Role_LLM_Cube / trainer_log.jsonl
ZhuangXialie's picture
Upload trainer_log.jsonl with huggingface_hub
5788e67 verified
{"current_steps": 1, "total_steps": 210, "loss": 1.6319, "learning_rate": 5e-08, "epoch": 0.02857142857142857, "percentage": 0.48, "elapsed_time": "0:00:07", "remaining_time": "0:26:58", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 2, "total_steps": 210, "loss": 1.5294, "learning_rate": 1e-07, "epoch": 0.05714285714285714, "percentage": 0.95, "elapsed_time": "0:00:12", "remaining_time": "0:21:33", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 3, "total_steps": 210, "loss": 1.568, "learning_rate": 1.5e-07, "epoch": 0.08571428571428572, "percentage": 1.43, "elapsed_time": "0:00:17", "remaining_time": "0:19:35", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 4, "total_steps": 210, "loss": 1.6628, "learning_rate": 2e-07, "epoch": 0.11428571428571428, "percentage": 1.9, "elapsed_time": "0:00:21", "remaining_time": "0:18:34", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 5, "total_steps": 210, "loss": 1.5738, "learning_rate": 2.5e-07, "epoch": 0.14285714285714285, "percentage": 2.38, "elapsed_time": "0:00:26", "remaining_time": "0:17:56", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 6, "total_steps": 210, "loss": 1.5898, "learning_rate": 3e-07, "epoch": 0.17142857142857143, "percentage": 2.86, "elapsed_time": "0:00:30", "remaining_time": "0:17:30", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 7, "total_steps": 210, "loss": 1.5891, "learning_rate": 3.5e-07, "epoch": 0.2, "percentage": 3.33, "elapsed_time": "0:00:35", "remaining_time": "0:17:11", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 8, "total_steps": 210, "loss": 1.5277, "learning_rate": 4e-07, "epoch": 0.22857142857142856, "percentage": 3.81, "elapsed_time": "0:00:40", "remaining_time": "0:16:53", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 9, "total_steps": 210, "loss": 1.5504, "learning_rate": 4.5e-07, "epoch": 0.2571428571428571, "percentage": 4.29, "elapsed_time": "0:00:44", "remaining_time": "0:16:32", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 10, "total_steps": 210, "loss": 1.5509, "learning_rate": 5e-07, "epoch": 0.2857142857142857, "percentage": 4.76, "elapsed_time": "0:00:49", "remaining_time": "0:16:21", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 11, "total_steps": 210, "loss": 1.5752, "learning_rate": 5.5e-07, "epoch": 0.3142857142857143, "percentage": 5.24, "elapsed_time": "0:00:53", "remaining_time": "0:16:11", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 12, "total_steps": 210, "loss": 1.6208, "learning_rate": 6e-07, "epoch": 0.34285714285714286, "percentage": 5.71, "elapsed_time": "0:00:58", "remaining_time": "0:16:02", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 13, "total_steps": 210, "loss": 1.515, "learning_rate": 6.5e-07, "epoch": 0.37142857142857144, "percentage": 6.19, "elapsed_time": "0:01:03", "remaining_time": "0:15:54", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 14, "total_steps": 210, "loss": 1.4752, "learning_rate": 7e-07, "epoch": 0.4, "percentage": 6.67, "elapsed_time": "0:01:07", "remaining_time": "0:15:46", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 15, "total_steps": 210, "loss": 1.5073, "learning_rate": 7.5e-07, "epoch": 0.42857142857142855, "percentage": 7.14, "elapsed_time": "0:01:12", "remaining_time": "0:15:39", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 16, "total_steps": 210, "loss": 1.4206, "learning_rate": 8e-07, "epoch": 0.45714285714285713, "percentage": 7.62, "elapsed_time": "0:01:16", "remaining_time": "0:15:32", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 17, "total_steps": 210, "loss": 1.3659, "learning_rate": 8.499999999999999e-07, "epoch": 0.4857142857142857, "percentage": 8.1, "elapsed_time": "0:01:21", "remaining_time": "0:15:26", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 18, "total_steps": 210, "loss": 1.4999, "learning_rate": 9e-07, "epoch": 0.5142857142857142, "percentage": 8.57, "elapsed_time": "0:01:26", "remaining_time": "0:15:19", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 19, "total_steps": 210, "loss": 1.452, "learning_rate": 9.499999999999999e-07, "epoch": 0.5428571428571428, "percentage": 9.05, "elapsed_time": "0:01:30", "remaining_time": "0:15:13", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 20, "total_steps": 210, "loss": 1.4059, "learning_rate": 1e-06, "epoch": 0.5714285714285714, "percentage": 9.52, "elapsed_time": "0:01:35", "remaining_time": "0:15:06", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 21, "total_steps": 210, "loss": 1.3416, "learning_rate": 9.999316524962345e-07, "epoch": 0.6, "percentage": 10.0, "elapsed_time": "0:01:40", "remaining_time": "0:15:00", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 22, "total_steps": 210, "loss": 1.3334, "learning_rate": 9.99726628670463e-07, "epoch": 0.6285714285714286, "percentage": 10.48, "elapsed_time": "0:01:44", "remaining_time": "0:14:54", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 23, "total_steps": 210, "loss": 1.3032, "learning_rate": 9.993849845741523e-07, "epoch": 0.6571428571428571, "percentage": 10.95, "elapsed_time": "0:01:49", "remaining_time": "0:14:48", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 24, "total_steps": 210, "loss": 1.3742, "learning_rate": 9.989068136093872e-07, "epoch": 0.6857142857142857, "percentage": 11.43, "elapsed_time": "0:01:53", "remaining_time": "0:14:42", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 25, "total_steps": 210, "loss": 1.2641, "learning_rate": 9.982922465033348e-07, "epoch": 0.7142857142857143, "percentage": 11.9, "elapsed_time": "0:01:58", "remaining_time": "0:14:37", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 26, "total_steps": 210, "loss": 1.2624, "learning_rate": 9.975414512725056e-07, "epoch": 0.7428571428571429, "percentage": 12.38, "elapsed_time": "0:02:03", "remaining_time": "0:14:32", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 27, "total_steps": 210, "loss": 1.258, "learning_rate": 9.966546331768192e-07, "epoch": 0.7714285714285715, "percentage": 12.86, "elapsed_time": "0:02:07", "remaining_time": "0:14:26", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 28, "total_steps": 210, "loss": 1.3228, "learning_rate": 9.956320346634875e-07, "epoch": 0.8, "percentage": 13.33, "elapsed_time": "0:02:12", "remaining_time": "0:14:20", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 29, "total_steps": 210, "loss": 1.2034, "learning_rate": 9.944739353007341e-07, "epoch": 0.8285714285714286, "percentage": 13.81, "elapsed_time": "0:02:17", "remaining_time": "0:14:15", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 30, "total_steps": 210, "loss": 1.1795, "learning_rate": 9.931806517013612e-07, "epoch": 0.8571428571428571, "percentage": 14.29, "elapsed_time": "0:02:21", "remaining_time": "0:14:10", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 31, "total_steps": 210, "loss": 1.2288, "learning_rate": 9.917525374361911e-07, "epoch": 0.8857142857142857, "percentage": 14.76, "elapsed_time": "0:02:26", "remaining_time": "0:14:03", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 32, "total_steps": 210, "loss": 1.1764, "learning_rate": 9.901899829374047e-07, "epoch": 0.9142857142857143, "percentage": 15.24, "elapsed_time": "0:02:30", "remaining_time": "0:13:58", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 33, "total_steps": 210, "loss": 1.1402, "learning_rate": 9.884934153917996e-07, "epoch": 0.9428571428571428, "percentage": 15.71, "elapsed_time": "0:02:35", "remaining_time": "0:13:53", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 34, "total_steps": 210, "loss": 1.1604, "learning_rate": 9.866632986240029e-07, "epoch": 0.9714285714285714, "percentage": 16.19, "elapsed_time": "0:02:40", "remaining_time": "0:13:48", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 35, "total_steps": 210, "loss": 1.1567, "learning_rate": 9.847001329696652e-07, "epoch": 1.0, "percentage": 16.67, "elapsed_time": "0:02:44", "remaining_time": "0:13:43", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 36, "total_steps": 210, "loss": 1.084, "learning_rate": 9.826044551386742e-07, "epoch": 1.0285714285714285, "percentage": 17.14, "elapsed_time": "0:02:49", "remaining_time": "0:13:38", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 37, "total_steps": 210, "loss": 1.1305, "learning_rate": 9.803768380684242e-07, "epoch": 1.0571428571428572, "percentage": 17.62, "elapsed_time": "0:02:54", "remaining_time": "0:13:33", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 38, "total_steps": 210, "loss": 1.0574, "learning_rate": 9.780178907671788e-07, "epoch": 1.0857142857142856, "percentage": 18.1, "elapsed_time": "0:02:58", "remaining_time": "0:13:28", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 39, "total_steps": 210, "loss": 1.1391, "learning_rate": 9.755282581475767e-07, "epoch": 1.1142857142857143, "percentage": 18.57, "elapsed_time": "0:03:03", "remaining_time": "0:13:23", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 40, "total_steps": 210, "loss": 1.1267, "learning_rate": 9.729086208503173e-07, "epoch": 1.1428571428571428, "percentage": 19.05, "elapsed_time": "0:03:07", "remaining_time": "0:13:18", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 41, "total_steps": 210, "loss": 1.1055, "learning_rate": 9.701596950580807e-07, "epoch": 1.1714285714285715, "percentage": 19.52, "elapsed_time": "0:03:12", "remaining_time": "0:13:14", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 42, "total_steps": 210, "loss": 1.0392, "learning_rate": 9.672822322997304e-07, "epoch": 1.2, "percentage": 20.0, "elapsed_time": "0:03:17", "remaining_time": "0:13:09", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 43, "total_steps": 210, "loss": 1.0393, "learning_rate": 9.642770192448535e-07, "epoch": 1.2285714285714286, "percentage": 20.48, "elapsed_time": "0:03:22", "remaining_time": "0:13:04", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 44, "total_steps": 210, "loss": 1.0795, "learning_rate": 9.611448774886923e-07, "epoch": 1.2571428571428571, "percentage": 20.95, "elapsed_time": "0:03:26", "remaining_time": "0:12:59", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 45, "total_steps": 210, "loss": 1.0194, "learning_rate": 9.578866633275286e-07, "epoch": 1.2857142857142856, "percentage": 21.43, "elapsed_time": "0:03:31", "remaining_time": "0:12:55", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 46, "total_steps": 210, "loss": 1.0409, "learning_rate": 9.545032675245813e-07, "epoch": 1.3142857142857143, "percentage": 21.9, "elapsed_time": "0:03:36", "remaining_time": "0:12:50", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 47, "total_steps": 210, "loss": 1.0475, "learning_rate": 9.509956150664795e-07, "epoch": 1.342857142857143, "percentage": 22.38, "elapsed_time": "0:03:40", "remaining_time": "0:12:45", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 48, "total_steps": 210, "loss": 1.046, "learning_rate": 9.473646649103817e-07, "epoch": 1.3714285714285714, "percentage": 22.86, "elapsed_time": "0:03:45", "remaining_time": "0:12:41", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 49, "total_steps": 210, "loss": 0.9876, "learning_rate": 9.436114097218058e-07, "epoch": 1.4, "percentage": 23.33, "elapsed_time": "0:03:50", "remaining_time": "0:12:36", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 50, "total_steps": 210, "loss": 1.0394, "learning_rate": 9.397368756032444e-07, "epoch": 1.4285714285714286, "percentage": 23.81, "elapsed_time": "0:03:54", "remaining_time": "0:12:31", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 51, "total_steps": 210, "loss": 0.9647, "learning_rate": 9.357421218136386e-07, "epoch": 1.457142857142857, "percentage": 24.29, "elapsed_time": "0:03:59", "remaining_time": "0:12:26", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 52, "total_steps": 210, "loss": 1.0986, "learning_rate": 9.316282404787869e-07, "epoch": 1.4857142857142858, "percentage": 24.76, "elapsed_time": "0:04:04", "remaining_time": "0:12:21", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 53, "total_steps": 210, "loss": 1.0493, "learning_rate": 9.273963562927694e-07, "epoch": 1.5142857142857142, "percentage": 25.24, "elapsed_time": "0:04:08", "remaining_time": "0:12:17", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 54, "total_steps": 210, "loss": 0.9847, "learning_rate": 9.230476262104676e-07, "epoch": 1.5428571428571427, "percentage": 25.71, "elapsed_time": "0:04:13", "remaining_time": "0:12:12", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 55, "total_steps": 210, "loss": 0.9794, "learning_rate": 9.185832391312642e-07, "epoch": 1.5714285714285714, "percentage": 26.19, "elapsed_time": "0:04:18", "remaining_time": "0:12:07", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 56, "total_steps": 210, "loss": 1.0607, "learning_rate": 9.1400441557401e-07, "epoch": 1.6, "percentage": 26.67, "elapsed_time": "0:04:22", "remaining_time": "0:12:02", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 57, "total_steps": 210, "loss": 0.9856, "learning_rate": 9.093124073433462e-07, "epoch": 1.6285714285714286, "percentage": 27.14, "elapsed_time": "0:04:27", "remaining_time": "0:11:58", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 58, "total_steps": 210, "loss": 0.9107, "learning_rate": 9.045084971874737e-07, "epoch": 1.657142857142857, "percentage": 27.62, "elapsed_time": "0:04:32", "remaining_time": "0:11:53", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 59, "total_steps": 210, "loss": 0.9733, "learning_rate": 8.995939984474623e-07, "epoch": 1.6857142857142857, "percentage": 28.1, "elapsed_time": "0:04:36", "remaining_time": "0:11:48", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 60, "total_steps": 210, "loss": 0.9476, "learning_rate": 8.945702546981968e-07, "epoch": 1.7142857142857144, "percentage": 28.57, "elapsed_time": "0:04:41", "remaining_time": "0:11:43", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 61, "total_steps": 210, "loss": 0.9161, "learning_rate": 8.894386393810562e-07, "epoch": 1.7428571428571429, "percentage": 29.05, "elapsed_time": "0:04:46", "remaining_time": "0:11:38", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 62, "total_steps": 210, "loss": 1.0058, "learning_rate": 8.842005554284295e-07, "epoch": 1.7714285714285714, "percentage": 29.52, "elapsed_time": "0:04:50", "remaining_time": "0:11:34", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 63, "total_steps": 210, "loss": 0.8815, "learning_rate": 8.788574348801674e-07, "epoch": 1.8, "percentage": 30.0, "elapsed_time": "0:04:55", "remaining_time": "0:11:29", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 64, "total_steps": 210, "loss": 0.9945, "learning_rate": 8.734107384920769e-07, "epoch": 1.8285714285714287, "percentage": 30.48, "elapsed_time": "0:05:00", "remaining_time": "0:11:24", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 65, "total_steps": 210, "loss": 0.9822, "learning_rate": 8.678619553365658e-07, "epoch": 1.8571428571428572, "percentage": 30.95, "elapsed_time": "0:05:04", "remaining_time": "0:11:19", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 66, "total_steps": 210, "loss": 0.9781, "learning_rate": 8.622126023955445e-07, "epoch": 1.8857142857142857, "percentage": 31.43, "elapsed_time": "0:05:09", "remaining_time": "0:11:14", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 67, "total_steps": 210, "loss": 0.9188, "learning_rate": 8.564642241456986e-07, "epoch": 1.9142857142857141, "percentage": 31.9, "elapsed_time": "0:05:14", "remaining_time": "0:11:10", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 68, "total_steps": 210, "loss": 0.9193, "learning_rate": 8.506183921362442e-07, "epoch": 1.9428571428571428, "percentage": 32.38, "elapsed_time": "0:05:18", "remaining_time": "0:11:05", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 69, "total_steps": 210, "loss": 0.9563, "learning_rate": 8.446767045592829e-07, "epoch": 1.9714285714285715, "percentage": 32.86, "elapsed_time": "0:05:22", "remaining_time": "0:10:59", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 70, "total_steps": 210, "loss": 0.9172, "learning_rate": 8.386407858128706e-07, "epoch": 2.0, "percentage": 33.33, "elapsed_time": "0:05:27", "remaining_time": "0:10:55", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 71, "total_steps": 210, "loss": 0.8843, "learning_rate": 8.325122860569241e-07, "epoch": 2.0285714285714285, "percentage": 33.81, "elapsed_time": "0:05:32", "remaining_time": "0:10:50", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 72, "total_steps": 210, "loss": 0.8547, "learning_rate": 8.262928807620843e-07, "epoch": 2.057142857142857, "percentage": 34.29, "elapsed_time": "0:05:36", "remaining_time": "0:10:45", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 73, "total_steps": 210, "loss": 0.9414, "learning_rate": 8.199842702516582e-07, "epoch": 2.085714285714286, "percentage": 34.76, "elapsed_time": "0:05:41", "remaining_time": "0:10:40", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 74, "total_steps": 210, "loss": 0.8748, "learning_rate": 8.135881792367685e-07, "epoch": 2.1142857142857143, "percentage": 35.24, "elapsed_time": "0:05:46", "remaining_time": "0:10:36", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 75, "total_steps": 210, "loss": 0.8646, "learning_rate": 8.071063563448339e-07, "epoch": 2.142857142857143, "percentage": 35.71, "elapsed_time": "0:05:50", "remaining_time": "0:10:31", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 76, "total_steps": 210, "loss": 0.8744, "learning_rate": 8.005405736415125e-07, "epoch": 2.1714285714285713, "percentage": 36.19, "elapsed_time": "0:05:55", "remaining_time": "0:10:26", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 77, "total_steps": 210, "loss": 0.8735, "learning_rate": 7.938926261462365e-07, "epoch": 2.2, "percentage": 36.67, "elapsed_time": "0:06:00", "remaining_time": "0:10:22", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 78, "total_steps": 210, "loss": 0.9161, "learning_rate": 7.871643313414718e-07, "epoch": 2.2285714285714286, "percentage": 37.14, "elapsed_time": "0:06:04", "remaining_time": "0:10:17", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 79, "total_steps": 210, "loss": 0.8119, "learning_rate": 7.803575286758363e-07, "epoch": 2.257142857142857, "percentage": 37.62, "elapsed_time": "0:06:09", "remaining_time": "0:10:12", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 80, "total_steps": 210, "loss": 0.8698, "learning_rate": 7.734740790612136e-07, "epoch": 2.2857142857142856, "percentage": 38.1, "elapsed_time": "0:06:14", "remaining_time": "0:10:07", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 81, "total_steps": 210, "loss": 0.8673, "learning_rate": 7.665158643639969e-07, "epoch": 2.314285714285714, "percentage": 38.57, "elapsed_time": "0:06:18", "remaining_time": "0:10:02", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 82, "total_steps": 210, "loss": 0.8561, "learning_rate": 7.594847868906076e-07, "epoch": 2.342857142857143, "percentage": 39.05, "elapsed_time": "0:06:23", "remaining_time": "0:09:58", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 83, "total_steps": 210, "loss": 0.9032, "learning_rate": 7.523827688674219e-07, "epoch": 2.3714285714285714, "percentage": 39.52, "elapsed_time": "0:06:27", "remaining_time": "0:09:53", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 84, "total_steps": 210, "loss": 0.8431, "learning_rate": 7.452117519152541e-07, "epoch": 2.4, "percentage": 40.0, "elapsed_time": "0:06:32", "remaining_time": "0:09:48", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 85, "total_steps": 210, "loss": 0.844, "learning_rate": 7.379736965185368e-07, "epoch": 2.4285714285714284, "percentage": 40.48, "elapsed_time": "0:06:37", "remaining_time": "0:09:44", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 86, "total_steps": 210, "loss": 0.8071, "learning_rate": 7.306705814893439e-07, "epoch": 2.4571428571428573, "percentage": 40.95, "elapsed_time": "0:06:41", "remaining_time": "0:09:39", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 87, "total_steps": 210, "loss": 0.8726, "learning_rate": 7.233044034264033e-07, "epoch": 2.4857142857142858, "percentage": 41.43, "elapsed_time": "0:06:46", "remaining_time": "0:09:34", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 88, "total_steps": 210, "loss": 0.8651, "learning_rate": 7.158771761692464e-07, "epoch": 2.5142857142857142, "percentage": 41.9, "elapsed_time": "0:06:51", "remaining_time": "0:09:30", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 89, "total_steps": 210, "loss": 0.8023, "learning_rate": 7.083909302476452e-07, "epoch": 2.5428571428571427, "percentage": 42.38, "elapsed_time": "0:06:55", "remaining_time": "0:09:25", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 90, "total_steps": 210, "loss": 0.8107, "learning_rate": 7.008477123264847e-07, "epoch": 2.571428571428571, "percentage": 42.86, "elapsed_time": "0:07:00", "remaining_time": "0:09:20", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 91, "total_steps": 210, "loss": 0.8321, "learning_rate": 6.932495846462261e-07, "epoch": 2.6, "percentage": 43.33, "elapsed_time": "0:07:05", "remaining_time": "0:09:16", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 92, "total_steps": 210, "loss": 0.8003, "learning_rate": 6.855986244591103e-07, "epoch": 2.6285714285714286, "percentage": 43.81, "elapsed_time": "0:07:09", "remaining_time": "0:09:11", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 93, "total_steps": 210, "loss": 0.81, "learning_rate": 6.778969234612583e-07, "epoch": 2.657142857142857, "percentage": 44.29, "elapsed_time": "0:07:14", "remaining_time": "0:09:06", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 94, "total_steps": 210, "loss": 0.8362, "learning_rate": 6.701465872208216e-07, "epoch": 2.685714285714286, "percentage": 44.76, "elapsed_time": "0:07:19", "remaining_time": "0:09:01", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 95, "total_steps": 210, "loss": 0.7408, "learning_rate": 6.623497346023417e-07, "epoch": 2.7142857142857144, "percentage": 45.24, "elapsed_time": "0:07:23", "remaining_time": "0:08:57", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 96, "total_steps": 210, "loss": 0.803, "learning_rate": 6.545084971874736e-07, "epoch": 2.742857142857143, "percentage": 45.71, "elapsed_time": "0:07:28", "remaining_time": "0:08:52", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 97, "total_steps": 210, "loss": 0.8499, "learning_rate": 6.466250186922324e-07, "epoch": 2.7714285714285714, "percentage": 46.19, "elapsed_time": "0:07:33", "remaining_time": "0:08:47", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 98, "total_steps": 210, "loss": 0.8536, "learning_rate": 6.387014543809223e-07, "epoch": 2.8, "percentage": 46.67, "elapsed_time": "0:07:37", "remaining_time": "0:08:43", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 99, "total_steps": 210, "loss": 0.8167, "learning_rate": 6.307399704769098e-07, "epoch": 2.8285714285714287, "percentage": 47.14, "elapsed_time": "0:07:42", "remaining_time": "0:08:38", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 100, "total_steps": 210, "loss": 0.8247, "learning_rate": 6.227427435703995e-07, "epoch": 2.857142857142857, "percentage": 47.62, "elapsed_time": "0:07:46", "remaining_time": "0:08:33", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 101, "total_steps": 210, "loss": 0.7923, "learning_rate": 6.147119600233758e-07, "epoch": 2.8857142857142857, "percentage": 48.1, "elapsed_time": "0:07:51", "remaining_time": "0:08:29", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 102, "total_steps": 210, "loss": 0.8259, "learning_rate": 6.066498153718734e-07, "epoch": 2.914285714285714, "percentage": 48.57, "elapsed_time": "0:07:56", "remaining_time": "0:08:24", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 103, "total_steps": 210, "loss": 0.7416, "learning_rate": 5.985585137257401e-07, "epoch": 2.942857142857143, "percentage": 49.05, "elapsed_time": "0:08:00", "remaining_time": "0:08:19", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 104, "total_steps": 210, "loss": 0.86, "learning_rate": 5.90440267166055e-07, "epoch": 2.9714285714285715, "percentage": 49.52, "elapsed_time": "0:08:05", "remaining_time": "0:08:14", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 105, "total_steps": 210, "loss": 0.7756, "learning_rate": 5.82297295140367e-07, "epoch": 3.0, "percentage": 50.0, "elapsed_time": "0:08:10", "remaining_time": "0:08:10", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 106, "total_steps": 210, "loss": 0.7417, "learning_rate": 5.741318238559209e-07, "epoch": 3.0285714285714285, "percentage": 50.48, "elapsed_time": "0:08:14", "remaining_time": "0:08:05", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 107, "total_steps": 210, "loss": 0.7413, "learning_rate": 5.659460856710345e-07, "epoch": 3.057142857142857, "percentage": 50.95, "elapsed_time": "0:08:19", "remaining_time": "0:08:00", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 108, "total_steps": 210, "loss": 0.774, "learning_rate": 5.577423184847931e-07, "epoch": 3.085714285714286, "percentage": 51.43, "elapsed_time": "0:08:24", "remaining_time": "0:07:56", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 109, "total_steps": 210, "loss": 0.7596, "learning_rate": 5.495227651252315e-07, "epoch": 3.1142857142857143, "percentage": 51.9, "elapsed_time": "0:08:28", "remaining_time": "0:07:51", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 110, "total_steps": 210, "loss": 0.7494, "learning_rate": 5.412896727361662e-07, "epoch": 3.142857142857143, "percentage": 52.38, "elapsed_time": "0:08:33", "remaining_time": "0:07:46", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 111, "total_steps": 210, "loss": 0.8146, "learning_rate": 5.330452921628497e-07, "epoch": 3.1714285714285713, "percentage": 52.86, "elapsed_time": "0:08:37", "remaining_time": "0:07:41", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 112, "total_steps": 210, "loss": 0.7437, "learning_rate": 5.247918773366111e-07, "epoch": 3.2, "percentage": 53.33, "elapsed_time": "0:08:42", "remaining_time": "0:07:37", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 113, "total_steps": 210, "loss": 0.732, "learning_rate": 5.165316846586541e-07, "epoch": 3.2285714285714286, "percentage": 53.81, "elapsed_time": "0:08:47", "remaining_time": "0:07:32", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 114, "total_steps": 210, "loss": 0.769, "learning_rate": 5.082669723831793e-07, "epoch": 3.257142857142857, "percentage": 54.29, "elapsed_time": "0:08:51", "remaining_time": "0:07:27", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 115, "total_steps": 210, "loss": 0.7586, "learning_rate": 5e-07, "epoch": 3.2857142857142856, "percentage": 54.76, "elapsed_time": "0:08:56", "remaining_time": "0:07:22", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 116, "total_steps": 210, "loss": 0.7513, "learning_rate": 4.917330276168208e-07, "epoch": 3.314285714285714, "percentage": 55.24, "elapsed_time": "0:09:00", "remaining_time": "0:07:18", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 117, "total_steps": 210, "loss": 0.7184, "learning_rate": 4.834683153413459e-07, "epoch": 3.342857142857143, "percentage": 55.71, "elapsed_time": "0:09:05", "remaining_time": "0:07:13", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 118, "total_steps": 210, "loss": 0.6937, "learning_rate": 4.752081226633888e-07, "epoch": 3.3714285714285714, "percentage": 56.19, "elapsed_time": "0:09:10", "remaining_time": "0:07:08", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 119, "total_steps": 210, "loss": 0.7638, "learning_rate": 4.669547078371503e-07, "epoch": 3.4, "percentage": 56.67, "elapsed_time": "0:09:14", "remaining_time": "0:07:04", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 120, "total_steps": 210, "loss": 0.7029, "learning_rate": 4.5871032726383385e-07, "epoch": 3.4285714285714284, "percentage": 57.14, "elapsed_time": "0:09:19", "remaining_time": "0:06:59", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 121, "total_steps": 210, "loss": 0.7298, "learning_rate": 4.5047723487476864e-07, "epoch": 3.4571428571428573, "percentage": 57.62, "elapsed_time": "0:09:24", "remaining_time": "0:06:54", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 122, "total_steps": 210, "loss": 0.7716, "learning_rate": 4.4225768151520694e-07, "epoch": 3.4857142857142858, "percentage": 58.1, "elapsed_time": "0:09:28", "remaining_time": "0:06:50", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 123, "total_steps": 210, "loss": 0.7276, "learning_rate": 4.340539143289655e-07, "epoch": 3.5142857142857142, "percentage": 58.57, "elapsed_time": "0:09:33", "remaining_time": "0:06:45", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 124, "total_steps": 210, "loss": 0.7345, "learning_rate": 4.258681761440789e-07, "epoch": 3.5428571428571427, "percentage": 59.05, "elapsed_time": "0:09:37", "remaining_time": "0:06:40", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 125, "total_steps": 210, "loss": 0.7323, "learning_rate": 4.1770270485963294e-07, "epoch": 3.571428571428571, "percentage": 59.52, "elapsed_time": "0:09:42", "remaining_time": "0:06:36", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 126, "total_steps": 210, "loss": 0.7606, "learning_rate": 4.095597328339452e-07, "epoch": 3.6, "percentage": 60.0, "elapsed_time": "0:09:47", "remaining_time": "0:06:31", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 127, "total_steps": 210, "loss": 0.7149, "learning_rate": 4.0144148627425986e-07, "epoch": 3.6285714285714286, "percentage": 60.48, "elapsed_time": "0:09:51", "remaining_time": "0:06:26", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 128, "total_steps": 210, "loss": 0.6956, "learning_rate": 3.9335018462812664e-07, "epoch": 3.657142857142857, "percentage": 60.95, "elapsed_time": "0:09:56", "remaining_time": "0:06:22", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 129, "total_steps": 210, "loss": 0.6894, "learning_rate": 3.8528803997662423e-07, "epoch": 3.685714285714286, "percentage": 61.43, "elapsed_time": "0:10:01", "remaining_time": "0:06:17", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 130, "total_steps": 210, "loss": 0.7188, "learning_rate": 3.772572564296004e-07, "epoch": 3.7142857142857144, "percentage": 61.9, "elapsed_time": "0:10:05", "remaining_time": "0:06:12", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 131, "total_steps": 210, "loss": 0.7059, "learning_rate": 3.692600295230901e-07, "epoch": 3.742857142857143, "percentage": 62.38, "elapsed_time": "0:10:10", "remaining_time": "0:06:08", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 132, "total_steps": 210, "loss": 0.7022, "learning_rate": 3.612985456190778e-07, "epoch": 3.7714285714285714, "percentage": 62.86, "elapsed_time": "0:10:15", "remaining_time": "0:06:03", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 133, "total_steps": 210, "loss": 0.692, "learning_rate": 3.533749813077677e-07, "epoch": 3.8, "percentage": 63.33, "elapsed_time": "0:10:19", "remaining_time": "0:05:58", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 134, "total_steps": 210, "loss": 0.7245, "learning_rate": 3.454915028125263e-07, "epoch": 3.8285714285714287, "percentage": 63.81, "elapsed_time": "0:10:24", "remaining_time": "0:05:54", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 135, "total_steps": 210, "loss": 0.6965, "learning_rate": 3.3765026539765827e-07, "epoch": 3.857142857142857, "percentage": 64.29, "elapsed_time": "0:10:29", "remaining_time": "0:05:49", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 136, "total_steps": 210, "loss": 0.7271, "learning_rate": 3.2985341277917846e-07, "epoch": 3.8857142857142857, "percentage": 64.76, "elapsed_time": "0:10:33", "remaining_time": "0:05:44", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 137, "total_steps": 210, "loss": 0.7287, "learning_rate": 3.221030765387417e-07, "epoch": 3.914285714285714, "percentage": 65.24, "elapsed_time": "0:10:38", "remaining_time": "0:05:40", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 138, "total_steps": 210, "loss": 0.7441, "learning_rate": 3.1440137554088953e-07, "epoch": 3.942857142857143, "percentage": 65.71, "elapsed_time": "0:10:42", "remaining_time": "0:05:35", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 139, "total_steps": 210, "loss": 0.7349, "learning_rate": 3.06750415353774e-07, "epoch": 3.9714285714285715, "percentage": 66.19, "elapsed_time": "0:10:47", "remaining_time": "0:05:30", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 140, "total_steps": 210, "loss": 0.7377, "learning_rate": 2.9915228767351535e-07, "epoch": 4.0, "percentage": 66.67, "elapsed_time": "0:10:52", "remaining_time": "0:05:26", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 141, "total_steps": 210, "loss": 0.6864, "learning_rate": 2.916090697523549e-07, "epoch": 4.0285714285714285, "percentage": 67.14, "elapsed_time": "0:10:56", "remaining_time": "0:05:21", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 142, "total_steps": 210, "loss": 0.7073, "learning_rate": 2.841228238307536e-07, "epoch": 4.057142857142857, "percentage": 67.62, "elapsed_time": "0:11:01", "remaining_time": "0:05:16", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 143, "total_steps": 210, "loss": 0.6669, "learning_rate": 2.7669559657359673e-07, "epoch": 4.085714285714285, "percentage": 68.1, "elapsed_time": "0:11:06", "remaining_time": "0:05:12", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 144, "total_steps": 210, "loss": 0.6673, "learning_rate": 2.6932941851065615e-07, "epoch": 4.114285714285714, "percentage": 68.57, "elapsed_time": "0:11:10", "remaining_time": "0:05:07", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 145, "total_steps": 210, "loss": 0.6644, "learning_rate": 2.620263034814632e-07, "epoch": 4.142857142857143, "percentage": 69.05, "elapsed_time": "0:11:15", "remaining_time": "0:05:02", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 146, "total_steps": 210, "loss": 0.6568, "learning_rate": 2.547882480847461e-07, "epoch": 4.171428571428572, "percentage": 69.52, "elapsed_time": "0:11:20", "remaining_time": "0:04:58", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 147, "total_steps": 210, "loss": 0.7048, "learning_rate": 2.476172311325783e-07, "epoch": 4.2, "percentage": 70.0, "elapsed_time": "0:11:24", "remaining_time": "0:04:53", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 148, "total_steps": 210, "loss": 0.7082, "learning_rate": 2.4051521310939254e-07, "epoch": 4.228571428571429, "percentage": 70.48, "elapsed_time": "0:11:29", "remaining_time": "0:04:48", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 149, "total_steps": 210, "loss": 0.6497, "learning_rate": 2.3348413563600323e-07, "epoch": 4.257142857142857, "percentage": 70.95, "elapsed_time": "0:11:34", "remaining_time": "0:04:44", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 150, "total_steps": 210, "loss": 0.6851, "learning_rate": 2.2652592093878665e-07, "epoch": 4.285714285714286, "percentage": 71.43, "elapsed_time": "0:11:38", "remaining_time": "0:04:39", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 151, "total_steps": 210, "loss": 0.6974, "learning_rate": 2.1964247132416368e-07, "epoch": 4.314285714285714, "percentage": 71.9, "elapsed_time": "0:11:43", "remaining_time": "0:04:34", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 152, "total_steps": 210, "loss": 0.6439, "learning_rate": 2.128356686585282e-07, "epoch": 4.3428571428571425, "percentage": 72.38, "elapsed_time": "0:11:48", "remaining_time": "0:04:30", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 153, "total_steps": 210, "loss": 0.7215, "learning_rate": 2.0610737385376348e-07, "epoch": 4.371428571428572, "percentage": 72.86, "elapsed_time": "0:11:52", "remaining_time": "0:04:25", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 154, "total_steps": 210, "loss": 0.644, "learning_rate": 1.9945942635848745e-07, "epoch": 4.4, "percentage": 73.33, "elapsed_time": "0:11:56", "remaining_time": "0:04:20", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 155, "total_steps": 210, "loss": 0.6397, "learning_rate": 1.9289364365516607e-07, "epoch": 4.428571428571429, "percentage": 73.81, "elapsed_time": "0:12:01", "remaining_time": "0:04:16", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 156, "total_steps": 210, "loss": 0.689, "learning_rate": 1.8641182076323148e-07, "epoch": 4.457142857142857, "percentage": 74.29, "elapsed_time": "0:12:05", "remaining_time": "0:04:11", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 157, "total_steps": 210, "loss": 0.6466, "learning_rate": 1.8001572974834168e-07, "epoch": 4.485714285714286, "percentage": 74.76, "elapsed_time": "0:12:10", "remaining_time": "0:04:06", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 158, "total_steps": 210, "loss": 0.6691, "learning_rate": 1.7370711923791564e-07, "epoch": 4.514285714285714, "percentage": 75.24, "elapsed_time": "0:12:15", "remaining_time": "0:04:01", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 159, "total_steps": 210, "loss": 0.6432, "learning_rate": 1.674877139430758e-07, "epoch": 4.542857142857143, "percentage": 75.71, "elapsed_time": "0:12:19", "remaining_time": "0:03:57", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 160, "total_steps": 210, "loss": 0.6685, "learning_rate": 1.6135921418712955e-07, "epoch": 4.571428571428571, "percentage": 76.19, "elapsed_time": "0:12:24", "remaining_time": "0:03:52", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 161, "total_steps": 210, "loss": 0.657, "learning_rate": 1.553232954407171e-07, "epoch": 4.6, "percentage": 76.67, "elapsed_time": "0:12:29", "remaining_time": "0:03:48", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 162, "total_steps": 210, "loss": 0.6671, "learning_rate": 1.493816078637557e-07, "epoch": 4.628571428571428, "percentage": 77.14, "elapsed_time": "0:12:33", "remaining_time": "0:03:43", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 163, "total_steps": 210, "loss": 0.7393, "learning_rate": 1.435357758543015e-07, "epoch": 4.6571428571428575, "percentage": 77.62, "elapsed_time": "0:12:38", "remaining_time": "0:03:38", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 164, "total_steps": 210, "loss": 0.6904, "learning_rate": 1.3778739760445552e-07, "epoch": 4.685714285714286, "percentage": 78.1, "elapsed_time": "0:12:43", "remaining_time": "0:03:34", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 165, "total_steps": 210, "loss": 0.7093, "learning_rate": 1.321380446634342e-07, "epoch": 4.714285714285714, "percentage": 78.57, "elapsed_time": "0:12:47", "remaining_time": "0:03:29", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 166, "total_steps": 210, "loss": 0.6588, "learning_rate": 1.2658926150792322e-07, "epoch": 4.742857142857143, "percentage": 79.05, "elapsed_time": "0:12:52", "remaining_time": "0:03:24", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 167, "total_steps": 210, "loss": 0.6914, "learning_rate": 1.2114256511983274e-07, "epoch": 4.771428571428571, "percentage": 79.52, "elapsed_time": "0:12:56", "remaining_time": "0:03:20", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 168, "total_steps": 210, "loss": 0.6819, "learning_rate": 1.1579944457157059e-07, "epoch": 4.8, "percentage": 80.0, "elapsed_time": "0:13:01", "remaining_time": "0:03:15", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 169, "total_steps": 210, "loss": 0.7107, "learning_rate": 1.1056136061894384e-07, "epoch": 4.828571428571428, "percentage": 80.48, "elapsed_time": "0:13:05", "remaining_time": "0:03:10", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 170, "total_steps": 210, "loss": 0.6577, "learning_rate": 1.0542974530180327e-07, "epoch": 4.857142857142857, "percentage": 80.95, "elapsed_time": "0:13:10", "remaining_time": "0:03:06", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 171, "total_steps": 210, "loss": 0.6926, "learning_rate": 1.0040600155253764e-07, "epoch": 4.885714285714286, "percentage": 81.43, "elapsed_time": "0:13:15", "remaining_time": "0:03:01", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 172, "total_steps": 210, "loss": 0.6824, "learning_rate": 9.549150281252632e-08, "epoch": 4.914285714285715, "percentage": 81.9, "elapsed_time": "0:13:19", "remaining_time": "0:02:56", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 173, "total_steps": 210, "loss": 0.6293, "learning_rate": 9.068759265665382e-08, "epoch": 4.942857142857143, "percentage": 82.38, "elapsed_time": "0:13:24", "remaining_time": "0:02:52", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 174, "total_steps": 210, "loss": 0.7605, "learning_rate": 8.599558442598998e-08, "epoch": 4.9714285714285715, "percentage": 82.86, "elapsed_time": "0:13:29", "remaining_time": "0:02:47", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 175, "total_steps": 210, "loss": 0.6685, "learning_rate": 8.141676086873573e-08, "epoch": 5.0, "percentage": 83.33, "elapsed_time": "0:13:33", "remaining_time": "0:02:42", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 176, "total_steps": 210, "loss": 0.6178, "learning_rate": 7.695237378953224e-08, "epoch": 5.0285714285714285, "percentage": 83.81, "elapsed_time": "0:13:38", "remaining_time": "0:02:38", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 177, "total_steps": 210, "loss": 0.6338, "learning_rate": 7.260364370723043e-08, "epoch": 5.057142857142857, "percentage": 84.29, "elapsed_time": "0:13:43", "remaining_time": "0:02:33", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 178, "total_steps": 210, "loss": 0.656, "learning_rate": 6.837175952121304e-08, "epoch": 5.085714285714285, "percentage": 84.76, "elapsed_time": "0:13:47", "remaining_time": "0:02:28", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 179, "total_steps": 210, "loss": 0.7062, "learning_rate": 6.42578781863613e-08, "epoch": 5.114285714285714, "percentage": 85.24, "elapsed_time": "0:13:52", "remaining_time": "0:02:24", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 180, "total_steps": 210, "loss": 0.6132, "learning_rate": 6.026312439675551e-08, "epoch": 5.142857142857143, "percentage": 85.71, "elapsed_time": "0:13:57", "remaining_time": "0:02:19", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 181, "total_steps": 210, "loss": 0.6846, "learning_rate": 5.638859027819409e-08, "epoch": 5.171428571428572, "percentage": 86.19, "elapsed_time": "0:14:01", "remaining_time": "0:02:14", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 182, "total_steps": 210, "loss": 0.695, "learning_rate": 5.263533508961826e-08, "epoch": 5.2, "percentage": 86.67, "elapsed_time": "0:14:06", "remaining_time": "0:02:10", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 183, "total_steps": 210, "loss": 0.6363, "learning_rate": 4.9004384933520547e-08, "epoch": 5.228571428571429, "percentage": 87.14, "elapsed_time": "0:14:11", "remaining_time": "0:02:05", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 184, "total_steps": 210, "loss": 0.6197, "learning_rate": 4.549673247541874e-08, "epoch": 5.257142857142857, "percentage": 87.62, "elapsed_time": "0:14:15", "remaining_time": "0:02:00", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 185, "total_steps": 210, "loss": 0.6325, "learning_rate": 4.2113336672471245e-08, "epoch": 5.285714285714286, "percentage": 88.1, "elapsed_time": "0:14:20", "remaining_time": "0:01:56", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 186, "total_steps": 210, "loss": 0.6074, "learning_rate": 3.8855122511307626e-08, "epoch": 5.314285714285714, "percentage": 88.57, "elapsed_time": "0:14:24", "remaining_time": "0:01:51", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 187, "total_steps": 210, "loss": 0.6298, "learning_rate": 3.572298075514652e-08, "epoch": 5.3428571428571425, "percentage": 89.05, "elapsed_time": "0:14:29", "remaining_time": "0:01:46", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 188, "total_steps": 210, "loss": 0.5991, "learning_rate": 3.271776770026963e-08, "epoch": 5.371428571428572, "percentage": 89.52, "elapsed_time": "0:14:34", "remaining_time": "0:01:42", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 189, "total_steps": 210, "loss": 0.6917, "learning_rate": 2.9840304941919416e-08, "epoch": 5.4, "percentage": 90.0, "elapsed_time": "0:14:38", "remaining_time": "0:01:37", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 190, "total_steps": 210, "loss": 0.6592, "learning_rate": 2.7091379149682682e-08, "epoch": 5.428571428571429, "percentage": 90.48, "elapsed_time": "0:14:43", "remaining_time": "0:01:32", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 191, "total_steps": 210, "loss": 0.6467, "learning_rate": 2.4471741852423233e-08, "epoch": 5.457142857142857, "percentage": 90.95, "elapsed_time": "0:14:48", "remaining_time": "0:01:28", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 192, "total_steps": 210, "loss": 0.6471, "learning_rate": 2.1982109232821176e-08, "epoch": 5.485714285714286, "percentage": 91.43, "elapsed_time": "0:14:52", "remaining_time": "0:01:23", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 193, "total_steps": 210, "loss": 0.6537, "learning_rate": 1.9623161931575926e-08, "epoch": 5.514285714285714, "percentage": 91.9, "elapsed_time": "0:14:57", "remaining_time": "0:01:19", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 194, "total_steps": 210, "loss": 0.6647, "learning_rate": 1.7395544861325718e-08, "epoch": 5.542857142857143, "percentage": 92.38, "elapsed_time": "0:15:02", "remaining_time": "0:01:14", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 195, "total_steps": 210, "loss": 0.6422, "learning_rate": 1.5299867030334813e-08, "epoch": 5.571428571428571, "percentage": 92.86, "elapsed_time": "0:15:06", "remaining_time": "0:01:09", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 196, "total_steps": 210, "loss": 0.7141, "learning_rate": 1.3336701375997127e-08, "epoch": 5.6, "percentage": 93.33, "elapsed_time": "0:15:11", "remaining_time": "0:01:05", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 197, "total_steps": 210, "loss": 0.6423, "learning_rate": 1.1506584608200364e-08, "epoch": 5.628571428571428, "percentage": 93.81, "elapsed_time": "0:15:16", "remaining_time": "0:01:00", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 198, "total_steps": 210, "loss": 0.6362, "learning_rate": 9.810017062595321e-09, "epoch": 5.6571428571428575, "percentage": 94.29, "elapsed_time": "0:15:20", "remaining_time": "0:00:55", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 199, "total_steps": 210, "loss": 0.6436, "learning_rate": 8.247462563808816e-09, "epoch": 5.685714285714286, "percentage": 94.76, "elapsed_time": "0:15:25", "remaining_time": "0:00:51", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 200, "total_steps": 210, "loss": 0.6434, "learning_rate": 6.819348298638839e-09, "epoch": 5.714285714285714, "percentage": 95.24, "elapsed_time": "0:15:29", "remaining_time": "0:00:46", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 200, "total_steps": 210, "eval_loss": 1.0673894882202148, "epoch": 5.714285714285714, "percentage": 95.24, "elapsed_time": "0:15:31", "remaining_time": "0:00:46", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 201, "total_steps": 210, "loss": 0.6946, "learning_rate": 5.526064699265753e-09, "epoch": 5.742857142857143, "percentage": 95.71, "elapsed_time": "0:15:35", "remaining_time": "0:00:41", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 202, "total_steps": 210, "loss": 0.6113, "learning_rate": 4.367965336512403e-09, "epoch": 5.771428571428571, "percentage": 96.19, "elapsed_time": "0:15:40", "remaining_time": "0:00:37", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 203, "total_steps": 210, "loss": 0.6493, "learning_rate": 3.3453668231809283e-09, "epoch": 5.8, "percentage": 96.67, "elapsed_time": "0:15:45", "remaining_time": "0:00:32", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 204, "total_steps": 210, "loss": 0.653, "learning_rate": 2.458548727494292e-09, "epoch": 5.828571428571428, "percentage": 97.14, "elapsed_time": "0:15:49", "remaining_time": "0:00:27", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 205, "total_steps": 210, "loss": 0.6527, "learning_rate": 1.7077534966650765e-09, "epoch": 5.857142857142857, "percentage": 97.62, "elapsed_time": "0:15:54", "remaining_time": "0:00:23", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 206, "total_steps": 210, "loss": 0.6935, "learning_rate": 1.0931863906127325e-09, "epoch": 5.885714285714286, "percentage": 98.1, "elapsed_time": "0:15:58", "remaining_time": "0:00:18", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 207, "total_steps": 210, "loss": 0.6559, "learning_rate": 6.150154258476314e-10, "epoch": 5.914285714285715, "percentage": 98.57, "elapsed_time": "0:16:03", "remaining_time": "0:00:13", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 208, "total_steps": 210, "loss": 0.693, "learning_rate": 2.733713295369755e-10, "epoch": 5.942857142857143, "percentage": 99.05, "elapsed_time": "0:16:08", "remaining_time": "0:00:09", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 209, "total_steps": 210, "loss": 0.7231, "learning_rate": 6.834750376549791e-11, "epoch": 5.9714285714285715, "percentage": 99.52, "elapsed_time": "0:16:12", "remaining_time": "0:00:04", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 210, "total_steps": 210, "loss": 0.6288, "learning_rate": 0.0, "epoch": 6.0, "percentage": 100.0, "elapsed_time": "0:16:17", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
{"current_steps": 210, "total_steps": 210, "epoch": 6.0, "percentage": 100.0, "elapsed_time": "0:17:11", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}