Terminal-terminal_traj / trainer_log.jsonl
cuong1692001's picture
Upload folder using huggingface_hub
561208d verified
Raw
History Blame Contribute Delete
233 kB
{"current_steps": 5, "total_steps": 5000, "loss": 0.4748, "lr": 9.999984208641271e-06, "epoch": 0.002, "percentage": 0.1, "elapsed_time": "0:01:15", "remaining_time": "20:50:50", "throughput": 5280.3, "total_tokens": 396688}
{"current_steps": 10, "total_steps": 5000, "loss": 0.3853, "lr": 9.999920056417385e-06, "epoch": 0.004, "percentage": 0.2, "elapsed_time": "0:02:18", "remaining_time": "19:09:25", "throughput": 5643.96, "total_tokens": 780032}
{"current_steps": 15, "total_steps": 5000, "loss": 0.3416, "lr": 9.999806557001092e-06, "epoch": 0.006, "percentage": 0.3, "elapsed_time": "0:03:25", "remaining_time": "18:55:32", "throughput": 6047.89, "total_tokens": 1239888}
{"current_steps": 20, "total_steps": 5000, "loss": 0.3701, "lr": 9.999643711512586e-06, "epoch": 0.008, "percentage": 0.4, "elapsed_time": "0:04:25", "remaining_time": "18:23:08", "throughput": 6032.22, "total_tokens": 1603472}
{"current_steps": 25, "total_steps": 5000, "loss": 0.3371, "lr": 9.999431521559081e-06, "epoch": 0.01, "percentage": 0.5, "elapsed_time": "0:05:25", "remaining_time": "18:00:25", "throughput": 6026.57, "total_tokens": 1963184}
{"current_steps": 30, "total_steps": 5000, "loss": 0.3436, "lr": 9.999169989234815e-06, "epoch": 0.012, "percentage": 0.6, "elapsed_time": "0:06:27", "remaining_time": "17:50:11", "throughput": 6001.77, "total_tokens": 2326256}
{"current_steps": 35, "total_steps": 5000, "loss": 0.3498, "lr": 9.998859117121e-06, "epoch": 0.014, "percentage": 0.7, "elapsed_time": "0:07:24", "remaining_time": "17:31:28", "throughput": 6101.78, "total_tokens": 2713648}
{"current_steps": 40, "total_steps": 5000, "loss": 0.3205, "lr": 9.99849890828582e-06, "epoch": 0.016, "percentage": 0.8, "elapsed_time": "0:08:30", "remaining_time": "17:35:41", "throughput": 6082.12, "total_tokens": 3106864}
{"current_steps": 45, "total_steps": 5000, "loss": 0.3272, "lr": 9.998089366284392e-06, "epoch": 0.018, "percentage": 0.9, "elapsed_time": "0:09:33", "remaining_time": "17:31:59", "throughput": 6129.63, "total_tokens": 3513728}
{"current_steps": 50, "total_steps": 5000, "loss": 0.3279, "lr": 9.997630495158728e-06, "epoch": 0.02, "percentage": 1.0, "elapsed_time": "0:10:51", "remaining_time": "17:54:56", "throughput": 6064.21, "total_tokens": 3950720}
{"current_steps": 55, "total_steps": 5000, "loss": 0.304, "lr": 9.9971222994377e-06, "epoch": 0.022, "percentage": 1.1, "elapsed_time": "0:12:03", "remaining_time": "18:03:29", "throughput": 6004.99, "total_tokens": 4341968}
{"current_steps": 60, "total_steps": 5000, "loss": 0.2791, "lr": 9.996564784137e-06, "epoch": 0.024, "percentage": 1.2, "elapsed_time": "0:13:09", "remaining_time": "18:03:42", "throughput": 5972.56, "total_tokens": 4716832}
{"current_steps": 65, "total_steps": 5000, "loss": 0.3242, "lr": 9.995957954759073e-06, "epoch": 0.026, "percentage": 1.3, "elapsed_time": "0:14:28", "remaining_time": "18:18:31", "throughput": 5978.94, "total_tokens": 5190560}
{"current_steps": 70, "total_steps": 5000, "loss": 0.3044, "lr": 9.995301817293084e-06, "epoch": 0.028, "percentage": 1.4, "elapsed_time": "0:15:31", "remaining_time": "18:13:07", "throughput": 5973.74, "total_tokens": 5563120}
{"current_steps": 75, "total_steps": 5000, "loss": 0.3096, "lr": 9.99459637821484e-06, "epoch": 0.03, "percentage": 1.5, "elapsed_time": "0:16:38", "remaining_time": "18:12:44", "throughput": 5980.07, "total_tokens": 5970768}
{"current_steps": 80, "total_steps": 5000, "loss": 0.3166, "lr": 9.993841644486747e-06, "epoch": 0.032, "percentage": 1.6, "elapsed_time": "0:17:19", "remaining_time": "17:45:23", "throughput": 6022.07, "total_tokens": 6259376}
{"current_steps": 85, "total_steps": 5000, "loss": 0.3017, "lr": 9.993037623557716e-06, "epoch": 0.034, "percentage": 1.7, "elapsed_time": "0:18:30", "remaining_time": "17:49:47", "throughput": 5994.66, "total_tokens": 6654464}
{"current_steps": 90, "total_steps": 5000, "loss": 0.2731, "lr": 9.992184323363112e-06, "epoch": 0.036, "percentage": 1.8, "elapsed_time": "0:19:43", "remaining_time": "17:56:16", "throughput": 5933.85, "total_tokens": 7023760}
{"current_steps": 95, "total_steps": 5000, "loss": 0.3023, "lr": 9.991281752324664e-06, "epoch": 0.038, "percentage": 1.9, "elapsed_time": "0:20:57", "remaining_time": "18:02:32", "throughput": 5911.11, "total_tokens": 7436112}
{"current_steps": 100, "total_steps": 5000, "loss": 0.2834, "lr": 9.990329919350382e-06, "epoch": 0.04, "percentage": 2.0, "elapsed_time": "0:22:02", "remaining_time": "18:00:07", "throughput": 5891.3, "total_tokens": 7791888}
{"current_steps": 105, "total_steps": 5000, "loss": 0.3008, "lr": 9.989328833834472e-06, "epoch": 0.042, "percentage": 2.1, "elapsed_time": "0:23:00", "remaining_time": "17:52:30", "throughput": 5930.3, "total_tokens": 8185936}
{"current_steps": 110, "total_steps": 5000, "loss": 0.2933, "lr": 9.988278505657247e-06, "epoch": 0.044, "percentage": 2.2, "elapsed_time": "0:24:07", "remaining_time": "17:52:26", "throughput": 5940.58, "total_tokens": 8598768}
{"current_steps": 115, "total_steps": 5000, "loss": 0.2986, "lr": 9.987178945185019e-06, "epoch": 0.046, "percentage": 2.3, "elapsed_time": "0:25:15", "remaining_time": "17:53:09", "throughput": 5948.73, "total_tokens": 9017264}
{"current_steps": 120, "total_steps": 5000, "loss": 0.3024, "lr": 9.986030163270011e-06, "epoch": 0.048, "percentage": 2.4, "elapsed_time": "0:26:33", "remaining_time": "18:00:17", "throughput": 5928.89, "total_tokens": 9449872}
{"current_steps": 125, "total_steps": 5000, "loss": 0.2553, "lr": 9.98483217125023e-06, "epoch": 0.05, "percentage": 2.5, "elapsed_time": "0:27:43", "remaining_time": "18:00:59", "throughput": 5937.37, "total_tokens": 9874192}
{"current_steps": 130, "total_steps": 5000, "loss": 0.3012, "lr": 9.98358498094938e-06, "epoch": 0.052, "percentage": 2.6, "elapsed_time": "0:28:47", "remaining_time": "17:58:26", "throughput": 5950.52, "total_tokens": 10278272}
{"current_steps": 135, "total_steps": 5000, "loss": 0.2758, "lr": 9.982288604676719e-06, "epoch": 0.054, "percentage": 2.7, "elapsed_time": "0:29:53", "remaining_time": "17:57:02", "throughput": 5964.21, "total_tokens": 10695136}
{"current_steps": 140, "total_steps": 5000, "loss": 0.3056, "lr": 9.980943055226964e-06, "epoch": 0.056, "percentage": 2.8, "elapsed_time": "0:30:54", "remaining_time": "17:53:04", "throughput": 5952.24, "total_tokens": 11039680}
{"current_steps": 145, "total_steps": 5000, "loss": 0.2943, "lr": 9.979548345880142e-06, "epoch": 0.058, "percentage": 2.9, "elapsed_time": "0:32:06", "remaining_time": "17:54:53", "throughput": 5946.55, "total_tokens": 11454128}
{"current_steps": 150, "total_steps": 5000, "loss": 0.2913, "lr": 9.978104490401468e-06, "epoch": 0.06, "percentage": 3.0, "elapsed_time": "0:32:58", "remaining_time": "17:46:15", "throughput": 5960.97, "total_tokens": 11794496}
{"current_steps": 155, "total_steps": 5000, "loss": 0.3153, "lr": 9.976611503041218e-06, "epoch": 0.062, "percentage": 3.1, "elapsed_time": "0:34:11", "remaining_time": "17:48:39", "throughput": 5932.45, "total_tokens": 12169264}
{"current_steps": 160, "total_steps": 5000, "loss": 0.2993, "lr": 9.975069398534574e-06, "epoch": 0.064, "percentage": 3.2, "elapsed_time": "0:35:13", "remaining_time": "17:45:29", "throughput": 5921.87, "total_tokens": 12515168}
{"current_steps": 165, "total_steps": 5000, "loss": 0.2946, "lr": 9.97347819210148e-06, "epoch": 0.066, "percentage": 3.3, "elapsed_time": "0:36:14", "remaining_time": "17:41:58", "throughput": 5934.98, "total_tokens": 12905488}
{"current_steps": 170, "total_steps": 5000, "loss": 0.3075, "lr": 9.971837899446505e-06, "epoch": 0.068, "percentage": 3.4, "elapsed_time": "0:37:32", "remaining_time": "17:46:39", "throughput": 5930.4, "total_tokens": 13358672}
{"current_steps": 175, "total_steps": 5000, "loss": 0.2952, "lr": 9.970148536758678e-06, "epoch": 0.07, "percentage": 3.5, "elapsed_time": "0:38:35", "remaining_time": "17:43:57", "throughput": 5951.34, "total_tokens": 13779472}
{"current_steps": 180, "total_steps": 5000, "loss": 0.2709, "lr": 9.968410120711321e-06, "epoch": 0.072, "percentage": 3.6, "elapsed_time": "0:39:31", "remaining_time": "17:38:26", "throughput": 5942.66, "total_tokens": 14093728}
{"current_steps": 185, "total_steps": 5000, "loss": 0.2928, "lr": 9.966622668461899e-06, "epoch": 0.074, "percentage": 3.7, "elapsed_time": "0:40:44", "remaining_time": "17:40:12", "throughput": 5971.86, "total_tokens": 14595840}
{"current_steps": 190, "total_steps": 5000, "loss": 0.2898, "lr": 9.964786197651848e-06, "epoch": 0.076, "percentage": 3.8, "elapsed_time": "0:41:37", "remaining_time": "17:33:45", "throughput": 5973.71, "total_tokens": 14919280}
{"current_steps": 195, "total_steps": 5000, "loss": 0.2992, "lr": 9.96290072640639e-06, "epoch": 0.078, "percentage": 3.9, "elapsed_time": "0:42:47", "remaining_time": "17:34:34", "throughput": 5945.92, "total_tokens": 15268256}
{"current_steps": 200, "total_steps": 5000, "loss": 0.3001, "lr": 9.96096627333437e-06, "epoch": 0.08, "percentage": 4.0, "elapsed_time": "0:43:55", "remaining_time": "17:34:13", "throughput": 5948.83, "total_tokens": 15678432}
{"current_steps": 205, "total_steps": 5000, "loss": 0.2888, "lr": 9.958982857528053e-06, "epoch": 0.082, "percentage": 4.1, "elapsed_time": "0:45:14", "remaining_time": "17:38:08", "throughput": 5954.18, "total_tokens": 16161600}
{"current_steps": 210, "total_steps": 5000, "loss": 0.2696, "lr": 9.956950498562954e-06, "epoch": 0.084, "percentage": 4.2, "elapsed_time": "0:46:29", "remaining_time": "17:40:28", "throughput": 5941.0, "total_tokens": 16572832}
{"current_steps": 215, "total_steps": 5000, "loss": 0.298, "lr": 9.954869216497636e-06, "epoch": 0.086, "percentage": 4.3, "elapsed_time": "0:47:38", "remaining_time": "17:40:07", "throughput": 5936.27, "total_tokens": 16966064}
{"current_steps": 220, "total_steps": 5000, "loss": 0.2919, "lr": 9.952739031873513e-06, "epoch": 0.088, "percentage": 4.4, "elapsed_time": "0:48:43", "remaining_time": "17:38:41", "throughput": 5926.49, "total_tokens": 17326464}
{"current_steps": 225, "total_steps": 5000, "loss": 0.29, "lr": 9.950559965714647e-06, "epoch": 0.09, "percentage": 4.5, "elapsed_time": "0:49:58", "remaining_time": "17:40:27", "throughput": 5936.6, "total_tokens": 17798944}
{"current_steps": 230, "total_steps": 5000, "loss": 0.281, "lr": 9.948332039527541e-06, "epoch": 0.092, "percentage": 4.6, "elapsed_time": "0:51:04", "remaining_time": "17:39:04", "throughput": 5940.99, "total_tokens": 18203216}
{"current_steps": 235, "total_steps": 5000, "loss": 0.2857, "lr": 9.946055275300929e-06, "epoch": 0.094, "percentage": 4.7, "elapsed_time": "0:52:02", "remaining_time": "17:35:21", "throughput": 5954.6, "total_tokens": 18595600}
{"current_steps": 240, "total_steps": 5000, "loss": 0.276, "lr": 9.943729695505552e-06, "epoch": 0.096, "percentage": 4.8, "elapsed_time": "0:53:08", "remaining_time": "17:33:57", "throughput": 5960.9, "total_tokens": 19005936}
{"current_steps": 245, "total_steps": 5000, "loss": 0.297, "lr": 9.941355323093944e-06, "epoch": 0.098, "percentage": 4.9, "elapsed_time": "0:54:15", "remaining_time": "17:32:57", "throughput": 5963.53, "total_tokens": 19412496}
{"current_steps": 250, "total_steps": 5000, "loss": 0.2649, "lr": 9.938932181500206e-06, "epoch": 0.1, "percentage": 5.0, "elapsed_time": "0:55:33", "remaining_time": "17:35:34", "throughput": 5949.22, "total_tokens": 19830960}
{"current_steps": 255, "total_steps": 5000, "loss": 0.252, "lr": 9.93646029463976e-06, "epoch": 0.102, "percentage": 5.1, "elapsed_time": "0:56:41", "remaining_time": "17:34:54", "throughput": 5941.58, "total_tokens": 20210288}
{"current_steps": 260, "total_steps": 5000, "loss": 0.2986, "lr": 9.933939686909137e-06, "epoch": 0.104, "percentage": 5.2, "elapsed_time": "0:57:55", "remaining_time": "17:36:03", "throughput": 5941.81, "total_tokens": 20651728}
{"current_steps": 265, "total_steps": 5000, "loss": 0.2679, "lr": 9.931370383185717e-06, "epoch": 0.106, "percentage": 5.3, "elapsed_time": "0:59:09", "remaining_time": "17:36:53", "throughput": 5940.8, "total_tokens": 21084048}
{"current_steps": 270, "total_steps": 5000, "loss": 0.2861, "lr": 9.92875240882749e-06, "epoch": 0.108, "percentage": 5.4, "elapsed_time": "1:00:01", "remaining_time": "17:31:28", "throughput": 5948.09, "total_tokens": 21420560}
{"current_steps": 275, "total_steps": 5000, "loss": 0.2649, "lr": 9.926085789672806e-06, "epoch": 0.11, "percentage": 5.5, "elapsed_time": "1:01:07", "remaining_time": "17:30:07", "throughput": 5943.24, "total_tokens": 21794608}
{"current_steps": 280, "total_steps": 5000, "loss": 0.3103, "lr": 9.923370552040117e-06, "epoch": 0.112, "percentage": 5.6, "elapsed_time": "1:02:15", "remaining_time": "17:29:30", "throughput": 5942.92, "total_tokens": 22200176}
{"current_steps": 285, "total_steps": 5000, "loss": 0.2771, "lr": 9.920606722727726e-06, "epoch": 0.114, "percentage": 5.7, "elapsed_time": "1:03:12", "remaining_time": "17:25:35", "throughput": 5956.79, "total_tokens": 22588416}
{"current_steps": 290, "total_steps": 5000, "loss": 0.2872, "lr": 9.917794329013511e-06, "epoch": 0.116, "percentage": 5.8, "elapsed_time": "1:04:17", "remaining_time": "17:24:15", "throughput": 5960.92, "total_tokens": 22996016}
{"current_steps": 295, "total_steps": 5000, "loss": 0.2847, "lr": 9.914933398654663e-06, "epoch": 0.118, "percentage": 5.9, "elapsed_time": "1:05:27", "remaining_time": "17:24:06", "throughput": 5965.89, "total_tokens": 23433456}
{"current_steps": 300, "total_steps": 5000, "loss": 0.2537, "lr": 9.912023959887408e-06, "epoch": 0.12, "percentage": 6.0, "elapsed_time": "1:06:22", "remaining_time": "17:19:47", "throughput": 5971.99, "total_tokens": 23781600}
{"current_steps": 305, "total_steps": 5000, "loss": 0.2843, "lr": 9.909066041426733e-06, "epoch": 0.122, "percentage": 6.1, "elapsed_time": "1:07:35", "remaining_time": "17:20:24", "throughput": 5973.74, "total_tokens": 24225024}
{"current_steps": 310, "total_steps": 5000, "loss": 0.2864, "lr": 9.9060596724661e-06, "epoch": 0.124, "percentage": 6.2, "elapsed_time": "1:08:35", "remaining_time": "17:17:39", "throughput": 5975.97, "total_tokens": 24592480}
{"current_steps": 315, "total_steps": 5000, "loss": 0.2892, "lr": 9.903004882677157e-06, "epoch": 0.126, "percentage": 6.3, "elapsed_time": "1:09:28", "remaining_time": "17:13:17", "throughput": 5987.1, "total_tokens": 24957024}
{"current_steps": 320, "total_steps": 5000, "loss": 0.2789, "lr": 9.899901702209445e-06, "epoch": 0.128, "percentage": 6.4, "elapsed_time": "1:10:44", "remaining_time": "17:14:32", "throughput": 5978.65, "total_tokens": 25374832}
{"current_steps": 325, "total_steps": 5000, "loss": 0.2766, "lr": 9.8967501616901e-06, "epoch": 0.13, "percentage": 6.5, "elapsed_time": "1:11:57", "remaining_time": "17:15:04", "throughput": 5978.31, "total_tokens": 25810848}
{"current_steps": 330, "total_steps": 5000, "loss": 0.293, "lr": 9.89355029222356e-06, "epoch": 0.132, "percentage": 6.6, "elapsed_time": "1:13:00", "remaining_time": "17:13:11", "throughput": 5989.45, "total_tokens": 26237024}
{"current_steps": 335, "total_steps": 5000, "loss": 0.286, "lr": 9.89030212539124e-06, "epoch": 0.134, "percentage": 6.7, "elapsed_time": "1:13:57", "remaining_time": "17:09:48", "throughput": 6001.43, "total_tokens": 26629216}
{"current_steps": 340, "total_steps": 5000, "loss": 0.3048, "lr": 9.88700569325124e-06, "epoch": 0.136, "percentage": 6.8, "elapsed_time": "1:15:03", "remaining_time": "17:08:42", "throughput": 6004.95, "total_tokens": 27042592}
{"current_steps": 345, "total_steps": 5000, "loss": 0.2555, "lr": 9.883661028338009e-06, "epoch": 0.138, "percentage": 6.9, "elapsed_time": "1:16:17", "remaining_time": "17:09:17", "throughput": 5993.61, "total_tokens": 27433280}
{"current_steps": 350, "total_steps": 5000, "loss": 0.2678, "lr": 9.880268163662043e-06, "epoch": 0.14, "percentage": 7.0, "elapsed_time": "1:17:20", "remaining_time": "17:07:34", "throughput": 5989.71, "total_tokens": 27796240}
{"current_steps": 355, "total_steps": 5000, "loss": 0.2818, "lr": 9.876827132709545e-06, "epoch": 0.142, "percentage": 7.1, "elapsed_time": "1:18:36", "remaining_time": "17:08:26", "throughput": 5988.7, "total_tokens": 28242816}
{"current_steps": 360, "total_steps": 5000, "loss": 0.2624, "lr": 9.873337969442102e-06, "epoch": 0.144, "percentage": 7.2, "elapsed_time": "1:19:44", "remaining_time": "17:07:45", "throughput": 5982.76, "total_tokens": 28623824}
{"current_steps": 365, "total_steps": 5000, "loss": 0.2888, "lr": 9.869800708296347e-06, "epoch": 0.146, "percentage": 7.3, "elapsed_time": "1:21:00", "remaining_time": "17:08:38", "throughput": 5979.0, "total_tokens": 29059536}
{"current_steps": 370, "total_steps": 5000, "loss": 0.2907, "lr": 9.86621538418362e-06, "epoch": 0.148, "percentage": 7.4, "elapsed_time": "1:22:01", "remaining_time": "17:06:30", "throughput": 5988.45, "total_tokens": 29474832}
{"current_steps": 375, "total_steps": 5000, "loss": 0.2706, "lr": 9.862582032489621e-06, "epoch": 0.15, "percentage": 7.5, "elapsed_time": "1:23:01", "remaining_time": "17:04:02", "throughput": 5996.33, "total_tokens": 29872512}
{"current_steps": 380, "total_steps": 5000, "loss": 0.2743, "lr": 9.858900689074065e-06, "epoch": 0.152, "percentage": 7.6, "elapsed_time": "1:24:16", "remaining_time": "17:04:33", "throughput": 6001.29, "total_tokens": 30343872}
{"current_steps": 385, "total_steps": 5000, "loss": 0.2688, "lr": 9.855171390270325e-06, "epoch": 0.154, "percentage": 7.7, "elapsed_time": "1:25:31", "remaining_time": "17:05:09", "throughput": 6011.86, "total_tokens": 30848768}
{"current_steps": 390, "total_steps": 5000, "loss": 0.2894, "lr": 9.851394172885075e-06, "epoch": 0.156, "percentage": 7.8, "elapsed_time": "1:26:43", "remaining_time": "17:05:11", "throughput": 6011.5, "total_tokens": 31282352}
{"current_steps": 395, "total_steps": 5000, "loss": 0.2886, "lr": 9.847569074197927e-06, "epoch": 0.158, "percentage": 7.9, "elapsed_time": "1:27:53", "remaining_time": "17:04:37", "throughput": 6008.54, "total_tokens": 31685040}
{"current_steps": 400, "total_steps": 5000, "loss": 0.273, "lr": 9.843696131961058e-06, "epoch": 0.16, "percentage": 8.0, "elapsed_time": "1:29:09", "remaining_time": "17:05:18", "throughput": 5991.67, "total_tokens": 32051808}
{"current_steps": 405, "total_steps": 5000, "loss": 0.2698, "lr": 9.839775384398846e-06, "epoch": 0.162, "percentage": 8.1, "elapsed_time": "1:30:24", "remaining_time": "17:05:48", "throughput": 5979.77, "total_tokens": 32439248}
{"current_steps": 410, "total_steps": 5000, "loss": 0.2574, "lr": 9.835806870207487e-06, "epoch": 0.164, "percentage": 8.2, "elapsed_time": "1:31:28", "remaining_time": "17:04:01", "throughput": 5987.49, "total_tokens": 32860528}
{"current_steps": 415, "total_steps": 5000, "loss": 0.2709, "lr": 9.831790628554613e-06, "epoch": 0.166, "percentage": 8.3, "elapsed_time": "1:32:38", "remaining_time": "17:03:31", "throughput": 5979.72, "total_tokens": 33238192}
{"current_steps": 420, "total_steps": 5000, "loss": 0.2656, "lr": 9.827726699078907e-06, "epoch": 0.168, "percentage": 8.4, "elapsed_time": "1:33:45", "remaining_time": "17:02:29", "throughput": 5988.35, "total_tokens": 33690160}
{"current_steps": 425, "total_steps": 5000, "loss": 0.29, "lr": 9.823615121889716e-06, "epoch": 0.17, "percentage": 8.5, "elapsed_time": "1:34:52", "remaining_time": "17:01:15", "throughput": 5985.96, "total_tokens": 34073536}
{"current_steps": 430, "total_steps": 5000, "loss": 0.2823, "lr": 9.819455937566642e-06, "epoch": 0.172, "percentage": 8.6, "elapsed_time": "1:35:54", "remaining_time": "16:59:22", "throughput": 5981.76, "total_tokens": 34424192}
{"current_steps": 435, "total_steps": 5000, "loss": 0.2496, "lr": 9.815249187159158e-06, "epoch": 0.174, "percentage": 8.7, "elapsed_time": "1:37:12", "remaining_time": "17:00:07", "throughput": 5968.26, "total_tokens": 34809680}
{"current_steps": 440, "total_steps": 5000, "loss": 0.2627, "lr": 9.81099491218619e-06, "epoch": 0.176, "percentage": 8.8, "elapsed_time": "1:38:15", "remaining_time": "16:58:20", "throughput": 5973.87, "total_tokens": 35219808}
{"current_steps": 445, "total_steps": 5000, "loss": 0.2774, "lr": 9.806693154635719e-06, "epoch": 0.178, "percentage": 8.9, "elapsed_time": "1:39:01", "remaining_time": "16:53:37", "throughput": 5985.83, "total_tokens": 35565248}
{"current_steps": 450, "total_steps": 5000, "loss": 0.2588, "lr": 9.802343956964348e-06, "epoch": 0.18, "percentage": 9.0, "elapsed_time": "1:40:03", "remaining_time": "16:51:46", "throughput": 5999.74, "total_tokens": 36022288}
{"current_steps": 455, "total_steps": 5000, "loss": 0.2588, "lr": 9.797947362096909e-06, "epoch": 0.182, "percentage": 9.1, "elapsed_time": "1:40:55", "remaining_time": "16:48:03", "throughput": 6008.19, "total_tokens": 36379920}
{"current_steps": 460, "total_steps": 5000, "loss": 0.283, "lr": 9.793503413426016e-06, "epoch": 0.184, "percentage": 9.2, "elapsed_time": "1:42:06", "remaining_time": "16:47:43", "throughput": 6002.36, "total_tokens": 36772016}
{"current_steps": 465, "total_steps": 5000, "loss": 0.2506, "lr": 9.789012154811648e-06, "epoch": 0.186, "percentage": 9.3, "elapsed_time": "1:43:21", "remaining_time": "16:47:57", "throughput": 5995.7, "total_tokens": 37179920}
{"current_steps": 470, "total_steps": 5000, "loss": 0.2597, "lr": 9.784473630580713e-06, "epoch": 0.188, "percentage": 9.4, "elapsed_time": "1:44:26", "remaining_time": "16:46:33", "throughput": 5994.99, "total_tokens": 37564736}
{"current_steps": 475, "total_steps": 5000, "loss": 0.2517, "lr": 9.779887885526616e-06, "epoch": 0.19, "percentage": 9.5, "elapsed_time": "1:45:31", "remaining_time": "16:45:15", "throughput": 5988.71, "total_tokens": 37917184}
{"current_steps": 480, "total_steps": 5000, "loss": 0.2538, "lr": 9.775254964908807e-06, "epoch": 0.192, "percentage": 9.6, "elapsed_time": "1:46:43", "remaining_time": "16:45:02", "throughput": 5989.87, "total_tokens": 38358080}
{"current_steps": 485, "total_steps": 5000, "loss": 0.26, "lr": 9.770574914452343e-06, "epoch": 0.194, "percentage": 9.7, "elapsed_time": "1:47:50", "remaining_time": "16:43:59", "throughput": 5990.89, "total_tokens": 38766496}
{"current_steps": 490, "total_steps": 5000, "loss": 0.3009, "lr": 9.765847780347433e-06, "epoch": 0.196, "percentage": 9.8, "elapsed_time": "1:48:52", "remaining_time": "16:42:04", "throughput": 5991.51, "total_tokens": 39138720}
{"current_steps": 495, "total_steps": 5000, "loss": 0.268, "lr": 9.761073609248981e-06, "epoch": 0.198, "percentage": 9.9, "elapsed_time": "1:49:53", "remaining_time": "16:40:03", "throughput": 5986.55, "total_tokens": 39469344}
{"current_steps": 500, "total_steps": 5000, "loss": 0.2887, "lr": 9.756252448276128e-06, "epoch": 0.2, "percentage": 10.0, "elapsed_time": "1:50:58", "remaining_time": "16:38:48", "throughput": 5986.88, "total_tokens": 39864896}
{"current_steps": 505, "total_steps": 5000, "loss": 0.2467, "lr": 9.751384345011787e-06, "epoch": 0.202, "percentage": 10.1, "elapsed_time": "1:52:09", "remaining_time": "16:38:20", "throughput": 5979.34, "total_tokens": 40238784}
{"current_steps": 510, "total_steps": 5000, "loss": 0.2698, "lr": 9.746469347502174e-06, "epoch": 0.204, "percentage": 10.2, "elapsed_time": "1:53:19", "remaining_time": "16:37:43", "throughput": 5980.64, "total_tokens": 40666368}
{"current_steps": 515, "total_steps": 5000, "loss": 0.2785, "lr": 9.741507504256327e-06, "epoch": 0.206, "percentage": 10.3, "elapsed_time": "1:54:26", "remaining_time": "16:36:36", "throughput": 5981.62, "total_tokens": 41071520}
{"current_steps": 520, "total_steps": 5000, "loss": 0.2527, "lr": 9.736498864245638e-06, "epoch": 0.208, "percentage": 10.4, "elapsed_time": "1:55:39", "remaining_time": "16:36:28", "throughput": 5981.8, "total_tokens": 41512256}
{"current_steps": 525, "total_steps": 5000, "loss": 0.29, "lr": 9.73144347690336e-06, "epoch": 0.21, "percentage": 10.5, "elapsed_time": "1:56:39", "remaining_time": "16:34:21", "throughput": 5982.45, "total_tokens": 41873264}
{"current_steps": 530, "total_steps": 5000, "loss": 0.2566, "lr": 9.726341392124127e-06, "epoch": 0.212, "percentage": 10.6, "elapsed_time": "1:57:33", "remaining_time": "16:31:29", "throughput": 5985.29, "total_tokens": 42217568}
{"current_steps": 535, "total_steps": 5000, "loss": 0.2762, "lr": 9.721192660263454e-06, "epoch": 0.214, "percentage": 10.7, "elapsed_time": "1:58:27", "remaining_time": "16:28:34", "throughput": 5984.55, "total_tokens": 42533184}
{"current_steps": 540, "total_steps": 5000, "loss": 0.2783, "lr": 9.715997332137248e-06, "epoch": 0.216, "percentage": 10.8, "elapsed_time": "1:59:37", "remaining_time": "16:27:58", "throughput": 5979.98, "total_tokens": 42919952}
{"current_steps": 545, "total_steps": 5000, "loss": 0.2809, "lr": 9.710755459021297e-06, "epoch": 0.218, "percentage": 10.9, "elapsed_time": "2:00:48", "remaining_time": "16:27:30", "throughput": 5979.03, "total_tokens": 43338336}
{"current_steps": 550, "total_steps": 5000, "loss": 0.2603, "lr": 9.705467092650775e-06, "epoch": 0.22, "percentage": 11.0, "elapsed_time": "2:01:41", "remaining_time": "16:24:37", "throughput": 5981.03, "total_tokens": 43671568}
{"current_steps": 555, "total_steps": 5000, "loss": 0.2591, "lr": 9.700132285219724e-06, "epoch": 0.222, "percentage": 11.1, "elapsed_time": "2:02:51", "remaining_time": "16:23:56", "throughput": 5973.48, "total_tokens": 44031712}
{"current_steps": 560, "total_steps": 5000, "loss": 0.2417, "lr": 9.694751089380536e-06, "epoch": 0.224, "percentage": 11.2, "elapsed_time": "2:03:54", "remaining_time": "16:22:27", "throughput": 5979.21, "total_tokens": 44454032}
{"current_steps": 565, "total_steps": 5000, "loss": 0.2764, "lr": 9.689323558243446e-06, "epoch": 0.226, "percentage": 11.3, "elapsed_time": "2:04:52", "remaining_time": "16:20:09", "throughput": 5982.94, "total_tokens": 44824640}
{"current_steps": 570, "total_steps": 5000, "loss": 0.2747, "lr": 9.683849745375991e-06, "epoch": 0.228, "percentage": 11.4, "elapsed_time": "2:06:01", "remaining_time": "16:19:24", "throughput": 5985.38, "total_tokens": 45255888}
{"current_steps": 575, "total_steps": 5000, "loss": 0.2908, "lr": 9.678329704802495e-06, "epoch": 0.23, "percentage": 11.5, "elapsed_time": "2:07:16", "remaining_time": "16:19:25", "throughput": 5983.86, "total_tokens": 45694304}
{"current_steps": 580, "total_steps": 5000, "loss": 0.2688, "lr": 9.672763491003531e-06, "epoch": 0.232, "percentage": 11.6, "elapsed_time": "2:08:26", "remaining_time": "16:18:50", "throughput": 5983.67, "total_tokens": 46114448}
{"current_steps": 585, "total_steps": 5000, "loss": 0.2664, "lr": 9.667151158915382e-06, "epoch": 0.234, "percentage": 11.7, "elapsed_time": "2:09:28", "remaining_time": "16:17:11", "throughput": 5984.38, "total_tokens": 46491280}
{"current_steps": 590, "total_steps": 5000, "loss": 0.2569, "lr": 9.661492763929502e-06, "epoch": 0.236, "percentage": 11.8, "elapsed_time": "2:10:46", "remaining_time": "16:17:30", "throughput": 5987.17, "total_tokens": 46979712}
{"current_steps": 595, "total_steps": 5000, "loss": 0.2726, "lr": 9.65578836189196e-06, "epoch": 0.238, "percentage": 11.9, "elapsed_time": "2:11:50", "remaining_time": "16:16:04", "throughput": 5982.15, "total_tokens": 47322192}
{"current_steps": 600, "total_steps": 5000, "loss": 0.2834, "lr": 9.650038009102905e-06, "epoch": 0.24, "percentage": 12.0, "elapsed_time": "2:12:46", "remaining_time": "16:13:38", "throughput": 5985.29, "total_tokens": 47679712}
{"current_steps": 605, "total_steps": 5000, "loss": 0.2423, "lr": 9.644241762315995e-06, "epoch": 0.242, "percentage": 12.1, "elapsed_time": "2:13:51", "remaining_time": "16:12:26", "throughput": 5984.64, "total_tokens": 48067456}
{"current_steps": 610, "total_steps": 5000, "loss": 0.2658, "lr": 9.63839967873785e-06, "epoch": 0.244, "percentage": 12.2, "elapsed_time": "2:15:02", "remaining_time": "16:11:54", "throughput": 5981.91, "total_tokens": 48471152}
{"current_steps": 615, "total_steps": 5000, "loss": 0.2777, "lr": 9.63251181602747e-06, "epoch": 0.246, "percentage": 12.3, "elapsed_time": "2:16:03", "remaining_time": "16:10:06", "throughput": 5980.45, "total_tokens": 48821504}
{"current_steps": 620, "total_steps": 5000, "loss": 0.2731, "lr": 9.626578232295689e-06, "epoch": 0.248, "percentage": 12.4, "elapsed_time": "2:17:18", "remaining_time": "16:10:00", "throughput": 5978.08, "total_tokens": 49249872}
{"current_steps": 625, "total_steps": 5000, "loss": 0.2416, "lr": 9.620598986104578e-06, "epoch": 0.25, "percentage": 12.5, "elapsed_time": "2:18:32", "remaining_time": "16:09:45", "throughput": 5981.88, "total_tokens": 49722272}
{"current_steps": 630, "total_steps": 5000, "loss": 0.2351, "lr": 9.61457413646689e-06, "epoch": 0.252, "percentage": 12.6, "elapsed_time": "2:19:45", "remaining_time": "16:09:28", "throughput": 5981.85, "total_tokens": 50162672}
{"current_steps": 635, "total_steps": 5000, "loss": 0.2645, "lr": 9.60850374284545e-06, "epoch": 0.254, "percentage": 12.7, "elapsed_time": "2:20:56", "remaining_time": "16:08:52", "throughput": 5978.77, "total_tokens": 50561280}
{"current_steps": 640, "total_steps": 5000, "loss": 0.2591, "lr": 9.602387865152597e-06, "epoch": 0.256, "percentage": 12.8, "elapsed_time": "2:22:03", "remaining_time": "16:07:46", "throughput": 5980.18, "total_tokens": 50972256}
{"current_steps": 645, "total_steps": 5000, "loss": 0.2685, "lr": 9.596226563749575e-06, "epoch": 0.258, "percentage": 12.9, "elapsed_time": "2:23:17", "remaining_time": "16:07:26", "throughput": 5978.35, "total_tokens": 51396304}
{"current_steps": 650, "total_steps": 5000, "loss": 0.2784, "lr": 9.59001989944594e-06, "epoch": 0.26, "percentage": 13.0, "elapsed_time": "2:24:28", "remaining_time": "16:06:54", "throughput": 5975.28, "total_tokens": 51798816}
{"current_steps": 655, "total_steps": 5000, "loss": 0.2514, "lr": 9.583767933498964e-06, "epoch": 0.262, "percentage": 13.1, "elapsed_time": "2:25:10", "remaining_time": "16:03:04", "throughput": 5985.52, "total_tokens": 52139568}
{"current_steps": 660, "total_steps": 5000, "loss": 0.2774, "lr": 9.577470727613025e-06, "epoch": 0.264, "percentage": 13.2, "elapsed_time": "2:26:05", "remaining_time": "16:00:40", "throughput": 5988.51, "total_tokens": 52493312}
{"current_steps": 665, "total_steps": 5000, "loss": 0.2814, "lr": 9.571128343939006e-06, "epoch": 0.266, "percentage": 13.3, "elapsed_time": "2:27:23", "remaining_time": "16:00:48", "throughput": 5977.73, "total_tokens": 52863632}
{"current_steps": 670, "total_steps": 5000, "loss": 0.261, "lr": 9.56474084507367e-06, "epoch": 0.268, "percentage": 13.4, "elapsed_time": "2:28:27", "remaining_time": "15:59:27", "throughput": 5974.15, "total_tokens": 53215856}
{"current_steps": 675, "total_steps": 5000, "loss": 0.2676, "lr": 9.558308294059055e-06, "epoch": 0.27, "percentage": 13.5, "elapsed_time": "2:29:25", "remaining_time": "15:57:23", "throughput": 5974.55, "total_tokens": 53562768}
{"current_steps": 680, "total_steps": 5000, "loss": 0.2357, "lr": 9.55183075438184e-06, "epoch": 0.272, "percentage": 13.6, "elapsed_time": "2:30:40", "remaining_time": "15:57:14", "throughput": 5976.43, "total_tokens": 54030624}
{"current_steps": 685, "total_steps": 5000, "loss": 0.2402, "lr": 9.545308289972727e-06, "epoch": 0.274, "percentage": 13.7, "elapsed_time": "2:31:26", "remaining_time": "15:53:58", "throughput": 5980.69, "total_tokens": 54343888}
{"current_steps": 690, "total_steps": 5000, "loss": 0.2372, "lr": 9.538740965205809e-06, "epoch": 0.276, "percentage": 13.8, "elapsed_time": "2:32:20", "remaining_time": "15:51:32", "throughput": 5981.18, "total_tokens": 54668576}
{"current_steps": 695, "total_steps": 5000, "loss": 0.2741, "lr": 9.532128844897928e-06, "epoch": 0.278, "percentage": 13.9, "elapsed_time": "2:33:29", "remaining_time": "15:50:43", "throughput": 5982.74, "total_tokens": 55095472}
{"current_steps": 700, "total_steps": 5000, "loss": 0.2364, "lr": 9.52547199430804e-06, "epoch": 0.28, "percentage": 14.0, "elapsed_time": "2:34:22", "remaining_time": "15:48:16", "throughput": 5982.74, "total_tokens": 55413664}
{"current_steps": 705, "total_steps": 5000, "loss": 0.2586, "lr": 9.51877047913658e-06, "epoch": 0.282, "percentage": 14.1, "elapsed_time": "2:35:20", "remaining_time": "15:46:23", "throughput": 5984.51, "total_tokens": 55779360}
{"current_steps": 710, "total_steps": 5000, "loss": 0.2655, "lr": 9.512024365524788e-06, "epoch": 0.284, "percentage": 14.2, "elapsed_time": "2:36:15", "remaining_time": "15:44:11", "throughput": 5986.65, "total_tokens": 56130272}
{"current_steps": 715, "total_steps": 5000, "loss": 0.2579, "lr": 9.505233720054086e-06, "epoch": 0.286, "percentage": 14.3, "elapsed_time": "2:37:20", "remaining_time": "15:42:58", "throughput": 5984.76, "total_tokens": 56500464}
{"current_steps": 720, "total_steps": 5000, "loss": 0.2478, "lr": 9.498398609745405e-06, "epoch": 0.288, "percentage": 14.4, "elapsed_time": "2:38:20", "remaining_time": "15:41:17", "throughput": 5983.09, "total_tokens": 56844928}
{"current_steps": 725, "total_steps": 5000, "loss": 0.2765, "lr": 9.491519102058523e-06, "epoch": 0.29, "percentage": 14.5, "elapsed_time": "2:39:33", "remaining_time": "15:40:52", "throughput": 5981.03, "total_tokens": 57261328}
{"current_steps": 730, "total_steps": 5000, "loss": 0.2419, "lr": 9.484595264891403e-06, "epoch": 0.292, "percentage": 14.6, "elapsed_time": "2:40:44", "remaining_time": "15:40:12", "throughput": 5975.88, "total_tokens": 57632624}
{"current_steps": 735, "total_steps": 5000, "loss": 0.271, "lr": 9.477627166579523e-06, "epoch": 0.294, "percentage": 14.7, "elapsed_time": "2:41:50", "remaining_time": "15:39:07", "throughput": 5975.49, "total_tokens": 58025408}
{"current_steps": 740, "total_steps": 5000, "loss": 0.2637, "lr": 9.4706148758952e-06, "epoch": 0.296, "percentage": 14.8, "elapsed_time": "2:42:57", "remaining_time": "15:38:07", "throughput": 5972.41, "total_tokens": 58396208}
{"current_steps": 745, "total_steps": 5000, "loss": 0.2727, "lr": 9.463558462046912e-06, "epoch": 0.298, "percentage": 14.9, "elapsed_time": "2:43:39", "remaining_time": "15:34:40", "throughput": 5978.91, "total_tokens": 58707376}
{"current_steps": 750, "total_steps": 5000, "loss": 0.2322, "lr": 9.456457994678616e-06, "epoch": 0.3, "percentage": 15.0, "elapsed_time": "2:44:50", "remaining_time": "15:34:05", "throughput": 5980.13, "total_tokens": 59145392}
{"current_steps": 755, "total_steps": 5000, "loss": 0.2846, "lr": 9.449313543869056e-06, "epoch": 0.302, "percentage": 15.1, "elapsed_time": "2:45:40", "remaining_time": "15:31:30", "throughput": 5980.66, "total_tokens": 59450400}
{"current_steps": 760, "total_steps": 5000, "loss": 0.2741, "lr": 9.44212518013108e-06, "epoch": 0.304, "percentage": 15.2, "elapsed_time": "2:46:53", "remaining_time": "15:31:06", "throughput": 5975.81, "total_tokens": 59840944}
{"current_steps": 765, "total_steps": 5000, "loss": 0.2604, "lr": 9.434892974410932e-06, "epoch": 0.306, "percentage": 15.3, "elapsed_time": "2:47:54", "remaining_time": "15:29:33", "throughput": 5977.0, "total_tokens": 60216688}
{"current_steps": 770, "total_steps": 5000, "loss": 0.2431, "lr": 9.427616998087568e-06, "epoch": 0.308, "percentage": 15.4, "elapsed_time": "2:49:06", "remaining_time": "15:29:02", "throughput": 5976.07, "total_tokens": 60638976}
{"current_steps": 775, "total_steps": 5000, "loss": 0.2526, "lr": 9.420297322971934e-06, "epoch": 0.31, "percentage": 15.5, "elapsed_time": "2:50:25", "remaining_time": "15:29:07", "throughput": 5978.38, "total_tokens": 61134256}
{"current_steps": 780, "total_steps": 5000, "loss": 0.2512, "lr": 9.412934021306267e-06, "epoch": 0.312, "percentage": 15.6, "elapsed_time": "2:51:26", "remaining_time": "15:27:33", "throughput": 5983.87, "total_tokens": 61553648}
{"current_steps": 785, "total_steps": 5000, "loss": 0.286, "lr": 9.405527165763384e-06, "epoch": 0.314, "percentage": 15.7, "elapsed_time": "2:52:32", "remaining_time": "15:26:28", "throughput": 5984.66, "total_tokens": 61957648}
{"current_steps": 790, "total_steps": 5000, "loss": 0.2711, "lr": 9.398076829445958e-06, "epoch": 0.316, "percentage": 15.8, "elapsed_time": "2:53:28", "remaining_time": "15:24:28", "throughput": 5984.37, "total_tokens": 62288880}
{"current_steps": 795, "total_steps": 5000, "loss": 0.2685, "lr": 9.3905830858858e-06, "epoch": 0.318, "percentage": 15.9, "elapsed_time": "2:54:27", "remaining_time": "15:22:48", "throughput": 5986.24, "total_tokens": 62663632}
{"current_steps": 800, "total_steps": 5000, "loss": 0.2693, "lr": 9.383046009043134e-06, "epoch": 0.32, "percentage": 16.0, "elapsed_time": "2:55:39", "remaining_time": "15:22:11", "throughput": 5983.06, "total_tokens": 63057792}
{"current_steps": 805, "total_steps": 5000, "loss": 0.2542, "lr": 9.37546567330587e-06, "epoch": 0.322, "percentage": 16.1, "elapsed_time": "2:56:46", "remaining_time": "15:21:11", "throughput": 5980.24, "total_tokens": 63428432}
{"current_steps": 810, "total_steps": 5000, "loss": 0.2482, "lr": 9.367842153488853e-06, "epoch": 0.324, "percentage": 16.2, "elapsed_time": "2:58:04", "remaining_time": "15:21:07", "throughput": 5974.97, "total_tokens": 63837776}
{"current_steps": 815, "total_steps": 5000, "loss": 0.2393, "lr": 9.360175524833153e-06, "epoch": 0.326, "percentage": 16.3, "elapsed_time": "2:59:06", "remaining_time": "15:19:41", "throughput": 5974.89, "total_tokens": 64207744}
{"current_steps": 820, "total_steps": 5000, "loss": 0.2464, "lr": 9.352465863005295e-06, "epoch": 0.328, "percentage": 16.4, "elapsed_time": "2:59:54", "remaining_time": "15:17:03", "throughput": 5978.03, "total_tokens": 64527552}
{"current_steps": 825, "total_steps": 5000, "loss": 0.2576, "lr": 9.344713244096533e-06, "epoch": 0.33, "percentage": 16.5, "elapsed_time": "3:01:01", "remaining_time": "15:16:06", "throughput": 5972.42, "total_tokens": 64870000}
{"current_steps": 830, "total_steps": 5000, "loss": 0.255, "lr": 9.336917744622083e-06, "epoch": 0.332, "percentage": 16.6, "elapsed_time": "3:02:09", "remaining_time": "15:15:09", "throughput": 5972.03, "total_tokens": 65269280}
{"current_steps": 835, "total_steps": 5000, "loss": 0.2511, "lr": 9.329079441520377e-06, "epoch": 0.334, "percentage": 16.7, "elapsed_time": "3:03:08", "remaining_time": "15:13:33", "throughput": 5972.17, "total_tokens": 65627792}
{"current_steps": 840, "total_steps": 5000, "loss": 0.2454, "lr": 9.321198412152303e-06, "epoch": 0.336, "percentage": 16.8, "elapsed_time": "3:04:18", "remaining_time": "15:12:45", "throughput": 5971.69, "total_tokens": 66037840}
{"current_steps": 845, "total_steps": 5000, "loss": 0.2629, "lr": 9.31327473430044e-06, "epoch": 0.338, "percentage": 16.9, "elapsed_time": "3:05:33", "remaining_time": "15:12:23", "throughput": 5966.61, "total_tokens": 66426768}
{"current_steps": 850, "total_steps": 5000, "loss": 0.2955, "lr": 9.305308486168288e-06, "epoch": 0.34, "percentage": 17.0, "elapsed_time": "3:06:31", "remaining_time": "15:10:40", "throughput": 5966.41, "total_tokens": 66772240}
{"current_steps": 855, "total_steps": 5000, "loss": 0.2835, "lr": 9.297299746379503e-06, "epoch": 0.342, "percentage": 17.1, "elapsed_time": "3:07:30", "remaining_time": "15:09:03", "throughput": 5964.99, "total_tokens": 67111024}
{"current_steps": 860, "total_steps": 5000, "loss": 0.2637, "lr": 9.28924859397711e-06, "epoch": 0.344, "percentage": 17.2, "elapsed_time": "3:08:38", "remaining_time": "15:08:07", "throughput": 5961.99, "total_tokens": 67482144}
{"current_steps": 865, "total_steps": 5000, "loss": 0.237, "lr": 9.281155108422732e-06, "epoch": 0.346, "percentage": 17.3, "elapsed_time": "3:09:42", "remaining_time": "15:06:53", "throughput": 5963.06, "total_tokens": 67876032}
{"current_steps": 870, "total_steps": 5000, "loss": 0.2797, "lr": 9.27301936959581e-06, "epoch": 0.348, "percentage": 17.4, "elapsed_time": "3:10:54", "remaining_time": "15:06:16", "throughput": 5961.13, "total_tokens": 68282368}
{"current_steps": 875, "total_steps": 5000, "loss": 0.2602, "lr": 9.264841457792795e-06, "epoch": 0.35, "percentage": 17.5, "elapsed_time": "3:12:04", "remaining_time": "15:05:30", "throughput": 5961.18, "total_tokens": 68701008}
{"current_steps": 880, "total_steps": 5000, "loss": 0.2757, "lr": 9.25662145372638e-06, "epoch": 0.352, "percentage": 17.6, "elapsed_time": "3:13:14", "remaining_time": "15:04:41", "throughput": 5963.35, "total_tokens": 69139648}
{"current_steps": 885, "total_steps": 5000, "loss": 0.2738, "lr": 9.248359438524683e-06, "epoch": 0.354, "percentage": 17.7, "elapsed_time": "3:14:29", "remaining_time": "15:04:18", "throughput": 5963.64, "total_tokens": 69591040}
{"current_steps": 890, "total_steps": 5000, "loss": 0.2693, "lr": 9.24005549373046e-06, "epoch": 0.356, "percentage": 17.8, "elapsed_time": "3:15:20", "remaining_time": "15:02:05", "throughput": 5965.52, "total_tokens": 69919248}
{"current_steps": 895, "total_steps": 5000, "loss": 0.2522, "lr": 9.231709701300293e-06, "epoch": 0.358, "percentage": 17.9, "elapsed_time": "3:16:31", "remaining_time": "15:01:23", "throughput": 5966.27, "total_tokens": 70352544}
{"current_steps": 900, "total_steps": 5000, "loss": 0.2546, "lr": 9.223322143603786e-06, "epoch": 0.36, "percentage": 18.0, "elapsed_time": "3:17:44", "remaining_time": "15:00:49", "throughput": 5962.57, "total_tokens": 70743040}
{"current_steps": 905, "total_steps": 5000, "loss": 0.2453, "lr": 9.214892903422745e-06, "epoch": 0.362, "percentage": 18.1, "elapsed_time": "3:19:02", "remaining_time": "15:00:38", "throughput": 5963.29, "total_tokens": 71217216}
{"current_steps": 910, "total_steps": 5000, "loss": 0.27, "lr": 9.206422063950368e-06, "epoch": 0.364, "percentage": 18.2, "elapsed_time": "3:20:14", "remaining_time": "15:00:00", "throughput": 5959.61, "total_tokens": 71603280}
{"current_steps": 915, "total_steps": 5000, "loss": 0.2542, "lr": 9.19790970879042e-06, "epoch": 0.366, "percentage": 18.3, "elapsed_time": "3:21:30", "remaining_time": "14:59:37", "throughput": 5959.33, "total_tokens": 72051488}
{"current_steps": 920, "total_steps": 5000, "loss": 0.2589, "lr": 9.189355921956414e-06, "epoch": 0.368, "percentage": 18.4, "elapsed_time": "3:22:48", "remaining_time": "14:59:24", "throughput": 5960.23, "total_tokens": 72527008}
{"current_steps": 925, "total_steps": 5000, "loss": 0.2867, "lr": 9.180760787870766e-06, "epoch": 0.37, "percentage": 18.5, "elapsed_time": "3:24:02", "remaining_time": "14:58:53", "throughput": 5958.56, "total_tokens": 72948304}
{"current_steps": 930, "total_steps": 5000, "loss": 0.2782, "lr": 9.172124391363986e-06, "epoch": 0.372, "percentage": 18.6, "elapsed_time": "3:24:59", "remaining_time": "14:57:08", "throughput": 5958.53, "total_tokens": 73288864}
{"current_steps": 935, "total_steps": 5000, "loss": 0.2686, "lr": 9.163446817673817e-06, "epoch": 0.374, "percentage": 18.7, "elapsed_time": "3:26:10", "remaining_time": "14:56:21", "throughput": 5960.82, "total_tokens": 73737984}
{"current_steps": 940, "total_steps": 5000, "loss": 0.2233, "lr": 9.154728152444408e-06, "epoch": 0.376, "percentage": 18.8, "elapsed_time": "3:27:23", "remaining_time": "14:55:44", "throughput": 5964.21, "total_tokens": 74213840}
{"current_steps": 945, "total_steps": 5000, "loss": 0.2441, "lr": 9.145968481725466e-06, "epoch": 0.378, "percentage": 18.9, "elapsed_time": "3:28:39", "remaining_time": "14:55:22", "throughput": 5960.73, "total_tokens": 74626672}
{"current_steps": 950, "total_steps": 5000, "loss": 0.2461, "lr": 9.137167891971407e-06, "epoch": 0.38, "percentage": 19.0, "elapsed_time": "3:29:53", "remaining_time": "14:54:47", "throughput": 5958.01, "total_tokens": 75031472}
{"current_steps": 955, "total_steps": 5000, "loss": 0.2524, "lr": 9.128326470040495e-06, "epoch": 0.382, "percentage": 19.1, "elapsed_time": "3:31:04", "remaining_time": "14:54:00", "throughput": 5955.44, "total_tokens": 75420768}
{"current_steps": 960, "total_steps": 5000, "loss": 0.2614, "lr": 9.119444303193997e-06, "epoch": 0.384, "percentage": 19.2, "elapsed_time": "3:32:07", "remaining_time": "14:52:43", "throughput": 5953.36, "total_tokens": 75773776}
{"current_steps": 965, "total_steps": 5000, "loss": 0.2407, "lr": 9.110521479095314e-06, "epoch": 0.386, "percentage": 19.3, "elapsed_time": "3:33:11", "remaining_time": "14:51:24", "throughput": 5956.95, "total_tokens": 76196496}
{"current_steps": 970, "total_steps": 5000, "loss": 0.2573, "lr": 9.101558085809114e-06, "epoch": 0.388, "percentage": 19.4, "elapsed_time": "3:34:15", "remaining_time": "14:50:10", "throughput": 5957.79, "total_tokens": 76591056}
{"current_steps": 975, "total_steps": 5000, "loss": 0.2697, "lr": 9.092554211800476e-06, "epoch": 0.39, "percentage": 19.5, "elapsed_time": "3:35:09", "remaining_time": "14:48:11", "throughput": 5961.32, "total_tokens": 76955088}
{"current_steps": 980, "total_steps": 5000, "loss": 0.2575, "lr": 9.083509945933996e-06, "epoch": 0.392, "percentage": 19.6, "elapsed_time": "3:36:24", "remaining_time": "14:47:44", "throughput": 5958.92, "total_tokens": 77376480}
{"current_steps": 985, "total_steps": 5000, "loss": 0.2609, "lr": 9.074425377472932e-06, "epoch": 0.394, "percentage": 19.7, "elapsed_time": "3:37:22", "remaining_time": "14:46:03", "throughput": 5959.27, "total_tokens": 77724816}
{"current_steps": 990, "total_steps": 5000, "loss": 0.2565, "lr": 9.065300596078304e-06, "epoch": 0.396, "percentage": 19.8, "elapsed_time": "3:38:40", "remaining_time": "14:45:46", "throughput": 5956.43, "total_tokens": 78153632}
{"current_steps": 995, "total_steps": 5000, "loss": 0.2617, "lr": 9.056135691808019e-06, "epoch": 0.398, "percentage": 19.9, "elapsed_time": "3:39:51", "remaining_time": "14:44:58", "throughput": 5956.76, "total_tokens": 78580512}
{"current_steps": 1000, "total_steps": 5000, "loss": 0.2443, "lr": 9.046930755115986e-06, "epoch": 0.4, "percentage": 20.0, "elapsed_time": "3:41:02", "remaining_time": "14:44:09", "throughput": 5957.92, "total_tokens": 79016832}
{"current_steps": 1005, "total_steps": 5000, "loss": 0.2496, "lr": 9.037685876851211e-06, "epoch": 0.402, "percentage": 20.1, "elapsed_time": "3:41:57", "remaining_time": "14:42:17", "throughput": 5957.67, "total_tokens": 79339488}
{"current_steps": 1010, "total_steps": 5000, "loss": 0.2595, "lr": 9.028401148256911e-06, "epoch": 0.404, "percentage": 20.2, "elapsed_time": "3:43:04", "remaining_time": "14:41:14", "throughput": 5957.29, "total_tokens": 79734112}
{"current_steps": 1015, "total_steps": 5000, "loss": 0.2649, "lr": 9.01907666096961e-06, "epoch": 0.406, "percentage": 20.3, "elapsed_time": "3:44:08", "remaining_time": "14:40:01", "throughput": 5956.94, "total_tokens": 80113424}
{"current_steps": 1020, "total_steps": 5000, "loss": 0.2566, "lr": 9.00971250701823e-06, "epoch": 0.408, "percentage": 20.4, "elapsed_time": "3:45:14", "remaining_time": "14:38:53", "throughput": 5955.44, "total_tokens": 80485408}
{"current_steps": 1025, "total_steps": 5000, "loss": 0.2335, "lr": 9.000308778823196e-06, "epoch": 0.41, "percentage": 20.5, "elapsed_time": "3:46:06", "remaining_time": "14:36:52", "throughput": 5956.03, "total_tokens": 80804000}
{"current_steps": 1030, "total_steps": 5000, "loss": 0.27, "lr": 8.990865569195502e-06, "epoch": 0.412, "percentage": 20.6, "elapsed_time": "3:47:19", "remaining_time": "14:36:12", "throughput": 5954.56, "total_tokens": 81218816}
{"current_steps": 1035, "total_steps": 5000, "loss": 0.2453, "lr": 8.98138297133582e-06, "epoch": 0.414, "percentage": 20.7, "elapsed_time": "3:48:26", "remaining_time": "14:35:07", "throughput": 5954.52, "total_tokens": 81613792}
{"current_steps": 1040, "total_steps": 5000, "loss": 0.2493, "lr": 8.971861078833558e-06, "epoch": 0.416, "percentage": 20.8, "elapsed_time": "3:49:44", "remaining_time": "14:34:47", "throughput": 5953.07, "total_tokens": 82060224}
{"current_steps": 1045, "total_steps": 5000, "loss": 0.2342, "lr": 8.962299985665955e-06, "epoch": 0.418, "percentage": 20.9, "elapsed_time": "3:50:49", "remaining_time": "14:33:36", "throughput": 5956.51, "total_tokens": 82494944}
{"current_steps": 1050, "total_steps": 5000, "loss": 0.2373, "lr": 8.952699786197137e-06, "epoch": 0.42, "percentage": 21.0, "elapsed_time": "3:51:54", "remaining_time": "14:32:26", "throughput": 5951.1, "total_tokens": 82808768}
{"current_steps": 1055, "total_steps": 5000, "loss": 0.243, "lr": 8.943060575177197e-06, "epoch": 0.422, "percentage": 21.1, "elapsed_time": "3:52:56", "remaining_time": "14:31:02", "throughput": 5952.64, "total_tokens": 83196256}
{"current_steps": 1060, "total_steps": 5000, "loss": 0.2866, "lr": 8.93338244774126e-06, "epoch": 0.424, "percentage": 21.2, "elapsed_time": "3:54:10", "remaining_time": "14:30:23", "throughput": 5954.54, "total_tokens": 83661872}
{"current_steps": 1065, "total_steps": 5000, "loss": 0.2466, "lr": 8.923665499408535e-06, "epoch": 0.426, "percentage": 21.3, "elapsed_time": "3:55:19", "remaining_time": "14:29:29", "throughput": 5950.11, "total_tokens": 84013360}
{"current_steps": 1070, "total_steps": 5000, "loss": 0.2593, "lr": 8.91390982608138e-06, "epoch": 0.428, "percentage": 21.4, "elapsed_time": "3:56:35", "remaining_time": "14:28:57", "throughput": 5945.53, "total_tokens": 84398000}
{"current_steps": 1075, "total_steps": 5000, "loss": 0.2553, "lr": 8.904115524044349e-06, "epoch": 0.43, "percentage": 21.5, "elapsed_time": "3:57:20", "remaining_time": "14:26:34", "throughput": 5948.68, "total_tokens": 84711792}
{"current_steps": 1080, "total_steps": 5000, "loss": 0.2611, "lr": 8.894282689963252e-06, "epoch": 0.432, "percentage": 21.6, "elapsed_time": "3:58:18", "remaining_time": "14:24:58", "throughput": 5952.86, "total_tokens": 85117264}
{"current_steps": 1085, "total_steps": 5000, "loss": 0.2605, "lr": 8.88441142088419e-06, "epoch": 0.434, "percentage": 21.7, "elapsed_time": "3:59:13", "remaining_time": "14:23:09", "throughput": 5955.59, "total_tokens": 85480624}
{"current_steps": 1090, "total_steps": 5000, "loss": 0.2476, "lr": 8.874501814232603e-06, "epoch": 0.436, "percentage": 21.8, "elapsed_time": "4:00:08", "remaining_time": "14:21:26", "throughput": 5956.91, "total_tokens": 85832000}
{"current_steps": 1095, "total_steps": 5000, "loss": 0.24, "lr": 8.86455396781231e-06, "epoch": 0.438, "percentage": 21.9, "elapsed_time": "4:01:11", "remaining_time": "14:20:06", "throughput": 5957.3, "total_tokens": 86208160}
{"current_steps": 1100, "total_steps": 5000, "loss": 0.2628, "lr": 8.854567979804538e-06, "epoch": 0.44, "percentage": 22.0, "elapsed_time": "4:02:21", "remaining_time": "14:19:17", "throughput": 5956.16, "total_tokens": 86613904}
{"current_steps": 1105, "total_steps": 5000, "loss": 0.2561, "lr": 8.844543948766958e-06, "epoch": 0.442, "percentage": 22.1, "elapsed_time": "4:03:36", "remaining_time": "14:18:40", "throughput": 5953.07, "total_tokens": 87012032}
{"current_steps": 1110, "total_steps": 5000, "loss": 0.2612, "lr": 8.834481973632709e-06, "epoch": 0.444, "percentage": 22.2, "elapsed_time": "4:04:37", "remaining_time": "14:17:17", "throughput": 5954.5, "total_tokens": 87397408}
{"current_steps": 1115, "total_steps": 5000, "loss": 0.2647, "lr": 8.824382153709423e-06, "epoch": 0.446, "percentage": 22.3, "elapsed_time": "4:05:50", "remaining_time": "14:16:35", "throughput": 5949.76, "total_tokens": 87762928}
{"current_steps": 1120, "total_steps": 5000, "loss": 0.242, "lr": 8.814244588678245e-06, "epoch": 0.448, "percentage": 22.4, "elapsed_time": "4:06:47", "remaining_time": "14:14:57", "throughput": 5951.16, "total_tokens": 88121120}
{"current_steps": 1125, "total_steps": 5000, "loss": 0.2395, "lr": 8.80406937859285e-06, "epoch": 0.45, "percentage": 22.5, "elapsed_time": "4:07:50", "remaining_time": "14:13:42", "throughput": 5952.86, "total_tokens": 88525008}
{"current_steps": 1130, "total_steps": 5000, "loss": 0.2401, "lr": 8.793856623878453e-06, "epoch": 0.452, "percentage": 22.6, "elapsed_time": "4:09:05", "remaining_time": "14:13:04", "throughput": 5952.22, "total_tokens": 88958160}
{"current_steps": 1135, "total_steps": 5000, "loss": 0.2585, "lr": 8.78360642533082e-06, "epoch": 0.454, "percentage": 22.7, "elapsed_time": "4:09:50", "remaining_time": "14:10:47", "throughput": 5953.89, "total_tokens": 89252000}
{"current_steps": 1140, "total_steps": 5000, "loss": 0.2189, "lr": 8.773318884115273e-06, "epoch": 0.456, "percentage": 22.8, "elapsed_time": "4:10:58", "remaining_time": "14:09:47", "throughput": 5951.98, "total_tokens": 89628016}
{"current_steps": 1145, "total_steps": 5000, "loss": 0.2649, "lr": 8.76299410176569e-06, "epoch": 0.458, "percentage": 22.9, "elapsed_time": "4:12:02", "remaining_time": "14:08:34", "throughput": 5953.66, "total_tokens": 90034128}
{"current_steps": 1150, "total_steps": 5000, "loss": 0.2562, "lr": 8.752632180183504e-06, "epoch": 0.46, "percentage": 23.0, "elapsed_time": "4:12:58", "remaining_time": "14:06:55", "throughput": 5953.5, "total_tokens": 90366512}
{"current_steps": 1155, "total_steps": 5000, "loss": 0.2366, "lr": 8.7422332216367e-06, "epoch": 0.462, "percentage": 23.1, "elapsed_time": "4:14:11", "remaining_time": "14:06:11", "throughput": 5949.63, "total_tokens": 90739280}
{"current_steps": 1160, "total_steps": 5000, "loss": 0.2465, "lr": 8.7317973287588e-06, "epoch": 0.464, "percentage": 23.2, "elapsed_time": "4:15:26", "remaining_time": "14:05:37", "throughput": 5944.52, "total_tokens": 91111104}
{"current_steps": 1165, "total_steps": 5000, "loss": 0.2689, "lr": 8.721324604547851e-06, "epoch": 0.466, "percentage": 23.3, "elapsed_time": "4:16:44", "remaining_time": "14:05:10", "throughput": 5941.37, "total_tokens": 91526176}
{"current_steps": 1170, "total_steps": 5000, "loss": 0.2943, "lr": 8.710815152365416e-06, "epoch": 0.468, "percentage": 23.4, "elapsed_time": "4:17:58", "remaining_time": "14:04:30", "throughput": 5937.38, "total_tokens": 91904368}
{"current_steps": 1175, "total_steps": 5000, "loss": 0.2485, "lr": 8.700269075935542e-06, "epoch": 0.47, "percentage": 23.5, "elapsed_time": "4:19:16", "remaining_time": "14:04:01", "throughput": 5936.99, "total_tokens": 92358160}
{"current_steps": 1180, "total_steps": 5000, "loss": 0.2464, "lr": 8.689686479343747e-06, "epoch": 0.472, "percentage": 23.6, "elapsed_time": "4:20:32", "remaining_time": "14:03:27", "throughput": 5937.72, "total_tokens": 92821904}
{"current_steps": 1185, "total_steps": 5000, "loss": 0.2504, "lr": 8.679067467035989e-06, "epoch": 0.474, "percentage": 23.7, "elapsed_time": "4:21:37", "remaining_time": "14:02:16", "throughput": 5936.46, "total_tokens": 93187600}
{"current_steps": 1190, "total_steps": 5000, "loss": 0.2568, "lr": 8.66841214381763e-06, "epoch": 0.476, "percentage": 23.8, "elapsed_time": "4:22:21", "remaining_time": "14:00:00", "throughput": 5938.81, "total_tokens": 93487696}
{"current_steps": 1195, "total_steps": 5000, "loss": 0.2278, "lr": 8.657720614852412e-06, "epoch": 0.478, "percentage": 23.9, "elapsed_time": "4:23:26", "remaining_time": "13:58:50", "throughput": 5938.96, "total_tokens": 93876672}
{"current_steps": 1200, "total_steps": 5000, "loss": 0.2417, "lr": 8.646992985661404e-06, "epoch": 0.48, "percentage": 24.0, "elapsed_time": "4:24:31", "remaining_time": "13:57:38", "throughput": 5937.68, "total_tokens": 94238000}
{"current_steps": 1205, "total_steps": 5000, "loss": 0.2496, "lr": 8.636229362121979e-06, "epoch": 0.482, "percentage": 24.1, "elapsed_time": "4:25:31", "remaining_time": "13:56:14", "throughput": 5935.82, "total_tokens": 94567520}
{"current_steps": 1210, "total_steps": 5000, "loss": 0.2244, "lr": 8.625429850466756e-06, "epoch": 0.484, "percentage": 24.2, "elapsed_time": "4:26:30", "remaining_time": "13:54:44", "throughput": 5934.52, "total_tokens": 94893184}
{"current_steps": 1215, "total_steps": 5000, "loss": 0.2397, "lr": 8.614594557282553e-06, "epoch": 0.486, "percentage": 24.3, "elapsed_time": "4:27:35", "remaining_time": "13:53:36", "throughput": 5934.15, "total_tokens": 95276080}
{"current_steps": 1220, "total_steps": 5000, "loss": 0.2477, "lr": 8.603723589509342e-06, "epoch": 0.488, "percentage": 24.4, "elapsed_time": "4:28:44", "remaining_time": "13:52:40", "throughput": 5936.36, "total_tokens": 95722112}
{"current_steps": 1225, "total_steps": 5000, "loss": 0.2625, "lr": 8.592817054439184e-06, "epoch": 0.49, "percentage": 24.5, "elapsed_time": "4:29:56", "remaining_time": "13:51:50", "throughput": 5936.03, "total_tokens": 96141024}
{"current_steps": 1230, "total_steps": 5000, "loss": 0.2503, "lr": 8.581875059715177e-06, "epoch": 0.492, "percentage": 24.6, "elapsed_time": "4:31:02", "remaining_time": "13:50:44", "throughput": 5939.39, "total_tokens": 96587392}
{"current_steps": 1235, "total_steps": 5000, "loss": 0.2599, "lr": 8.570897713330392e-06, "epoch": 0.494, "percentage": 24.7, "elapsed_time": "4:32:16", "remaining_time": "13:50:02", "throughput": 5939.09, "total_tokens": 97023264}
{"current_steps": 1240, "total_steps": 5000, "loss": 0.2513, "lr": 8.559885123626806e-06, "epoch": 0.496, "percentage": 24.8, "elapsed_time": "4:33:17", "remaining_time": "13:48:42", "throughput": 5941.67, "total_tokens": 97430560}
{"current_steps": 1245, "total_steps": 5000, "loss": 0.2637, "lr": 8.548837399294235e-06, "epoch": 0.498, "percentage": 24.9, "elapsed_time": "4:34:15", "remaining_time": "13:47:09", "throughput": 5945.14, "total_tokens": 97827472}
{"current_steps": 1250, "total_steps": 5000, "loss": 0.2419, "lr": 8.537754649369256e-06, "epoch": 0.5, "percentage": 25.0, "elapsed_time": "4:35:32", "remaining_time": "13:46:38", "throughput": 5941.42, "total_tokens": 98229376}
{"current_steps": 1255, "total_steps": 5000, "loss": 0.2418, "lr": 8.526636983234135e-06, "epoch": 0.502, "percentage": 25.1, "elapsed_time": "4:36:26", "remaining_time": "13:44:54", "throughput": 5944.66, "total_tokens": 98599872}
{"current_steps": 1260, "total_steps": 5000, "loss": 0.2554, "lr": 8.515484510615753e-06, "epoch": 0.504, "percentage": 25.2, "elapsed_time": "4:37:33", "remaining_time": "13:43:51", "throughput": 5946.35, "total_tokens": 99026864}
{"current_steps": 1265, "total_steps": 5000, "loss": 0.2658, "lr": 8.504297341584509e-06, "epoch": 0.506, "percentage": 25.3, "elapsed_time": "4:38:42", "remaining_time": "13:42:53", "throughput": 5943.94, "total_tokens": 99395904}
{"current_steps": 1270, "total_steps": 5000, "loss": 0.2281, "lr": 8.493075586553245e-06, "epoch": 0.508, "percentage": 25.4, "elapsed_time": "4:39:47", "remaining_time": "13:41:45", "throughput": 5946.32, "total_tokens": 99825616}
{"current_steps": 1275, "total_steps": 5000, "loss": 0.2434, "lr": 8.481819356276155e-06, "epoch": 0.51, "percentage": 25.5, "elapsed_time": "4:40:55", "remaining_time": "13:40:45", "throughput": 5945.75, "total_tokens": 100220256}
{"current_steps": 1280, "total_steps": 5000, "loss": 0.2503, "lr": 8.470528761847684e-06, "epoch": 0.512, "percentage": 25.6, "elapsed_time": "4:42:06", "remaining_time": "13:39:52", "throughput": 5944.6, "total_tokens": 100620576}
{"current_steps": 1285, "total_steps": 5000, "loss": 0.2738, "lr": 8.459203914701444e-06, "epoch": 0.514, "percentage": 25.7, "elapsed_time": "4:43:06", "remaining_time": "13:38:28", "throughput": 5947.08, "total_tokens": 101019904}
{"current_steps": 1290, "total_steps": 5000, "loss": 0.2742, "lr": 8.447844926609103e-06, "epoch": 0.516, "percentage": 25.8, "elapsed_time": "4:44:24", "remaining_time": "13:37:57", "throughput": 5946.58, "total_tokens": 101476336}
{"current_steps": 1295, "total_steps": 5000, "loss": 0.2436, "lr": 8.436451909679286e-06, "epoch": 0.518, "percentage": 25.9, "elapsed_time": "4:45:21", "remaining_time": "13:36:25", "throughput": 5948.0, "total_tokens": 101840464}
{"current_steps": 1300, "total_steps": 5000, "loss": 0.2449, "lr": 8.425024976356474e-06, "epoch": 0.52, "percentage": 26.0, "elapsed_time": "4:46:26", "remaining_time": "13:35:14", "throughput": 5947.52, "total_tokens": 102215776}
{"current_steps": 1305, "total_steps": 5000, "loss": 0.2516, "lr": 8.413564239419883e-06, "epoch": 0.522, "percentage": 26.1, "elapsed_time": "4:47:40", "remaining_time": "13:34:32", "throughput": 5945.3, "total_tokens": 102620256}
{"current_steps": 1310, "total_steps": 5000, "loss": 0.2496, "lr": 8.40206981198236e-06, "epoch": 0.524, "percentage": 26.2, "elapsed_time": "4:48:35", "remaining_time": "13:32:54", "throughput": 5947.31, "total_tokens": 102981744}
{"current_steps": 1315, "total_steps": 5000, "loss": 0.2612, "lr": 8.390541807489266e-06, "epoch": 0.526, "percentage": 26.3, "elapsed_time": "4:49:54", "remaining_time": "13:32:22", "throughput": 5945.77, "total_tokens": 103420880}
{"current_steps": 1320, "total_steps": 5000, "loss": 0.2544, "lr": 8.378980339717348e-06, "epoch": 0.528, "percentage": 26.4, "elapsed_time": "4:51:09", "remaining_time": "13:31:42", "throughput": 5946.5, "total_tokens": 103881808}
{"current_steps": 1325, "total_steps": 5000, "loss": 0.2626, "lr": 8.367385522773625e-06, "epoch": 0.53, "percentage": 26.5, "elapsed_time": "4:52:05", "remaining_time": "13:30:07", "throughput": 5948.62, "total_tokens": 104250576}
{"current_steps": 1330, "total_steps": 5000, "loss": 0.2524, "lr": 8.355757471094263e-06, "epoch": 0.532, "percentage": 26.6, "elapsed_time": "4:53:06", "remaining_time": "13:28:48", "throughput": 5947.27, "total_tokens": 104591808}
{"current_steps": 1335, "total_steps": 5000, "loss": 0.2493, "lr": 8.344096299443434e-06, "epoch": 0.534, "percentage": 26.7, "elapsed_time": "4:54:11", "remaining_time": "13:27:39", "throughput": 5948.45, "total_tokens": 104999392}
{"current_steps": 1340, "total_steps": 5000, "loss": 0.2369, "lr": 8.332402122912198e-06, "epoch": 0.536, "percentage": 26.8, "elapsed_time": "4:55:14", "remaining_time": "13:26:23", "throughput": 5947.78, "total_tokens": 105360928}
{"current_steps": 1345, "total_steps": 5000, "loss": 0.2566, "lr": 8.320675056917353e-06, "epoch": 0.538, "percentage": 26.9, "elapsed_time": "4:56:18", "remaining_time": "13:25:12", "throughput": 5947.8, "total_tokens": 105742624}
{"current_steps": 1350, "total_steps": 5000, "loss": 0.2643, "lr": 8.308915217200305e-06, "epoch": 0.54, "percentage": 27.0, "elapsed_time": "4:57:17", "remaining_time": "13:23:46", "throughput": 5949.41, "total_tokens": 106120016}
{"current_steps": 1355, "total_steps": 5000, "loss": 0.2274, "lr": 8.297122719825928e-06, "epoch": 0.542, "percentage": 27.1, "elapsed_time": "4:58:31", "remaining_time": "13:23:01", "throughput": 5945.97, "total_tokens": 106498992}
{"current_steps": 1360, "total_steps": 5000, "loss": 0.233, "lr": 8.285297681181408e-06, "epoch": 0.544, "percentage": 27.2, "elapsed_time": "4:59:33", "remaining_time": "13:21:46", "throughput": 5947.87, "total_tokens": 106906656}
{"current_steps": 1365, "total_steps": 5000, "loss": 0.2527, "lr": 8.273440217975103e-06, "epoch": 0.546, "percentage": 27.3, "elapsed_time": "5:00:23", "remaining_time": "13:19:57", "throughput": 5948.31, "total_tokens": 107212272}
{"current_steps": 1370, "total_steps": 5000, "loss": 0.2356, "lr": 8.261550447235389e-06, "epoch": 0.548, "percentage": 27.4, "elapsed_time": "5:01:20", "remaining_time": "13:18:26", "throughput": 5949.32, "total_tokens": 107567200}
{"current_steps": 1375, "total_steps": 5000, "loss": 0.2204, "lr": 8.2496284863095e-06, "epoch": 0.55, "percentage": 27.5, "elapsed_time": "5:02:31", "remaining_time": "13:17:33", "throughput": 5950.11, "total_tokens": 108001632}
{"current_steps": 1380, "total_steps": 5000, "loss": 0.2518, "lr": 8.23767445286238e-06, "epoch": 0.552, "percentage": 27.6, "elapsed_time": "5:03:36", "remaining_time": "13:16:26", "throughput": 5950.49, "total_tokens": 108400032}
{"current_steps": 1385, "total_steps": 5000, "loss": 0.254, "lr": 8.225688464875514e-06, "epoch": 0.554, "percentage": 27.7, "elapsed_time": "5:04:54", "remaining_time": "13:15:51", "throughput": 5946.65, "total_tokens": 108793600}
{"current_steps": 1390, "total_steps": 5000, "loss": 0.2616, "lr": 8.213670640645762e-06, "epoch": 0.556, "percentage": 27.8, "elapsed_time": "5:06:01", "remaining_time": "13:14:47", "throughput": 5949.37, "total_tokens": 109239856}
{"current_steps": 1395, "total_steps": 5000, "loss": 0.2497, "lr": 8.201621098784198e-06, "epoch": 0.558, "percentage": 27.9, "elapsed_time": "5:07:03", "remaining_time": "13:13:31", "throughput": 5948.05, "total_tokens": 109586848}
{"current_steps": 1400, "total_steps": 5000, "loss": 0.2422, "lr": 8.189539958214934e-06, "epoch": 0.56, "percentage": 28.0, "elapsed_time": "5:08:06", "remaining_time": "13:12:15", "throughput": 5950.68, "total_tokens": 110004576}
{"current_steps": 1405, "total_steps": 5000, "loss": 0.2511, "lr": 8.177427338173955e-06, "epoch": 0.562, "percentage": 28.1, "elapsed_time": "5:09:16", "remaining_time": "13:11:22", "throughput": 5950.63, "total_tokens": 110425520}
{"current_steps": 1410, "total_steps": 5000, "loss": 0.2545, "lr": 8.165283358207924e-06, "epoch": 0.564, "percentage": 28.2, "elapsed_time": "5:10:17", "remaining_time": "13:10:01", "throughput": 5951.35, "total_tokens": 110798416}
{"current_steps": 1415, "total_steps": 5000, "loss": 0.243, "lr": 8.153108138173027e-06, "epoch": 0.566, "percentage": 28.3, "elapsed_time": "5:11:33", "remaining_time": "13:09:22", "throughput": 5949.59, "total_tokens": 111221456}
{"current_steps": 1420, "total_steps": 5000, "loss": 0.2481, "lr": 8.140901798233766e-06, "epoch": 0.568, "percentage": 28.4, "elapsed_time": "5:12:41", "remaining_time": "13:08:20", "throughput": 5947.48, "total_tokens": 111584784}
{"current_steps": 1425, "total_steps": 5000, "loss": 0.2444, "lr": 8.12866445886179e-06, "epoch": 0.57, "percentage": 28.5, "elapsed_time": "5:13:46", "remaining_time": "13:07:10", "throughput": 5945.06, "total_tokens": 111922640}
{"current_steps": 1430, "total_steps": 5000, "loss": 0.2414, "lr": 8.116396240834699e-06, "epoch": 0.572, "percentage": 28.6, "elapsed_time": "5:14:55", "remaining_time": "13:06:13", "throughput": 5942.49, "total_tokens": 112287760}
{"current_steps": 1435, "total_steps": 5000, "loss": 0.2424, "lr": 8.10409726523485e-06, "epoch": 0.574, "percentage": 28.7, "elapsed_time": "5:15:47", "remaining_time": "13:04:31", "throughput": 5946.02, "total_tokens": 112661728}
{"current_steps": 1440, "total_steps": 5000, "loss": 0.2563, "lr": 8.091767653448169e-06, "epoch": 0.576, "percentage": 28.8, "elapsed_time": "5:16:53", "remaining_time": "13:03:24", "throughput": 5946.68, "total_tokens": 113064880}
{"current_steps": 1445, "total_steps": 5000, "loss": 0.2386, "lr": 8.079407527162944e-06, "epoch": 0.578, "percentage": 28.9, "elapsed_time": "5:18:00", "remaining_time": "13:02:22", "throughput": 5946.56, "total_tokens": 113464160}
{"current_steps": 1450, "total_steps": 5000, "loss": 0.2558, "lr": 8.067017008368632e-06, "epoch": 0.58, "percentage": 29.0, "elapsed_time": "5:19:05", "remaining_time": "13:01:12", "throughput": 5947.64, "total_tokens": 113867952}
{"current_steps": 1455, "total_steps": 5000, "loss": 0.2554, "lr": 8.054596219354655e-06, "epoch": 0.582, "percentage": 29.1, "elapsed_time": "5:20:22", "remaining_time": "13:00:34", "throughput": 5944.73, "total_tokens": 114273424}
{"current_steps": 1460, "total_steps": 5000, "loss": 0.2601, "lr": 8.042145282709181e-06, "epoch": 0.584, "percentage": 29.2, "elapsed_time": "5:21:29", "remaining_time": "12:59:29", "throughput": 5947.2, "total_tokens": 114717424}
{"current_steps": 1465, "total_steps": 5000, "loss": 0.2601, "lr": 8.029664321317932e-06, "epoch": 0.586, "percentage": 29.3, "elapsed_time": "5:22:34", "remaining_time": "12:58:21", "throughput": 5948.84, "total_tokens": 115135984}
{"current_steps": 1470, "total_steps": 5000, "loss": 0.2652, "lr": 8.017153458362957e-06, "epoch": 0.588, "percentage": 29.4, "elapsed_time": "5:23:34", "remaining_time": "12:57:01", "throughput": 5951.48, "total_tokens": 115545440}
{"current_steps": 1475, "total_steps": 5000, "loss": 0.2579, "lr": 8.004612817321419e-06, "epoch": 0.59, "percentage": 29.5, "elapsed_time": "5:24:41", "remaining_time": "12:55:58", "throughput": 5951.37, "total_tokens": 115943440}
{"current_steps": 1480, "total_steps": 5000, "loss": 0.2586, "lr": 7.99204252196439e-06, "epoch": 0.592, "percentage": 29.6, "elapsed_time": "5:25:50", "remaining_time": "12:54:59", "throughput": 5951.97, "total_tokens": 116366400}
{"current_steps": 1485, "total_steps": 5000, "loss": 0.2324, "lr": 7.979442696355601e-06, "epoch": 0.594, "percentage": 29.7, "elapsed_time": "5:26:59", "remaining_time": "12:53:59", "throughput": 5949.99, "total_tokens": 116736672}
{"current_steps": 1490, "total_steps": 5000, "loss": 0.2577, "lr": 7.966813464850252e-06, "epoch": 0.596, "percentage": 29.8, "elapsed_time": "5:27:59", "remaining_time": "12:52:38", "throughput": 5951.26, "total_tokens": 117116064}
{"current_steps": 1495, "total_steps": 5000, "loss": 0.2366, "lr": 7.954154952093754e-06, "epoch": 0.598, "percentage": 29.9, "elapsed_time": "5:29:14", "remaining_time": "12:51:54", "throughput": 5951.28, "total_tokens": 117565696}
{"current_steps": 1500, "total_steps": 5000, "loss": 0.2458, "lr": 7.941467283020521e-06, "epoch": 0.6, "percentage": 30.0, "elapsed_time": "5:30:25", "remaining_time": "12:51:00", "throughput": 5950.88, "total_tokens": 117980528}
{"current_steps": 1505, "total_steps": 5000, "loss": 0.2354, "lr": 7.928750582852722e-06, "epoch": 0.602, "percentage": 30.1, "elapsed_time": "5:31:34", "remaining_time": "12:49:59", "throughput": 5951.03, "total_tokens": 118392000}
{"current_steps": 1510, "total_steps": 5000, "loss": 0.2437, "lr": 7.916004977099054e-06, "epoch": 0.604, "percentage": 30.2, "elapsed_time": "5:32:39", "remaining_time": "12:48:51", "throughput": 5950.71, "total_tokens": 118773680}
{"current_steps": 1515, "total_steps": 5000, "loss": 0.2312, "lr": 7.903230591553504e-06, "epoch": 0.606, "percentage": 30.3, "elapsed_time": "5:33:31", "remaining_time": "12:47:12", "throughput": 5952.37, "total_tokens": 119115104}
{"current_steps": 1520, "total_steps": 5000, "loss": 0.2591, "lr": 7.890427552294093e-06, "epoch": 0.608, "percentage": 30.4, "elapsed_time": "5:34:34", "remaining_time": "12:46:01", "throughput": 5950.72, "total_tokens": 119460384}
{"current_steps": 1525, "total_steps": 5000, "loss": 0.2653, "lr": 7.877595985681656e-06, "epoch": 0.61, "percentage": 30.5, "elapsed_time": "5:35:41", "remaining_time": "12:44:56", "throughput": 5950.76, "total_tokens": 119858560}
{"current_steps": 1530, "total_steps": 5000, "loss": 0.2344, "lr": 7.864736018358571e-06, "epoch": 0.612, "percentage": 30.6, "elapsed_time": "5:36:51", "remaining_time": "12:43:58", "throughput": 5952.03, "total_tokens": 120298352}
{"current_steps": 1535, "total_steps": 5000, "loss": 0.2657, "lr": 7.851847777247528e-06, "epoch": 0.614, "percentage": 30.7, "elapsed_time": "5:38:09", "remaining_time": "12:43:20", "throughput": 5950.59, "total_tokens": 120735536}
{"current_steps": 1540, "total_steps": 5000, "loss": 0.2744, "lr": 7.83893138955026e-06, "epoch": 0.616, "percentage": 30.8, "elapsed_time": "5:39:14", "remaining_time": "12:42:11", "throughput": 5950.15, "total_tokens": 121111328}
{"current_steps": 1545, "total_steps": 5000, "loss": 0.2471, "lr": 7.8259869827463e-06, "epoch": 0.618, "percentage": 30.9, "elapsed_time": "5:40:14", "remaining_time": "12:40:52", "throughput": 5951.81, "total_tokens": 121505792}
{"current_steps": 1550, "total_steps": 5000, "loss": 0.2406, "lr": 7.813014684591718e-06, "epoch": 0.62, "percentage": 31.0, "elapsed_time": "5:41:32", "remaining_time": "12:40:12", "throughput": 5947.91, "total_tokens": 121888000}
{"current_steps": 1555, "total_steps": 5000, "loss": 0.2424, "lr": 7.800014623117858e-06, "epoch": 0.622, "percentage": 31.1, "elapsed_time": "5:42:46", "remaining_time": "12:39:23", "throughput": 5946.71, "total_tokens": 122302912}
{"current_steps": 1560, "total_steps": 5000, "loss": 0.2585, "lr": 7.786986926630079e-06, "epoch": 0.624, "percentage": 31.2, "elapsed_time": "5:43:38", "remaining_time": "12:37:45", "throughput": 5950.0, "total_tokens": 122677712}
{"current_steps": 1565, "total_steps": 5000, "loss": 0.2532, "lr": 7.773931723706487e-06, "epoch": 0.626, "percentage": 31.3, "elapsed_time": "5:44:38", "remaining_time": "12:36:27", "throughput": 5950.72, "total_tokens": 123054656}
{"current_steps": 1570, "total_steps": 5000, "loss": 0.2555, "lr": 7.760849143196664e-06, "epoch": 0.628, "percentage": 31.4, "elapsed_time": "5:45:56", "remaining_time": "12:35:46", "throughput": 5948.78, "total_tokens": 123475648}
{"current_steps": 1575, "total_steps": 5000, "loss": 0.2416, "lr": 7.747739314220398e-06, "epoch": 0.63, "percentage": 31.5, "elapsed_time": "5:47:11", "remaining_time": "12:35:01", "throughput": 5948.7, "total_tokens": 123922816}
{"current_steps": 1580, "total_steps": 5000, "loss": 0.2552, "lr": 7.734602366166406e-06, "epoch": 0.632, "percentage": 31.6, "elapsed_time": "5:48:08", "remaining_time": "12:33:34", "throughput": 5949.5, "total_tokens": 124277408}
{"current_steps": 1585, "total_steps": 5000, "loss": 0.2438, "lr": 7.721438428691065e-06, "epoch": 0.634, "percentage": 31.7, "elapsed_time": "5:49:22", "remaining_time": "12:32:44", "throughput": 5948.21, "total_tokens": 124687888}
{"current_steps": 1590, "total_steps": 5000, "loss": 0.2349, "lr": 7.708247631717122e-06, "epoch": 0.636, "percentage": 31.8, "elapsed_time": "5:50:19", "remaining_time": "12:31:19", "throughput": 5948.5, "total_tokens": 125035328}
{"current_steps": 1595, "total_steps": 5000, "loss": 0.2621, "lr": 7.695030105432417e-06, "epoch": 0.638, "percentage": 31.9, "elapsed_time": "5:51:16", "remaining_time": "12:29:53", "throughput": 5949.82, "total_tokens": 125398688}
{"current_steps": 1600, "total_steps": 5000, "loss": 0.2424, "lr": 7.681785980288601e-06, "epoch": 0.64, "percentage": 32.0, "elapsed_time": "5:52:18", "remaining_time": "12:28:39", "throughput": 5950.9, "total_tokens": 125792304}
{"current_steps": 1605, "total_steps": 5000, "loss": 0.2416, "lr": 7.668515386999837e-06, "epoch": 0.642, "percentage": 32.1, "elapsed_time": "5:53:33", "remaining_time": "12:27:52", "throughput": 5950.94, "total_tokens": 126242176}
{"current_steps": 1610, "total_steps": 5000, "loss": 0.2298, "lr": 7.65521845654153e-06, "epoch": 0.644, "percentage": 32.2, "elapsed_time": "5:54:49", "remaining_time": "12:27:06", "throughput": 5947.6, "total_tokens": 126620048}
{"current_steps": 1615, "total_steps": 5000, "loss": 0.2582, "lr": 7.641895320149008e-06, "epoch": 0.646, "percentage": 32.3, "elapsed_time": "5:55:53", "remaining_time": "12:25:56", "throughput": 5948.71, "total_tokens": 127024944}
{"current_steps": 1620, "total_steps": 5000, "loss": 0.2617, "lr": 7.628546109316257e-06, "epoch": 0.648, "percentage": 32.4, "elapsed_time": "5:57:07", "remaining_time": "12:25:06", "throughput": 5948.22, "total_tokens": 127455024}
{"current_steps": 1625, "total_steps": 5000, "loss": 0.2782, "lr": 7.615170955794592e-06, "epoch": 0.65, "percentage": 32.5, "elapsed_time": "5:58:24", "remaining_time": "12:24:22", "throughput": 5944.61, "total_tokens": 127834640}
{"current_steps": 1630, "total_steps": 5000, "loss": 0.25, "lr": 7.60176999159138e-06, "epoch": 0.652, "percentage": 32.6, "elapsed_time": "5:59:19", "remaining_time": "12:22:53", "throughput": 5945.88, "total_tokens": 128188304}
{"current_steps": 1635, "total_steps": 5000, "loss": 0.2343, "lr": 7.588343348968728e-06, "epoch": 0.654, "percentage": 32.7, "elapsed_time": "6:00:37", "remaining_time": "12:22:12", "throughput": 5944.45, "total_tokens": 128624560}
{"current_steps": 1640, "total_steps": 5000, "loss": 0.2391, "lr": 7.574891160442179e-06, "epoch": 0.656, "percentage": 32.8, "elapsed_time": "6:01:36", "remaining_time": "12:20:50", "throughput": 5944.85, "total_tokens": 128979536}
{"current_steps": 1645, "total_steps": 5000, "loss": 0.2453, "lr": 7.561413558779401e-06, "epoch": 0.658, "percentage": 32.9, "elapsed_time": "6:02:53", "remaining_time": "12:20:07", "throughput": 5942.83, "total_tokens": 129395280}
{"current_steps": 1650, "total_steps": 5000, "loss": 0.2445, "lr": 7.547910676998883e-06, "epoch": 0.66, "percentage": 33.0, "elapsed_time": "6:03:59", "remaining_time": "12:19:01", "throughput": 5942.81, "total_tokens": 129790480}
{"current_steps": 1655, "total_steps": 5000, "loss": 0.2519, "lr": 7.534382648368617e-06, "epoch": 0.662, "percentage": 33.1, "elapsed_time": "6:05:01", "remaining_time": "12:17:46", "throughput": 5943.82, "total_tokens": 130179568}
{"current_steps": 1660, "total_steps": 5000, "loss": 0.2464, "lr": 7.520829606404781e-06, "epoch": 0.664, "percentage": 33.2, "elapsed_time": "6:05:56", "remaining_time": "12:16:17", "throughput": 5945.77, "total_tokens": 130546960}
{"current_steps": 1665, "total_steps": 5000, "loss": 0.2613, "lr": 7.507251684870433e-06, "epoch": 0.666, "percentage": 33.3, "elapsed_time": "6:07:07", "remaining_time": "12:15:21", "throughput": 5947.15, "total_tokens": 131000944}
{"current_steps": 1670, "total_steps": 5000, "loss": 0.2391, "lr": 7.493649017774172e-06, "epoch": 0.668, "percentage": 33.4, "elapsed_time": "6:08:12", "remaining_time": "12:14:11", "throughput": 5948.21, "total_tokens": 131408096}
{"current_steps": 1675, "total_steps": 5000, "loss": 0.238, "lr": 7.480021739368831e-06, "epoch": 0.67, "percentage": 33.5, "elapsed_time": "6:09:25", "remaining_time": "12:13:19", "throughput": 5948.2, "total_tokens": 131842384}
{"current_steps": 1680, "total_steps": 5000, "loss": 0.2482, "lr": 7.46636998415015e-06, "epoch": 0.672, "percentage": 33.6, "elapsed_time": "6:10:41", "remaining_time": "12:12:32", "throughput": 5947.3, "total_tokens": 132275008}
{"current_steps": 1685, "total_steps": 5000, "loss": 0.2456, "lr": 7.452693886855438e-06, "epoch": 0.674, "percentage": 33.7, "elapsed_time": "6:11:22", "remaining_time": "12:10:37", "throughput": 5949.25, "total_tokens": 132563520}
{"current_steps": 1690, "total_steps": 5000, "loss": 0.2424, "lr": 7.438993582462255e-06, "epoch": 0.676, "percentage": 33.8, "elapsed_time": "6:12:32", "remaining_time": "12:09:39", "throughput": 5949.97, "total_tokens": 132997392}
{"current_steps": 1695, "total_steps": 5000, "loss": 0.2544, "lr": 7.425269206187076e-06, "epoch": 0.678, "percentage": 33.9, "elapsed_time": "6:13:50", "remaining_time": "12:08:56", "throughput": 5948.38, "total_tokens": 133426496}
{"current_steps": 1700, "total_steps": 5000, "loss": 0.2391, "lr": 7.411520893483952e-06, "epoch": 0.68, "percentage": 34.0, "elapsed_time": "6:15:09", "remaining_time": "12:08:14", "throughput": 5947.35, "total_tokens": 133870544}
{"current_steps": 1705, "total_steps": 5000, "loss": 0.2578, "lr": 7.397748780043179e-06, "epoch": 0.682, "percentage": 34.1, "elapsed_time": "6:16:13", "remaining_time": "12:07:05", "throughput": 5949.23, "total_tokens": 134297232}
{"current_steps": 1710, "total_steps": 5000, "loss": 0.2515, "lr": 7.38395300178996e-06, "epoch": 0.684, "percentage": 34.2, "elapsed_time": "6:17:24", "remaining_time": "12:06:07", "throughput": 5946.87, "total_tokens": 134663632}
{"current_steps": 1715, "total_steps": 5000, "loss": 0.2333, "lr": 7.370133694883052e-06, "epoch": 0.686, "percentage": 34.3, "elapsed_time": "6:18:25", "remaining_time": "12:04:51", "throughput": 5947.81, "total_tokens": 135047920}
{"current_steps": 1720, "total_steps": 5000, "loss": 0.2569, "lr": 7.356290995713436e-06, "epoch": 0.688, "percentage": 34.4, "elapsed_time": "6:19:43", "remaining_time": "12:04:08", "throughput": 5948.64, "total_tokens": 135533312}
{"current_steps": 1725, "total_steps": 5000, "loss": 0.2587, "lr": 7.342425040902967e-06, "epoch": 0.69, "percentage": 34.5, "elapsed_time": "6:20:51", "remaining_time": "12:03:04", "throughput": 5948.24, "total_tokens": 135924224}
{"current_steps": 1730, "total_steps": 5000, "loss": 0.2396, "lr": 7.32853596730302e-06, "epoch": 0.692, "percentage": 34.6, "elapsed_time": "6:21:58", "remaining_time": "12:01:59", "throughput": 5945.84, "total_tokens": 136269040}
{"current_steps": 1735, "total_steps": 5000, "loss": 0.2483, "lr": 7.314623911993143e-06, "epoch": 0.694, "percentage": 34.7, "elapsed_time": "6:22:58", "remaining_time": "12:00:41", "throughput": 5946.48, "total_tokens": 136639296}
{"current_steps": 1740, "total_steps": 5000, "loss": 0.2255, "lr": 7.300689012279706e-06, "epoch": 0.696, "percentage": 34.8, "elapsed_time": "6:24:07", "remaining_time": "11:59:41", "throughput": 5946.37, "total_tokens": 137049552}
{"current_steps": 1745, "total_steps": 5000, "loss": 0.2147, "lr": 7.286731405694544e-06, "epoch": 0.698, "percentage": 34.9, "elapsed_time": "6:25:10", "remaining_time": "11:58:27", "throughput": 5947.29, "total_tokens": 137441952}
{"current_steps": 1750, "total_steps": 5000, "loss": 0.2395, "lr": 7.272751229993598e-06, "epoch": 0.7, "percentage": 35.0, "elapsed_time": "6:26:12", "remaining_time": "11:57:14", "throughput": 5948.72, "total_tokens": 137846304}
{"current_steps": 1755, "total_steps": 5000, "loss": 0.2618, "lr": 7.258748623155558e-06, "epoch": 0.702, "percentage": 35.1, "elapsed_time": "6:27:11", "remaining_time": "11:55:55", "throughput": 5949.7, "total_tokens": 138221600}
{"current_steps": 1760, "total_steps": 5000, "loss": 0.2495, "lr": 7.244723723380504e-06, "epoch": 0.704, "percentage": 35.2, "elapsed_time": "6:28:05", "remaining_time": "11:54:27", "throughput": 5949.99, "total_tokens": 138551408}
{"current_steps": 1765, "total_steps": 5000, "loss": 0.2567, "lr": 7.23067666908853e-06, "epoch": 0.706, "percentage": 35.3, "elapsed_time": "6:29:15", "remaining_time": "11:53:28", "throughput": 5949.74, "total_tokens": 138961472}
{"current_steps": 1770, "total_steps": 5000, "loss": 0.2481, "lr": 7.216607598918392e-06, "epoch": 0.708, "percentage": 35.4, "elapsed_time": "6:30:23", "remaining_time": "11:52:24", "throughput": 5949.5, "total_tokens": 139357456}
{"current_steps": 1775, "total_steps": 5000, "loss": 0.2582, "lr": 7.202516651726135e-06, "epoch": 0.71, "percentage": 35.5, "elapsed_time": "6:31:35", "remaining_time": "11:51:29", "throughput": 5948.91, "total_tokens": 139772704}
{"current_steps": 1780, "total_steps": 5000, "loss": 0.2319, "lr": 7.1884039665837165e-06, "epoch": 0.712, "percentage": 35.6, "elapsed_time": "6:32:46", "remaining_time": "11:50:31", "throughput": 5948.12, "total_tokens": 140175600}
{"current_steps": 1785, "total_steps": 5000, "loss": 0.2401, "lr": 7.1742696827776415e-06, "epoch": 0.714, "percentage": 35.7, "elapsed_time": "6:33:57", "remaining_time": "11:49:34", "throughput": 5947.28, "total_tokens": 140581648}
{"current_steps": 1790, "total_steps": 5000, "loss": 0.239, "lr": 7.160113939807587e-06, "epoch": 0.716, "percentage": 35.8, "elapsed_time": "6:35:04", "remaining_time": "11:48:29", "throughput": 5946.85, "total_tokens": 140968624}
{"current_steps": 1795, "total_steps": 5000, "loss": 0.2254, "lr": 7.145936877385019e-06, "epoch": 0.718, "percentage": 35.9, "elapsed_time": "6:36:20", "remaining_time": "11:47:40", "throughput": 5948.45, "total_tokens": 141456880}
{"current_steps": 1800, "total_steps": 5000, "loss": 0.2468, "lr": 7.131738635431822e-06, "epoch": 0.72, "percentage": 36.0, "elapsed_time": "6:37:11", "remaining_time": "11:46:07", "throughput": 5948.3, "total_tokens": 141757984}
{"current_steps": 1805, "total_steps": 5000, "loss": 0.2488, "lr": 7.11751935407891e-06, "epoch": 0.722, "percentage": 36.1, "elapsed_time": "6:38:14", "remaining_time": "11:44:55", "throughput": 5951.92, "total_tokens": 142217936}
{"current_steps": 1810, "total_steps": 5000, "loss": 0.2444, "lr": 7.103279173664851e-06, "epoch": 0.724, "percentage": 36.2, "elapsed_time": "6:39:27", "remaining_time": "11:44:01", "throughput": 5951.13, "total_tokens": 142634320}
{"current_steps": 1815, "total_steps": 5000, "loss": 0.2165, "lr": 7.089018234734476e-06, "epoch": 0.726, "percentage": 36.3, "elapsed_time": "6:40:25", "remaining_time": "11:42:41", "throughput": 5949.84, "total_tokens": 142950304}
{"current_steps": 1820, "total_steps": 5000, "loss": 0.2464, "lr": 7.074736678037495e-06, "epoch": 0.728, "percentage": 36.4, "elapsed_time": "6:41:43", "remaining_time": "11:41:55", "throughput": 5947.01, "total_tokens": 143344704}
{"current_steps": 1825, "total_steps": 5000, "loss": 0.2115, "lr": 7.060434644527105e-06, "epoch": 0.73, "percentage": 36.5, "elapsed_time": "6:42:57", "remaining_time": "11:41:02", "throughput": 5945.31, "total_tokens": 143742144}
{"current_steps": 1830, "total_steps": 5000, "loss": 0.234, "lr": 7.046112275358607e-06, "epoch": 0.732, "percentage": 36.6, "elapsed_time": "6:43:47", "remaining_time": "11:39:28", "throughput": 5946.76, "total_tokens": 144077152}
{"current_steps": 1835, "total_steps": 5000, "loss": 0.2143, "lr": 7.031769711887999e-06, "epoch": 0.734, "percentage": 36.7, "elapsed_time": "6:44:52", "remaining_time": "11:38:20", "throughput": 5947.6, "total_tokens": 144484576}
{"current_steps": 1840, "total_steps": 5000, "loss": 0.2273, "lr": 7.017407095670594e-06, "epoch": 0.736, "percentage": 36.8, "elapsed_time": "6:45:49", "remaining_time": "11:36:58", "throughput": 5948.79, "total_tokens": 144852640}
{"current_steps": 1845, "total_steps": 5000, "loss": 0.2441, "lr": 7.003024568459614e-06, "epoch": 0.738, "percentage": 36.9, "elapsed_time": "6:46:40", "remaining_time": "11:35:24", "throughput": 5950.09, "total_tokens": 145182656}
{"current_steps": 1850, "total_steps": 5000, "loss": 0.2422, "lr": 6.988622272204799e-06, "epoch": 0.74, "percentage": 37.0, "elapsed_time": "6:47:55", "remaining_time": "11:34:34", "throughput": 5949.64, "total_tokens": 145621648}
{"current_steps": 1855, "total_steps": 5000, "loss": 0.235, "lr": 6.974200349050996e-06, "epoch": 0.742, "percentage": 37.1, "elapsed_time": "6:49:01", "remaining_time": "11:33:28", "throughput": 5949.56, "total_tokens": 146013264}
{"current_steps": 1860, "total_steps": 5000, "loss": 0.2716, "lr": 6.959758941336762e-06, "epoch": 0.744, "percentage": 37.2, "elapsed_time": "6:50:01", "remaining_time": "11:32:12", "throughput": 5949.34, "total_tokens": 146365616}
{"current_steps": 1865, "total_steps": 5000, "loss": 0.2341, "lr": 6.945298191592967e-06, "epoch": 0.746, "percentage": 37.3, "elapsed_time": "6:51:07", "remaining_time": "11:31:06", "throughput": 5949.18, "total_tokens": 146754320}
{"current_steps": 1870, "total_steps": 5000, "loss": 0.2514, "lr": 6.930818242541368e-06, "epoch": 0.748, "percentage": 37.4, "elapsed_time": "6:52:07", "remaining_time": "11:29:49", "throughput": 5951.64, "total_tokens": 147171456}
{"current_steps": 1875, "total_steps": 5000, "loss": 0.2189, "lr": 6.916319237093219e-06, "epoch": 0.75, "percentage": 37.5, "elapsed_time": "6:53:26", "remaining_time": "11:29:04", "throughput": 5951.87, "total_tokens": 147646320}
{"current_steps": 1880, "total_steps": 5000, "loss": 0.2585, "lr": 6.901801318347848e-06, "epoch": 0.752, "percentage": 37.6, "elapsed_time": "6:54:24", "remaining_time": "11:27:45", "throughput": 5951.17, "total_tokens": 147975568}
{"current_steps": 1885, "total_steps": 5000, "loss": 0.2672, "lr": 6.887264629591254e-06, "epoch": 0.754, "percentage": 37.7, "elapsed_time": "6:55:34", "remaining_time": "11:26:45", "throughput": 5951.52, "total_tokens": 148400576}
{"current_steps": 1890, "total_steps": 5000, "loss": 0.2799, "lr": 6.872709314294685e-06, "epoch": 0.756, "percentage": 37.8, "elapsed_time": "6:56:42", "remaining_time": "11:25:42", "throughput": 5950.61, "total_tokens": 148783072}
{"current_steps": 1895, "total_steps": 5000, "loss": 0.2466, "lr": 6.858135516113226e-06, "epoch": 0.758, "percentage": 37.9, "elapsed_time": "6:57:45", "remaining_time": "11:24:30", "throughput": 5949.64, "total_tokens": 149130848}
{"current_steps": 1900, "total_steps": 5000, "loss": 0.2659, "lr": 6.8435433788843865e-06, "epoch": 0.76, "percentage": 38.0, "elapsed_time": "6:58:56", "remaining_time": "11:23:31", "throughput": 5950.12, "total_tokens": 149563296}
{"current_steps": 1905, "total_steps": 5000, "loss": 0.2309, "lr": 6.8289330466266635e-06, "epoch": 0.762, "percentage": 38.1, "elapsed_time": "6:59:54", "remaining_time": "11:22:12", "throughput": 5950.36, "total_tokens": 149916624}
{"current_steps": 1910, "total_steps": 5000, "loss": 0.2335, "lr": 6.814304663538142e-06, "epoch": 0.764, "percentage": 38.2, "elapsed_time": "7:01:01", "remaining_time": "11:21:08", "throughput": 5949.15, "total_tokens": 150286112}
{"current_steps": 1915, "total_steps": 5000, "loss": 0.2577, "lr": 6.799658373995054e-06, "epoch": 0.766, "percentage": 38.3, "elapsed_time": "7:02:07", "remaining_time": "11:20:01", "throughput": 5947.97, "total_tokens": 150645008}
{"current_steps": 1920, "total_steps": 5000, "loss": 0.2399, "lr": 6.784994322550367e-06, "epoch": 0.768, "percentage": 38.4, "elapsed_time": "7:03:17", "remaining_time": "11:19:01", "throughput": 5947.85, "total_tokens": 151060512}
{"current_steps": 1925, "total_steps": 5000, "loss": 0.2615, "lr": 6.770312653932346e-06, "epoch": 0.77, "percentage": 38.5, "elapsed_time": "7:04:09", "remaining_time": "11:17:33", "throughput": 5947.74, "total_tokens": 151368336}
{"current_steps": 1930, "total_steps": 5000, "loss": 0.2686, "lr": 6.755613513043136e-06, "epoch": 0.772, "percentage": 38.6, "elapsed_time": "7:05:20", "remaining_time": "11:16:35", "throughput": 5945.92, "total_tokens": 151745056}
{"current_steps": 1935, "total_steps": 5000, "loss": 0.2523, "lr": 6.740897044957322e-06, "epoch": 0.774, "percentage": 38.7, "elapsed_time": "7:06:30", "remaining_time": "11:15:34", "throughput": 5949.77, "total_tokens": 152255616}
{"current_steps": 1940, "total_steps": 5000, "loss": 0.2364, "lr": 6.726163394920503e-06, "epoch": 0.776, "percentage": 38.8, "elapsed_time": "7:07:40", "remaining_time": "11:14:35", "throughput": 5949.36, "total_tokens": 152666400}
{"current_steps": 1945, "total_steps": 5000, "loss": 0.2455, "lr": 6.711412708347857e-06, "epoch": 0.778, "percentage": 38.9, "elapsed_time": "7:08:40", "remaining_time": "11:13:19", "throughput": 5949.88, "total_tokens": 153036000}
{"current_steps": 1950, "total_steps": 5000, "loss": 0.2646, "lr": 6.696645130822704e-06, "epoch": 0.78, "percentage": 39.0, "elapsed_time": "7:09:35", "remaining_time": "11:11:56", "throughput": 5950.61, "total_tokens": 153381872}
{"current_steps": 1955, "total_steps": 5000, "loss": 0.2373, "lr": 6.681860808095074e-06, "epoch": 0.782, "percentage": 39.1, "elapsed_time": "7:10:43", "remaining_time": "11:10:52", "throughput": 5951.12, "total_tokens": 153796576}
{"current_steps": 1960, "total_steps": 5000, "loss": 0.2367, "lr": 6.667059886080263e-06, "epoch": 0.784, "percentage": 39.2, "elapsed_time": "7:11:42", "remaining_time": "11:09:35", "throughput": 5952.44, "total_tokens": 154185392}
{"current_steps": 1965, "total_steps": 5000, "loss": 0.2566, "lr": 6.652242510857395e-06, "epoch": 0.786, "percentage": 39.3, "elapsed_time": "7:12:36", "remaining_time": "11:08:10", "throughput": 5954.14, "total_tokens": 154549680}
{"current_steps": 1970, "total_steps": 5000, "loss": 0.2559, "lr": 6.637408828667982e-06, "epoch": 0.788, "percentage": 39.4, "elapsed_time": "7:13:45", "remaining_time": "11:07:08", "throughput": 5954.74, "total_tokens": 154973808}
{"current_steps": 1975, "total_steps": 5000, "loss": 0.2273, "lr": 6.622558985914478e-06, "epoch": 0.79, "percentage": 39.5, "elapsed_time": "7:14:55", "remaining_time": "11:06:09", "throughput": 5953.68, "total_tokens": 155365328}
{"current_steps": 1980, "total_steps": 5000, "loss": 0.2382, "lr": 6.6076931291588375e-06, "epoch": 0.792, "percentage": 39.6, "elapsed_time": "7:15:56", "remaining_time": "11:04:55", "throughput": 5953.04, "total_tokens": 155713088}
{"current_steps": 1985, "total_steps": 5000, "loss": 0.2294, "lr": 6.592811405121064e-06, "epoch": 0.794, "percentage": 39.7, "elapsed_time": "7:17:04", "remaining_time": "11:03:52", "throughput": 5952.63, "total_tokens": 156104880}
{"current_steps": 1990, "total_steps": 5000, "loss": 0.2317, "lr": 6.577913960677766e-06, "epoch": 0.796, "percentage": 39.8, "elapsed_time": "7:18:00", "remaining_time": "11:02:30", "throughput": 5953.99, "total_tokens": 156474112}
{"current_steps": 1995, "total_steps": 5000, "loss": 0.2452, "lr": 6.5630009428607065e-06, "epoch": 0.798, "percentage": 39.9, "elapsed_time": "7:18:58", "remaining_time": "11:01:12", "throughput": 5953.48, "total_tokens": 156803472}
{"current_steps": 2000, "total_steps": 5000, "loss": 0.2334, "lr": 6.54807249885535e-06, "epoch": 0.8, "percentage": 40.0, "elapsed_time": "7:19:43", "remaining_time": "10:59:34", "throughput": 5954.94, "total_tokens": 157110992}
{"current_steps": 2005, "total_steps": 5000, "loss": 0.2265, "lr": 6.533128775999411e-06, "epoch": 0.802, "percentage": 40.1, "elapsed_time": "7:20:54", "remaining_time": "10:58:37", "throughput": 5953.58, "total_tokens": 157500272}
{"current_steps": 2010, "total_steps": 5000, "loss": 0.2163, "lr": 6.5181699217814025e-06, "epoch": 0.804, "percentage": 40.2, "elapsed_time": "7:22:02", "remaining_time": "10:57:33", "throughput": 5950.97, "total_tokens": 157834992}
{"current_steps": 2015, "total_steps": 5000, "loss": 0.2625, "lr": 6.503196083839175e-06, "epoch": 0.806, "percentage": 40.3, "elapsed_time": "7:23:07", "remaining_time": "10:56:26", "throughput": 5951.02, "total_tokens": 158224720}
{"current_steps": 2020, "total_steps": 5000, "loss": 0.2608, "lr": 6.488207409958466e-06, "epoch": 0.808, "percentage": 40.4, "elapsed_time": "7:24:02", "remaining_time": "10:55:03", "throughput": 5952.7, "total_tokens": 158592160}
{"current_steps": 2025, "total_steps": 5000, "loss": 0.253, "lr": 6.473204048071433e-06, "epoch": 0.81, "percentage": 40.5, "elapsed_time": "7:24:58", "remaining_time": "10:53:43", "throughput": 5953.77, "total_tokens": 158955232}
{"current_steps": 2030, "total_steps": 5000, "loss": 0.2568, "lr": 6.458186146255203e-06, "epoch": 0.812, "percentage": 40.6, "elapsed_time": "7:25:54", "remaining_time": "10:52:23", "throughput": 5953.21, "total_tokens": 159277888}
{"current_steps": 2035, "total_steps": 5000, "loss": 0.229, "lr": 6.443153852730404e-06, "epoch": 0.814, "percentage": 40.7, "elapsed_time": "7:26:58", "remaining_time": "10:51:14", "throughput": 5954.92, "total_tokens": 159700576}
{"current_steps": 2040, "total_steps": 5000, "loss": 0.2511, "lr": 6.428107315859702e-06, "epoch": 0.816, "percentage": 40.8, "elapsed_time": "7:28:00", "remaining_time": "10:50:02", "throughput": 5953.04, "total_tokens": 160017808}
{"current_steps": 2045, "total_steps": 5000, "loss": 0.2343, "lr": 6.413046684146343e-06, "epoch": 0.818, "percentage": 40.9, "elapsed_time": "7:29:10", "remaining_time": "10:49:02", "throughput": 5950.72, "total_tokens": 160373024}
{"current_steps": 2050, "total_steps": 5000, "loss": 0.2231, "lr": 6.3979721062326815e-06, "epoch": 0.82, "percentage": 41.0, "elapsed_time": "7:30:19", "remaining_time": "10:48:01", "throughput": 5950.45, "total_tokens": 160775872}
{"current_steps": 2055, "total_steps": 5000, "loss": 0.2134, "lr": 6.382883730898717e-06, "epoch": 0.822, "percentage": 41.1, "elapsed_time": "7:31:31", "remaining_time": "10:47:04", "throughput": 5950.59, "total_tokens": 161209616}
{"current_steps": 2060, "total_steps": 5000, "loss": 0.2574, "lr": 6.36778170706062e-06, "epoch": 0.824, "percentage": 41.2, "elapsed_time": "7:32:19", "remaining_time": "10:45:33", "throughput": 5951.68, "total_tokens": 161526656}
{"current_steps": 2065, "total_steps": 5000, "loss": 0.2264, "lr": 6.352666183769269e-06, "epoch": 0.826, "percentage": 41.3, "elapsed_time": "7:33:34", "remaining_time": "10:44:40", "throughput": 5952.69, "total_tokens": 162002192}
{"current_steps": 2070, "total_steps": 5000, "loss": 0.2579, "lr": 6.337537310208779e-06, "epoch": 0.828, "percentage": 41.4, "elapsed_time": "7:34:44", "remaining_time": "10:43:39", "throughput": 5951.09, "total_tokens": 162370528}
{"current_steps": 2075, "total_steps": 5000, "loss": 0.2442, "lr": 6.322395235695022e-06, "epoch": 0.83, "percentage": 41.5, "elapsed_time": "7:35:50", "remaining_time": "10:42:34", "throughput": 5950.3, "total_tokens": 162742848}
{"current_steps": 2080, "total_steps": 5000, "loss": 0.2468, "lr": 6.307240109674162e-06, "epoch": 0.832, "percentage": 41.6, "elapsed_time": "7:36:42", "remaining_time": "10:41:08", "throughput": 5952.56, "total_tokens": 163114144}
{"current_steps": 2085, "total_steps": 5000, "loss": 0.2531, "lr": 6.292072081721173e-06, "epoch": 0.834, "percentage": 41.7, "elapsed_time": "7:37:46", "remaining_time": "10:40:00", "throughput": 5952.83, "total_tokens": 163504080}
{"current_steps": 2090, "total_steps": 5000, "loss": 0.2476, "lr": 6.2768913015383696e-06, "epoch": 0.836, "percentage": 41.8, "elapsed_time": "7:39:03", "remaining_time": "10:39:09", "throughput": 5953.3, "total_tokens": 163972864}
{"current_steps": 2095, "total_steps": 5000, "loss": 0.2503, "lr": 6.261697918953922e-06, "epoch": 0.838, "percentage": 41.9, "elapsed_time": "7:40:08", "remaining_time": "10:38:03", "throughput": 5954.39, "total_tokens": 164394080}
{"current_steps": 2100, "total_steps": 5000, "loss": 0.2337, "lr": 6.2464920839203805e-06, "epoch": 0.84, "percentage": 42.0, "elapsed_time": "7:41:15", "remaining_time": "10:36:59", "throughput": 5954.74, "total_tokens": 164803104}
{"current_steps": 2105, "total_steps": 5000, "loss": 0.2475, "lr": 6.231273946513201e-06, "epoch": 0.842, "percentage": 42.1, "elapsed_time": "7:42:22", "remaining_time": "10:35:54", "throughput": 5953.45, "total_tokens": 165165728}
{"current_steps": 2110, "total_steps": 5000, "loss": 0.226, "lr": 6.216043656929254e-06, "epoch": 0.844, "percentage": 42.2, "elapsed_time": "7:43:36", "remaining_time": "10:34:58", "throughput": 5951.71, "total_tokens": 165552752}
{"current_steps": 2115, "total_steps": 5000, "loss": 0.239, "lr": 6.2008013654853505e-06, "epoch": 0.846, "percentage": 42.3, "elapsed_time": "7:44:36", "remaining_time": "10:33:45", "throughput": 5953.07, "total_tokens": 165952016}
{"current_steps": 2120, "total_steps": 5000, "loss": 0.2259, "lr": 6.1855472226167525e-06, "epoch": 0.848, "percentage": 42.4, "elapsed_time": "7:45:52", "remaining_time": "10:32:53", "throughput": 5953.08, "total_tokens": 166406208}
{"current_steps": 2125, "total_steps": 5000, "loss": 0.2217, "lr": 6.170281378875692e-06, "epoch": 0.85, "percentage": 42.5, "elapsed_time": "7:47:06", "remaining_time": "10:31:58", "throughput": 5951.21, "total_tokens": 166793568}
{"current_steps": 2130, "total_steps": 5000, "loss": 0.2205, "lr": 6.155003984929883e-06, "epoch": 0.852, "percentage": 42.6, "elapsed_time": "7:48:03", "remaining_time": "10:30:39", "throughput": 5950.54, "total_tokens": 167110880}
{"current_steps": 2135, "total_steps": 5000, "loss": 0.2505, "lr": 6.139715191561038e-06, "epoch": 0.854, "percentage": 42.7, "elapsed_time": "7:49:11", "remaining_time": "10:29:36", "throughput": 5951.07, "total_tokens": 167529632}
{"current_steps": 2140, "total_steps": 5000, "loss": 0.2498, "lr": 6.124415149663374e-06, "epoch": 0.856, "percentage": 42.8, "elapsed_time": "7:50:12", "remaining_time": "10:28:24", "throughput": 5951.28, "total_tokens": 167902176}
{"current_steps": 2145, "total_steps": 5000, "loss": 0.2226, "lr": 6.109104010242127e-06, "epoch": 0.858, "percentage": 42.9, "elapsed_time": "7:51:12", "remaining_time": "10:27:10", "throughput": 5952.1, "total_tokens": 168281184}
{"current_steps": 2150, "total_steps": 5000, "loss": 0.223, "lr": 6.093781924412063e-06, "epoch": 0.86, "percentage": 43.0, "elapsed_time": "7:52:16", "remaining_time": "10:26:01", "throughput": 5951.72, "total_tokens": 168648480}
{"current_steps": 2155, "total_steps": 5000, "loss": 0.2435, "lr": 6.078449043395982e-06, "epoch": 0.862, "percentage": 43.1, "elapsed_time": "7:53:22", "remaining_time": "10:24:56", "throughput": 5950.79, "total_tokens": 169014928}
{"current_steps": 2160, "total_steps": 5000, "loss": 0.2333, "lr": 6.06310551852323e-06, "epoch": 0.864, "percentage": 43.2, "elapsed_time": "7:54:25", "remaining_time": "10:23:46", "throughput": 5950.9, "total_tokens": 169395632}
{"current_steps": 2165, "total_steps": 5000, "loss": 0.2464, "lr": 6.047751501228203e-06, "epoch": 0.866, "percentage": 43.3, "elapsed_time": "7:55:43", "remaining_time": "10:22:56", "throughput": 5949.21, "total_tokens": 169811824}
{"current_steps": 2170, "total_steps": 5000, "loss": 0.231, "lr": 6.032387143048853e-06, "epoch": 0.868, "percentage": 43.4, "elapsed_time": "7:56:42", "remaining_time": "10:21:41", "throughput": 5948.88, "total_tokens": 170151744}
{"current_steps": 2175, "total_steps": 5000, "loss": 0.2206, "lr": 6.0170125956251935e-06, "epoch": 0.87, "percentage": 43.5, "elapsed_time": "7:57:48", "remaining_time": "10:20:36", "throughput": 5948.43, "total_tokens": 170534368}
{"current_steps": 2180, "total_steps": 5000, "loss": 0.2541, "lr": 6.0016280106978e-06, "epoch": 0.872, "percentage": 43.6, "elapsed_time": "7:58:59", "remaining_time": "10:19:36", "throughput": 5947.9, "total_tokens": 170939264}
{"current_steps": 2185, "total_steps": 5000, "loss": 0.2198, "lr": 5.986233540106315e-06, "epoch": 0.874, "percentage": 43.7, "elapsed_time": "8:00:10", "remaining_time": "10:18:37", "throughput": 5946.71, "total_tokens": 171327728}
{"current_steps": 2190, "total_steps": 5000, "loss": 0.2446, "lr": 5.970829335787946e-06, "epoch": 0.876, "percentage": 43.8, "elapsed_time": "8:01:07", "remaining_time": "10:17:19", "throughput": 5947.33, "total_tokens": 171683792}
{"current_steps": 2195, "total_steps": 5000, "loss": 0.2166, "lr": 5.955415549775975e-06, "epoch": 0.878, "percentage": 43.9, "elapsed_time": "8:01:57", "remaining_time": "10:15:54", "throughput": 5947.2, "total_tokens": 171980720}
{"current_steps": 2200, "total_steps": 5000, "loss": 0.2486, "lr": 5.939992334198242e-06, "epoch": 0.88, "percentage": 44.0, "elapsed_time": "8:03:15", "remaining_time": "10:15:03", "throughput": 5945.92, "total_tokens": 172406304}
{"current_steps": 2205, "total_steps": 5000, "loss": 0.2502, "lr": 5.924559841275661e-06, "epoch": 0.882, "percentage": 44.1, "elapsed_time": "8:04:18", "remaining_time": "10:13:53", "throughput": 5946.12, "total_tokens": 172786272}
{"current_steps": 2210, "total_steps": 5000, "loss": 0.2422, "lr": 5.9091182233207075e-06, "epoch": 0.884, "percentage": 44.2, "elapsed_time": "8:05:31", "remaining_time": "10:12:56", "throughput": 5946.38, "total_tokens": 173227264}
{"current_steps": 2215, "total_steps": 5000, "loss": 0.2352, "lr": 5.893667632735915e-06, "epoch": 0.886, "percentage": 44.3, "elapsed_time": "8:06:42", "remaining_time": "10:11:56", "throughput": 5944.71, "total_tokens": 173598624}
{"current_steps": 2220, "total_steps": 5000, "loss": 0.2289, "lr": 5.878208222012377e-06, "epoch": 0.888, "percentage": 44.4, "elapsed_time": "8:07:40", "remaining_time": "10:10:42", "throughput": 5946.41, "total_tokens": 173997648}
{"current_steps": 2225, "total_steps": 5000, "loss": 0.2277, "lr": 5.8627401437282334e-06, "epoch": 0.89, "percentage": 44.5, "elapsed_time": "8:08:58", "remaining_time": "10:09:51", "throughput": 5945.71, "total_tokens": 174440288}
{"current_steps": 2230, "total_steps": 5000, "loss": 0.2295, "lr": 5.847263550547174e-06, "epoch": 0.892, "percentage": 44.6, "elapsed_time": "8:10:04", "remaining_time": "10:08:45", "throughput": 5946.19, "total_tokens": 174846016}
{"current_steps": 2235, "total_steps": 5000, "loss": 0.2405, "lr": 5.8317785952169245e-06, "epoch": 0.894, "percentage": 44.7, "elapsed_time": "8:11:05", "remaining_time": "10:07:32", "throughput": 5945.83, "total_tokens": 175197376}
{"current_steps": 2240, "total_steps": 5000, "loss": 0.2464, "lr": 5.816285430567743e-06, "epoch": 0.896, "percentage": 44.8, "elapsed_time": "8:11:52", "remaining_time": "10:06:03", "throughput": 5948.14, "total_tokens": 175543776}
{"current_steps": 2245, "total_steps": 5000, "loss": 0.2315, "lr": 5.80078420951091e-06, "epoch": 0.898, "percentage": 44.9, "elapsed_time": "8:13:05", "remaining_time": "10:05:06", "throughput": 5947.55, "total_tokens": 175959728}
{"current_steps": 2250, "total_steps": 5000, "loss": 0.2683, "lr": 5.785275085037218e-06, "epoch": 0.9, "percentage": 45.0, "elapsed_time": "8:14:01", "remaining_time": "10:03:48", "throughput": 5947.64, "total_tokens": 176298768}
{"current_steps": 2255, "total_steps": 5000, "loss": 0.2277, "lr": 5.769758210215466e-06, "epoch": 0.902, "percentage": 45.1, "elapsed_time": "8:15:16", "remaining_time": "10:02:53", "throughput": 5948.16, "total_tokens": 176757936}
{"current_steps": 2260, "total_steps": 5000, "loss": 0.2306, "lr": 5.754233738190942e-06, "epoch": 0.904, "percentage": 45.2, "elapsed_time": "8:16:19", "remaining_time": "10:01:43", "throughput": 5948.91, "total_tokens": 177153168}
{"current_steps": 2265, "total_steps": 5000, "loss": 0.2447, "lr": 5.7387018221839195e-06, "epoch": 0.906, "percentage": 45.3, "elapsed_time": "8:17:27", "remaining_time": "10:00:40", "throughput": 5948.91, "total_tokens": 177558336}
{"current_steps": 2270, "total_steps": 5000, "loss": 0.2224, "lr": 5.723162615488137e-06, "epoch": 0.908, "percentage": 45.4, "elapsed_time": "8:18:35", "remaining_time": "9:59:37", "throughput": 5949.15, "total_tokens": 177970112}
{"current_steps": 2275, "total_steps": 5000, "loss": 0.2213, "lr": 5.707616271469293e-06, "epoch": 0.91, "percentage": 45.5, "elapsed_time": "8:19:47", "remaining_time": "9:58:38", "throughput": 5948.02, "total_tokens": 178365456}
{"current_steps": 2280, "total_steps": 5000, "loss": 0.2283, "lr": 5.692062943563525e-06, "epoch": 0.912, "percentage": 45.6, "elapsed_time": "8:21:00", "remaining_time": "9:57:42", "throughput": 5946.08, "total_tokens": 178744496}
{"current_steps": 2285, "total_steps": 5000, "loss": 0.2273, "lr": 5.6765027852759015e-06, "epoch": 0.914, "percentage": 45.7, "elapsed_time": "8:21:56", "remaining_time": "9:56:23", "throughput": 5946.57, "total_tokens": 179089216}
{"current_steps": 2290, "total_steps": 5000, "loss": 0.2114, "lr": 5.660935950178904e-06, "epoch": 0.916, "percentage": 45.8, "elapsed_time": "8:23:05", "remaining_time": "9:55:22", "throughput": 5945.27, "total_tokens": 179463584}
{"current_steps": 2295, "total_steps": 5000, "loss": 0.2317, "lr": 5.645362591910908e-06, "epoch": 0.918, "percentage": 45.9, "elapsed_time": "8:24:04", "remaining_time": "9:54:07", "throughput": 5945.97, "total_tokens": 179834016}
{"current_steps": 2300, "total_steps": 5000, "loss": 0.2542, "lr": 5.629782864174672e-06, "epoch": 0.92, "percentage": 46.0, "elapsed_time": "8:25:14", "remaining_time": "9:53:06", "throughput": 5946.4, "total_tokens": 180259712}
{"current_steps": 2305, "total_steps": 5000, "loss": 0.253, "lr": 5.614196920735822e-06, "epoch": 0.922, "percentage": 46.1, "elapsed_time": "8:26:30", "remaining_time": "9:52:12", "throughput": 5948.22, "total_tokens": 180769440}
{"current_steps": 2310, "total_steps": 5000, "loss": 0.2404, "lr": 5.598604915421324e-06, "epoch": 0.924, "percentage": 46.2, "elapsed_time": "8:27:26", "remaining_time": "9:50:55", "throughput": 5949.4, "total_tokens": 181141040}
{"current_steps": 2315, "total_steps": 5000, "loss": 0.2475, "lr": 5.5830070021179785e-06, "epoch": 0.926, "percentage": 46.3, "elapsed_time": "8:28:31", "remaining_time": "9:49:48", "throughput": 5948.9, "total_tokens": 181512128}
{"current_steps": 2320, "total_steps": 5000, "loss": 0.241, "lr": 5.567403334770891e-06, "epoch": 0.928, "percentage": 46.4, "elapsed_time": "8:29:35", "remaining_time": "9:48:40", "throughput": 5949.15, "total_tokens": 181898720}
{"current_steps": 2325, "total_steps": 5000, "loss": 0.2296, "lr": 5.551794067381959e-06, "epoch": 0.93, "percentage": 46.5, "elapsed_time": "8:30:53", "remaining_time": "9:47:47", "throughput": 5948.49, "total_tokens": 182339792}
{"current_steps": 2330, "total_steps": 5000, "loss": 0.2179, "lr": 5.536179354008351e-06, "epoch": 0.932, "percentage": 46.6, "elapsed_time": "8:32:06", "remaining_time": "9:46:50", "throughput": 5947.88, "total_tokens": 182758928}
{"current_steps": 2335, "total_steps": 5000, "loss": 0.2383, "lr": 5.520559348760984e-06, "epoch": 0.934, "percentage": 46.7, "elapsed_time": "8:33:16", "remaining_time": "9:45:49", "throughput": 5946.46, "total_tokens": 183131360}
{"current_steps": 2340, "total_steps": 5000, "loss": 0.2529, "lr": 5.504934205803002e-06, "epoch": 0.936, "percentage": 46.8, "elapsed_time": "8:34:30", "remaining_time": "9:44:52", "throughput": 5945.36, "total_tokens": 183537936}
{"current_steps": 2345, "total_steps": 5000, "loss": 0.2478, "lr": 5.489304079348259e-06, "epoch": 0.938, "percentage": 46.9, "elapsed_time": "8:35:33", "remaining_time": "9:43:42", "throughput": 5943.84, "total_tokens": 183862896}
{"current_steps": 2350, "total_steps": 5000, "loss": 0.2532, "lr": 5.473669123659793e-06, "epoch": 0.94, "percentage": 47.0, "elapsed_time": "8:36:36", "remaining_time": "9:42:33", "throughput": 5944.57, "total_tokens": 184259888}
{"current_steps": 2355, "total_steps": 5000, "loss": 0.2123, "lr": 5.458029493048303e-06, "epoch": 0.942, "percentage": 47.1, "elapsed_time": "8:37:47", "remaining_time": "9:41:32", "throughput": 5943.81, "total_tokens": 184656352}
{"current_steps": 2360, "total_steps": 5000, "loss": 0.2118, "lr": 5.442385341870633e-06, "epoch": 0.944, "percentage": 47.2, "elapsed_time": "8:38:51", "remaining_time": "9:40:25", "throughput": 5943.15, "total_tokens": 185019024}
{"current_steps": 2365, "total_steps": 5000, "loss": 0.2506, "lr": 5.426736824528236e-06, "epoch": 0.946, "percentage": 47.3, "elapsed_time": "8:40:05", "remaining_time": "9:39:27", "throughput": 5943.73, "total_tokens": 185474944}
{"current_steps": 2370, "total_steps": 5000, "loss": 0.253, "lr": 5.411084095465661e-06, "epoch": 0.948, "percentage": 47.4, "elapsed_time": "8:41:15", "remaining_time": "9:38:26", "throughput": 5945.96, "total_tokens": 185960416}
{"current_steps": 2375, "total_steps": 5000, "loss": 0.2305, "lr": 5.3954273091690245e-06, "epoch": 0.95, "percentage": 47.5, "elapsed_time": "8:42:25", "remaining_time": "9:37:25", "throughput": 5946.23, "total_tokens": 186388384}
{"current_steps": 2380, "total_steps": 5000, "loss": 0.242, "lr": 5.379766620164488e-06, "epoch": 0.952, "percentage": 47.6, "elapsed_time": "8:43:34", "remaining_time": "9:36:22", "throughput": 5947.03, "total_tokens": 186822368}
{"current_steps": 2385, "total_steps": 5000, "loss": 0.231, "lr": 5.36410218301673e-06, "epoch": 0.954, "percentage": 47.7, "elapsed_time": "8:44:47", "remaining_time": "9:35:24", "throughput": 5946.47, "total_tokens": 187241824}
{"current_steps": 2390, "total_steps": 5000, "loss": 0.2367, "lr": 5.348434152327418e-06, "epoch": 0.956, "percentage": 47.8, "elapsed_time": "8:45:57", "remaining_time": "9:34:22", "throughput": 5945.74, "total_tokens": 187634528}
{"current_steps": 2395, "total_steps": 5000, "loss": 0.23, "lr": 5.3327626827336906e-06, "epoch": 0.958, "percentage": 47.9, "elapsed_time": "8:47:01", "remaining_time": "9:33:14", "throughput": 5947.02, "total_tokens": 188055872}
{"current_steps": 2400, "total_steps": 5000, "loss": 0.2423, "lr": 5.3170879289066265e-06, "epoch": 0.96, "percentage": 48.0, "elapsed_time": "8:48:01", "remaining_time": "9:32:01", "throughput": 5947.18, "total_tokens": 188417040}
{"current_steps": 2405, "total_steps": 5000, "loss": 0.2283, "lr": 5.301410045549719e-06, "epoch": 0.962, "percentage": 48.1, "elapsed_time": "8:48:55", "remaining_time": "9:30:43", "throughput": 5947.74, "total_tokens": 188757392}
{"current_steps": 2410, "total_steps": 5000, "loss": 0.2321, "lr": 5.285729187397344e-06, "epoch": 0.964, "percentage": 48.2, "elapsed_time": "8:50:03", "remaining_time": "9:29:38", "throughput": 5946.24, "total_tokens": 189109872}
{"current_steps": 2415, "total_steps": 5000, "loss": 0.2244, "lr": 5.270045509213244e-06, "epoch": 0.966, "percentage": 48.3, "elapsed_time": "8:51:11", "remaining_time": "9:28:34", "throughput": 5944.6, "total_tokens": 189461472}
{"current_steps": 2420, "total_steps": 5000, "loss": 0.2451, "lr": 5.25435916578899e-06, "epoch": 0.968, "percentage": 48.4, "elapsed_time": "8:52:25", "remaining_time": "9:27:37", "throughput": 5944.07, "total_tokens": 189885568}
{"current_steps": 2425, "total_steps": 5000, "loss": 0.2443, "lr": 5.238670311942459e-06, "epoch": 0.97, "percentage": 48.5, "elapsed_time": "8:53:13", "remaining_time": "9:26:12", "throughput": 5946.36, "total_tokens": 190242304}
{"current_steps": 2430, "total_steps": 5000, "loss": 0.2422, "lr": 5.222979102516304e-06, "epoch": 0.972, "percentage": 48.6, "elapsed_time": "8:54:14", "remaining_time": "9:25:01", "throughput": 5946.06, "total_tokens": 190598224}
{"current_steps": 2435, "total_steps": 5000, "loss": 0.2372, "lr": 5.207285692376427e-06, "epoch": 0.974, "percentage": 48.7, "elapsed_time": "8:55:20", "remaining_time": "9:23:55", "throughput": 5945.8, "total_tokens": 190981888}
{"current_steps": 2440, "total_steps": 5000, "loss": 0.2312, "lr": 5.191590236410451e-06, "epoch": 0.976, "percentage": 48.8, "elapsed_time": "8:56:30", "remaining_time": "9:22:53", "throughput": 5943.58, "total_tokens": 191325504}
{"current_steps": 2445, "total_steps": 5000, "loss": 0.2086, "lr": 5.175892889526189e-06, "epoch": 0.978, "percentage": 48.9, "elapsed_time": "8:57:30", "remaining_time": "9:21:41", "throughput": 5943.81, "total_tokens": 191691824}
{"current_steps": 2450, "total_steps": 5000, "loss": 0.2279, "lr": 5.16019380665012e-06, "epoch": 0.98, "percentage": 49.0, "elapsed_time": "8:58:49", "remaining_time": "9:20:48", "throughput": 5943.99, "total_tokens": 192164848}
{"current_steps": 2455, "total_steps": 5000, "loss": 0.2391, "lr": 5.144493142725851e-06, "epoch": 0.982, "percentage": 49.1, "elapsed_time": "8:59:52", "remaining_time": "9:19:39", "throughput": 5943.36, "total_tokens": 192517376}
{"current_steps": 2460, "total_steps": 5000, "loss": 0.236, "lr": 5.128791052712597e-06, "epoch": 0.984, "percentage": 49.2, "elapsed_time": "9:01:07", "remaining_time": "9:18:42", "throughput": 5943.73, "total_tokens": 192975344}
{"current_steps": 2465, "total_steps": 5000, "loss": 0.2355, "lr": 5.1130876915836495e-06, "epoch": 0.986, "percentage": 49.3, "elapsed_time": "9:02:23", "remaining_time": "9:17:47", "throughput": 5944.28, "total_tokens": 193448704}
{"current_steps": 2470, "total_steps": 5000, "loss": 0.2254, "lr": 5.0973832143248405e-06, "epoch": 0.988, "percentage": 49.4, "elapsed_time": "9:03:18", "remaining_time": "9:16:29", "throughput": 5945.83, "total_tokens": 193822592}
{"current_steps": 2475, "total_steps": 5000, "loss": 0.2537, "lr": 5.0816777759330215e-06, "epoch": 0.99, "percentage": 49.5, "elapsed_time": "9:04:30", "remaining_time": "9:15:30", "throughput": 5945.23, "total_tokens": 194232336}
{"current_steps": 2480, "total_steps": 5000, "loss": 0.2267, "lr": 5.065971531414528e-06, "epoch": 0.992, "percentage": 49.6, "elapsed_time": "9:05:32", "remaining_time": "9:14:20", "throughput": 5944.3, "total_tokens": 194573072}
{"current_steps": 2485, "total_steps": 5000, "loss": 0.2445, "lr": 5.050264635783654e-06, "epoch": 0.994, "percentage": 49.7, "elapsed_time": "9:06:48", "remaining_time": "9:13:24", "throughput": 5943.41, "total_tokens": 194995520}
{"current_steps": 2490, "total_steps": 5000, "loss": 0.2221, "lr": 5.034557244061117e-06, "epoch": 0.996, "percentage": 49.8, "elapsed_time": "9:07:46", "remaining_time": "9:12:10", "throughput": 5945.08, "total_tokens": 195391968}
{"current_steps": 2495, "total_steps": 5000, "loss": 0.2541, "lr": 5.018849511272532e-06, "epoch": 0.998, "percentage": 49.9, "elapsed_time": "9:08:37", "remaining_time": "9:10:49", "throughput": 5945.85, "total_tokens": 195720288}
{"current_steps": 2500, "total_steps": 5000, "loss": 0.2342, "lr": 5.0031415924468816e-06, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "9:09:51", "remaining_time": "9:09:51", "throughput": 5946.09, "total_tokens": 196169248}
{"current_steps": 2505, "total_steps": 5000, "loss": 0.179, "lr": 4.987433642614981e-06, "epoch": 1.002, "percentage": 50.1, "elapsed_time": "9:12:46", "remaining_time": "9:10:33", "throughput": 5924.51, "total_tokens": 196494000}
{"current_steps": 2510, "total_steps": 5000, "loss": 0.1623, "lr": 4.971725816807956e-06, "epoch": 1.004, "percentage": 50.2, "elapsed_time": "9:14:04", "remaining_time": "9:09:39", "throughput": 5923.16, "total_tokens": 196910592}
{"current_steps": 2515, "total_steps": 5000, "loss": 0.1427, "lr": 4.956018270055703e-06, "epoch": 1.006, "percentage": 50.3, "elapsed_time": "9:14:53", "remaining_time": "9:08:16", "throughput": 5924.52, "total_tokens": 197247360}
{"current_steps": 2520, "total_steps": 5000, "loss": 0.1741, "lr": 4.940311157385369e-06, "epoch": 1.008, "percentage": 50.4, "elapsed_time": "9:15:48", "remaining_time": "9:06:59", "throughput": 5925.64, "total_tokens": 197613104}
{"current_steps": 2525, "total_steps": 5000, "loss": 0.1804, "lr": 4.924604633819815e-06, "epoch": 1.01, "percentage": 50.5, "elapsed_time": "9:16:50", "remaining_time": "9:05:48", "throughput": 5924.72, "total_tokens": 197948240}
{"current_steps": 2530, "total_steps": 5000, "loss": 0.1432, "lr": 4.908898854376086e-06, "epoch": 1.012, "percentage": 50.6, "elapsed_time": "9:17:55", "remaining_time": "9:04:41", "throughput": 5923.67, "total_tokens": 198299104}
{"current_steps": 2535, "total_steps": 5000, "loss": 0.1555, "lr": 4.893193974063885e-06, "epoch": 1.014, "percentage": 50.7, "elapsed_time": "9:18:56", "remaining_time": "9:03:30", "throughput": 5924.65, "total_tokens": 198690672}
{"current_steps": 2540, "total_steps": 5000, "loss": 0.1601, "lr": 4.877490147884042e-06, "epoch": 1.016, "percentage": 50.8, "elapsed_time": "9:20:06", "remaining_time": "9:02:27", "throughput": 5925.78, "total_tokens": 199144304}
{"current_steps": 2545, "total_steps": 5000, "loss": 0.1782, "lr": 4.861787530826979e-06, "epoch": 1.018, "percentage": 50.9, "elapsed_time": "9:21:07", "remaining_time": "9:01:17", "throughput": 5925.31, "total_tokens": 199492576}
{"current_steps": 2550, "total_steps": 5000, "loss": 0.1579, "lr": 4.846086277871188e-06, "epoch": 1.02, "percentage": 51.0, "elapsed_time": "9:22:12", "remaining_time": "9:00:09", "throughput": 5926.63, "total_tokens": 199922256}
{"current_steps": 2555, "total_steps": 5000, "loss": 0.1415, "lr": 4.830386543981696e-06, "epoch": 1.022, "percentage": 51.1, "elapsed_time": "9:23:12", "remaining_time": "8:58:57", "throughput": 5926.63, "total_tokens": 200273824}
{"current_steps": 2560, "total_steps": 5000, "loss": 0.1778, "lr": 4.8146884841085405e-06, "epoch": 1.024, "percentage": 51.2, "elapsed_time": "9:24:28", "remaining_time": "8:58:01", "throughput": 5926.11, "total_tokens": 200711360}
{"current_steps": 2565, "total_steps": 5000, "loss": 0.1405, "lr": 4.798992253185233e-06, "epoch": 1.026, "percentage": 51.3, "elapsed_time": "9:25:36", "remaining_time": "8:56:56", "throughput": 5925.16, "total_tokens": 201079552}
{"current_steps": 2570, "total_steps": 5000, "loss": 0.1822, "lr": 4.783298006127238e-06, "epoch": 1.028, "percentage": 51.4, "elapsed_time": "9:26:41", "remaining_time": "8:55:49", "throughput": 5926.44, "total_tokens": 201507760}
{"current_steps": 2575, "total_steps": 5000, "loss": 0.1772, "lr": 4.767605897830436e-06, "epoch": 1.03, "percentage": 51.5, "elapsed_time": "9:27:52", "remaining_time": "8:54:47", "throughput": 5928.63, "total_tokens": 202004576}
{"current_steps": 2580, "total_steps": 5000, "loss": 0.1745, "lr": 4.7519160831696e-06, "epoch": 1.032, "percentage": 51.6, "elapsed_time": "9:29:01", "remaining_time": "8:53:44", "throughput": 5928.99, "total_tokens": 202427216}
{"current_steps": 2585, "total_steps": 5000, "loss": 0.1639, "lr": 4.736228716996868e-06, "epoch": 1.034, "percentage": 51.7, "elapsed_time": "9:30:10", "remaining_time": "8:52:40", "throughput": 5929.15, "total_tokens": 202837472}
{"current_steps": 2590, "total_steps": 5000, "loss": 0.1646, "lr": 4.72054395414021e-06, "epoch": 1.036, "percentage": 51.8, "elapsed_time": "9:31:15", "remaining_time": "8:51:33", "throughput": 5930.31, "total_tokens": 203262240}
{"current_steps": 2595, "total_steps": 5000, "loss": 0.1651, "lr": 4.704861949401904e-06, "epoch": 1.038, "percentage": 51.9, "elapsed_time": "9:32:21", "remaining_time": "8:50:26", "throughput": 5930.64, "total_tokens": 203665168}
{"current_steps": 2600, "total_steps": 5000, "loss": 0.1572, "lr": 4.689182857557006e-06, "epoch": 1.04, "percentage": 52.0, "elapsed_time": "9:33:06", "remaining_time": "8:49:01", "throughput": 5933.21, "total_tokens": 204024048}
{"current_steps": 2605, "total_steps": 5000, "loss": 0.1605, "lr": 4.673506833351821e-06, "epoch": 1.042, "percentage": 52.1, "elapsed_time": "9:34:20", "remaining_time": "8:48:02", "throughput": 5932.36, "total_tokens": 204431792}
{"current_steps": 2610, "total_steps": 5000, "loss": 0.1616, "lr": 4.65783403150238e-06, "epoch": 1.044, "percentage": 52.2, "elapsed_time": "9:35:27", "remaining_time": "8:46:56", "throughput": 5931.55, "total_tokens": 204799008}
{"current_steps": 2615, "total_steps": 5000, "loss": 0.1549, "lr": 4.642164606692912e-06, "epoch": 1.046, "percentage": 52.3, "elapsed_time": "9:36:38", "remaining_time": "8:45:55", "throughput": 5931.72, "total_tokens": 205228960}
{"current_steps": 2620, "total_steps": 5000, "loss": 0.168, "lr": 4.626498713574311e-06, "epoch": 1.048, "percentage": 52.4, "elapsed_time": "9:37:49", "remaining_time": "8:44:53", "throughput": 5929.91, "total_tokens": 205586784}
{"current_steps": 2625, "total_steps": 5000, "loss": 0.1796, "lr": 4.610836506762618e-06, "epoch": 1.05, "percentage": 52.5, "elapsed_time": "9:39:07", "remaining_time": "8:43:58", "throughput": 5928.65, "total_tokens": 206006096}
{"current_steps": 2630, "total_steps": 5000, "loss": 0.1714, "lr": 4.5951781408374915e-06, "epoch": 1.052, "percentage": 52.6, "elapsed_time": "9:40:05", "remaining_time": "8:42:44", "throughput": 5928.64, "total_tokens": 206348848}
{"current_steps": 2635, "total_steps": 5000, "loss": 0.1777, "lr": 4.579523770340681e-06, "epoch": 1.054, "percentage": 52.7, "elapsed_time": "9:41:07", "remaining_time": "8:41:34", "throughput": 5928.6, "total_tokens": 206713632}
{"current_steps": 2640, "total_steps": 5000, "loss": 0.1582, "lr": 4.563873549774506e-06, "epoch": 1.056, "percentage": 52.8, "elapsed_time": "9:42:12", "remaining_time": "8:40:27", "throughput": 5930.49, "total_tokens": 207167536}
{"current_steps": 2645, "total_steps": 5000, "loss": 0.1607, "lr": 4.548227633600322e-06, "epoch": 1.058, "percentage": 52.9, "elapsed_time": "9:43:31", "remaining_time": "8:39:32", "throughput": 5931.57, "total_tokens": 207670624}
{"current_steps": 2650, "total_steps": 5000, "loss": 0.1679, "lr": 4.532586176237007e-06, "epoch": 1.06, "percentage": 53.0, "elapsed_time": "9:44:25", "remaining_time": "8:38:15", "throughput": 5931.19, "total_tokens": 207981200}
{"current_steps": 2655, "total_steps": 5000, "loss": 0.1718, "lr": 4.516949332059429e-06, "epoch": 1.062, "percentage": 53.1, "elapsed_time": "9:45:28", "remaining_time": "8:37:07", "throughput": 5931.63, "total_tokens": 208370544}
{"current_steps": 2660, "total_steps": 5000, "loss": 0.1636, "lr": 4.501317255396931e-06, "epoch": 1.064, "percentage": 53.2, "elapsed_time": "9:46:31", "remaining_time": "8:35:58", "throughput": 5931.73, "total_tokens": 208748112}
{"current_steps": 2665, "total_steps": 5000, "loss": 0.157, "lr": 4.485690100531793e-06, "epoch": 1.066, "percentage": 53.3, "elapsed_time": "9:47:39", "remaining_time": "8:34:53", "throughput": 5931.67, "total_tokens": 209150032}
{"current_steps": 2670, "total_steps": 5000, "loss": 0.1565, "lr": 4.470068021697728e-06, "epoch": 1.068, "percentage": 53.4, "elapsed_time": "9:48:41", "remaining_time": "8:33:43", "throughput": 5931.75, "total_tokens": 209517296}
{"current_steps": 2675, "total_steps": 5000, "loss": 0.173, "lr": 4.454451173078347e-06, "epoch": 1.07, "percentage": 53.5, "elapsed_time": "9:49:59", "remaining_time": "8:32:47", "throughput": 5930.95, "total_tokens": 209952960}
{"current_steps": 2680, "total_steps": 5000, "loss": 0.1545, "lr": 4.43883970880564e-06, "epoch": 1.072, "percentage": 53.6, "elapsed_time": "9:51:01", "remaining_time": "8:31:38", "throughput": 5930.57, "total_tokens": 210308672}
{"current_steps": 2685, "total_steps": 5000, "loss": 0.1552, "lr": 4.423233782958459e-06, "epoch": 1.074, "percentage": 53.7, "elapsed_time": "9:51:51", "remaining_time": "8:30:18", "throughput": 5931.21, "total_tokens": 210626720}
{"current_steps": 2690, "total_steps": 5000, "loss": 0.1752, "lr": 4.407633549560991e-06, "epoch": 1.076, "percentage": 53.8, "elapsed_time": "9:53:04", "remaining_time": "8:29:17", "throughput": 5931.1, "total_tokens": 211055456}
{"current_steps": 2695, "total_steps": 5000, "loss": 0.1608, "lr": 4.392039162581239e-06, "epoch": 1.078, "percentage": 53.9, "elapsed_time": "9:54:15", "remaining_time": "8:28:15", "throughput": 5931.03, "total_tokens": 211475760}
{"current_steps": 2700, "total_steps": 5000, "loss": 0.1658, "lr": 4.37645077592951e-06, "epoch": 1.08, "percentage": 54.0, "elapsed_time": "9:55:17", "remaining_time": "8:27:05", "throughput": 5931.73, "total_tokens": 211864080}
{"current_steps": 2705, "total_steps": 5000, "loss": 0.1707, "lr": 4.360868543456883e-06, "epoch": 1.082, "percentage": 54.1, "elapsed_time": "9:56:27", "remaining_time": "8:26:03", "throughput": 5932.25, "total_tokens": 212299776}
{"current_steps": 2710, "total_steps": 5000, "loss": 0.1534, "lr": 4.3452926189537056e-06, "epoch": 1.084, "percentage": 54.2, "elapsed_time": "9:57:45", "remaining_time": "8:25:07", "throughput": 5932.17, "total_tokens": 212762192}
{"current_steps": 2715, "total_steps": 5000, "loss": 0.1615, "lr": 4.329723156148064e-06, "epoch": 1.086, "percentage": 54.3, "elapsed_time": "9:58:53", "remaining_time": "8:24:02", "throughput": 5933.12, "total_tokens": 213195072}
{"current_steps": 2720, "total_steps": 5000, "loss": 0.1604, "lr": 4.314160308704269e-06, "epoch": 1.088, "percentage": 54.4, "elapsed_time": "10:00:03", "remaining_time": "8:22:59", "throughput": 5933.63, "total_tokens": 213630928}
{"current_steps": 2725, "total_steps": 5000, "loss": 0.1665, "lr": 4.298604230221341e-06, "epoch": 1.09, "percentage": 54.5, "elapsed_time": "10:01:15", "remaining_time": "8:21:58", "throughput": 5933.44, "total_tokens": 214053840}
{"current_steps": 2730, "total_steps": 5000, "loss": 0.1638, "lr": 4.283055074231498e-06, "epoch": 1.092, "percentage": 54.6, "elapsed_time": "10:02:08", "remaining_time": "8:20:41", "throughput": 5935.4, "total_tokens": 214438800}
{"current_steps": 2735, "total_steps": 5000, "loss": 0.1783, "lr": 4.267512994198629e-06, "epoch": 1.094, "percentage": 54.7, "elapsed_time": "10:03:20", "remaining_time": "8:19:39", "throughput": 5935.31, "total_tokens": 214859088}
{"current_steps": 2740, "total_steps": 5000, "loss": 0.1546, "lr": 4.251978143516789e-06, "epoch": 1.096, "percentage": 54.8, "elapsed_time": "10:04:35", "remaining_time": "8:18:40", "throughput": 5935.9, "total_tokens": 215328352}
{"current_steps": 2745, "total_steps": 5000, "loss": 0.1638, "lr": 4.2364506755086856e-06, "epoch": 1.098, "percentage": 54.9, "elapsed_time": "10:05:44", "remaining_time": "8:17:36", "throughput": 5934.68, "total_tokens": 215694144}
{"current_steps": 2750, "total_steps": 5000, "loss": 0.1749, "lr": 4.220930743424157e-06, "epoch": 1.1, "percentage": 55.0, "elapsed_time": "10:06:45", "remaining_time": "8:16:25", "throughput": 5934.25, "total_tokens": 216036784}
{"current_steps": 2755, "total_steps": 5000, "loss": 0.1536, "lr": 4.2054185004386675e-06, "epoch": 1.102, "percentage": 55.1, "elapsed_time": "10:07:57", "remaining_time": "8:15:25", "throughput": 5933.51, "total_tokens": 216440592}
{"current_steps": 2760, "total_steps": 5000, "loss": 0.176, "lr": 4.1899140996517934e-06, "epoch": 1.104, "percentage": 55.2, "elapsed_time": "10:09:02", "remaining_time": "8:14:17", "throughput": 5933.37, "total_tokens": 216818816}
{"current_steps": 2765, "total_steps": 5000, "loss": 0.17, "lr": 4.174417694085711e-06, "epoch": 1.106, "percentage": 55.3, "elapsed_time": "10:09:51", "remaining_time": "8:12:57", "throughput": 5934.87, "total_tokens": 217166288}
{"current_steps": 2770, "total_steps": 5000, "loss": 0.1498, "lr": 4.158929436683687e-06, "epoch": 1.108, "percentage": 55.4, "elapsed_time": "10:10:42", "remaining_time": "8:11:39", "throughput": 5936.38, "total_tokens": 217524848}
{"current_steps": 2775, "total_steps": 5000, "loss": 0.1686, "lr": 4.143449480308569e-06, "epoch": 1.11, "percentage": 55.5, "elapsed_time": "10:11:40", "remaining_time": "8:10:26", "throughput": 5935.76, "total_tokens": 217843776}
{"current_steps": 2780, "total_steps": 5000, "loss": 0.1593, "lr": 4.127977977741277e-06, "epoch": 1.112, "percentage": 55.6, "elapsed_time": "10:12:35", "remaining_time": "8:09:11", "throughput": 5935.82, "total_tokens": 218174688}
{"current_steps": 2785, "total_steps": 5000, "loss": 0.1739, "lr": 4.112515081679295e-06, "epoch": 1.114, "percentage": 55.7, "elapsed_time": "10:13:40", "remaining_time": "8:08:04", "throughput": 5935.77, "total_tokens": 218560048}
{"current_steps": 2790, "total_steps": 5000, "loss": 0.1641, "lr": 4.0970609447351635e-06, "epoch": 1.116, "percentage": 55.8, "elapsed_time": "10:14:26", "remaining_time": "8:06:42", "throughput": 5937.3, "total_tokens": 218888000}
{"current_steps": 2795, "total_steps": 5000, "loss": 0.1496, "lr": 4.081615719434978e-06, "epoch": 1.1179999999999999, "percentage": 55.9, "elapsed_time": "10:15:28", "remaining_time": "8:05:32", "throughput": 5936.56, "total_tokens": 219226272}
{"current_steps": 2800, "total_steps": 5000, "loss": 0.1596, "lr": 4.066179558216874e-06, "epoch": 1.12, "percentage": 56.0, "elapsed_time": "10:16:38", "remaining_time": "8:04:30", "throughput": 5935.79, "total_tokens": 219614112}
{"current_steps": 2805, "total_steps": 5000, "loss": 0.1649, "lr": 4.0507526134295314e-06, "epoch": 1.1219999999999999, "percentage": 56.1, "elapsed_time": "10:17:52", "remaining_time": "8:03:30", "throughput": 5935.85, "total_tokens": 220054416}
{"current_steps": 2810, "total_steps": 5000, "loss": 0.1585, "lr": 4.035335037330668e-06, "epoch": 1.124, "percentage": 56.2, "elapsed_time": "10:18:52", "remaining_time": "8:02:19", "throughput": 5937.65, "total_tokens": 220482096}
{"current_steps": 2815, "total_steps": 5000, "loss": 0.1638, "lr": 4.019926982085536e-06, "epoch": 1.126, "percentage": 56.3, "elapsed_time": "10:19:45", "remaining_time": "8:01:03", "throughput": 5937.85, "total_tokens": 220802496}
{"current_steps": 2820, "total_steps": 5000, "loss": 0.1583, "lr": 4.004528599765419e-06, "epoch": 1.1280000000000001, "percentage": 56.4, "elapsed_time": "10:20:57", "remaining_time": "8:00:01", "throughput": 5937.56, "total_tokens": 221218208}
{"current_steps": 2825, "total_steps": 5000, "loss": 0.1714, "lr": 3.989140042346134e-06, "epoch": 1.13, "percentage": 56.5, "elapsed_time": "10:22:05", "remaining_time": "7:58:57", "throughput": 5938.07, "total_tokens": 221641024}
{"current_steps": 2830, "total_steps": 5000, "loss": 0.1524, "lr": 3.97376146170653e-06, "epoch": 1.1320000000000001, "percentage": 56.6, "elapsed_time": "10:23:23", "remaining_time": "7:58:00", "throughput": 5936.57, "total_tokens": 222048304}
{"current_steps": 2835, "total_steps": 5000, "loss": 0.1606, "lr": 3.95839300962699e-06, "epoch": 1.134, "percentage": 56.7, "elapsed_time": "10:24:24", "remaining_time": "7:56:50", "throughput": 5935.83, "total_tokens": 222383824}
{"current_steps": 2840, "total_steps": 5000, "loss": 0.1703, "lr": 3.9430348377879315e-06, "epoch": 1.1360000000000001, "percentage": 56.8, "elapsed_time": "10:25:16", "remaining_time": "7:55:33", "throughput": 5936.13, "total_tokens": 222702688}
{"current_steps": 2845, "total_steps": 5000, "loss": 0.1612, "lr": 3.927687097768309e-06, "epoch": 1.138, "percentage": 56.9, "elapsed_time": "10:26:21", "remaining_time": "7:54:27", "throughput": 5937.4, "total_tokens": 223138048}
{"current_steps": 2850, "total_steps": 5000, "loss": 0.1756, "lr": 3.912349941044122e-06, "epoch": 1.1400000000000001, "percentage": 57.0, "elapsed_time": "10:27:27", "remaining_time": "7:53:20", "throughput": 5938.11, "total_tokens": 223556928}
{"current_steps": 2855, "total_steps": 5000, "loss": 0.1546, "lr": 3.897023518986915e-06, "epoch": 1.142, "percentage": 57.1, "elapsed_time": "10:28:36", "remaining_time": "7:52:16", "throughput": 5936.9, "total_tokens": 223918384}
{"current_steps": 2860, "total_steps": 5000, "loss": 0.1618, "lr": 3.8817079828622855e-06, "epoch": 1.144, "percentage": 57.2, "elapsed_time": "10:29:49", "remaining_time": "7:51:15", "throughput": 5935.96, "total_tokens": 224316224}
{"current_steps": 2865, "total_steps": 5000, "loss": 0.1891, "lr": 3.866403483828392e-06, "epoch": 1.146, "percentage": 57.3, "elapsed_time": "10:31:02", "remaining_time": "7:50:15", "throughput": 5935.84, "total_tokens": 224745296}
{"current_steps": 2870, "total_steps": 5000, "loss": 0.166, "lr": 3.851110172934463e-06, "epoch": 1.148, "percentage": 57.4, "elapsed_time": "10:32:00", "remaining_time": "7:49:02", "throughput": 5935.44, "total_tokens": 225073936}
{"current_steps": 2875, "total_steps": 5000, "loss": 0.1702, "lr": 3.835828201119302e-06, "epoch": 1.15, "percentage": 57.5, "elapsed_time": "10:33:17", "remaining_time": "7:48:05", "throughput": 5933.37, "total_tokens": 225454176}
{"current_steps": 2880, "total_steps": 5000, "loss": 0.1539, "lr": 3.820557719209799e-06, "epoch": 1.152, "percentage": 57.6, "elapsed_time": "10:34:26", "remaining_time": "7:47:01", "throughput": 5933.79, "total_tokens": 225879344}
{"current_steps": 2885, "total_steps": 5000, "loss": 0.1578, "lr": 3.8052988779194478e-06, "epoch": 1.154, "percentage": 57.7, "elapsed_time": "10:35:24", "remaining_time": "7:45:49", "throughput": 5934.81, "total_tokens": 226262112}
{"current_steps": 2890, "total_steps": 5000, "loss": 0.1625, "lr": 3.790051827846851e-06, "epoch": 1.156, "percentage": 57.8, "elapsed_time": "10:36:38", "remaining_time": "7:44:48", "throughput": 5933.46, "total_tokens": 226648544}
{"current_steps": 2895, "total_steps": 5000, "loss": 0.1799, "lr": 3.774816719474238e-06, "epoch": 1.158, "percentage": 57.9, "elapsed_time": "10:37:35", "remaining_time": "7:43:36", "throughput": 5934.05, "total_tokens": 227010720}
{"current_steps": 2900, "total_steps": 5000, "loss": 0.1679, "lr": 3.7595937031659775e-06, "epoch": 1.16, "percentage": 58.0, "elapsed_time": "10:38:48", "remaining_time": "7:42:35", "throughput": 5933.58, "total_tokens": 227427232}
{"current_steps": 2905, "total_steps": 5000, "loss": 0.1538, "lr": 3.744382929167094e-06, "epoch": 1.162, "percentage": 58.1, "elapsed_time": "10:40:01", "remaining_time": "7:41:33", "throughput": 5933.32, "total_tokens": 227847312}
{"current_steps": 2910, "total_steps": 5000, "loss": 0.178, "lr": 3.729184547601786e-06, "epoch": 1.164, "percentage": 58.2, "elapsed_time": "10:40:56", "remaining_time": "7:40:20", "throughput": 5933.07, "total_tokens": 228165488}
{"current_steps": 2915, "total_steps": 5000, "loss": 0.1525, "lr": 3.7139987084719463e-06, "epoch": 1.166, "percentage": 58.3, "elapsed_time": "10:41:56", "remaining_time": "7:39:09", "throughput": 5933.91, "total_tokens": 228555376}
{"current_steps": 2920, "total_steps": 5000, "loss": 0.1753, "lr": 3.6988255616556725e-06, "epoch": 1.168, "percentage": 58.4, "elapsed_time": "10:43:07", "remaining_time": "7:38:06", "throughput": 5934.25, "total_tokens": 228986000}
{"current_steps": 2925, "total_steps": 5000, "loss": 0.1329, "lr": 3.6836652569057994e-06, "epoch": 1.17, "percentage": 58.5, "elapsed_time": "10:44:14", "remaining_time": "7:37:01", "throughput": 5935.01, "total_tokens": 229411824}
{"current_steps": 2930, "total_steps": 5000, "loss": 0.1795, "lr": 3.668517943848416e-06, "epoch": 1.172, "percentage": 58.6, "elapsed_time": "10:45:22", "remaining_time": "7:35:56", "throughput": 5934.01, "total_tokens": 229778192}
{"current_steps": 2935, "total_steps": 5000, "loss": 0.1649, "lr": 3.653383771981385e-06, "epoch": 1.174, "percentage": 58.7, "elapsed_time": "10:46:24", "remaining_time": "7:34:47", "throughput": 5933.8, "total_tokens": 230140048}
{"current_steps": 2940, "total_steps": 5000, "loss": 0.1572, "lr": 3.6382628906728735e-06, "epoch": 1.176, "percentage": 58.8, "elapsed_time": "10:47:34", "remaining_time": "7:33:44", "throughput": 5933.33, "total_tokens": 230533984}
{"current_steps": 2945, "total_steps": 5000, "loss": 0.1687, "lr": 3.6231554491598766e-06, "epoch": 1.178, "percentage": 58.9, "elapsed_time": "10:48:38", "remaining_time": "7:32:36", "throughput": 5932.24, "total_tokens": 230871408}
{"current_steps": 2950, "total_steps": 5000, "loss": 0.1841, "lr": 3.60806159654674e-06, "epoch": 1.18, "percentage": 59.0, "elapsed_time": "10:49:40", "remaining_time": "7:31:28", "throughput": 5933.08, "total_tokens": 231276048}
{"current_steps": 2955, "total_steps": 5000, "loss": 0.1734, "lr": 3.592981481803699e-06, "epoch": 1.182, "percentage": 59.1, "elapsed_time": "10:50:51", "remaining_time": "7:30:25", "throughput": 5934.51, "total_tokens": 231750416}
{"current_steps": 2960, "total_steps": 5000, "loss": 0.1746, "lr": 3.577915253765396e-06, "epoch": 1.184, "percentage": 59.2, "elapsed_time": "10:52:01", "remaining_time": "7:29:22", "throughput": 5934.01, "total_tokens": 232149872}
{"current_steps": 2965, "total_steps": 5000, "loss": 0.1536, "lr": 3.562863061129419e-06, "epoch": 1.186, "percentage": 59.3, "elapsed_time": "10:53:09", "remaining_time": "7:28:17", "throughput": 5932.74, "total_tokens": 232498144}
{"current_steps": 2970, "total_steps": 5000, "loss": 0.1697, "lr": 3.547825052454833e-06, "epoch": 1.188, "percentage": 59.4, "elapsed_time": "10:54:17", "remaining_time": "7:27:12", "throughput": 5931.02, "total_tokens": 232837008}
{"current_steps": 2975, "total_steps": 5000, "loss": 0.1655, "lr": 3.532801376160713e-06, "epoch": 1.19, "percentage": 59.5, "elapsed_time": "10:55:29", "remaining_time": "7:26:10", "throughput": 5931.13, "total_tokens": 233268432}
{"current_steps": 2980, "total_steps": 5000, "loss": 0.1545, "lr": 3.5177921805246772e-06, "epoch": 1.192, "percentage": 59.6, "elapsed_time": "10:56:46", "remaining_time": "7:25:11", "throughput": 5930.36, "total_tokens": 233693104}
{"current_steps": 2985, "total_steps": 5000, "loss": 0.1584, "lr": 3.502797613681429e-06, "epoch": 1.194, "percentage": 59.7, "elapsed_time": "10:57:58", "remaining_time": "7:24:09", "throughput": 5929.97, "total_tokens": 234108256}
{"current_steps": 2990, "total_steps": 5000, "loss": 0.1716, "lr": 3.4878178236212883e-06, "epoch": 1.196, "percentage": 59.8, "elapsed_time": "10:59:08", "remaining_time": "7:23:06", "throughput": 5929.36, "total_tokens": 234497200}
{"current_steps": 2995, "total_steps": 5000, "loss": 0.156, "lr": 3.472852958188736e-06, "epoch": 1.198, "percentage": 59.9, "elapsed_time": "11:00:00", "remaining_time": "7:21:50", "throughput": 5929.9, "total_tokens": 234829648}
{"current_steps": 3000, "total_steps": 5000, "loss": 0.1658, "lr": 3.457903165080952e-06, "epoch": 1.2, "percentage": 60.0, "elapsed_time": "11:01:10", "remaining_time": "7:20:47", "throughput": 5929.35, "total_tokens": 235222976}
{"current_steps": 3005, "total_steps": 5000, "loss": 0.1759, "lr": 3.442968591846359e-06, "epoch": 1.202, "percentage": 60.1, "elapsed_time": "11:02:22", "remaining_time": "7:19:45", "throughput": 5930.05, "total_tokens": 235677408}
{"current_steps": 3010, "total_steps": 5000, "loss": 0.1662, "lr": 3.4280493858831665e-06, "epoch": 1.204, "percentage": 60.2, "elapsed_time": "11:03:35", "remaining_time": "7:18:43", "throughput": 5929.85, "total_tokens": 236101648}
{"current_steps": 3015, "total_steps": 5000, "loss": 0.1649, "lr": 3.4131456944379126e-06, "epoch": 1.206, "percentage": 60.3, "elapsed_time": "11:04:40", "remaining_time": "7:17:36", "throughput": 5929.79, "total_tokens": 236482832}
{"current_steps": 3020, "total_steps": 5000, "loss": 0.1506, "lr": 3.398257664604015e-06, "epoch": 1.208, "percentage": 60.4, "elapsed_time": "11:05:39", "remaining_time": "7:16:25", "throughput": 5930.22, "total_tokens": 236848400}
{"current_steps": 3025, "total_steps": 5000, "loss": 0.1814, "lr": 3.3833854433203185e-06, "epoch": 1.21, "percentage": 60.5, "elapsed_time": "11:06:48", "remaining_time": "7:15:21", "throughput": 5929.59, "total_tokens": 237235776}
{"current_steps": 3030, "total_steps": 5000, "loss": 0.165, "lr": 3.3685291773696425e-06, "epoch": 1.212, "percentage": 60.6, "elapsed_time": "11:07:41", "remaining_time": "7:14:06", "throughput": 5930.58, "total_tokens": 237587584}
{"current_steps": 3035, "total_steps": 5000, "loss": 0.158, "lr": 3.3536890133773346e-06, "epoch": 1.214, "percentage": 60.7, "elapsed_time": "11:08:36", "remaining_time": "7:12:53", "throughput": 5930.58, "total_tokens": 237916544}
{"current_steps": 3040, "total_steps": 5000, "loss": 0.1717, "lr": 3.3388650978098218e-06, "epoch": 1.216, "percentage": 60.8, "elapsed_time": "11:09:43", "remaining_time": "7:11:47", "throughput": 5929.82, "total_tokens": 238282032}
{"current_steps": 3045, "total_steps": 5000, "loss": 0.1584, "lr": 3.3240575769731662e-06, "epoch": 1.218, "percentage": 60.9, "elapsed_time": "11:10:55", "remaining_time": "7:10:45", "throughput": 5929.43, "total_tokens": 238693680}
{"current_steps": 3050, "total_steps": 5000, "loss": 0.1559, "lr": 3.309266597011621e-06, "epoch": 1.22, "percentage": 61.0, "elapsed_time": "11:11:58", "remaining_time": "7:09:37", "throughput": 5928.61, "total_tokens": 239034096}
{"current_steps": 3055, "total_steps": 5000, "loss": 0.1681, "lr": 3.294492303906188e-06, "epoch": 1.222, "percentage": 61.1, "elapsed_time": "11:13:11", "remaining_time": "7:08:35", "throughput": 5927.96, "total_tokens": 239441184}
{"current_steps": 3060, "total_steps": 5000, "loss": 0.1596, "lr": 3.2797348434731725e-06, "epoch": 1.224, "percentage": 61.2, "elapsed_time": "11:14:19", "remaining_time": "7:07:30", "throughput": 5927.05, "total_tokens": 239805952}
{"current_steps": 3065, "total_steps": 5000, "loss": 0.1764, "lr": 3.264994361362753e-06, "epoch": 1.226, "percentage": 61.3, "elapsed_time": "11:15:32", "remaining_time": "7:06:29", "throughput": 5927.2, "total_tokens": 240245696}
{"current_steps": 3070, "total_steps": 5000, "loss": 0.1557, "lr": 3.250271003057537e-06, "epoch": 1.228, "percentage": 61.4, "elapsed_time": "11:16:32", "remaining_time": "7:05:18", "throughput": 5926.86, "total_tokens": 240583344}
{"current_steps": 3075, "total_steps": 5000, "loss": 0.1648, "lr": 3.235564913871126e-06, "epoch": 1.23, "percentage": 61.5, "elapsed_time": "11:17:32", "remaining_time": "7:04:08", "throughput": 5927.36, "total_tokens": 240959856}
{"current_steps": 3080, "total_steps": 5000, "loss": 0.1688, "lr": 3.220876238946684e-06, "epoch": 1.232, "percentage": 61.6, "elapsed_time": "11:18:46", "remaining_time": "7:03:07", "throughput": 5926.41, "total_tokens": 241359872}
{"current_steps": 3085, "total_steps": 5000, "loss": 0.1615, "lr": 3.2062051232555024e-06, "epoch": 1.234, "percentage": 61.7, "elapsed_time": "11:19:54", "remaining_time": "7:02:03", "throughput": 5926.92, "total_tokens": 241787296}
{"current_steps": 3090, "total_steps": 5000, "loss": 0.1539, "lr": 3.1915517115955704e-06, "epoch": 1.236, "percentage": 61.8, "elapsed_time": "11:20:57", "remaining_time": "7:00:54", "throughput": 5925.6, "total_tokens": 242103696}
{"current_steps": 3095, "total_steps": 5000, "loss": 0.1544, "lr": 3.1769161485901445e-06, "epoch": 1.238, "percentage": 61.9, "elapsed_time": "11:22:03", "remaining_time": "6:59:48", "throughput": 5926.5, "total_tokens": 242530544}
{"current_steps": 3100, "total_steps": 5000, "loss": 0.158, "lr": 3.1622985786863236e-06, "epoch": 1.24, "percentage": 62.0, "elapsed_time": "11:23:04", "remaining_time": "6:58:39", "throughput": 5926.76, "total_tokens": 242906448}
{"current_steps": 3105, "total_steps": 5000, "loss": 0.1563, "lr": 3.147699146153621e-06, "epoch": 1.242, "percentage": 62.1, "elapsed_time": "11:24:20", "remaining_time": "6:57:39", "throughput": 5926.0, "total_tokens": 243322160}
{"current_steps": 3110, "total_steps": 5000, "loss": 0.1557, "lr": 3.1331179950825415e-06, "epoch": 1.244, "percentage": 62.2, "elapsed_time": "11:25:18", "remaining_time": "6:56:28", "throughput": 5924.88, "total_tokens": 243624320}
{"current_steps": 3115, "total_steps": 5000, "loss": 0.1482, "lr": 3.1185552693831595e-06, "epoch": 1.246, "percentage": 62.3, "elapsed_time": "11:26:37", "remaining_time": "6:55:30", "throughput": 5924.04, "total_tokens": 244055008}
{"current_steps": 3120, "total_steps": 5000, "loss": 0.1644, "lr": 3.1040111127836994e-06, "epoch": 1.248, "percentage": 62.4, "elapsed_time": "11:27:34", "remaining_time": "6:54:18", "throughput": 5924.5, "total_tokens": 244411056}
{"current_steps": 3125, "total_steps": 5000, "loss": 0.1562, "lr": 3.089485668829113e-06, "epoch": 1.25, "percentage": 62.5, "elapsed_time": "11:28:37", "remaining_time": "6:53:10", "throughput": 5924.96, "total_tokens": 244801856}
{"current_steps": 3130, "total_steps": 5000, "loss": 0.1669, "lr": 3.074979080879671e-06, "epoch": 1.252, "percentage": 62.6, "elapsed_time": "11:29:53", "remaining_time": "6:52:10", "throughput": 5926.11, "total_tokens": 245303888}
{"current_steps": 3135, "total_steps": 5000, "loss": 0.1616, "lr": 3.0604914921095373e-06, "epoch": 1.254, "percentage": 62.7, "elapsed_time": "11:31:11", "remaining_time": "6:51:11", "throughput": 5924.45, "total_tokens": 245696576}
{"current_steps": 3140, "total_steps": 5000, "loss": 0.1582, "lr": 3.046023045505366e-06, "epoch": 1.256, "percentage": 62.8, "elapsed_time": "11:32:19", "remaining_time": "6:50:05", "throughput": 5923.86, "total_tokens": 246072144}
{"current_steps": 3145, "total_steps": 5000, "loss": 0.1639, "lr": 3.031573883864882e-06, "epoch": 1.258, "percentage": 62.9, "elapsed_time": "11:33:37", "remaining_time": "6:49:07", "throughput": 5923.15, "total_tokens": 246507184}
{"current_steps": 3150, "total_steps": 5000, "loss": 0.1395, "lr": 3.0171441497954807e-06, "epoch": 1.26, "percentage": 63.0, "elapsed_time": "11:34:41", "remaining_time": "6:47:59", "throughput": 5922.8, "total_tokens": 246873408}
{"current_steps": 3155, "total_steps": 5000, "loss": 0.1715, "lr": 3.002733985712808e-06, "epoch": 1.262, "percentage": 63.1, "elapsed_time": "11:35:45", "remaining_time": "6:46:51", "throughput": 5924.54, "total_tokens": 247320912}
{"current_steps": 3160, "total_steps": 5000, "loss": 0.1814, "lr": 2.9883435338393674e-06, "epoch": 1.264, "percentage": 63.2, "elapsed_time": "11:36:50", "remaining_time": "6:45:45", "throughput": 5923.31, "total_tokens": 247653568}
{"current_steps": 3165, "total_steps": 5000, "loss": 0.1655, "lr": 2.97397293620311e-06, "epoch": 1.266, "percentage": 63.3, "elapsed_time": "11:38:03", "remaining_time": "6:44:43", "throughput": 5921.88, "total_tokens": 248031600}
{"current_steps": 3170, "total_steps": 5000, "loss": 0.1643, "lr": 2.959622334636031e-06, "epoch": 1.268, "percentage": 63.4, "elapsed_time": "11:39:15", "remaining_time": "6:43:40", "throughput": 5921.13, "total_tokens": 248424528}
{"current_steps": 3175, "total_steps": 5000, "loss": 0.1791, "lr": 2.945291870772776e-06, "epoch": 1.27, "percentage": 63.5, "elapsed_time": "11:40:25", "remaining_time": "6:42:36", "throughput": 5920.98, "total_tokens": 248832000}
{"current_steps": 3180, "total_steps": 5000, "loss": 0.1572, "lr": 2.930981686049237e-06, "epoch": 1.272, "percentage": 63.6, "elapsed_time": "11:41:26", "remaining_time": "6:41:27", "throughput": 5920.56, "total_tokens": 249175552}
{"current_steps": 3185, "total_steps": 5000, "loss": 0.1537, "lr": 2.91669192170116e-06, "epoch": 1.274, "percentage": 63.7, "elapsed_time": "11:42:33", "remaining_time": "6:40:21", "throughput": 5920.11, "total_tokens": 249553200}
{"current_steps": 3190, "total_steps": 5000, "loss": 0.1632, "lr": 2.902422718762752e-06, "epoch": 1.276, "percentage": 63.8, "elapsed_time": "11:43:36", "remaining_time": "6:39:13", "throughput": 5920.55, "total_tokens": 249943936}
{"current_steps": 3195, "total_steps": 5000, "loss": 0.1657, "lr": 2.8881742180652813e-06, "epoch": 1.278, "percentage": 63.9, "elapsed_time": "11:44:47", "remaining_time": "6:38:10", "throughput": 5920.36, "total_tokens": 250358672}
{"current_steps": 3200, "total_steps": 5000, "loss": 0.1622, "lr": 2.8739465602357014e-06, "epoch": 1.28, "percentage": 64.0, "elapsed_time": "11:46:03", "remaining_time": "6:37:09", "throughput": 5919.13, "total_tokens": 250754560}
{"current_steps": 3205, "total_steps": 5000, "loss": 0.166, "lr": 2.8597398856952473e-06, "epoch": 1.282, "percentage": 64.1, "elapsed_time": "11:47:09", "remaining_time": "6:36:03", "throughput": 5918.44, "total_tokens": 251117984}
{"current_steps": 3210, "total_steps": 5000, "loss": 0.1619, "lr": 2.845554334658066e-06, "epoch": 1.284, "percentage": 64.2, "elapsed_time": "11:48:20", "remaining_time": "6:34:59", "throughput": 5918.02, "total_tokens": 251519024}
{"current_steps": 3215, "total_steps": 5000, "loss": 0.1561, "lr": 2.831390047129815e-06, "epoch": 1.286, "percentage": 64.3, "elapsed_time": "11:49:17", "remaining_time": "6:33:48", "throughput": 5918.16, "total_tokens": 251863440}
{"current_steps": 3220, "total_steps": 5000, "loss": 0.1666, "lr": 2.817247162906297e-06, "epoch": 1.288, "percentage": 64.4, "elapsed_time": "11:50:35", "remaining_time": "6:32:48", "throughput": 5918.56, "total_tokens": 252342144}
{"current_steps": 3225, "total_steps": 5000, "loss": 0.1488, "lr": 2.803125821572068e-06, "epoch": 1.29, "percentage": 64.5, "elapsed_time": "11:51:50", "remaining_time": "6:31:47", "throughput": 5916.99, "total_tokens": 252714960}
{"current_steps": 3230, "total_steps": 5000, "loss": 0.1654, "lr": 2.7890261624990643e-06, "epoch": 1.292, "percentage": 64.6, "elapsed_time": "11:52:53", "remaining_time": "6:30:39", "throughput": 5917.06, "total_tokens": 253093040}
{"current_steps": 3235, "total_steps": 5000, "loss": 0.1564, "lr": 2.7749483248452324e-06, "epoch": 1.294, "percentage": 64.7, "elapsed_time": "11:54:12", "remaining_time": "6:29:39", "throughput": 5916.49, "total_tokens": 253534096}
{"current_steps": 3240, "total_steps": 5000, "loss": 0.1615, "lr": 2.760892447553143e-06, "epoch": 1.296, "percentage": 64.8, "elapsed_time": "11:55:09", "remaining_time": "6:28:28", "throughput": 5916.59, "total_tokens": 253877168}
{"current_steps": 3245, "total_steps": 5000, "loss": 0.1518, "lr": 2.746858669348634e-06, "epoch": 1.298, "percentage": 64.9, "elapsed_time": "11:56:23", "remaining_time": "6:27:26", "throughput": 5917.13, "total_tokens": 254340192}
{"current_steps": 3250, "total_steps": 5000, "loss": 0.173, "lr": 2.7328471287394265e-06, "epoch": 1.3, "percentage": 65.0, "elapsed_time": "11:57:35", "remaining_time": "6:26:23", "throughput": 5915.97, "total_tokens": 254712384}
{"current_steps": 3255, "total_steps": 5000, "loss": 0.1619, "lr": 2.718857964013773e-06, "epoch": 1.302, "percentage": 65.1, "elapsed_time": "11:58:36", "remaining_time": "6:25:14", "throughput": 5916.05, "total_tokens": 255079824}
{"current_steps": 3260, "total_steps": 5000, "loss": 0.1559, "lr": 2.7048913132390787e-06, "epoch": 1.304, "percentage": 65.2, "elapsed_time": "11:59:47", "remaining_time": "6:24:10", "throughput": 5917.14, "total_tokens": 255544896}
{"current_steps": 3265, "total_steps": 5000, "loss": 0.1604, "lr": 2.6909473142605522e-06, "epoch": 1.306, "percentage": 65.3, "elapsed_time": "12:00:49", "remaining_time": "6:23:02", "throughput": 5917.72, "total_tokens": 255937552}
{"current_steps": 3270, "total_steps": 5000, "loss": 0.1509, "lr": 2.6770261046998315e-06, "epoch": 1.308, "percentage": 65.4, "elapsed_time": "12:02:04", "remaining_time": "6:22:00", "throughput": 5918.12, "total_tokens": 256399136}
{"current_steps": 3275, "total_steps": 5000, "loss": 0.1676, "lr": 2.663127821953633e-06, "epoch": 1.31, "percentage": 65.5, "elapsed_time": "12:03:08", "remaining_time": "6:20:53", "throughput": 5916.88, "total_tokens": 256726480}
{"current_steps": 3280, "total_steps": 5000, "loss": 0.1677, "lr": 2.6492526031924005e-06, "epoch": 1.312, "percentage": 65.6, "elapsed_time": "12:04:15", "remaining_time": "6:19:47", "throughput": 5916.65, "total_tokens": 257112800}
{"current_steps": 3285, "total_steps": 5000, "loss": 0.1699, "lr": 2.635400585358937e-06, "epoch": 1.314, "percentage": 65.7, "elapsed_time": "12:05:13", "remaining_time": "6:18:37", "throughput": 5918.17, "total_tokens": 257521472}
{"current_steps": 3290, "total_steps": 5000, "loss": 0.164, "lr": 2.6215719051670705e-06, "epoch": 1.316, "percentage": 65.8, "elapsed_time": "12:06:22", "remaining_time": "6:17:32", "throughput": 5917.31, "total_tokens": 257892352}
{"current_steps": 3295, "total_steps": 5000, "loss": 0.1548, "lr": 2.607766699100288e-06, "epoch": 1.318, "percentage": 65.9, "elapsed_time": "12:07:24", "remaining_time": "6:16:24", "throughput": 5917.26, "total_tokens": 258258560}
{"current_steps": 3300, "total_steps": 5000, "loss": 0.1614, "lr": 2.5939851034104035e-06, "epoch": 1.32, "percentage": 66.0, "elapsed_time": "12:08:33", "remaining_time": "6:15:18", "throughput": 5916.64, "total_tokens": 258634672}
{"current_steps": 3305, "total_steps": 5000, "loss": 0.1577, "lr": 2.580227254116199e-06, "epoch": 1.322, "percentage": 66.1, "elapsed_time": "12:09:38", "remaining_time": "6:14:11", "throughput": 5916.98, "total_tokens": 259033664}
{"current_steps": 3310, "total_steps": 5000, "loss": 0.1719, "lr": 2.5664932870020966e-06, "epoch": 1.324, "percentage": 66.2, "elapsed_time": "12:10:44", "remaining_time": "6:13:05", "throughput": 5916.33, "total_tokens": 259396128}
{"current_steps": 3315, "total_steps": 5000, "loss": 0.1672, "lr": 2.5527833376168055e-06, "epoch": 1.326, "percentage": 66.3, "elapsed_time": "12:11:51", "remaining_time": "6:12:00", "throughput": 5917.65, "total_tokens": 259854000}
{"current_steps": 3320, "total_steps": 5000, "loss": 0.157, "lr": 2.5390975412719897e-06, "epoch": 1.328, "percentage": 66.4, "elapsed_time": "12:12:49", "remaining_time": "6:10:49", "throughput": 5918.09, "total_tokens": 260216000}
{"current_steps": 3325, "total_steps": 5000, "loss": 0.1788, "lr": 2.5254360330409343e-06, "epoch": 1.33, "percentage": 66.5, "elapsed_time": "12:14:02", "remaining_time": "6:09:46", "throughput": 5918.06, "total_tokens": 260648016}
{"current_steps": 3330, "total_steps": 5000, "loss": 0.1476, "lr": 2.5117989477572126e-06, "epoch": 1.332, "percentage": 66.6, "elapsed_time": "12:15:15", "remaining_time": "6:08:43", "throughput": 5917.52, "total_tokens": 261051520}
{"current_steps": 3335, "total_steps": 5000, "loss": 0.1646, "lr": 2.4981864200133483e-06, "epoch": 1.334, "percentage": 66.7, "elapsed_time": "12:16:22", "remaining_time": "6:07:38", "throughput": 5916.65, "total_tokens": 261412496}
{"current_steps": 3340, "total_steps": 5000, "loss": 0.1568, "lr": 2.484598584159494e-06, "epoch": 1.336, "percentage": 66.8, "elapsed_time": "12:17:23", "remaining_time": "6:06:29", "throughput": 5916.19, "total_tokens": 261753792}
{"current_steps": 3345, "total_steps": 5000, "loss": 0.1666, "lr": 2.4710355743021077e-06, "epoch": 1.338, "percentage": 66.9, "elapsed_time": "12:18:31", "remaining_time": "6:05:23", "throughput": 5916.68, "total_tokens": 262177136}
{"current_steps": 3350, "total_steps": 5000, "loss": 0.1648, "lr": 2.457497524302616e-06, "epoch": 1.34, "percentage": 67.0, "elapsed_time": "12:19:30", "remaining_time": "6:04:14", "throughput": 5917.12, "total_tokens": 262546256}
{"current_steps": 3355, "total_steps": 5000, "loss": 0.1685, "lr": 2.4439845677761124e-06, "epoch": 1.342, "percentage": 67.1, "elapsed_time": "12:20:36", "remaining_time": "6:03:07", "throughput": 5917.26, "total_tokens": 262941872}
{"current_steps": 3360, "total_steps": 5000, "loss": 0.1571, "lr": 2.430496838090017e-06, "epoch": 1.3439999999999999, "percentage": 67.2, "elapsed_time": "12:21:40", "remaining_time": "6:02:00", "throughput": 5917.06, "total_tokens": 263313296}
{"current_steps": 3365, "total_steps": 5000, "loss": 0.157, "lr": 2.417034468362782e-06, "epoch": 1.346, "percentage": 67.3, "elapsed_time": "12:22:58", "remaining_time": "6:01:00", "throughput": 5917.35, "total_tokens": 263787248}
{"current_steps": 3370, "total_steps": 5000, "loss": 0.1776, "lr": 2.403597591462557e-06, "epoch": 1.3479999999999999, "percentage": 67.4, "elapsed_time": "12:24:02", "remaining_time": "5:59:52", "throughput": 5917.21, "total_tokens": 264157904}
{"current_steps": 3375, "total_steps": 5000, "loss": 0.1713, "lr": 2.3901863400058954e-06, "epoch": 1.35, "percentage": 67.5, "elapsed_time": "12:25:01", "remaining_time": "5:58:42", "throughput": 5918.2, "total_tokens": 264551248}
{"current_steps": 3380, "total_steps": 5000, "loss": 0.1594, "lr": 2.376800846356434e-06, "epoch": 1.3519999999999999, "percentage": 67.6, "elapsed_time": "12:25:56", "remaining_time": "5:57:31", "throughput": 5919.01, "total_tokens": 264916240}
{"current_steps": 3385, "total_steps": 5000, "loss": 0.154, "lr": 2.3634412426235886e-06, "epoch": 1.354, "percentage": 67.7, "elapsed_time": "12:26:54", "remaining_time": "5:56:21", "throughput": 5919.48, "total_tokens": 265281024}
{"current_steps": 3390, "total_steps": 5000, "loss": 0.1657, "lr": 2.3501076606612587e-06, "epoch": 1.3559999999999999, "percentage": 67.8, "elapsed_time": "12:28:01", "remaining_time": "5:55:15", "throughput": 5919.68, "total_tokens": 265682112}
{"current_steps": 3395, "total_steps": 5000, "loss": 0.1581, "lr": 2.3368002320665118e-06, "epoch": 1.358, "percentage": 67.9, "elapsed_time": "12:29:14", "remaining_time": "5:54:12", "throughput": 5919.44, "total_tokens": 266105504}
{"current_steps": 3400, "total_steps": 5000, "loss": 0.1688, "lr": 2.323519088178299e-06, "epoch": 1.3599999999999999, "percentage": 68.0, "elapsed_time": "12:30:22", "remaining_time": "5:53:06", "throughput": 5919.05, "total_tokens": 266487728}
{"current_steps": 3405, "total_steps": 5000, "loss": 0.1658, "lr": 2.3102643600761445e-06, "epoch": 1.362, "percentage": 68.1, "elapsed_time": "12:31:10", "remaining_time": "5:51:52", "throughput": 5919.68, "total_tokens": 266804880}
{"current_steps": 3410, "total_steps": 5000, "loss": 0.1712, "lr": 2.2970361785788673e-06, "epoch": 1.3639999999999999, "percentage": 68.2, "elapsed_time": "12:31:47", "remaining_time": "5:50:32", "throughput": 5921.22, "total_tokens": 267089664}
{"current_steps": 3415, "total_steps": 5000, "loss": 0.1602, "lr": 2.2838346742432753e-06, "epoch": 1.366, "percentage": 68.3, "elapsed_time": "12:32:54", "remaining_time": "5:49:26", "throughput": 5921.37, "total_tokens": 267493472}
{"current_steps": 3420, "total_steps": 5000, "loss": 0.1424, "lr": 2.2706599773628906e-06, "epoch": 1.3679999999999999, "percentage": 68.4, "elapsed_time": "12:33:49", "remaining_time": "5:48:15", "throughput": 5920.91, "total_tokens": 267800368}
{"current_steps": 3425, "total_steps": 5000, "loss": 0.1604, "lr": 2.25751221796665e-06, "epoch": 1.37, "percentage": 68.5, "elapsed_time": "12:34:46", "remaining_time": "5:47:05", "throughput": 5921.43, "total_tokens": 268160336}
{"current_steps": 3430, "total_steps": 5000, "loss": 0.1704, "lr": 2.2443915258176283e-06, "epoch": 1.3719999999999999, "percentage": 68.6, "elapsed_time": "12:35:49", "remaining_time": "5:45:57", "throughput": 5921.4, "total_tokens": 268535248}
{"current_steps": 3435, "total_steps": 5000, "loss": 0.1633, "lr": 2.2312980304117656e-06, "epoch": 1.374, "percentage": 68.7, "elapsed_time": "12:37:02", "remaining_time": "5:44:54", "throughput": 5921.3, "total_tokens": 268962320}
{"current_steps": 3440, "total_steps": 5000, "loss": 0.1599, "lr": 2.2182318609765703e-06, "epoch": 1.376, "percentage": 68.8, "elapsed_time": "12:37:50", "remaining_time": "5:43:40", "throughput": 5922.0, "total_tokens": 269273584}
{"current_steps": 3445, "total_steps": 5000, "loss": 0.1588, "lr": 2.2051931464698636e-06, "epoch": 1.3780000000000001, "percentage": 68.9, "elapsed_time": "12:38:48", "remaining_time": "5:42:30", "throughput": 5922.02, "total_tokens": 269618864}
{"current_steps": 3450, "total_steps": 5000, "loss": 0.1642, "lr": 2.19218201557849e-06, "epoch": 1.38, "percentage": 69.0, "elapsed_time": "12:39:47", "remaining_time": "5:41:21", "throughput": 5922.62, "total_tokens": 270000000}
{"current_steps": 3455, "total_steps": 5000, "loss": 0.1585, "lr": 2.179198596717063e-06, "epoch": 1.3820000000000001, "percentage": 69.1, "elapsed_time": "12:40:31", "remaining_time": "5:40:05", "throughput": 5924.81, "total_tokens": 270358256}
{"current_steps": 3460, "total_steps": 5000, "loss": 0.1493, "lr": 2.1662430180266808e-06, "epoch": 1.384, "percentage": 69.2, "elapsed_time": "12:41:32", "remaining_time": "5:38:57", "throughput": 5925.5, "total_tokens": 270752928}
{"current_steps": 3465, "total_steps": 5000, "loss": 0.1592, "lr": 2.153315407373679e-06, "epoch": 1.3860000000000001, "percentage": 69.3, "elapsed_time": "12:42:28", "remaining_time": "5:37:46", "throughput": 5926.04, "total_tokens": 271107200}
{"current_steps": 3470, "total_steps": 5000, "loss": 0.1634, "lr": 2.1404158923483524e-06, "epoch": 1.388, "percentage": 69.4, "elapsed_time": "12:43:29", "remaining_time": "5:36:38", "throughput": 5925.26, "total_tokens": 271433216}
{"current_steps": 3475, "total_steps": 5000, "loss": 0.1663, "lr": 2.1275446002637063e-06, "epoch": 1.3900000000000001, "percentage": 69.5, "elapsed_time": "12:44:25", "remaining_time": "5:35:28", "throughput": 5926.05, "total_tokens": 271802272}
{"current_steps": 3480, "total_steps": 5000, "loss": 0.1663, "lr": 2.1147016581542e-06, "epoch": 1.392, "percentage": 69.6, "elapsed_time": "12:45:09", "remaining_time": "5:34:12", "throughput": 5927.46, "total_tokens": 272124656}
{"current_steps": 3485, "total_steps": 5000, "loss": 0.1606, "lr": 2.1018871927744844e-06, "epoch": 1.3940000000000001, "percentage": 69.7, "elapsed_time": "12:46:04", "remaining_time": "5:33:01", "throughput": 5929.0, "total_tokens": 272526576}
{"current_steps": 3490, "total_steps": 5000, "loss": 0.1777, "lr": 2.0891013305981615e-06, "epoch": 1.396, "percentage": 69.8, "elapsed_time": "12:47:18", "remaining_time": "5:31:59", "throughput": 5928.91, "total_tokens": 272960928}
{"current_steps": 3495, "total_steps": 5000, "loss": 0.159, "lr": 2.076344197816527e-06, "epoch": 1.3980000000000001, "percentage": 69.9, "elapsed_time": "12:48:26", "remaining_time": "5:30:54", "throughput": 5928.9, "total_tokens": 273359360}
{"current_steps": 3500, "total_steps": 5000, "loss": 0.1688, "lr": 2.0636159203373344e-06, "epoch": 1.4, "percentage": 70.0, "elapsed_time": "12:49:36", "remaining_time": "5:29:50", "throughput": 5928.86, "total_tokens": 273776336}
{"current_steps": 3505, "total_steps": 5000, "loss": 0.1531, "lr": 2.0509166237835398e-06, "epoch": 1.4020000000000001, "percentage": 70.1, "elapsed_time": "12:50:40", "remaining_time": "5:28:43", "throughput": 5929.34, "total_tokens": 274174848}
{"current_steps": 3510, "total_steps": 5000, "loss": 0.1608, "lr": 2.0382464334920774e-06, "epoch": 1.404, "percentage": 70.2, "elapsed_time": "12:51:52", "remaining_time": "5:27:39", "throughput": 5930.57, "total_tokens": 274657952}
{"current_steps": 3515, "total_steps": 5000, "loss": 0.15, "lr": 2.025605474512608e-06, "epoch": 1.4060000000000001, "percentage": 70.3, "elapsed_time": "12:52:53", "remaining_time": "5:26:31", "throughput": 5930.82, "total_tokens": 275033072}
{"current_steps": 3520, "total_steps": 5000, "loss": 0.1671, "lr": 2.0129938716062917e-06, "epoch": 1.408, "percentage": 70.4, "elapsed_time": "12:53:53", "remaining_time": "5:25:23", "throughput": 5930.24, "total_tokens": 275362944}
{"current_steps": 3525, "total_steps": 5000, "loss": 0.1481, "lr": 2.0004117492445614e-06, "epoch": 1.41, "percentage": 70.5, "elapsed_time": "12:55:10", "remaining_time": "5:24:21", "throughput": 5929.03, "total_tokens": 275762640}
{"current_steps": 3530, "total_steps": 5000, "loss": 0.1511, "lr": 1.9878592316078813e-06, "epoch": 1.412, "percentage": 70.6, "elapsed_time": "12:56:16", "remaining_time": "5:23:15", "throughput": 5929.49, "total_tokens": 276174128}
{"current_steps": 3535, "total_steps": 5000, "loss": 0.1509, "lr": 1.975336442584537e-06, "epoch": 1.414, "percentage": 70.7, "elapsed_time": "12:57:24", "remaining_time": "5:22:10", "throughput": 5929.26, "total_tokens": 276565680}
{"current_steps": 3540, "total_steps": 5000, "loss": 0.1595, "lr": 1.9628435057693963e-06, "epoch": 1.416, "percentage": 70.8, "elapsed_time": "12:58:34", "remaining_time": "5:21:06", "throughput": 5928.34, "total_tokens": 276941040}
{"current_steps": 3545, "total_steps": 5000, "loss": 0.1604, "lr": 1.9503805444627054e-06, "epoch": 1.418, "percentage": 70.9, "elapsed_time": "12:59:47", "remaining_time": "5:20:03", "throughput": 5928.91, "total_tokens": 277400160}
{"current_steps": 3550, "total_steps": 5000, "loss": 0.1483, "lr": 1.937947681668858e-06, "epoch": 1.42, "percentage": 71.0, "elapsed_time": "13:00:40", "remaining_time": "5:18:52", "throughput": 5929.42, "total_tokens": 277738800}
{"current_steps": 3555, "total_steps": 5000, "loss": 0.1545, "lr": 1.9255450400951937e-06, "epoch": 1.422, "percentage": 71.1, "elapsed_time": "13:01:37", "remaining_time": "5:17:42", "throughput": 5930.64, "total_tokens": 278133904}
{"current_steps": 3560, "total_steps": 5000, "loss": 0.1719, "lr": 1.913172742150774e-06, "epoch": 1.424, "percentage": 71.2, "elapsed_time": "13:02:49", "remaining_time": "5:16:38", "throughput": 5929.47, "total_tokens": 278502048}
{"current_steps": 3565, "total_steps": 5000, "loss": 0.1564, "lr": 1.900830909945189e-06, "epoch": 1.426, "percentage": 71.3, "elapsed_time": "13:04:06", "remaining_time": "5:15:37", "throughput": 5929.05, "total_tokens": 278939024}
{"current_steps": 3570, "total_steps": 5000, "loss": 0.1466, "lr": 1.8885196652873372e-06, "epoch": 1.428, "percentage": 71.4, "elapsed_time": "13:05:11", "remaining_time": "5:14:31", "throughput": 5927.77, "total_tokens": 279267216}
{"current_steps": 3575, "total_steps": 5000, "loss": 0.1859, "lr": 1.876239129684232e-06, "epoch": 1.43, "percentage": 71.5, "elapsed_time": "13:06:20", "remaining_time": "5:13:26", "throughput": 5928.32, "total_tokens": 279700784}
{"current_steps": 3580, "total_steps": 5000, "loss": 0.1595, "lr": 1.8639894243398055e-06, "epoch": 1.432, "percentage": 71.6, "elapsed_time": "13:07:24", "remaining_time": "5:12:19", "throughput": 5927.77, "total_tokens": 280056448}
{"current_steps": 3585, "total_steps": 5000, "loss": 0.1596, "lr": 1.8517706701536998e-06, "epoch": 1.434, "percentage": 71.7, "elapsed_time": "13:08:25", "remaining_time": "5:11:11", "throughput": 5927.75, "total_tokens": 280414336}
{"current_steps": 3590, "total_steps": 5000, "loss": 0.1472, "lr": 1.8395829877200904e-06, "epoch": 1.436, "percentage": 71.8, "elapsed_time": "13:09:30", "remaining_time": "5:10:05", "throughput": 5928.47, "total_tokens": 280832880}
{"current_steps": 3595, "total_steps": 5000, "loss": 0.1507, "lr": 1.8274264973264782e-06, "epoch": 1.438, "percentage": 71.9, "elapsed_time": "13:10:43", "remaining_time": "5:09:01", "throughput": 5927.7, "total_tokens": 281229968}
{"current_steps": 3600, "total_steps": 5000, "loss": 0.163, "lr": 1.8153013189525192e-06, "epoch": 1.44, "percentage": 72.0, "elapsed_time": "13:11:46", "remaining_time": "5:07:54", "throughput": 5927.95, "total_tokens": 281613376}
{"current_steps": 3605, "total_steps": 5000, "loss": 0.1731, "lr": 1.803207572268826e-06, "epoch": 1.442, "percentage": 72.1, "elapsed_time": "13:12:43", "remaining_time": "5:06:45", "throughput": 5929.6, "total_tokens": 282032944}
{"current_steps": 3610, "total_steps": 5000, "loss": 0.1618, "lr": 1.7911453766357983e-06, "epoch": 1.444, "percentage": 72.2, "elapsed_time": "13:13:46", "remaining_time": "5:05:38", "throughput": 5929.32, "total_tokens": 282389792}
{"current_steps": 3615, "total_steps": 5000, "loss": 0.1633, "lr": 1.779114851102437e-06, "epoch": 1.446, "percentage": 72.3, "elapsed_time": "13:14:55", "remaining_time": "5:04:33", "throughput": 5931.23, "total_tokens": 282890112}
{"current_steps": 3620, "total_steps": 5000, "loss": 0.1526, "lr": 1.767116114405169e-06, "epoch": 1.448, "percentage": 72.4, "elapsed_time": "13:16:02", "remaining_time": "5:03:27", "throughput": 5931.13, "total_tokens": 283283696}
{"current_steps": 3625, "total_steps": 5000, "loss": 0.1725, "lr": 1.7551492849666857e-06, "epoch": 1.45, "percentage": 72.5, "elapsed_time": "13:17:04", "remaining_time": "5:02:20", "throughput": 5931.86, "total_tokens": 283685808}
{"current_steps": 3630, "total_steps": 5000, "loss": 0.1691, "lr": 1.7432144808947587e-06, "epoch": 1.452, "percentage": 72.6, "elapsed_time": "13:18:22", "remaining_time": "5:01:18", "throughput": 5931.1, "total_tokens": 284112096}
{"current_steps": 3635, "total_steps": 5000, "loss": 0.1858, "lr": 1.7313118199810897e-06, "epoch": 1.454, "percentage": 72.7, "elapsed_time": "13:19:17", "remaining_time": "5:00:08", "throughput": 5931.55, "total_tokens": 284461312}
{"current_steps": 3640, "total_steps": 5000, "loss": 0.164, "lr": 1.719441419700133e-06, "epoch": 1.456, "percentage": 72.8, "elapsed_time": "13:20:29", "remaining_time": "4:59:04", "throughput": 5931.16, "total_tokens": 284868512}
{"current_steps": 3645, "total_steps": 5000, "loss": 0.1564, "lr": 1.7076033972079503e-06, "epoch": 1.458, "percentage": 72.9, "elapsed_time": "13:21:31", "remaining_time": "4:57:57", "throughput": 5930.05, "total_tokens": 285185056}
{"current_steps": 3650, "total_steps": 5000, "loss": 0.1632, "lr": 1.6957978693410414e-06, "epoch": 1.46, "percentage": 73.0, "elapsed_time": "13:22:29", "remaining_time": "4:56:48", "throughput": 5930.89, "total_tokens": 285571648}
{"current_steps": 3655, "total_steps": 5000, "loss": 0.1668, "lr": 1.6840249526152036e-06, "epoch": 1.462, "percentage": 73.1, "elapsed_time": "13:23:31", "remaining_time": "4:55:41", "throughput": 5931.87, "total_tokens": 285983264}
{"current_steps": 3660, "total_steps": 5000, "loss": 0.1591, "lr": 1.6722847632243699e-06, "epoch": 1.464, "percentage": 73.2, "elapsed_time": "13:24:48", "remaining_time": "4:54:39", "throughput": 5932.2, "total_tokens": 286456640}
{"current_steps": 3665, "total_steps": 5000, "loss": 0.1556, "lr": 1.6605774170394683e-06, "epoch": 1.466, "percentage": 73.3, "elapsed_time": "13:26:01", "remaining_time": "4:53:36", "throughput": 5932.53, "total_tokens": 286908176}
{"current_steps": 3670, "total_steps": 5000, "loss": 0.151, "lr": 1.6489030296072833e-06, "epoch": 1.468, "percentage": 73.4, "elapsed_time": "13:26:58", "remaining_time": "4:52:26", "throughput": 5933.51, "total_tokens": 287294160}
{"current_steps": 3675, "total_steps": 5000, "loss": 0.1758, "lr": 1.6372617161493014e-06, "epoch": 1.47, "percentage": 73.5, "elapsed_time": "13:28:14", "remaining_time": "4:51:24", "throughput": 5932.95, "total_tokens": 287716720}
{"current_steps": 3680, "total_steps": 5000, "loss": 0.1624, "lr": 1.6256535915605904e-06, "epoch": 1.472, "percentage": 73.6, "elapsed_time": "13:29:23", "remaining_time": "4:50:19", "throughput": 5933.48, "total_tokens": 288152368}
{"current_steps": 3685, "total_steps": 5000, "loss": 0.157, "lr": 1.6140787704086502e-06, "epoch": 1.474, "percentage": 73.7, "elapsed_time": "13:30:30", "remaining_time": "4:49:13", "throughput": 5934.07, "total_tokens": 288577920}
{"current_steps": 3690, "total_steps": 5000, "loss": 0.1628, "lr": 1.6025373669322963e-06, "epoch": 1.476, "percentage": 73.8, "elapsed_time": "13:31:16", "remaining_time": "4:48:00", "throughput": 5935.76, "total_tokens": 288934560}
{"current_steps": 3695, "total_steps": 5000, "loss": 0.1564, "lr": 1.591029495040518e-06, "epoch": 1.478, "percentage": 73.9, "elapsed_time": "13:32:25", "remaining_time": "4:46:55", "throughput": 5935.32, "total_tokens": 289320864}
{"current_steps": 3700, "total_steps": 5000, "loss": 0.1628, "lr": 1.5795552683113679e-06, "epoch": 1.48, "percentage": 74.0, "elapsed_time": "13:33:27", "remaining_time": "4:45:48", "throughput": 5935.68, "total_tokens": 289703696}
{"current_steps": 3705, "total_steps": 5000, "loss": 0.159, "lr": 1.5681147999908308e-06, "epoch": 1.482, "percentage": 74.1, "elapsed_time": "13:34:28", "remaining_time": "4:44:41", "throughput": 5936.39, "total_tokens": 290105360}
{"current_steps": 3710, "total_steps": 5000, "loss": 0.1742, "lr": 1.5567082029917074e-06, "epoch": 1.484, "percentage": 74.2, "elapsed_time": "13:35:38", "remaining_time": "4:43:36", "throughput": 5935.5, "total_tokens": 290475616}
{"current_steps": 3715, "total_steps": 5000, "loss": 0.1537, "lr": 1.5453355898925094e-06, "epoch": 1.486, "percentage": 74.3, "elapsed_time": "13:36:47", "remaining_time": "4:42:31", "throughput": 5935.84, "total_tokens": 290900160}
{"current_steps": 3720, "total_steps": 5000, "loss": 0.1732, "lr": 1.533997072936333e-06, "epoch": 1.488, "percentage": 74.4, "elapsed_time": "13:37:54", "remaining_time": "4:41:25", "throughput": 5936.16, "total_tokens": 291311376}
{"current_steps": 3725, "total_steps": 5000, "loss": 0.1657, "lr": 1.5226927640297663e-06, "epoch": 1.49, "percentage": 74.5, "elapsed_time": "13:39:03", "remaining_time": "4:40:21", "throughput": 5935.97, "total_tokens": 291717008}
{"current_steps": 3730, "total_steps": 5000, "loss": 0.1593, "lr": 1.511422774741771e-06, "epoch": 1.492, "percentage": 74.6, "elapsed_time": "13:40:13", "remaining_time": "4:39:16", "throughput": 5935.8, "total_tokens": 292120192}
{"current_steps": 3735, "total_steps": 5000, "loss": 0.149, "lr": 1.5001872163025954e-06, "epoch": 1.494, "percentage": 74.7, "elapsed_time": "13:41:26", "remaining_time": "4:38:12", "throughput": 5935.44, "total_tokens": 292536320}
{"current_steps": 3740, "total_steps": 5000, "loss": 0.1528, "lr": 1.4889861996026617e-06, "epoch": 1.496, "percentage": 74.8, "elapsed_time": "13:42:30", "remaining_time": "4:37:06", "throughput": 5936.08, "total_tokens": 292950032}
{"current_steps": 3745, "total_steps": 5000, "loss": 0.1563, "lr": 1.4778198351914853e-06, "epoch": 1.498, "percentage": 74.9, "elapsed_time": "13:43:34", "remaining_time": "4:35:59", "throughput": 5936.33, "total_tokens": 293339328}
{"current_steps": 3750, "total_steps": 5000, "loss": 0.1423, "lr": 1.4666882332765747e-06, "epoch": 1.5, "percentage": 75.0, "elapsed_time": "13:44:38", "remaining_time": "4:34:52", "throughput": 5935.56, "total_tokens": 293683568}
{"current_steps": 3755, "total_steps": 5000, "loss": 0.1538, "lr": 1.4555915037223438e-06, "epoch": 1.502, "percentage": 75.1, "elapsed_time": "13:45:36", "remaining_time": "4:33:44", "throughput": 5936.06, "total_tokens": 294050448}
{"current_steps": 3760, "total_steps": 5000, "loss": 0.1608, "lr": 1.4445297560490373e-06, "epoch": 1.504, "percentage": 75.2, "elapsed_time": "13:46:33", "remaining_time": "4:32:35", "throughput": 5936.8, "total_tokens": 294429296}
{"current_steps": 3765, "total_steps": 5000, "loss": 0.1671, "lr": 1.4335030994316357e-06, "epoch": 1.506, "percentage": 75.3, "elapsed_time": "13:47:43", "remaining_time": "4:31:30", "throughput": 5936.29, "total_tokens": 294819536}
{"current_steps": 3770, "total_steps": 5000, "loss": 0.1636, "lr": 1.4225116426987916e-06, "epoch": 1.508, "percentage": 75.4, "elapsed_time": "13:48:43", "remaining_time": "4:30:22", "throughput": 5936.22, "total_tokens": 295168448}
{"current_steps": 3775, "total_steps": 5000, "loss": 0.1775, "lr": 1.4115554943317416e-06, "epoch": 1.51, "percentage": 75.5, "elapsed_time": "13:49:49", "remaining_time": "4:29:16", "throughput": 5937.32, "total_tokens": 295616576}
{"current_steps": 3780, "total_steps": 5000, "loss": 0.1524, "lr": 1.4006347624632505e-06, "epoch": 1.512, "percentage": 75.6, "elapsed_time": "13:50:59", "remaining_time": "4:28:12", "throughput": 5937.34, "total_tokens": 296032560}
{"current_steps": 3785, "total_steps": 5000, "loss": 0.1603, "lr": 1.38974955487653e-06, "epoch": 1.514, "percentage": 75.7, "elapsed_time": "13:52:08", "remaining_time": "4:27:07", "throughput": 5937.55, "total_tokens": 296454512}
{"current_steps": 3790, "total_steps": 5000, "loss": 0.1649, "lr": 1.3788999790041867e-06, "epoch": 1.516, "percentage": 75.8, "elapsed_time": "13:53:11", "remaining_time": "4:26:00", "throughput": 5937.93, "total_tokens": 296844976}
{"current_steps": 3795, "total_steps": 5000, "loss": 0.1556, "lr": 1.368086141927154e-06, "epoch": 1.518, "percentage": 75.9, "elapsed_time": "13:54:12", "remaining_time": "4:24:52", "throughput": 5938.99, "total_tokens": 297262656}
{"current_steps": 3800, "total_steps": 5000, "loss": 0.1623, "lr": 1.3573081503736362e-06, "epoch": 1.52, "percentage": 76.0, "elapsed_time": "13:55:24", "remaining_time": "4:23:48", "throughput": 5938.55, "total_tokens": 297664192}
{"current_steps": 3805, "total_steps": 5000, "loss": 0.1721, "lr": 1.346566110718061e-06, "epoch": 1.522, "percentage": 76.1, "elapsed_time": "13:56:30", "remaining_time": "4:22:42", "throughput": 5938.22, "total_tokens": 298044432}
{"current_steps": 3810, "total_steps": 5000, "loss": 0.1573, "lr": 1.3358601289800211e-06, "epoch": 1.524, "percentage": 76.2, "elapsed_time": "13:57:34", "remaining_time": "4:21:36", "throughput": 5938.64, "total_tokens": 298445792}
{"current_steps": 3815, "total_steps": 5000, "loss": 0.1726, "lr": 1.3251903108232362e-06, "epoch": 1.526, "percentage": 76.3, "elapsed_time": "13:58:34", "remaining_time": "4:20:28", "throughput": 5938.59, "total_tokens": 298799232}
{"current_steps": 3820, "total_steps": 5000, "loss": 0.1556, "lr": 1.3145567615545013e-06, "epoch": 1.528, "percentage": 76.4, "elapsed_time": "13:59:50", "remaining_time": "4:19:25", "throughput": 5938.5, "total_tokens": 299246880}
{"current_steps": 3825, "total_steps": 5000, "loss": 0.1562, "lr": 1.3039595861226579e-06, "epoch": 1.53, "percentage": 76.5, "elapsed_time": "14:00:59", "remaining_time": "4:18:20", "throughput": 5938.36, "total_tokens": 299644480}
{"current_steps": 3830, "total_steps": 5000, "loss": 0.1392, "lr": 1.2933988891175458e-06, "epoch": 1.532, "percentage": 76.6, "elapsed_time": "14:01:46", "remaining_time": "4:17:08", "throughput": 5938.81, "total_tokens": 299946608}
{"current_steps": 3835, "total_steps": 5000, "loss": 0.1676, "lr": 1.2828747747689846e-06, "epoch": 1.534, "percentage": 76.7, "elapsed_time": "14:02:44", "remaining_time": "4:16:00", "throughput": 5938.83, "total_tokens": 300291984}
{"current_steps": 3840, "total_steps": 5000, "loss": 0.1464, "lr": 1.2723873469457304e-06, "epoch": 1.536, "percentage": 76.8, "elapsed_time": "14:03:43", "remaining_time": "4:14:52", "throughput": 5939.77, "total_tokens": 300690848}
{"current_steps": 3845, "total_steps": 5000, "loss": 0.1485, "lr": 1.2619367091544654e-06, "epoch": 1.538, "percentage": 76.9, "elapsed_time": "14:04:35", "remaining_time": "4:13:42", "throughput": 5939.66, "total_tokens": 300993296}
{"current_steps": 3850, "total_steps": 5000, "loss": 0.1625, "lr": 1.2515229645387639e-06, "epoch": 1.54, "percentage": 77.0, "elapsed_time": "14:05:36", "remaining_time": "4:12:35", "throughput": 5940.09, "total_tokens": 301381456}
{"current_steps": 3855, "total_steps": 5000, "loss": 0.1542, "lr": 1.2411462158780791e-06, "epoch": 1.542, "percentage": 77.1, "elapsed_time": "14:06:50", "remaining_time": "4:11:31", "throughput": 5940.35, "total_tokens": 301831440}
{"current_steps": 3860, "total_steps": 5000, "loss": 0.1687, "lr": 1.2308065655867346e-06, "epoch": 1.544, "percentage": 77.2, "elapsed_time": "14:07:35", "remaining_time": "4:10:19", "throughput": 5941.42, "total_tokens": 302152880}
{"current_steps": 3865, "total_steps": 5000, "loss": 0.1646, "lr": 1.2205041157129017e-06, "epoch": 1.546, "percentage": 77.3, "elapsed_time": "14:08:45", "remaining_time": "4:09:14", "throughput": 5941.47, "total_tokens": 302571152}
{"current_steps": 3870, "total_steps": 5000, "loss": 0.153, "lr": 1.2102389679376037e-06, "epoch": 1.548, "percentage": 77.4, "elapsed_time": "14:09:52", "remaining_time": "4:08:09", "throughput": 5941.98, "total_tokens": 302999424}
{"current_steps": 3875, "total_steps": 5000, "loss": 0.1668, "lr": 1.200011223573702e-06, "epoch": 1.55, "percentage": 77.5, "elapsed_time": "14:10:47", "remaining_time": "4:07:00", "throughput": 5942.16, "total_tokens": 303335568}
{"current_steps": 3880, "total_steps": 5000, "loss": 0.1389, "lr": 1.1898209835649083e-06, "epoch": 1.552, "percentage": 77.6, "elapsed_time": "14:12:05", "remaining_time": "4:05:58", "throughput": 5941.08, "total_tokens": 303743248}
{"current_steps": 3885, "total_steps": 5000, "loss": 0.1514, "lr": 1.1796683484847731e-06, "epoch": 1.554, "percentage": 77.7, "elapsed_time": "14:13:15", "remaining_time": "4:04:53", "throughput": 5940.14, "total_tokens": 304106352}
{"current_steps": 3890, "total_steps": 5000, "loss": 0.1616, "lr": 1.16955341853571e-06, "epoch": 1.556, "percentage": 77.8, "elapsed_time": "14:14:19", "remaining_time": "4:03:46", "throughput": 5940.0, "total_tokens": 304480976}
{"current_steps": 3895, "total_steps": 5000, "loss": 0.1694, "lr": 1.159476293547992e-06, "epoch": 1.558, "percentage": 77.9, "elapsed_time": "14:15:30", "remaining_time": "4:02:42", "throughput": 5941.06, "total_tokens": 304955440}
{"current_steps": 3900, "total_steps": 5000, "loss": 0.1439, "lr": 1.149437072978773e-06, "epoch": 1.56, "percentage": 78.0, "elapsed_time": "14:16:44", "remaining_time": "4:01:38", "throughput": 5940.54, "total_tokens": 305368592}
{"current_steps": 3905, "total_steps": 5000, "loss": 0.1629, "lr": 1.1394358559111101e-06, "epoch": 1.562, "percentage": 78.1, "elapsed_time": "14:17:33", "remaining_time": "4:00:28", "throughput": 5940.8, "total_tokens": 305674576}
{"current_steps": 3910, "total_steps": 5000, "loss": 0.1417, "lr": 1.1294727410529754e-06, "epoch": 1.564, "percentage": 78.2, "elapsed_time": "14:18:28", "remaining_time": "3:59:19", "throughput": 5941.76, "total_tokens": 306050064}
{"current_steps": 3915, "total_steps": 5000, "loss": 0.1683, "lr": 1.1195478267362924e-06, "epoch": 1.5659999999999998, "percentage": 78.3, "elapsed_time": "14:19:36", "remaining_time": "3:58:13", "throughput": 5941.47, "total_tokens": 306442352}
{"current_steps": 3920, "total_steps": 5000, "loss": 0.1539, "lr": 1.109661210915956e-06, "epoch": 1.568, "percentage": 78.4, "elapsed_time": "14:20:48", "remaining_time": "3:57:09", "throughput": 5941.58, "total_tokens": 306873936}
{"current_steps": 3925, "total_steps": 5000, "loss": 0.1469, "lr": 1.0998129911688766e-06, "epoch": 1.5699999999999998, "percentage": 78.5, "elapsed_time": "14:21:52", "remaining_time": "3:56:03", "throughput": 5941.2, "total_tokens": 307235072}
{"current_steps": 3930, "total_steps": 5000, "loss": 0.1545, "lr": 1.090003264693003e-06, "epoch": 1.572, "percentage": 78.6, "elapsed_time": "14:23:07", "remaining_time": "3:54:59", "throughput": 5939.98, "total_tokens": 307618096}
{"current_steps": 3935, "total_steps": 5000, "loss": 0.171, "lr": 1.0802321283063794e-06, "epoch": 1.5739999999999998, "percentage": 78.7, "elapsed_time": "14:24:19", "remaining_time": "3:53:55", "throughput": 5938.88, "total_tokens": 307988144}
{"current_steps": 3940, "total_steps": 5000, "loss": 0.1768, "lr": 1.0704996784461753e-06, "epoch": 1.576, "percentage": 78.8, "elapsed_time": "14:25:29", "remaining_time": "3:52:50", "throughput": 5938.21, "total_tokens": 308369536}
{"current_steps": 3945, "total_steps": 5000, "loss": 0.165, "lr": 1.0608060111677409e-06, "epoch": 1.5779999999999998, "percentage": 78.9, "elapsed_time": "14:26:35", "remaining_time": "3:51:45", "throughput": 5938.02, "total_tokens": 308753040}
{"current_steps": 3950, "total_steps": 5000, "loss": 0.1595, "lr": 1.0511512221436581e-06, "epoch": 1.58, "percentage": 79.0, "elapsed_time": "14:27:24", "remaining_time": "3:50:34", "throughput": 5938.28, "total_tokens": 309055504}
{"current_steps": 3955, "total_steps": 5000, "loss": 0.1424, "lr": 1.0415354066627993e-06, "epoch": 1.5819999999999999, "percentage": 79.1, "elapsed_time": "14:28:31", "remaining_time": "3:49:28", "throughput": 5938.31, "total_tokens": 309452224}
{"current_steps": 3960, "total_steps": 5000, "loss": 0.1516, "lr": 1.03195865962938e-06, "epoch": 1.584, "percentage": 79.2, "elapsed_time": "14:29:25", "remaining_time": "3:48:20", "throughput": 5938.95, "total_tokens": 309809200}
{"current_steps": 3965, "total_steps": 5000, "loss": 0.162, "lr": 1.0224210755620257e-06, "epoch": 1.5859999999999999, "percentage": 79.3, "elapsed_time": "14:30:38", "remaining_time": "3:47:15", "throughput": 5939.23, "total_tokens": 310253648}
{"current_steps": 3970, "total_steps": 5000, "loss": 0.1585, "lr": 1.0129227485928432e-06, "epoch": 1.588, "percentage": 79.4, "elapsed_time": "14:31:42", "remaining_time": "3:46:09", "throughput": 5940.4, "total_tokens": 310700400}
{"current_steps": 3975, "total_steps": 5000, "loss": 0.1463, "lr": 1.0034637724664832e-06, "epoch": 1.5899999999999999, "percentage": 79.5, "elapsed_time": "14:32:54", "remaining_time": "3:45:05", "throughput": 5939.9, "total_tokens": 311100192}
{"current_steps": 3980, "total_steps": 5000, "loss": 0.1671, "lr": 9.940442405392226e-07, "epoch": 1.592, "percentage": 79.6, "elapsed_time": "14:34:00", "remaining_time": "3:43:59", "throughput": 5940.36, "total_tokens": 311518048}
{"current_steps": 3985, "total_steps": 5000, "loss": 0.159, "lr": 9.84664245778037e-07, "epoch": 1.5939999999999999, "percentage": 79.7, "elapsed_time": "14:34:51", "remaining_time": "3:42:49", "throughput": 5940.4, "total_tokens": 311819200}
{"current_steps": 3990, "total_steps": 5000, "loss": 0.1586, "lr": 9.753238807596903e-07, "epoch": 1.596, "percentage": 79.8, "elapsed_time": "14:35:56", "remaining_time": "3:41:43", "throughput": 5940.3, "total_tokens": 312203520}
{"current_steps": 3995, "total_steps": 5000, "loss": 0.152, "lr": 9.66023237669812e-07, "epoch": 1.5979999999999999, "percentage": 79.9, "elapsed_time": "14:36:48", "remaining_time": "3:40:34", "throughput": 5940.29, "total_tokens": 312507584}
{"current_steps": 4000, "total_steps": 5000, "loss": 0.139, "lr": 9.567624083019966e-07, "epoch": 1.6, "percentage": 80.0, "elapsed_time": "14:38:05", "remaining_time": "3:39:31", "throughput": 5940.69, "total_tokens": 312985888}
{"current_steps": 4005, "total_steps": 5000, "loss": 0.1412, "lr": 9.475414840568903e-07, "epoch": 1.6019999999999999, "percentage": 80.1, "elapsed_time": "14:39:16", "remaining_time": "3:38:26", "throughput": 5940.53, "total_tokens": 313402192}
{"current_steps": 4010, "total_steps": 5000, "loss": 0.1521, "lr": 9.383605559412911e-07, "epoch": 1.604, "percentage": 80.2, "elapsed_time": "14:40:34", "remaining_time": "3:37:24", "throughput": 5941.0, "total_tokens": 313892192}
{"current_steps": 4015, "total_steps": 5000, "loss": 0.1414, "lr": 9.29219714567256e-07, "epoch": 1.6059999999999999, "percentage": 80.3, "elapsed_time": "14:41:53", "remaining_time": "3:36:21", "throughput": 5940.34, "total_tokens": 314322864}
{"current_steps": 4020, "total_steps": 5000, "loss": 0.1489, "lr": 9.201190501511964e-07, "epoch": 1.608, "percentage": 80.4, "elapsed_time": "14:43:05", "remaining_time": "3:35:16", "throughput": 5939.87, "total_tokens": 314726832}
{"current_steps": 4025, "total_steps": 5000, "loss": 0.1555, "lr": 9.110586525129988e-07, "epoch": 1.6099999999999999, "percentage": 80.5, "elapsed_time": "14:44:17", "remaining_time": "3:34:12", "throughput": 5940.28, "total_tokens": 315177056}
{"current_steps": 4030, "total_steps": 5000, "loss": 0.1598, "lr": 9.020386110751267e-07, "epoch": 1.612, "percentage": 80.6, "elapsed_time": "14:45:18", "remaining_time": "3:33:05", "throughput": 5940.57, "total_tokens": 315552336}
{"current_steps": 4035, "total_steps": 5000, "loss": 0.1819, "lr": 8.930590148617513e-07, "epoch": 1.6139999999999999, "percentage": 80.7, "elapsed_time": "14:46:24", "remaining_time": "3:31:59", "throughput": 5940.76, "total_tokens": 315957232}
{"current_steps": 4040, "total_steps": 5000, "loss": 0.1531, "lr": 8.841199524978583e-07, "epoch": 1.616, "percentage": 80.8, "elapsed_time": "14:47:31", "remaining_time": "3:30:53", "throughput": 5940.04, "total_tokens": 316314048}
{"current_steps": 4045, "total_steps": 5000, "loss": 0.1489, "lr": 8.752215122083874e-07, "epoch": 1.6179999999999999, "percentage": 80.9, "elapsed_time": "14:48:33", "remaining_time": "3:29:47", "throughput": 5940.96, "total_tokens": 316735184}
{"current_steps": 4050, "total_steps": 5000, "loss": 0.156, "lr": 8.663637818173504e-07, "epoch": 1.62, "percentage": 81.0, "elapsed_time": "14:49:45", "remaining_time": "3:28:42", "throughput": 5941.75, "total_tokens": 317204928}
{"current_steps": 4055, "total_steps": 5000, "loss": 0.173, "lr": 8.575468487469696e-07, "epoch": 1.6219999999999999, "percentage": 81.1, "elapsed_time": "14:50:53", "remaining_time": "3:27:37", "throughput": 5941.14, "total_tokens": 317577008}
{"current_steps": 4060, "total_steps": 5000, "loss": 0.1648, "lr": 8.487708000168166e-07, "epoch": 1.624, "percentage": 81.2, "elapsed_time": "14:52:09", "remaining_time": "3:26:33", "throughput": 5940.72, "total_tokens": 318002288}
{"current_steps": 4065, "total_steps": 5000, "loss": 0.1659, "lr": 8.400357222429473e-07, "epoch": 1.626, "percentage": 81.3, "elapsed_time": "14:53:10", "remaining_time": "3:25:26", "throughput": 5941.71, "total_tokens": 318419952}
{"current_steps": 4070, "total_steps": 5000, "loss": 0.1496, "lr": 8.313417016370557e-07, "epoch": 1.6280000000000001, "percentage": 81.4, "elapsed_time": "14:53:52", "remaining_time": "3:24:15", "throughput": 5942.66, "total_tokens": 318719648}
{"current_steps": 4075, "total_steps": 5000, "loss": 0.1544, "lr": 8.226888240056114e-07, "epoch": 1.63, "percentage": 81.5, "elapsed_time": "14:55:07", "remaining_time": "3:23:11", "throughput": 5942.31, "total_tokens": 319146480}
{"current_steps": 4080, "total_steps": 5000, "loss": 0.1534, "lr": 8.140771747490273e-07, "epoch": 1.6320000000000001, "percentage": 81.6, "elapsed_time": "14:56:12", "remaining_time": "3:22:05", "throughput": 5942.33, "total_tokens": 319534576}
{"current_steps": 4085, "total_steps": 5000, "loss": 0.1744, "lr": 8.055068388608011e-07, "epoch": 1.634, "percentage": 81.7, "elapsed_time": "14:57:17", "remaining_time": "3:20:59", "throughput": 5942.51, "total_tokens": 319929424}
{"current_steps": 4090, "total_steps": 5000, "loss": 0.1493, "lr": 7.969779009266915e-07, "epoch": 1.6360000000000001, "percentage": 81.8, "elapsed_time": "14:58:29", "remaining_time": "3:19:54", "throughput": 5942.67, "total_tokens": 320369280}
{"current_steps": 4095, "total_steps": 5000, "loss": 0.1599, "lr": 7.884904451238712e-07, "epoch": 1.638, "percentage": 81.9, "elapsed_time": "14:59:20", "remaining_time": "3:18:45", "throughput": 5943.33, "total_tokens": 320707392}
{"current_steps": 4100, "total_steps": 5000, "loss": 0.1556, "lr": 7.800445552201014e-07, "epoch": 1.6400000000000001, "percentage": 82.0, "elapsed_time": "15:00:32", "remaining_time": "3:17:40", "throughput": 5942.63, "total_tokens": 321094592}
{"current_steps": 4105, "total_steps": 5000, "loss": 0.1519, "lr": 7.716403145729073e-07, "epoch": 1.642, "percentage": 82.1, "elapsed_time": "15:01:40", "remaining_time": "3:16:35", "throughput": 5942.39, "total_tokens": 321483936}
{"current_steps": 4110, "total_steps": 5000, "loss": 0.1624, "lr": 7.632778061287494e-07, "epoch": 1.6440000000000001, "percentage": 82.2, "elapsed_time": "15:02:24", "remaining_time": "3:15:24", "throughput": 5943.44, "total_tokens": 321804816}
{"current_steps": 4115, "total_steps": 5000, "loss": 0.1407, "lr": 7.549571124222127e-07, "epoch": 1.646, "percentage": 82.3, "elapsed_time": "15:03:31", "remaining_time": "3:14:19", "throughput": 5943.09, "total_tokens": 322181776}
{"current_steps": 4120, "total_steps": 5000, "loss": 0.1509, "lr": 7.466783155751816e-07, "epoch": 1.6480000000000001, "percentage": 82.4, "elapsed_time": "15:04:25", "remaining_time": "3:13:10", "throughput": 5944.24, "total_tokens": 322569200}
{"current_steps": 4125, "total_steps": 5000, "loss": 0.1619, "lr": 7.384414972960419e-07, "epoch": 1.65, "percentage": 82.5, "elapsed_time": "15:05:41", "remaining_time": "3:12:07", "throughput": 5944.0, "total_tokens": 323008496}
{"current_steps": 4130, "total_steps": 5000, "loss": 0.1539, "lr": 7.302467388788614e-07, "epoch": 1.6520000000000001, "percentage": 82.6, "elapsed_time": "15:06:59", "remaining_time": "3:11:03", "throughput": 5943.17, "total_tokens": 323424624}
{"current_steps": 4135, "total_steps": 5000, "loss": 0.1369, "lr": 7.220941212026005e-07, "epoch": 1.654, "percentage": 82.7, "elapsed_time": "15:08:11", "remaining_time": "3:09:59", "throughput": 5942.59, "total_tokens": 323819312}
{"current_steps": 4140, "total_steps": 5000, "loss": 0.1485, "lr": 7.139837247303027e-07, "epoch": 1.6560000000000001, "percentage": 82.8, "elapsed_time": "15:09:15", "remaining_time": "3:08:52", "throughput": 5942.07, "total_tokens": 324175520}
{"current_steps": 4145, "total_steps": 5000, "loss": 0.1655, "lr": 7.059156295083064e-07, "epoch": 1.658, "percentage": 82.9, "elapsed_time": "15:10:27", "remaining_time": "3:07:48", "throughput": 5942.36, "total_tokens": 324614832}
{"current_steps": 4150, "total_steps": 5000, "loss": 0.1412, "lr": 6.978899151654556e-07, "epoch": 1.6600000000000001, "percentage": 83.0, "elapsed_time": "15:11:25", "remaining_time": "3:06:40", "throughput": 5942.15, "total_tokens": 324951920}
{"current_steps": 4155, "total_steps": 5000, "loss": 0.1551, "lr": 6.89906660912309e-07, "epoch": 1.662, "percentage": 83.1, "elapsed_time": "15:12:21", "remaining_time": "3:05:32", "throughput": 5942.48, "total_tokens": 325298624}
{"current_steps": 4160, "total_steps": 5000, "loss": 0.1623, "lr": 6.819659455403654e-07, "epoch": 1.6640000000000001, "percentage": 83.2, "elapsed_time": "15:13:30", "remaining_time": "3:04:27", "throughput": 5941.63, "total_tokens": 325665392}
{"current_steps": 4165, "total_steps": 5000, "loss": 0.1769, "lr": 6.74067847421277e-07, "epoch": 1.666, "percentage": 83.3, "elapsed_time": "15:14:37", "remaining_time": "3:03:21", "throughput": 5941.82, "total_tokens": 326069408}
{"current_steps": 4170, "total_steps": 5000, "loss": 0.1513, "lr": 6.662124445060863e-07, "epoch": 1.6680000000000001, "percentage": 83.4, "elapsed_time": "15:15:43", "remaining_time": "3:02:15", "throughput": 5942.53, "total_tokens": 326501792}
{"current_steps": 4175, "total_steps": 5000, "loss": 0.1415, "lr": 6.583998143244463e-07, "epoch": 1.67, "percentage": 83.5, "elapsed_time": "15:16:38", "remaining_time": "3:01:08", "throughput": 5943.56, "total_tokens": 326889952}
{"current_steps": 4180, "total_steps": 5000, "loss": 0.1585, "lr": 6.506300339838656e-07, "epoch": 1.6720000000000002, "percentage": 83.6, "elapsed_time": "15:17:53", "remaining_time": "3:00:03", "throughput": 5943.24, "total_tokens": 327314752}
{"current_steps": 4185, "total_steps": 5000, "loss": 0.1578, "lr": 6.429031801689362e-07, "epoch": 1.674, "percentage": 83.7, "elapsed_time": "15:19:06", "remaining_time": "2:58:59", "throughput": 5943.25, "total_tokens": 327750640}
{"current_steps": 4190, "total_steps": 5000, "loss": 0.1551, "lr": 6.352193291405884e-07, "epoch": 1.6760000000000002, "percentage": 83.8, "elapsed_time": "15:20:18", "remaining_time": "2:57:54", "throughput": 5943.66, "total_tokens": 328201488}
{"current_steps": 4195, "total_steps": 5000, "loss": 0.1493, "lr": 6.275785567353293e-07, "epoch": 1.678, "percentage": 83.9, "elapsed_time": "15:21:25", "remaining_time": "2:56:49", "throughput": 5943.57, "total_tokens": 328593632}
{"current_steps": 4200, "total_steps": 5000, "loss": 0.1413, "lr": 6.199809383644956e-07, "epoch": 1.6800000000000002, "percentage": 84.0, "elapsed_time": "15:22:30", "remaining_time": "2:55:42", "throughput": 5943.46, "total_tokens": 328971728}
{"current_steps": 4205, "total_steps": 5000, "loss": 0.1523, "lr": 6.124265490135161e-07, "epoch": 1.682, "percentage": 84.1, "elapsed_time": "15:23:40", "remaining_time": "2:54:37", "throughput": 5942.15, "total_tokens": 329316976}
{"current_steps": 4210, "total_steps": 5000, "loss": 0.1524, "lr": 6.049154632411625e-07, "epoch": 1.6840000000000002, "percentage": 84.2, "elapsed_time": "15:24:58", "remaining_time": "2:53:34", "throughput": 5940.89, "total_tokens": 329709072}
{"current_steps": 4215, "total_steps": 5000, "loss": 0.1547, "lr": 5.974477551788194e-07, "epoch": 1.686, "percentage": 84.3, "elapsed_time": "15:26:09", "remaining_time": "2:52:29", "throughput": 5940.39, "total_tokens": 330101328}
{"current_steps": 4220, "total_steps": 5000, "loss": 0.1523, "lr": 5.900234985297498e-07, "epoch": 1.688, "percentage": 84.4, "elapsed_time": "15:27:17", "remaining_time": "2:51:23", "throughput": 5940.51, "total_tokens": 330512448}
{"current_steps": 4225, "total_steps": 5000, "loss": 0.1618, "lr": 5.826427665683715e-07, "epoch": 1.69, "percentage": 84.5, "elapsed_time": "15:28:23", "remaining_time": "2:50:17", "throughput": 5940.39, "total_tokens": 330900992}
{"current_steps": 4230, "total_steps": 5000, "loss": 0.1562, "lr": 5.753056321395267e-07, "epoch": 1.692, "percentage": 84.6, "elapsed_time": "15:29:32", "remaining_time": "2:49:12", "throughput": 5939.78, "total_tokens": 331273936}
{"current_steps": 4235, "total_steps": 5000, "loss": 0.1613, "lr": 5.680121676577721e-07, "epoch": 1.694, "percentage": 84.7, "elapsed_time": "15:30:38", "remaining_time": "2:48:06", "throughput": 5939.96, "total_tokens": 331678640}
{"current_steps": 4240, "total_steps": 5000, "loss": 0.1549, "lr": 5.607624451066568e-07, "epoch": 1.696, "percentage": 84.8, "elapsed_time": "15:31:53", "remaining_time": "2:47:02", "throughput": 5938.69, "total_tokens": 332056128}
{"current_steps": 4245, "total_steps": 5000, "loss": 0.1523, "lr": 5.535565360380146e-07, "epoch": 1.698, "percentage": 84.9, "elapsed_time": "15:33:06", "remaining_time": "2:45:57", "throughput": 5938.79, "total_tokens": 332493344}
{"current_steps": 4250, "total_steps": 5000, "loss": 0.158, "lr": 5.46394511571261e-07, "epoch": 1.7, "percentage": 85.0, "elapsed_time": "15:34:22", "remaining_time": "2:44:53", "throughput": 5938.08, "total_tokens": 332902464}
{"current_steps": 4255, "total_steps": 5000, "loss": 0.1306, "lr": 5.392764423926844e-07, "epoch": 1.702, "percentage": 85.1, "elapsed_time": "15:35:27", "remaining_time": "2:43:47", "throughput": 5937.22, "total_tokens": 333240368}
{"current_steps": 4260, "total_steps": 5000, "loss": 0.1574, "lr": 5.322023987547547e-07, "epoch": 1.704, "percentage": 85.2, "elapsed_time": "15:36:23", "remaining_time": "2:42:39", "throughput": 5938.08, "total_tokens": 333619536}
{"current_steps": 4265, "total_steps": 5000, "loss": 0.1523, "lr": 5.251724504754258e-07, "epoch": 1.706, "percentage": 85.3, "elapsed_time": "15:37:32", "remaining_time": "2:41:34", "throughput": 5938.07, "total_tokens": 334030848}
{"current_steps": 4270, "total_steps": 5000, "loss": 0.1614, "lr": 5.181866669374507e-07, "epoch": 1.708, "percentage": 85.4, "elapsed_time": "15:38:51", "remaining_time": "2:40:30", "throughput": 5938.55, "total_tokens": 334524720}
{"current_steps": 4275, "total_steps": 5000, "loss": 0.1472, "lr": 5.112451170876903e-07, "epoch": 1.71, "percentage": 85.5, "elapsed_time": "15:40:09", "remaining_time": "2:39:26", "throughput": 5938.78, "total_tokens": 335002128}
{"current_steps": 4280, "total_steps": 5000, "loss": 0.1363, "lr": 5.043478694364423e-07, "epoch": 1.712, "percentage": 85.6, "elapsed_time": "15:41:12", "remaining_time": "2:38:19", "throughput": 5938.57, "total_tokens": 335363280}
{"current_steps": 4285, "total_steps": 5000, "loss": 0.1498, "lr": 4.97494992056754e-07, "epoch": 1.714, "percentage": 85.7, "elapsed_time": "15:42:09", "remaining_time": "2:37:12", "throughput": 5939.24, "total_tokens": 335742592}
{"current_steps": 4290, "total_steps": 5000, "loss": 0.1634, "lr": 4.90686552583759e-07, "epoch": 1.716, "percentage": 85.8, "elapsed_time": "15:43:20", "remaining_time": "2:36:07", "throughput": 5938.81, "total_tokens": 336140320}
{"current_steps": 4295, "total_steps": 5000, "loss": 0.1917, "lr": 4.839226182140072e-07, "epoch": 1.718, "percentage": 85.9, "elapsed_time": "15:44:14", "remaining_time": "2:34:59", "throughput": 5939.63, "total_tokens": 336507328}
{"current_steps": 4300, "total_steps": 5000, "loss": 0.1577, "lr": 4.772032557047984e-07, "epoch": 1.72, "percentage": 86.0, "elapsed_time": "15:45:08", "remaining_time": "2:33:51", "throughput": 5939.69, "total_tokens": 336833552}
{"current_steps": 4305, "total_steps": 5000, "loss": 0.1688, "lr": 4.705285313735297e-07, "epoch": 1.722, "percentage": 86.1, "elapsed_time": "15:46:20", "remaining_time": "2:32:46", "throughput": 5939.4, "total_tokens": 337243936}
{"current_steps": 4310, "total_steps": 5000, "loss": 0.1492, "lr": 4.63898511097034e-07, "epoch": 1.724, "percentage": 86.2, "elapsed_time": "15:47:08", "remaining_time": "2:31:37", "throughput": 5940.26, "total_tokens": 337576960}
{"current_steps": 4315, "total_steps": 5000, "loss": 0.1489, "lr": 4.5731326031093645e-07, "epoch": 1.726, "percentage": 86.3, "elapsed_time": "15:48:14", "remaining_time": "2:30:31", "throughput": 5940.92, "total_tokens": 338007872}
{"current_steps": 4320, "total_steps": 5000, "loss": 0.1482, "lr": 4.5077284400900147e-07, "epoch": 1.728, "percentage": 86.4, "elapsed_time": "15:49:15", "remaining_time": "2:29:25", "throughput": 5940.83, "total_tokens": 338365776}
{"current_steps": 4325, "total_steps": 5000, "loss": 0.1511, "lr": 4.4427732674250045e-07, "epoch": 1.73, "percentage": 86.5, "elapsed_time": "15:50:14", "remaining_time": "2:28:18", "throughput": 5940.92, "total_tokens": 338719792}
{"current_steps": 4330, "total_steps": 5000, "loss": 0.1515, "lr": 4.378267726195645e-07, "epoch": 1.732, "percentage": 86.6, "elapsed_time": "15:51:25", "remaining_time": "2:27:13", "throughput": 5942.37, "total_tokens": 339222768}
{"current_steps": 4335, "total_steps": 5000, "loss": 0.1491, "lr": 4.31421245304558e-07, "epoch": 1.734, "percentage": 86.7, "elapsed_time": "15:52:34", "remaining_time": "2:26:07", "throughput": 5942.16, "total_tokens": 339620128}
{"current_steps": 4340, "total_steps": 5000, "loss": 0.1569, "lr": 4.250608080174512e-07, "epoch": 1.736, "percentage": 86.8, "elapsed_time": "15:53:36", "remaining_time": "2:25:01", "throughput": 5943.32, "total_tokens": 340054832}
{"current_steps": 4345, "total_steps": 5000, "loss": 0.1376, "lr": 4.1874552353319107e-07, "epoch": 1.738, "percentage": 86.9, "elapsed_time": "15:54:35", "remaining_time": "2:23:54", "throughput": 5943.48, "total_tokens": 340418352}
{"current_steps": 4350, "total_steps": 5000, "loss": 0.1614, "lr": 4.1247545418108715e-07, "epoch": 1.74, "percentage": 87.0, "elapsed_time": "15:55:25", "remaining_time": "2:22:45", "throughput": 5944.58, "total_tokens": 340772864}
{"current_steps": 4355, "total_steps": 5000, "loss": 0.1438, "lr": 4.062506618441908e-07, "epoch": 1.742, "percentage": 87.1, "elapsed_time": "15:56:20", "remaining_time": "2:21:38", "throughput": 5944.98, "total_tokens": 341127504}
{"current_steps": 4360, "total_steps": 5000, "loss": 0.1392, "lr": 4.000712079586916e-07, "epoch": 1.744, "percentage": 87.2, "elapsed_time": "15:57:32", "remaining_time": "2:20:33", "throughput": 5943.88, "total_tokens": 341489712}
{"current_steps": 4365, "total_steps": 5000, "loss": 0.1662, "lr": 3.9393715351330243e-07, "epoch": 1.746, "percentage": 87.3, "elapsed_time": "15:58:42", "remaining_time": "2:19:28", "throughput": 5943.5, "total_tokens": 341885936}
{"current_steps": 4370, "total_steps": 5000, "loss": 0.1566, "lr": 3.8784855904866637e-07, "epoch": 1.748, "percentage": 87.4, "elapsed_time": "15:59:52", "remaining_time": "2:18:22", "throughput": 5943.08, "total_tokens": 342278816}
{"current_steps": 4375, "total_steps": 5000, "loss": 0.1537, "lr": 3.818054846567515e-07, "epoch": 1.75, "percentage": 87.5, "elapsed_time": "16:00:58", "remaining_time": "2:17:16", "throughput": 5942.37, "total_tokens": 342626672}
{"current_steps": 4380, "total_steps": 5000, "loss": 0.1457, "lr": 3.758079899802619e-07, "epoch": 1.752, "percentage": 87.6, "elapsed_time": "16:02:10", "remaining_time": "2:16:11", "throughput": 5941.48, "total_tokens": 343003552}
{"current_steps": 4385, "total_steps": 5000, "loss": 0.1544, "lr": 3.698561342120499e-07, "epoch": 1.754, "percentage": 87.7, "elapsed_time": "16:03:16", "remaining_time": "2:15:05", "throughput": 5941.74, "total_tokens": 343410656}
{"current_steps": 4390, "total_steps": 5000, "loss": 0.1624, "lr": 3.6394997609452755e-07, "epoch": 1.756, "percentage": 87.8, "elapsed_time": "16:04:19", "remaining_time": "2:13:59", "throughput": 5942.65, "total_tokens": 343837312}
{"current_steps": 4395, "total_steps": 5000, "loss": 0.15, "lr": 3.5808957391909315e-07, "epoch": 1.758, "percentage": 87.9, "elapsed_time": "16:05:14", "remaining_time": "2:12:52", "throughput": 5942.54, "total_tokens": 344159872}
{"current_steps": 4400, "total_steps": 5000, "loss": 0.1628, "lr": 3.5227498552554805e-07, "epoch": 1.76, "percentage": 88.0, "elapsed_time": "16:06:08", "remaining_time": "2:11:44", "throughput": 5943.68, "total_tokens": 344547168}
{"current_steps": 4405, "total_steps": 5000, "loss": 0.1535, "lr": 3.465062683015341e-07, "epoch": 1.762, "percentage": 88.1, "elapsed_time": "16:06:59", "remaining_time": "2:10:36", "throughput": 5944.08, "total_tokens": 344875120}
{"current_steps": 4410, "total_steps": 5000, "loss": 0.1603, "lr": 3.407834791819603e-07, "epoch": 1.764, "percentage": 88.2, "elapsed_time": "16:08:17", "remaining_time": "2:09:32", "throughput": 5943.37, "total_tokens": 345297504}
{"current_steps": 4415, "total_steps": 5000, "loss": 0.1461, "lr": 3.351066746484455e-07, "epoch": 1.766, "percentage": 88.3, "elapsed_time": "16:09:31", "remaining_time": "2:08:27", "throughput": 5943.51, "total_tokens": 345745392}
{"current_steps": 4420, "total_steps": 5000, "loss": 0.1437, "lr": 3.294759107287582e-07, "epoch": 1.768, "percentage": 88.4, "elapsed_time": "16:10:47", "remaining_time": "2:07:23", "throughput": 5943.2, "total_tokens": 346174448}
{"current_steps": 4425, "total_steps": 5000, "loss": 0.1532, "lr": 3.2389124299626483e-07, "epoch": 1.77, "percentage": 88.5, "elapsed_time": "16:11:50", "remaining_time": "2:06:17", "throughput": 5942.83, "total_tokens": 346527968}
{"current_steps": 4430, "total_steps": 5000, "loss": 0.1495, "lr": 3.18352726569382e-07, "epoch": 1.772, "percentage": 88.6, "elapsed_time": "16:12:49", "remaining_time": "2:05:10", "throughput": 5943.31, "total_tokens": 346910736}
{"current_steps": 4435, "total_steps": 5000, "loss": 0.1711, "lr": 3.128604161110299e-07, "epoch": 1.774, "percentage": 88.7, "elapsed_time": "16:14:04", "remaining_time": "2:04:05", "throughput": 5943.28, "total_tokens": 347352048}
{"current_steps": 4440, "total_steps": 5000, "loss": 0.1553, "lr": 3.07414365828097e-07, "epoch": 1.776, "percentage": 88.8, "elapsed_time": "16:15:19", "remaining_time": "2:03:00", "throughput": 5942.41, "total_tokens": 347744080}
{"current_steps": 4445, "total_steps": 5000, "loss": 0.1396, "lr": 3.0201462947089865e-07, "epoch": 1.778, "percentage": 88.9, "elapsed_time": "16:16:22", "remaining_time": "2:01:54", "throughput": 5942.09, "total_tokens": 348104384}
{"current_steps": 4450, "total_steps": 5000, "loss": 0.1562, "lr": 2.9666126033265517e-07, "epoch": 1.78, "percentage": 89.0, "elapsed_time": "16:17:32", "remaining_time": "2:00:49", "throughput": 5942.55, "total_tokens": 348543616}
{"current_steps": 4455, "total_steps": 5000, "loss": 0.1575, "lr": 2.913543112489564e-07, "epoch": 1.782, "percentage": 89.1, "elapsed_time": "16:18:39", "remaining_time": "1:59:43", "throughput": 5943.52, "total_tokens": 349003296}
{"current_steps": 4460, "total_steps": 5000, "loss": 0.1686, "lr": 2.8609383459724915e-07, "epoch": 1.784, "percentage": 89.2, "elapsed_time": "16:19:52", "remaining_time": "1:58:38", "throughput": 5943.5, "total_tokens": 349434512}
{"current_steps": 4465, "total_steps": 5000, "loss": 0.1445, "lr": 2.8087988229631325e-07, "epoch": 1.786, "percentage": 89.3, "elapsed_time": "16:20:44", "remaining_time": "1:57:30", "throughput": 5943.68, "total_tokens": 349754592}
{"current_steps": 4470, "total_steps": 5000, "loss": 0.1537, "lr": 2.757125058057536e-07, "epoch": 1.788, "percentage": 89.4, "elapsed_time": "16:21:50", "remaining_time": "1:56:24", "throughput": 5943.06, "total_tokens": 350108128}
{"current_steps": 4475, "total_steps": 5000, "loss": 0.1422, "lr": 2.7059175612548947e-07, "epoch": 1.79, "percentage": 89.5, "elapsed_time": "16:22:57", "remaining_time": "1:55:19", "throughput": 5942.26, "total_tokens": 350460560}
{"current_steps": 4480, "total_steps": 5000, "loss": 0.1512, "lr": 2.655176837952528e-07, "epoch": 1.792, "percentage": 89.6, "elapsed_time": "16:24:03", "remaining_time": "1:54:13", "throughput": 5942.13, "total_tokens": 350845008}
{"current_steps": 4485, "total_steps": 5000, "loss": 0.1478, "lr": 2.604903388940899e-07, "epoch": 1.794, "percentage": 89.7, "elapsed_time": "16:25:12", "remaining_time": "1:53:07", "throughput": 5940.97, "total_tokens": 351184624}
{"current_steps": 4490, "total_steps": 5000, "loss": 0.1612, "lr": 2.555097710398635e-07, "epoch": 1.796, "percentage": 89.8, "elapsed_time": "16:26:22", "remaining_time": "1:52:02", "throughput": 5940.01, "total_tokens": 351541888}
{"current_steps": 4495, "total_steps": 5000, "loss": 0.1533, "lr": 2.505760293887699e-07, "epoch": 1.798, "percentage": 89.9, "elapsed_time": "16:27:23", "remaining_time": "1:50:55", "throughput": 5939.66, "total_tokens": 351887408}
{"current_steps": 4500, "total_steps": 5000, "loss": 0.1601, "lr": 2.456891626348451e-07, "epoch": 1.8, "percentage": 90.0, "elapsed_time": "16:28:21", "remaining_time": "1:49:49", "throughput": 5939.69, "total_tokens": 352230768}
{"current_steps": 4505, "total_steps": 5000, "loss": 0.1495, "lr": 2.40849219009493e-07, "epoch": 1.802, "percentage": 90.1, "elapsed_time": "16:29:26", "remaining_time": "1:48:43", "throughput": 5939.61, "total_tokens": 352616368}
{"current_steps": 4510, "total_steps": 5000, "loss": 0.1568, "lr": 2.3605624628100178e-07, "epoch": 1.804, "percentage": 90.2, "elapsed_time": "16:30:31", "remaining_time": "1:47:37", "throughput": 5939.4, "total_tokens": 352985856}
{"current_steps": 4515, "total_steps": 5000, "loss": 0.1472, "lr": 2.3131029175407883e-07, "epoch": 1.806, "percentage": 90.3, "elapsed_time": "16:31:42", "remaining_time": "1:46:31", "throughput": 5938.35, "total_tokens": 353348672}
{"current_steps": 4520, "total_steps": 5000, "loss": 0.1692, "lr": 2.2661140226937773e-07, "epoch": 1.808, "percentage": 90.4, "elapsed_time": "16:32:55", "remaining_time": "1:45:26", "throughput": 5938.83, "total_tokens": 353810608}
{"current_steps": 4525, "total_steps": 5000, "loss": 0.1548, "lr": 2.2195962420304083e-07, "epoch": 1.81, "percentage": 90.5, "elapsed_time": "16:34:09", "remaining_time": "1:44:21", "throughput": 5939.16, "total_tokens": 354265984}
{"current_steps": 4530, "total_steps": 5000, "loss": 0.1466, "lr": 2.1735500346624083e-07, "epoch": 1.812, "percentage": 90.6, "elapsed_time": "16:35:14", "remaining_time": "1:43:15", "throughput": 5939.28, "total_tokens": 354663520}
{"current_steps": 4535, "total_steps": 5000, "loss": 0.1529, "lr": 2.127975855047243e-07, "epoch": 1.814, "percentage": 90.7, "elapsed_time": "16:36:28", "remaining_time": "1:42:10", "throughput": 5939.24, "total_tokens": 355100976}
{"current_steps": 4540, "total_steps": 5000, "loss": 0.1474, "lr": 2.0828741529836771e-07, "epoch": 1.8159999999999998, "percentage": 90.8, "elapsed_time": "16:37:30", "remaining_time": "1:41:04", "throughput": 5939.28, "total_tokens": 355468432}
{"current_steps": 4545, "total_steps": 5000, "loss": 0.1685, "lr": 2.0382453736072838e-07, "epoch": 1.818, "percentage": 90.9, "elapsed_time": "16:38:48", "remaining_time": "1:39:59", "throughput": 5938.3, "total_tokens": 355871536}
{"current_steps": 4550, "total_steps": 5000, "loss": 0.1495, "lr": 1.9940899573861195e-07, "epoch": 1.8199999999999998, "percentage": 91.0, "elapsed_time": "16:39:59", "remaining_time": "1:38:54", "throughput": 5937.83, "total_tokens": 356268624}
{"current_steps": 4555, "total_steps": 5000, "loss": 0.1574, "lr": 1.9504083401162999e-07, "epoch": 1.822, "percentage": 91.1, "elapsed_time": "16:41:16", "remaining_time": "1:37:49", "throughput": 5937.92, "total_tokens": 356731600}
{"current_steps": 4560, "total_steps": 5000, "loss": 0.1614, "lr": 1.907200952917765e-07, "epoch": 1.8239999999999998, "percentage": 91.2, "elapsed_time": "16:42:35", "remaining_time": "1:36:44", "throughput": 5937.11, "total_tokens": 357148736}
{"current_steps": 4565, "total_steps": 5000, "loss": 0.1668, "lr": 1.8644682222299703e-07, "epoch": 1.826, "percentage": 91.3, "elapsed_time": "16:43:41", "remaining_time": "1:35:38", "throughput": 5936.88, "total_tokens": 357530208}
{"current_steps": 4570, "total_steps": 5000, "loss": 0.1758, "lr": 1.8222105698077253e-07, "epoch": 1.8279999999999998, "percentage": 91.4, "elapsed_time": "16:45:00", "remaining_time": "1:34:33", "throughput": 5935.79, "total_tokens": 357929040}
{"current_steps": 4575, "total_steps": 5000, "loss": 0.1532, "lr": 1.7804284127169946e-07, "epoch": 1.83, "percentage": 91.5, "elapsed_time": "16:46:08", "remaining_time": "1:33:28", "throughput": 5936.51, "total_tokens": 358378688}
{"current_steps": 4580, "total_steps": 5000, "loss": 0.1459, "lr": 1.7391221633308032e-07, "epoch": 1.8319999999999999, "percentage": 91.6, "elapsed_time": "16:47:13", "remaining_time": "1:32:21", "throughput": 5936.9, "total_tokens": 358789536}
{"current_steps": 4585, "total_steps": 5000, "loss": 0.1522, "lr": 1.6982922293251548e-07, "epoch": 1.834, "percentage": 91.7, "elapsed_time": "16:48:14", "remaining_time": "1:31:15", "throughput": 5937.69, "total_tokens": 359199840}
{"current_steps": 4590, "total_steps": 5000, "loss": 0.1687, "lr": 1.6579390136750086e-07, "epoch": 1.8359999999999999, "percentage": 91.8, "elapsed_time": "16:49:31", "remaining_time": "1:30:10", "throughput": 5937.84, "total_tokens": 359666192}
{"current_steps": 4595, "total_steps": 5000, "loss": 0.1542, "lr": 1.6180629146503256e-07, "epoch": 1.838, "percentage": 91.9, "elapsed_time": "16:50:42", "remaining_time": "1:29:04", "throughput": 5937.87, "total_tokens": 360085104}
{"current_steps": 4600, "total_steps": 5000, "loss": 0.1516, "lr": 1.5786643258120905e-07, "epoch": 1.8399999999999999, "percentage": 92.0, "elapsed_time": "16:51:57", "remaining_time": "1:27:59", "throughput": 5937.85, "total_tokens": 360529536}
{"current_steps": 4605, "total_steps": 5000, "loss": 0.1744, "lr": 1.5397436360084784e-07, "epoch": 1.842, "percentage": 92.1, "elapsed_time": "16:53:11", "remaining_time": "1:26:54", "throughput": 5937.79, "total_tokens": 360968864}
{"current_steps": 4610, "total_steps": 5000, "loss": 0.1603, "lr": 1.5013012293709828e-07, "epoch": 1.8439999999999999, "percentage": 92.2, "elapsed_time": "16:54:21", "remaining_time": "1:25:48", "throughput": 5938.34, "total_tokens": 361417600}
{"current_steps": 4615, "total_steps": 5000, "loss": 0.1525, "lr": 1.463337485310634e-07, "epoch": 1.846, "percentage": 92.3, "elapsed_time": "16:55:37", "remaining_time": "1:24:43", "throughput": 5937.87, "total_tokens": 361839200}
{"current_steps": 4620, "total_steps": 5000, "loss": 0.1512, "lr": 1.425852778514264e-07, "epoch": 1.8479999999999999, "percentage": 92.4, "elapsed_time": "16:56:52", "remaining_time": "1:23:38", "throughput": 5937.49, "total_tokens": 362259616}
{"current_steps": 4625, "total_steps": 5000, "loss": 0.1478, "lr": 1.388847478940797e-07, "epoch": 1.85, "percentage": 92.5, "elapsed_time": "16:58:00", "remaining_time": "1:22:32", "throughput": 5937.74, "total_tokens": 362678496}
{"current_steps": 4630, "total_steps": 5000, "loss": 0.1567, "lr": 1.3523219518175924e-07, "epoch": 1.8519999999999999, "percentage": 92.6, "elapsed_time": "16:58:44", "remaining_time": "1:21:24", "throughput": 5939.12, "total_tokens": 363027968}
{"current_steps": 4635, "total_steps": 5000, "loss": 0.1484, "lr": 1.3162765576368587e-07, "epoch": 1.854, "percentage": 92.7, "elapsed_time": "16:59:52", "remaining_time": "1:20:18", "throughput": 5938.51, "total_tokens": 363395040}
{"current_steps": 4640, "total_steps": 5000, "loss": 0.1595, "lr": 1.2807116521520947e-07, "epoch": 1.8559999999999999, "percentage": 92.8, "elapsed_time": "17:01:04", "remaining_time": "1:19:13", "throughput": 5938.04, "total_tokens": 363789744}
{"current_steps": 4645, "total_steps": 5000, "loss": 0.1655, "lr": 1.2456275863745426e-07, "epoch": 1.858, "percentage": 92.9, "elapsed_time": "17:02:22", "remaining_time": "1:18:08", "throughput": 5937.95, "total_tokens": 364247552}
{"current_steps": 4650, "total_steps": 5000, "loss": 0.1425, "lr": 1.21102470656978e-07, "epoch": 1.8599999999999999, "percentage": 93.0, "elapsed_time": "17:03:39", "remaining_time": "1:17:02", "throughput": 5938.28, "total_tokens": 364725648}
{"current_steps": 4655, "total_steps": 5000, "loss": 0.1431, "lr": 1.1769033542542552e-07, "epoch": 1.862, "percentage": 93.1, "elapsed_time": "17:04:56", "remaining_time": "1:15:57", "throughput": 5938.22, "total_tokens": 365182608}
{"current_steps": 4660, "total_steps": 5000, "loss": 0.1512, "lr": 1.1432638661919515e-07, "epoch": 1.8639999999999999, "percentage": 93.2, "elapsed_time": "17:06:05", "remaining_time": "1:14:51", "throughput": 5937.6, "total_tokens": 365552736}
{"current_steps": 4665, "total_steps": 5000, "loss": 0.1497, "lr": 1.1101065743910122e-07, "epoch": 1.866, "percentage": 93.3, "elapsed_time": "17:07:04", "remaining_time": "1:13:45", "throughput": 5937.97, "total_tokens": 365922048}
{"current_steps": 4670, "total_steps": 5000, "loss": 0.154, "lr": 1.0774318061005484e-07, "epoch": 1.8679999999999999, "percentage": 93.4, "elapsed_time": "17:08:07", "remaining_time": "1:12:39", "throughput": 5938.27, "total_tokens": 366317200}
{"current_steps": 4675, "total_steps": 5000, "loss": 0.157, "lr": 1.0452398838073141e-07, "epoch": 1.87, "percentage": 93.5, "elapsed_time": "17:09:22", "remaining_time": "1:11:33", "throughput": 5937.95, "total_tokens": 366742816}
{"current_steps": 4680, "total_steps": 5000, "loss": 0.1532, "lr": 1.0135311252325863e-07, "epoch": 1.8719999999999999, "percentage": 93.6, "elapsed_time": "17:10:21", "remaining_time": "1:10:27", "throughput": 5938.12, "total_tokens": 367106336}
{"current_steps": 4685, "total_steps": 5000, "loss": 0.1573, "lr": 9.823058433290178e-08, "epoch": 1.874, "percentage": 93.7, "elapsed_time": "17:11:15", "remaining_time": "1:09:20", "throughput": 5938.21, "total_tokens": 367428640}
{"current_steps": 4690, "total_steps": 5000, "loss": 0.1385, "lr": 9.515643462775337e-08, "epoch": 1.876, "percentage": 93.8, "elapsed_time": "17:12:20", "remaining_time": "1:08:14", "throughput": 5938.18, "total_tokens": 367814192}
{"current_steps": 4695, "total_steps": 5000, "loss": 0.1574, "lr": 9.213069374842953e-08, "epoch": 1.8780000000000001, "percentage": 93.9, "elapsed_time": "17:13:28", "remaining_time": "1:07:08", "throughput": 5938.16, "total_tokens": 368216192}
{"current_steps": 4700, "total_steps": 5000, "loss": 0.1661, "lr": 8.915339155777136e-08, "epoch": 1.88, "percentage": 94.0, "elapsed_time": "17:14:47", "remaining_time": "1:06:03", "throughput": 5938.39, "total_tokens": 368698608}
{"current_steps": 4705, "total_steps": 5000, "loss": 0.1657, "lr": 8.622455744054958e-08, "epoch": 1.8820000000000001, "percentage": 94.1, "elapsed_time": "17:16:03", "remaining_time": "1:04:57", "throughput": 5938.6, "total_tokens": 369162816}
{"current_steps": 4710, "total_steps": 5000, "loss": 0.1618, "lr": 8.334422030317424e-08, "epoch": 1.884, "percentage": 94.2, "elapsed_time": "17:17:06", "remaining_time": "1:03:51", "throughput": 5938.54, "total_tokens": 369534656}
{"current_steps": 4715, "total_steps": 5000, "loss": 0.147, "lr": 8.051240857341102e-08, "epoch": 1.8860000000000001, "percentage": 94.3, "elapsed_time": "17:18:09", "remaining_time": "1:02:45", "throughput": 5938.52, "total_tokens": 369905840}
{"current_steps": 4720, "total_steps": 5000, "loss": 0.1517, "lr": 7.772915020009708e-08, "epoch": 1.888, "percentage": 94.4, "elapsed_time": "17:19:22", "remaining_time": "1:01:39", "throughput": 5938.14, "total_tokens": 370319248}
{"current_steps": 4725, "total_steps": 5000, "loss": 0.1539, "lr": 7.499447265286952e-08, "epoch": 1.8900000000000001, "percentage": 94.5, "elapsed_time": "17:20:35", "remaining_time": "1:00:33", "throughput": 5938.91, "total_tokens": 370800368}
{"current_steps": 4730, "total_steps": 5000, "loss": 0.1681, "lr": 7.230840292189179e-08, "epoch": 1.892, "percentage": 94.6, "elapsed_time": "17:21:49", "remaining_time": "0:59:28", "throughput": 5938.52, "total_tokens": 371215312}
{"current_steps": 4735, "total_steps": 5000, "loss": 0.1502, "lr": 6.967096751758773e-08, "epoch": 1.8940000000000001, "percentage": 94.7, "elapsed_time": "17:22:36", "remaining_time": "0:58:21", "throughput": 5938.74, "total_tokens": 371507376}
{"current_steps": 4740, "total_steps": 5000, "loss": 0.1561, "lr": 6.708219247038017e-08, "epoch": 1.896, "percentage": 94.8, "elapsed_time": "17:23:54", "remaining_time": "0:57:15", "throughput": 5938.17, "total_tokens": 371934544}
{"current_steps": 4745, "total_steps": 5000, "loss": 0.1426, "lr": 6.454210333043275e-08, "epoch": 1.8980000000000001, "percentage": 94.9, "elapsed_time": "17:24:53", "remaining_time": "0:56:09", "throughput": 5938.55, "total_tokens": 372310320}
{"current_steps": 4750, "total_steps": 5000, "loss": 0.1511, "lr": 6.205072516740129e-08, "epoch": 1.9, "percentage": 95.0, "elapsed_time": "17:25:51", "remaining_time": "0:55:02", "throughput": 5938.73, "total_tokens": 372661872}
{"current_steps": 4755, "total_steps": 5000, "loss": 0.1648, "lr": 5.960808257018113e-08, "epoch": 1.9020000000000001, "percentage": 95.1, "elapsed_time": "17:26:57", "remaining_time": "0:53:56", "throughput": 5939.15, "total_tokens": 373084368}
{"current_steps": 4760, "total_steps": 5000, "loss": 0.149, "lr": 5.7214199646669076e-08, "epoch": 1.904, "percentage": 95.2, "elapsed_time": "17:28:15", "remaining_time": "0:52:51", "throughput": 5938.22, "total_tokens": 373490144}
{"current_steps": 4765, "total_steps": 5000, "loss": 0.1523, "lr": 5.4869100023523526e-08, "epoch": 1.9060000000000001, "percentage": 95.3, "elapsed_time": "17:29:13", "remaining_time": "0:51:44", "throughput": 5938.15, "total_tokens": 373829536}
{"current_steps": 4770, "total_steps": 5000, "loss": 0.1497, "lr": 5.2572806845930244e-08, "epoch": 1.908, "percentage": 95.4, "elapsed_time": "17:30:16", "remaining_time": "0:50:38", "throughput": 5937.68, "total_tokens": 374173664}
{"current_steps": 4775, "total_steps": 5000, "loss": 0.1747, "lr": 5.032534277737644e-08, "epoch": 1.9100000000000001, "percentage": 95.5, "elapsed_time": "17:31:23", "remaining_time": "0:49:32", "throughput": 5937.99, "total_tokens": 374591792}
{"current_steps": 4780, "total_steps": 5000, "loss": 0.1591, "lr": 4.81267299994248e-08, "epoch": 1.912, "percentage": 95.6, "elapsed_time": "17:32:41", "remaining_time": "0:48:27", "throughput": 5938.05, "total_tokens": 375056544}
{"current_steps": 4785, "total_steps": 5000, "loss": 0.1481, "lr": 4.597699021149649e-08, "epoch": 1.9140000000000001, "percentage": 95.7, "elapsed_time": "17:33:52", "remaining_time": "0:47:21", "throughput": 5938.02, "total_tokens": 375473328}
{"current_steps": 4790, "total_steps": 5000, "loss": 0.1595, "lr": 4.387614463065404e-08, "epoch": 1.916, "percentage": 95.8, "elapsed_time": "17:35:07", "remaining_time": "0:46:15", "throughput": 5938.28, "total_tokens": 375937584}
{"current_steps": 4795, "total_steps": 5000, "loss": 0.1659, "lr": 4.1824213991396024e-08, "epoch": 1.9180000000000001, "percentage": 95.9, "elapsed_time": "17:36:13", "remaining_time": "0:45:09", "throughput": 5938.5, "total_tokens": 376345344}
{"current_steps": 4800, "total_steps": 5000, "loss": 0.1663, "lr": 3.9821218545449956e-08, "epoch": 1.92, "percentage": 96.0, "elapsed_time": "17:37:16", "remaining_time": "0:44:03", "throughput": 5938.28, "total_tokens": 376703552}
{"current_steps": 4805, "total_steps": 5000, "loss": 0.1634, "lr": 3.786717806157136e-08, "epoch": 1.9220000000000002, "percentage": 96.1, "elapsed_time": "17:38:26", "remaining_time": "0:42:57", "throughput": 5937.91, "total_tokens": 377097632}
{"current_steps": 4810, "total_steps": 5000, "loss": 0.1494, "lr": 3.5962111825350585e-08, "epoch": 1.924, "percentage": 96.2, "elapsed_time": "17:39:36", "remaining_time": "0:41:51", "throughput": 5937.63, "total_tokens": 377493120}
{"current_steps": 4815, "total_steps": 5000, "loss": 0.1455, "lr": 3.410603863902406e-08, "epoch": 1.9260000000000002, "percentage": 96.3, "elapsed_time": "17:40:38", "remaining_time": "0:40:45", "throughput": 5937.76, "total_tokens": 377869200}
{"current_steps": 4820, "total_steps": 5000, "loss": 0.153, "lr": 3.2298976821282804e-08, "epoch": 1.928, "percentage": 96.4, "elapsed_time": "17:41:40", "remaining_time": "0:39:38", "throughput": 5937.79, "total_tokens": 378239120}
{"current_steps": 4825, "total_steps": 5000, "loss": 0.1493, "lr": 3.054094420709863e-08, "epoch": 1.9300000000000002, "percentage": 96.5, "elapsed_time": "17:42:49", "remaining_time": "0:38:32", "throughput": 5937.58, "total_tokens": 378639088}
{"current_steps": 4830, "total_steps": 5000, "loss": 0.1456, "lr": 2.8831958147543805e-08, "epoch": 1.932, "percentage": 96.6, "elapsed_time": "17:43:40", "remaining_time": "0:37:26", "throughput": 5938.33, "total_tokens": 378986240}
{"current_steps": 4835, "total_steps": 5000, "loss": 0.1509, "lr": 2.7172035509619442e-08, "epoch": 1.9340000000000002, "percentage": 96.7, "elapsed_time": "17:44:51", "remaining_time": "0:36:20", "throughput": 5938.24, "total_tokens": 379402800}
{"current_steps": 4840, "total_steps": 5000, "loss": 0.1631, "lr": 2.556119267609347e-08, "epoch": 1.936, "percentage": 96.8, "elapsed_time": "17:45:49", "remaining_time": "0:35:14", "throughput": 5938.23, "total_tokens": 379748272}
{"current_steps": 4845, "total_steps": 5000, "loss": 0.1486, "lr": 2.3999445545332955e-08, "epoch": 1.938, "percentage": 96.9, "elapsed_time": "17:46:53", "remaining_time": "0:34:07", "throughput": 5938.16, "total_tokens": 380120432}
{"current_steps": 4850, "total_steps": 5000, "loss": 0.1553, "lr": 2.2486809531152563e-08, "epoch": 1.94, "percentage": 97.0, "elapsed_time": "17:47:56", "remaining_time": "0:33:01", "throughput": 5937.69, "total_tokens": 380466704}
{"current_steps": 4855, "total_steps": 5000, "loss": 0.159, "lr": 2.1023299562658584e-08, "epoch": 1.942, "percentage": 97.1, "elapsed_time": "17:48:40", "remaining_time": "0:31:55", "throughput": 5938.77, "total_tokens": 380797952}
{"current_steps": 4860, "total_steps": 5000, "loss": 0.151, "lr": 1.9608930084104027e-08, "epoch": 1.944, "percentage": 97.2, "elapsed_time": "17:49:42", "remaining_time": "0:30:48", "throughput": 5939.74, "total_tokens": 381229408}
{"current_steps": 4865, "total_steps": 5000, "loss": 0.1501, "lr": 1.8243715054744315e-08, "epoch": 1.946, "percentage": 97.3, "elapsed_time": "17:50:48", "remaining_time": "0:29:42", "throughput": 5939.31, "total_tokens": 381589840}
{"current_steps": 4870, "total_steps": 5000, "loss": 0.1671, "lr": 1.6927667948700155e-08, "epoch": 1.948, "percentage": 97.4, "elapsed_time": "17:51:59", "remaining_time": "0:28:36", "throughput": 5939.81, "total_tokens": 382043232}
{"current_steps": 4875, "total_steps": 5000, "loss": 0.1458, "lr": 1.5660801754825983e-08, "epoch": 1.95, "percentage": 97.5, "elapsed_time": "17:53:17", "remaining_time": "0:27:31", "throughput": 5938.74, "total_tokens": 382438480}
{"current_steps": 4880, "total_steps": 5000, "loss": 0.1399, "lr": 1.4443128976579513e-08, "epoch": 1.952, "percentage": 97.6, "elapsed_time": "17:54:25", "remaining_time": "0:26:25", "throughput": 5938.54, "total_tokens": 382832560}
{"current_steps": 4885, "total_steps": 5000, "loss": 0.141, "lr": 1.3274661631899055e-08, "epoch": 1.954, "percentage": 97.7, "elapsed_time": "17:55:19", "remaining_time": "0:25:18", "throughput": 5939.04, "total_tokens": 383181280}
{"current_steps": 4890, "total_steps": 5000, "loss": 0.1554, "lr": 1.2155411253085835e-08, "epoch": 1.956, "percentage": 97.8, "elapsed_time": "17:56:31", "remaining_time": "0:24:12", "throughput": 5938.03, "total_tokens": 383546752}
{"current_steps": 4895, "total_steps": 5000, "loss": 0.1543, "lr": 1.1085388886689085e-08, "epoch": 1.958, "percentage": 97.9, "elapsed_time": "17:57:29", "remaining_time": "0:23:06", "throughput": 5938.67, "total_tokens": 383933440}
{"current_steps": 4900, "total_steps": 5000, "loss": 0.1515, "lr": 1.0064605093397794e-08, "epoch": 1.96, "percentage": 98.0, "elapsed_time": "17:58:46", "remaining_time": "0:22:00", "throughput": 5938.62, "total_tokens": 384386960}
{"current_steps": 4905, "total_steps": 5000, "loss": 0.1521, "lr": 9.09306994793635e-09, "epoch": 1.962, "percentage": 98.1, "elapsed_time": "17:59:42", "remaining_time": "0:20:54", "throughput": 5938.89, "total_tokens": 384734336}
{"current_steps": 4910, "total_steps": 5000, "loss": 0.1519, "lr": 8.17079303896351e-09, "epoch": 1.964, "percentage": 98.2, "elapsed_time": "18:00:57", "remaining_time": "0:19:48", "throughput": 5938.6, "total_tokens": 385162112}
{"current_steps": 4915, "total_steps": 5000, "loss": 0.162, "lr": 7.297783468980246e-09, "epoch": 1.966, "percentage": 98.3, "elapsed_time": "18:02:09", "remaining_time": "0:18:42", "throughput": 5938.66, "total_tokens": 385595168}
{"current_steps": 4920, "total_steps": 5000, "loss": 0.1453, "lr": 6.4740498542387174e-09, "epoch": 1.968, "percentage": 98.4, "elapsed_time": "18:03:13", "remaining_time": "0:17:36", "throughput": 5938.73, "total_tokens": 385979072}
{"current_steps": 4925, "total_steps": 5000, "loss": 0.1494, "lr": 5.699600324657328e-09, "epoch": 1.97, "percentage": 98.5, "elapsed_time": "18:04:18", "remaining_time": "0:16:30", "throughput": 5939.16, "total_tokens": 386395168}
{"current_steps": 4930, "total_steps": 5000, "loss": 0.1559, "lr": 4.9744425237396865e-09, "epoch": 1.972, "percentage": 98.6, "elapsed_time": "18:05:35", "remaining_time": "0:15:24", "throughput": 5939.1, "total_tokens": 386844528}
{"current_steps": 4935, "total_steps": 5000, "loss": 0.1714, "lr": 4.298583608501328e-09, "epoch": 1.974, "percentage": 98.7, "elapsed_time": "18:06:30", "remaining_time": "0:14:18", "throughput": 5940.1, "total_tokens": 387236864}
{"current_steps": 4940, "total_steps": 5000, "loss": 0.1646, "lr": 3.672030249396441e-09, "epoch": 1.976, "percentage": 98.8, "elapsed_time": "18:07:34", "remaining_time": "0:13:12", "throughput": 5940.43, "total_tokens": 387642192}
{"current_steps": 4945, "total_steps": 5000, "loss": 0.162, "lr": 3.094788630254031e-09, "epoch": 1.978, "percentage": 98.9, "elapsed_time": "18:08:37", "remaining_time": "0:12:06", "throughput": 5941.13, "total_tokens": 388059072}
{"current_steps": 4950, "total_steps": 5000, "loss": 0.1452, "lr": 2.5668644482151892e-09, "epoch": 1.98, "percentage": 99.0, "elapsed_time": "18:09:46", "remaining_time": "0:11:00", "throughput": 5941.36, "total_tokens": 388484560}
{"current_steps": 4955, "total_steps": 5000, "loss": 0.1581, "lr": 2.088262913679251e-09, "epoch": 1.982, "percentage": 99.1, "elapsed_time": "18:10:40", "remaining_time": "0:09:54", "throughput": 5941.69, "total_tokens": 388827712}
{"current_steps": 4960, "total_steps": 5000, "loss": 0.1581, "lr": 1.6589887502493907e-09, "epoch": 1.984, "percentage": 99.2, "elapsed_time": "18:11:58", "remaining_time": "0:08:48", "throughput": 5941.07, "total_tokens": 389247824}
{"current_steps": 4965, "total_steps": 5000, "loss": 0.157, "lr": 1.2790461946887712e-09, "epoch": 1.986, "percentage": 99.3, "elapsed_time": "18:13:15", "remaining_time": "0:07:42", "throughput": 5940.0, "total_tokens": 389639584}
{"current_steps": 4970, "total_steps": 5000, "loss": 0.158, "lr": 9.484389968766882e-10, "epoch": 1.988, "percentage": 99.4, "elapsed_time": "18:14:20", "remaining_time": "0:06:36", "throughput": 5940.41, "total_tokens": 390047648}
{"current_steps": 4975, "total_steps": 5000, "loss": 0.1632, "lr": 6.671704197735995e-10, "epoch": 1.99, "percentage": 99.5, "elapsed_time": "18:15:17", "remaining_time": "0:05:30", "throughput": 5940.87, "total_tokens": 390419856}
{"current_steps": 4980, "total_steps": 5000, "loss": 0.153, "lr": 4.3524323938559655e-10, "epoch": 1.992, "percentage": 99.6, "elapsed_time": "18:16:25", "remaining_time": "0:04:24", "throughput": 5940.66, "total_tokens": 390808512}
{"current_steps": 4985, "total_steps": 5000, "loss": 0.1537, "lr": 2.5265974474109054e-10, "epoch": 1.994, "percentage": 99.7, "elapsed_time": "18:17:24", "remaining_time": "0:03:18", "throughput": 5941.53, "total_tokens": 391214192}
{"current_steps": 4990, "total_steps": 5000, "loss": 0.1569, "lr": 1.1942173786527732e-10, "epoch": 1.996, "percentage": 99.8, "elapsed_time": "18:18:36", "remaining_time": "0:02:12", "throughput": 5940.85, "total_tokens": 391600608}
{"current_steps": 4995, "total_steps": 5000, "loss": 0.1555, "lr": 3.55305337634837e-11, "epoch": 1.998, "percentage": 99.9, "elapsed_time": "18:19:50", "remaining_time": "0:01:06", "throughput": 5940.13, "total_tokens": 391994016}
{"current_steps": 5000, "total_steps": 5000, "loss": 0.1515, "lr": 9.869604078449612e-13, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "18:20:52", "remaining_time": "0:00:00", "throughput": 5939.83, "total_tokens": 392342880}
{"current_steps": 5000, "total_steps": 5000, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "18:22:50", "remaining_time": "0:00:00", "throughput": 5929.29, "total_tokens": 392342880}