trainer_log.jsonl

{"current_steps": 200, "total_steps": 2925, "loss": 1.0325, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.942542412504543e-05, "epoch": 0.07, "percentage": 6.84, "elapsed_time": "0:02:50", "remaining_time": "0:38:44"}
{"current_steps": 200, "total_steps": 2925, "loss": null, "eval_loss": 0.8921748995780945, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.07, "percentage": 6.84, "elapsed_time": "0:02:50", "remaining_time": "0:38:44"}
{"current_steps": 400, "total_steps": 2925, "loss": 0.9136, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.77281074950681e-05, "epoch": 0.14, "percentage": 13.68, "elapsed_time": "0:07:37", "remaining_time": "0:48:09"}
{"current_steps": 400, "total_steps": 2925, "loss": null, "eval_loss": 0.880075991153717, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.14, "percentage": 13.68, "elapsed_time": "0:07:37", "remaining_time": "0:48:09"}
{"current_steps": 600, "total_steps": 2925, "loss": 0.9043, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.498606908508754e-05, "epoch": 0.21, "percentage": 20.51, "elapsed_time": "0:12:23", "remaining_time": "0:48:01"}
{"current_steps": 600, "total_steps": 2925, "loss": null, "eval_loss": 0.8752565979957581, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.21, "percentage": 20.51, "elapsed_time": "0:12:23", "remaining_time": "0:48:01"}
{"current_steps": 800, "total_steps": 2925, "loss": 0.8903, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.132534962458962e-05, "epoch": 0.27, "percentage": 27.35, "elapsed_time": "0:17:08", "remaining_time": "0:45:33"}
{"current_steps": 800, "total_steps": 2925, "loss": null, "eval_loss": 0.8710557222366333, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.27, "percentage": 27.35, "elapsed_time": "0:17:08", "remaining_time": "0:45:33"}
{"current_steps": 1000, "total_steps": 2925, "loss": 0.9056, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.69142180005327e-05, "epoch": 0.34, "percentage": 34.19, "elapsed_time": "0:21:59", "remaining_time": "0:42:20"}
{"current_steps": 1000, "total_steps": 2925, "loss": null, "eval_loss": 0.8682616949081421, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.34, "percentage": 34.19, "elapsed_time": "0:21:59", "remaining_time": "0:42:20"}
{"current_steps": 1200, "total_steps": 2925, "loss": 0.9001, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.195543659791132e-05, "epoch": 0.41, "percentage": 41.03, "elapsed_time": "0:26:49", "remaining_time": "0:38:33"}
{"current_steps": 1200, "total_steps": 2925, "loss": null, "eval_loss": 0.867277204990387, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.41, "percentage": 41.03, "elapsed_time": "0:26:49", "remaining_time": "0:38:33"}
{"current_steps": 1400, "total_steps": 2925, "loss": 0.8949, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.667694110977506e-05, "epoch": 0.48, "percentage": 47.86, "elapsed_time": "0:31:39", "remaining_time": "0:34:29"}
{"current_steps": 1400, "total_steps": 2925, "loss": null, "eval_loss": 0.8667991161346436, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.48, "percentage": 47.86, "elapsed_time": "0:31:39", "remaining_time": "0:34:29"}
{"current_steps": 1600, "total_steps": 2925, "loss": 0.8917, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1321363229207096e-05, "epoch": 0.55, "percentage": 54.7, "elapsed_time": "0:36:29", "remaining_time": "0:30:13"}
{"current_steps": 1600, "total_steps": 2925, "loss": null, "eval_loss": 0.8655699491500854, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.55, "percentage": 54.7, "elapsed_time": "0:36:29", "remaining_time": "0:30:13"}
{"current_steps": 1800, "total_steps": 2925, "loss": 0.8951, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.613487782393661e-05, "epoch": 0.62, "percentage": 61.54, "elapsed_time": "0:41:18", "remaining_time": "0:25:49"}
{"current_steps": 1800, "total_steps": 2925, "loss": null, "eval_loss": 0.8647685050964355, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.62, "percentage": 61.54, "elapsed_time": "0:41:18", "remaining_time": "0:25:49"}
{"current_steps": 2000, "total_steps": 2925, "loss": 0.9014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1355887245137383e-05, "epoch": 0.68, "percentage": 68.38, "elapsed_time": "0:46:05", "remaining_time": "0:21:18"}
{"current_steps": 2000, "total_steps": 2925, "loss": null, "eval_loss": 0.8637479543685913, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.68, "percentage": 68.38, "elapsed_time": "0:46:05", "remaining_time": "0:21:18"}
{"current_steps": 2200, "total_steps": 2925, "loss": 0.8874, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.20406290826649e-06, "epoch": 0.75, "percentage": 75.21, "elapsed_time": "0:50:52", "remaining_time": "0:16:45"}
{"current_steps": 2200, "total_steps": 2925, "loss": null, "eval_loss": 0.8629816174507141, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.75, "percentage": 75.21, "elapsed_time": "0:50:52", "remaining_time": "0:16:45"}
{"current_steps": 2400, "total_steps": 2925, "loss": 0.8968, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8702478614051355e-06, "epoch": 0.82, "percentage": 82.05, "elapsed_time": "0:55:40", "remaining_time": "0:12:10"}
{"current_steps": 2400, "total_steps": 2925, "loss": null, "eval_loss": 0.8628040552139282, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.82, "percentage": 82.05, "elapsed_time": "0:55:40", "remaining_time": "0:12:10"}
{"current_steps": 2600, "total_steps": 2925, "loss": 0.8755, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5076844803522922e-06, "epoch": 0.89, "percentage": 88.89, "elapsed_time": "1:00:29", "remaining_time": "0:07:33"}
{"current_steps": 2600, "total_steps": 2925, "loss": null, "eval_loss": 0.8626384735107422, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.89, "percentage": 88.89, "elapsed_time": "1:00:29", "remaining_time": "0:07:33"}
{"current_steps": 2800, "total_steps": 2925, "loss": 0.9029, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2497051885228827e-07, "epoch": 0.96, "percentage": 95.73, "elapsed_time": "1:05:20", "remaining_time": "0:02:55"}
{"current_steps": 2800, "total_steps": 2925, "loss": null, "eval_loss": 0.8625245094299316, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.96, "percentage": 95.73, "elapsed_time": "1:05:20", "remaining_time": "0:02:55"}
{"current_steps": 2925, "total_steps": 2925, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:09:07", "remaining_time": "0:00:00"}
{"current_steps": 2601, "total_steps": 2601, "loss": null, "eval_loss": 0.862533688545227, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:11:07", "remaining_time": "0:00:00"}