Saiga-lora-2048-2epochs / trainer_log.jsonl
SouthMemphis's picture
Upload 13 files
2c2ca11 verified
{"current_steps": 10, "total_steps": 500, "loss": 1.1181, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.995066821070679e-05, "epoch": 0.04, "percentage": 2.0, "elapsed_time": "0:03:27", "remaining_time": "2:49:43"}
{"current_steps": 20, "total_steps": 500, "loss": 1.048, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.980286753286195e-05, "epoch": 0.08, "percentage": 4.0, "elapsed_time": "0:06:48", "remaining_time": "2:43:31"}
{"current_steps": 30, "total_steps": 500, "loss": 1.0172, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9557181268217227e-05, "epoch": 0.12, "percentage": 6.0, "elapsed_time": "0:10:17", "remaining_time": "2:41:06"}
{"current_steps": 40, "total_steps": 500, "loss": 1.0621, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9214579028215776e-05, "epoch": 0.16, "percentage": 8.0, "elapsed_time": "0:13:47", "remaining_time": "2:38:37"}
{"current_steps": 50, "total_steps": 500, "loss": 0.994, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.877641290737884e-05, "epoch": 0.2, "percentage": 10.0, "elapsed_time": "0:17:12", "remaining_time": "2:34:51"}
{"current_steps": 60, "total_steps": 500, "loss": 1.0483, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8244412147206284e-05, "epoch": 0.24, "percentage": 12.0, "elapsed_time": "0:20:40", "remaining_time": "2:31:34"}
{"current_steps": 70, "total_steps": 500, "loss": 1.0077, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.762067631165049e-05, "epoch": 0.28, "percentage": 14.0, "elapsed_time": "0:24:05", "remaining_time": "2:27:57"}
{"current_steps": 80, "total_steps": 500, "loss": 0.9627, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.690766700109659e-05, "epoch": 0.32, "percentage": 16.0, "elapsed_time": "0:27:23", "remaining_time": "2:23:47"}
{"current_steps": 90, "total_steps": 500, "loss": 0.9753, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.610819813755038e-05, "epoch": 0.36, "percentage": 18.0, "elapsed_time": "0:30:50", "remaining_time": "2:20:28"}
{"current_steps": 100, "total_steps": 500, "loss": 1.0424, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.522542485937369e-05, "epoch": 0.4, "percentage": 20.0, "elapsed_time": "0:34:18", "remaining_time": "2:17:14"}
{"current_steps": 110, "total_steps": 500, "loss": 0.9185, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.426283106939474e-05, "epoch": 0.44, "percentage": 22.0, "elapsed_time": "0:37:39", "remaining_time": "2:13:30"}
{"current_steps": 120, "total_steps": 500, "loss": 1.0032, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3224215685535294e-05, "epoch": 0.48, "percentage": 24.0, "elapsed_time": "0:41:07", "remaining_time": "2:10:12"}
{"current_steps": 130, "total_steps": 500, "loss": 0.995, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.211367764821722e-05, "epoch": 0.52, "percentage": 26.0, "elapsed_time": "0:44:32", "remaining_time": "2:06:46"}
{"current_steps": 140, "total_steps": 500, "loss": 1.0167, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.093559974371725e-05, "epoch": 0.56, "percentage": 28.0, "elapsed_time": "0:47:53", "remaining_time": "2:03:08"}
{"current_steps": 150, "total_steps": 500, "loss": 0.9908, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.969463130731183e-05, "epoch": 0.6, "percentage": 30.0, "elapsed_time": "0:51:20", "remaining_time": "1:59:48"}
{"current_steps": 160, "total_steps": 500, "loss": 0.9903, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8395669874474915e-05, "epoch": 0.64, "percentage": 32.0, "elapsed_time": "0:54:51", "remaining_time": "1:56:34"}
{"current_steps": 170, "total_steps": 500, "loss": 1.0031, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.704384185254288e-05, "epoch": 0.68, "percentage": 34.0, "elapsed_time": "0:58:20", "remaining_time": "1:53:15"}
{"current_steps": 180, "total_steps": 500, "loss": 0.9469, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.564448228912682e-05, "epoch": 0.72, "percentage": 36.0, "elapsed_time": "1:01:43", "remaining_time": "1:49:43"}
{"current_steps": 190, "total_steps": 500, "loss": 0.9221, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.4203113817116957e-05, "epoch": 0.76, "percentage": 38.0, "elapsed_time": "1:05:11", "remaining_time": "1:46:22"}
{"current_steps": 200, "total_steps": 500, "loss": 0.9588, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.287466299138262e-05, "epoch": 0.8, "percentage": 40.0, "elapsed_time": "1:08:38", "remaining_time": "1:42:57"}
{"current_steps": 210, "total_steps": 500, "loss": 0.9762, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.1369268142084556e-05, "epoch": 0.84, "percentage": 42.0, "elapsed_time": "1:12:01", "remaining_time": "1:39:27"}
{"current_steps": 220, "total_steps": 500, "loss": 0.9577, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9838736701271514e-05, "epoch": 0.88, "percentage": 44.0, "elapsed_time": "1:15:32", "remaining_time": "1:36:08"}
{"current_steps": 230, "total_steps": 500, "loss": 1.0061, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8289108977307067e-05, "epoch": 0.92, "percentage": 46.0, "elapsed_time": "1:19:01", "remaining_time": "1:32:46"}
{"current_steps": 240, "total_steps": 500, "loss": 1.0507, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6726500642860154e-05, "epoch": 0.96, "percentage": 48.0, "elapsed_time": "1:22:24", "remaining_time": "1:29:16"}
{"current_steps": 250, "total_steps": 500, "loss": 0.951, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5157078599138977e-05, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "1:25:48", "remaining_time": "1:25:48"}
{"current_steps": 260, "total_steps": 500, "loss": 0.8208, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3587036637949388e-05, "epoch": 1.04, "percentage": 52.0, "elapsed_time": "1:29:13", "remaining_time": "1:22:21"}
{"current_steps": 270, "total_steps": 500, "loss": 0.7953, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2022570997628256e-05, "epoch": 1.08, "percentage": 54.0, "elapsed_time": "1:32:42", "remaining_time": "1:18:58"}
{"current_steps": 280, "total_steps": 500, "loss": 0.7427, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0469855909321564e-05, "epoch": 1.12, "percentage": 56.0, "elapsed_time": "1:36:10", "remaining_time": "1:15:33"}
{"current_steps": 290, "total_steps": 500, "loss": 0.763, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.908752507440689e-05, "epoch": 1.16, "percentage": 58.0, "elapsed_time": "1:39:36", "remaining_time": "1:12:08"}
{"current_steps": 300, "total_steps": 500, "loss": 0.7914, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7573960460574133e-05, "epoch": 1.2, "percentage": 60.0, "elapsed_time": "1:43:03", "remaining_time": "1:08:42"}
{"current_steps": 310, "total_steps": 500, "loss": 0.7915, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6089703032168733e-05, "epoch": 1.24, "percentage": 62.0, "elapsed_time": "1:46:31", "remaining_time": "1:05:17"}
{"current_steps": 320, "total_steps": 500, "loss": 0.785, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4640610475167898e-05, "epoch": 1.28, "percentage": 64.0, "elapsed_time": "1:49:58", "remaining_time": "1:01:51"}
{"current_steps": 330, "total_steps": 500, "loss": 0.7762, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3232401695866687e-05, "epoch": 1.32, "percentage": 66.0, "elapsed_time": "1:53:22", "remaining_time": "0:58:24"}
{"current_steps": 340, "total_steps": 500, "loss": 0.8098, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1870634250967605e-05, "epoch": 1.36, "percentage": 68.0, "elapsed_time": "1:56:49", "remaining_time": "0:54:58"}
{"current_steps": 350, "total_steps": 500, "loss": 0.7372, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0560682414443315e-05, "epoch": 1.4, "percentage": 70.0, "elapsed_time": "2:00:16", "remaining_time": "0:51:32"}
{"current_steps": 360, "total_steps": 500, "loss": 0.8166, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.307715967732491e-06, "epoch": 1.44, "percentage": 72.0, "elapsed_time": "2:03:45", "remaining_time": "0:48:07"}
{"current_steps": 370, "total_steps": 500, "loss": 0.7472, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.116679796974388e-06, "epoch": 1.48, "percentage": 74.0, "elapsed_time": "2:07:11", "remaining_time": "0:44:41"}
{"current_steps": 380, "total_steps": 500, "loss": 0.7355, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.992274377802327e-06, "epoch": 1.52, "percentage": 76.0, "elapsed_time": "2:10:29", "remaining_time": "0:41:12"}
{"current_steps": 390, "total_steps": 500, "loss": 0.7639, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.9389372247138e-06, "epoch": 1.56, "percentage": 78.0, "elapsed_time": "2:13:50", "remaining_time": "0:37:45"}
{"current_steps": 400, "total_steps": 500, "loss": 0.8115, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.960825378228082e-06, "epoch": 1.6, "percentage": 80.0, "elapsed_time": "2:17:20", "remaining_time": "0:34:20"}
{"current_steps": 410, "total_steps": 500, "loss": 0.7761, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.061798998946459e-06, "epoch": 1.64, "percentage": 82.0, "elapsed_time": "2:20:49", "remaining_time": "0:30:54"}
{"current_steps": 420, "total_steps": 500, "loss": 0.805, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.245406133261858e-06, "epoch": 1.68, "percentage": 84.0, "elapsed_time": "2:24:19", "remaining_time": "0:27:29"}
{"current_steps": 430, "total_steps": 500, "loss": 0.7729, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.514868710840723e-06, "epoch": 1.72, "percentage": 86.0, "elapsed_time": "2:27:43", "remaining_time": "0:24:02"}
{"current_steps": 440, "total_steps": 500, "loss": 0.7135, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8730698291385518e-06, "epoch": 1.76, "percentage": 88.0, "elapsed_time": "2:31:00", "remaining_time": "0:20:35"}
{"current_steps": 450, "total_steps": 500, "loss": 0.827, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3225423751313942e-06, "epoch": 1.8, "percentage": 90.0, "elapsed_time": "2:34:20", "remaining_time": "0:17:08"}
{"current_steps": 460, "total_steps": 500, "loss": 0.7455, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.65459029168153e-07, "epoch": 1.84, "percentage": 92.0, "elapsed_time": "2:37:44", "remaining_time": "0:13:42"}
{"current_steps": 470, "total_steps": 500, "loss": 0.8043, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.036236903938285e-07, "epoch": 1.88, "percentage": 94.0, "elapsed_time": "2:41:12", "remaining_time": "0:10:17"}
{"current_steps": 480, "total_steps": 500, "loss": 0.8145, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.384643575837203e-07, "epoch": 1.92, "percentage": 96.0, "elapsed_time": "2:44:38", "remaining_time": "0:06:51"}
{"current_steps": 490, "total_steps": 500, "loss": 0.7569, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.102749348465165e-08, "epoch": 1.96, "percentage": 98.0, "elapsed_time": "2:48:05", "remaining_time": "0:03:25"}
{"current_steps": 500, "total_steps": 500, "loss": 0.7338, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.973894904597207e-09, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "2:51:35", "remaining_time": "0:00:00"}
{"current_steps": 500, "total_steps": 500, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "2:51:35", "remaining_time": "0:00:00"}