "2:18:49", "remaining_time": "2:04:12"}
{"current_steps": 39, "total_steps": 72, "loss": 0.4953, "lr": 4.1962706973096726e-05, "epoch": 1.6082474226804124, "percentage": 54.17, "elapsed_time": "2:22:27", "remaining_time": "2:00:32"}
{"current_steps": 40, "total_steps": 72, "loss": 0.501, "lr": 4e-05, "epoch": 1.6494845360824741, "percentage": 55.56, "elapsed_time": "2:26:05", "remaining_time": "1:56:52"}
{"current_steps": 41, "total_steps": 72, "loss": 0.4918, "lr": 3.803729302690328e-05, "epoch": 1.690721649484536, "percentage": 56.94, "elapsed_time": "2:29:41", "remaining_time": "1:53:11"}
{"current_steps": 42, "total_steps": 72, "loss": 0.4852, "lr": 3.6079314386817575e-05, "epoch": 1.731958762886598, "percentage": 58.33, "elapsed_time": "2:33:18", "remaining_time": "1:49:30"}
{"current_steps": 43, "total_steps": 72, "loss": 0.4897, "lr": 3.4130781021785535e-05, "epoch": 1.7731958762886597, "percentage": 59.72, "elapsed_time": "2:36:56", "remaining_time": "1:45:50"}
{"current_steps": 44, "total_steps": 72, "loss": 0.4919, "lr": 3.219638711935488e-05, "epoch": 1.8144329896907216, "percentage": 61.11, "elapsed_time": "2:40:33", "remaining_time": "1:42:10"}
{"current_steps": 45, "total_steps": 72, "loss": 0.4846, "lr": 3.028079280386945e-05, "epoch": 1.8556701030927836, "percentage": 62.5, "elapsed_time": "2:44:10", "remaining_time": "1:38:30"}
{"current_steps": 46, "total_steps": 72, "loss": 0.4865, "lr": 2.8388612909821515e-05, "epoch": 1.8969072164948453, "percentage": 63.89, "elapsed_time": "2:47:47", "remaining_time": "1:34:50"}
{"current_steps": 47, "total_steps": 72, "loss": 0.4828, "lr": 2.6524405864311203e-05, "epoch": 1.9381443298969072, "percentage": 65.28, "elapsed_time": "2:51:24", "remaining_time": "1:31:10"}
{"current_steps": 48, "total_steps": 72, "loss": 0.4896, "lr": 2.4692662705396412e-05, "epoch": 1.9793814432989691, "percentage": 66.67, "elapsed_time": "2:55:01", "remaining_time": "1:27:30"}
{"current_steps": 49, "total_steps": 72, "loss": 0.4781, "lr": 2.2897796262788728e-05, "epoch": 2.020618556701031, "percentage": 68.06, "elapsed_time": "2:59:40", "remaining_time": "1:24:20"}
{"current_steps": 50, "total_steps": 72, "loss": 0.4651, "lr": 2.1144130526960093e-05, "epoch": 2.0618556701030926, "percentage": 69.44, "elapsed_time": "3:03:17", "remaining_time": "1:20:38"}
{"current_steps": 51, "total_steps": 72, "loss": 0.4684, "lr": 1.9435890232271136e-05, "epoch": 2.1030927835051547, "percentage": 70.83, "elapsed_time": "3:06:54", "remaining_time": "1:16:57"}
{"current_steps": 52, "total_steps": 72, "loss": 0.4625, "lr": 1.7777190679215923e-05, "epoch": 2.1443298969072164, "percentage": 72.22, "elapsed_time": "3:10:32", "remaining_time": "1:13:17"}
{"current_steps": 53, "total_steps": 72, "loss": 0.4694, "lr": 1.617202782030267e-05, "epoch": 2.1855670103092786, "percentage": 73.61, "elapsed_time": "3:14:11", "remaining_time": "1:09:36"}
{"current_steps": 54, "total_steps": 72, "loss": 0.4671, "lr": 1.4624268633454187e-05, "epoch": 2.2268041237113403, "percentage": 75.0, "elapsed_time": "3:17:48", "remaining_time": "1:05:56"}
{"current_steps": 55, "total_steps": 72, "loss": 0.4519, "lr": 1.3137641806119264e-05, "epoch": 2.268041237113402, "percentage": 76.39, "elapsed_time": "3:21:24", "remaining_time": "1:02:15"}
{"current_steps": 56, "total_steps": 72, "loss": 0.4659, "lr": 1.1715728752538103e-05, "epoch": 2.3092783505154637, "percentage": 77.78, "elapsed_time": "3:25:01", "remaining_time": "0:58:34"}
{"current_steps": 57, "total_steps": 72, "loss": 0.4603, "lr": 1.0361954985801646e-05, "epoch": 2.350515463917526, "percentage": 79.17, "elapsed_time": "3:28:37", "remaining_time": "0:54:54"}
{"current_steps": 58, "total_steps": 72, "loss": 0.4613, "lr": 9.07958186549052e-06, "epoch": 2.3917525773195876, "percentage": 80.56, "elapsed_time": "3:32:12", "remaining_time": "0:51:13"}
{"current_steps": 59, "total_steps": 72, "loss": 0.46, "lr": 7.871698740774208e-06, "epoch": 2.4329896907216497, "percentage": 81.94, "elapsed_time": "3:35:48", "remaining_time": "0:47:32"}
{"current_steps": 60, "total_steps": 72, "loss": 0.458, "lr": 6.7412155078981865e-06, "epoch": 2.4742268041237114, "percentage": 83.33, "elapsed_time": "3:39:18", "remaining_time": "0:43:51"}
{"current_steps": 61, "total_steps": 72, "loss": 0.456, "lr": 5.690855599989121e-06, "epoch": 2.515463917525773, "percentage": 84.72, "elapsed_time": "3:42:48", "remaining_time": "0:40:10"}
{"current_steps": 62, "total_steps": 72, "loss": 0.4533, "lr": 4.723149426065803e-06, "epoch": 2.556701030927835, "percentage": 86.11, "elapsed_time": "3:46:24", "remaining_time": "0:36:30"}
{"current_steps": 63, "total_steps": 72, "loss": 0.4668, "lr": 3.840428275062267e-06, "epoch": 2.597938144329897, "percentage": 87.5, "elapsed_time": "3:49:59", "remaining_time": "0:32:51"}
{"current_steps": 64, "total_steps": 72, "loss": 0.4556, "lr": 3.0448186995485307e-06, "epoch": 2.6391752577319587, "percentage": 88.89, "elapsed_time": "3:53:35", "remaining_time": "0:29:11"}
{"current_steps": 65, "total_steps": 72, "loss": 0.4621, "lr": 2.3382373926791722e-06, "epoch": 2.680412371134021, "percentage": 90.28, "elapsed_time": "3:57:11", "remaining_time": "0:25:32"}
{"current_steps": 66, "total_steps": 72, "loss": 0.4479, "lr": 1.7223865707116472e-06, "epoch": 2.7216494845360826, "percentage": 91.67, "elapsed_time": "4:00:48", "remaining_time": "0:21:53"}
{"current_steps": 67, "total_steps": 72, "loss": 0.4554, "lr": 1.1987498722182411e-06, "epoch": 2.7628865979381443, "percentage": 93.06, "elapsed_time": "4:04:24", "remaining_time": "0:18:14"}
{"current_steps": 68, "total_steps": 72, "loss": 0.4546, "lr": 7.685887838707828e-07, "epoch": 2.804123711340206, "percentage": 94.44, "elapsed_time": "4:08:00", "remaining_time": "0:14:35"}
{"current_steps": 69, "total_steps": 72, "loss": 0.4593, "lr": 4.3293960140875946e-07, "epoch": 2.845360824742268, "percentage": 95.83, "elapsed_time": "4:11:37", "remaining_time": "0:10:56"}
{"current_steps": 70, "total_steps": 72, "loss": 0.4613, "lr": 1.926109331121273e-07, "epoch": 2.88659793814433, "percentage": 97.22, "elapsed_time": "4:15:13", "remaining_time": "0:07:17"}
{"current_steps": 71, "total_steps": 72, "loss": 0.4534, "lr": 4.8181751793103806e-08, "epoch": 2.927835051546392, "percentage": 98.61, "elapsed_time": "4:18:43", "remaining_time": "0:03:38"}
{"current_steps": 72, "total_steps": 72, "loss": 0.4659, "lr": 0.0, "epoch": 2.9690721649484537, "percentage": 100.0, "elapsed_time": "4:22:16", "remaining_time": "0:00:00"}
{"current_steps": 72, "total_steps": 72, "epoch": 2.9690721649484537, "percentage": 100.0, "elapsed_time": "4:23:24", "remaining_time": "0:00:00"}