trainer_log.jsonl

{"current_steps": 5, "total_steps": 250, "loss": 1.8035, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00019980267284282717, "epoch": 0.04, "percentage": 2.0, "elapsed_time": "0:00:06", "remaining_time": "0:05:37"}
{"current_steps": 10, "total_steps": 250, "loss": 1.7043, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.0001992114701314478, "epoch": 0.08, "percentage": 4.0, "elapsed_time": "0:00:13", "remaining_time": "0:05:32"}
{"current_steps": 15, "total_steps": 250, "loss": 1.5984, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.0001982287250728689, "epoch": 0.12, "percentage": 6.0, "elapsed_time": "0:00:20", "remaining_time": "0:05:22"}
{"current_steps": 20, "total_steps": 250, "loss": 1.6024, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.0001968583161128631, "epoch": 0.16, "percentage": 8.0, "elapsed_time": "0:00:27", "remaining_time": "0:05:20"}
{"current_steps": 25, "total_steps": 250, "loss": 1.4862, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00019510565162951537, "epoch": 0.2, "percentage": 10.0, "elapsed_time": "0:00:34", "remaining_time": "0:05:11"}
{"current_steps": 30, "total_steps": 250, "loss": 1.5183, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00019297764858882514, "epoch": 0.24, "percentage": 12.0, "elapsed_time": "0:00:41", "remaining_time": "0:05:06"}
{"current_steps": 35, "total_steps": 250, "loss": 1.396, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00019048270524660196, "epoch": 0.28, "percentage": 14.0, "elapsed_time": "0:00:49", "remaining_time": "0:05:01"}
{"current_steps": 40, "total_steps": 250, "loss": 1.5583, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00018763066800438636, "epoch": 0.32, "percentage": 16.0, "elapsed_time": "0:00:55", "remaining_time": "0:04:53"}
{"current_steps": 45, "total_steps": 250, "loss": 1.4023, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00018443279255020152, "epoch": 0.36, "percentage": 18.0, "elapsed_time": "0:01:03", "remaining_time": "0:04:48"}
{"current_steps": 50, "total_steps": 250, "loss": 1.4386, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00018090169943749476, "epoch": 0.4, "percentage": 20.0, "elapsed_time": "0:01:10", "remaining_time": "0:04:41"}
{"current_steps": 55, "total_steps": 250, "loss": 1.4218, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00017705132427757895, "epoch": 0.44, "percentage": 22.0, "elapsed_time": "0:01:17", "remaining_time": "0:04:33"}
{"current_steps": 60, "total_steps": 250, "loss": 1.4874, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00017289686274214118, "epoch": 0.48, "percentage": 24.0, "elapsed_time": "0:01:24", "remaining_time": "0:04:26"}
{"current_steps": 65, "total_steps": 250, "loss": 1.4279, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00016845471059286887, "epoch": 0.52, "percentage": 26.0, "elapsed_time": "0:01:32", "remaining_time": "0:04:21"}
{"current_steps": 70, "total_steps": 250, "loss": 1.4142, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.000163742398974869, "epoch": 0.56, "percentage": 28.0, "elapsed_time": "0:01:40", "remaining_time": "0:04:17"}
{"current_steps": 75, "total_steps": 250, "loss": 1.3489, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00015877852522924732, "epoch": 0.6, "percentage": 30.0, "elapsed_time": "0:01:47", "remaining_time": "0:04:11"}
{"current_steps": 80, "total_steps": 250, "loss": 1.4629, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00015358267949789966, "epoch": 0.64, "percentage": 32.0, "elapsed_time": "0:01:54", "remaining_time": "0:04:03"}
{"current_steps": 85, "total_steps": 250, "loss": 1.3914, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00014817536741017152, "epoch": 0.68, "percentage": 34.0, "elapsed_time": "0:02:01", "remaining_time": "0:03:55"}
{"current_steps": 90, "total_steps": 250, "loss": 1.407, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00014257792915650728, "epoch": 0.72, "percentage": 36.0, "elapsed_time": "0:02:09", "remaining_time": "0:03:49"}
{"current_steps": 95, "total_steps": 250, "loss": 1.3214, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00013681245526846783, "epoch": 0.76, "percentage": 38.0, "elapsed_time": "0:02:16", "remaining_time": "0:03:42"}
{"current_steps": 100, "total_steps": 250, "loss": 1.5119, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00013090169943749476, "epoch": 0.8, "percentage": 40.0, "elapsed_time": "0:02:23", "remaining_time": "0:03:35"}
{"current_steps": 105, "total_steps": 250, "loss": 1.431, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.0001248689887164855, "epoch": 0.84, "percentage": 42.0, "elapsed_time": "0:02:32", "remaining_time": "0:03:30"}
{"current_steps": 110, "total_steps": 250, "loss": 1.3285, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00011873813145857249, "epoch": 0.88, "percentage": 44.0, "elapsed_time": "0:02:39", "remaining_time": "0:03:23"}
{"current_steps": 115, "total_steps": 250, "loss": 1.486, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00011253332335643043, "epoch": 0.92, "percentage": 46.0, "elapsed_time": "0:02:46", "remaining_time": "0:03:15"}
{"current_steps": 120, "total_steps": 250, "loss": 1.3244, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.00010627905195293135, "epoch": 0.96, "percentage": 48.0, "elapsed_time": "0:02:55", "remaining_time": "0:03:09"}
{"current_steps": 125, "total_steps": 250, "loss": 1.4051, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.0001, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:03:01", "remaining_time": "0:03:01"}
{"current_steps": 130, "total_steps": 250, "loss": 1.3832, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 9.372094804706867e-05, "epoch": 1.04, "percentage": 52.0, "elapsed_time": "0:03:08", "remaining_time": "0:02:53"}
{"current_steps": 135, "total_steps": 250, "loss": 1.3841, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 8.746667664356956e-05, "epoch": 1.08, "percentage": 54.0, "elapsed_time": "0:03:16", "remaining_time": "0:02:46"}
{"current_steps": 140, "total_steps": 250, "loss": 1.4901, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 8.126186854142752e-05, "epoch": 1.12, "percentage": 56.0, "elapsed_time": "0:03:23", "remaining_time": "0:02:39"}
{"current_steps": 145, "total_steps": 250, "loss": 1.3792, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 7.513101128351454e-05, "epoch": 1.16, "percentage": 58.0, "elapsed_time": "0:03:30", "remaining_time": "0:02:32"}
{"current_steps": 150, "total_steps": 250, "loss": 1.3908, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 6.909830056250527e-05, "epoch": 1.2, "percentage": 60.0, "elapsed_time": "0:03:39", "remaining_time": "0:02:26"}
{"current_steps": 155, "total_steps": 250, "loss": 1.3803, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 6.318754473153221e-05, "epoch": 1.24, "percentage": 62.0, "elapsed_time": "0:03:46", "remaining_time": "0:02:18"}
{"current_steps": 160, "total_steps": 250, "loss": 1.3799, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 5.7422070843492734e-05, "epoch": 1.28, "percentage": 64.0, "elapsed_time": "0:03:54", "remaining_time": "0:02:11"}
{"current_steps": 165, "total_steps": 250, "loss": 1.4348, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 5.182463258982846e-05, "epoch": 1.32, "percentage": 66.0, "elapsed_time": "0:04:01", "remaining_time": "0:02:04"}
{"current_steps": 170, "total_steps": 250, "loss": 1.4014, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.6417320502100316e-05, "epoch": 1.36, "percentage": 68.0, "elapsed_time": "0:04:08", "remaining_time": "0:01:57"}
{"current_steps": 175, "total_steps": 250, "loss": 1.3101, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.12214747707527e-05, "epoch": 1.4, "percentage": 70.0, "elapsed_time": "0:04:16", "remaining_time": "0:01:50"}
{"current_steps": 180, "total_steps": 250, "loss": 1.3661, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.6257601025131026e-05, "epoch": 1.44, "percentage": 72.0, "elapsed_time": "0:04:23", "remaining_time": "0:01:42"}
{"current_steps": 185, "total_steps": 250, "loss": 1.3185, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.154528940713113e-05, "epoch": 1.48, "percentage": 74.0, "elapsed_time": "0:04:30", "remaining_time": "0:01:35"}
{"current_steps": 190, "total_steps": 250, "loss": 1.348, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.7103137257858868e-05, "epoch": 1.52, "percentage": 76.0, "elapsed_time": "0:04:38", "remaining_time": "0:01:27"}
{"current_steps": 195, "total_steps": 250, "loss": 1.4324, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.2948675722421086e-05, "epoch": 1.56, "percentage": 78.0, "elapsed_time": "0:04:45", "remaining_time": "0:01:20"}
{"current_steps": 200, "total_steps": 250, "loss": 1.4251, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.9098300562505266e-05, "epoch": 1.6, "percentage": 80.0, "elapsed_time": "0:04:53", "remaining_time": "0:01:13"}
{"current_steps": 205, "total_steps": 250, "loss": 1.2895, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.5567207449798515e-05, "epoch": 1.64, "percentage": 82.0, "elapsed_time": "0:05:02", "remaining_time": "0:01:06"}
{"current_steps": 210, "total_steps": 250, "loss": 1.2964, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.2369331995613665e-05, "epoch": 1.68, "percentage": 84.0, "elapsed_time": "0:05:10", "remaining_time": "0:00:59"}
{"current_steps": 215, "total_steps": 250, "loss": 1.4526, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 9.517294753398064e-06, "epoch": 1.72, "percentage": 86.0, "elapsed_time": "0:05:19", "remaining_time": "0:00:51"}
{"current_steps": 220, "total_steps": 250, "loss": 1.4139, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 7.022351411174866e-06, "epoch": 1.76, "percentage": 88.0, "elapsed_time": "0:05:25", "remaining_time": "0:00:44"}
{"current_steps": 225, "total_steps": 250, "loss": 1.3556, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.8943483704846475e-06, "epoch": 1.8, "percentage": 90.0, "elapsed_time": "0:05:34", "remaining_time": "0:00:37"}
{"current_steps": 230, "total_steps": 250, "loss": 1.3191, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.1416838871368924e-06, "epoch": 1.84, "percentage": 92.0, "elapsed_time": "0:05:41", "remaining_time": "0:00:29"}
{"current_steps": 235, "total_steps": 250, "loss": 1.4144, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.771274927131139e-06, "epoch": 1.88, "percentage": 94.0, "elapsed_time": "0:05:47", "remaining_time": "0:00:22"}
{"current_steps": 240, "total_steps": 250, "loss": 1.4032, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 7.885298685522235e-07, "epoch": 1.92, "percentage": 96.0, "elapsed_time": "0:05:54", "remaining_time": "0:00:14"}
{"current_steps": 245, "total_steps": 250, "loss": 1.3548, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.973271571728441e-07, "epoch": 1.96, "percentage": 98.0, "elapsed_time": "0:06:02", "remaining_time": "0:00:07"}
{"current_steps": 250, "total_steps": 250, "loss": 1.3039, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:06:09", "remaining_time": "0:00:00"}
{"current_steps": 250, "total_steps": 250, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:06:09", "remaining_time": "0:00:00"}