qwen72B_models/qwen_72B_d0_iter1_model/trainer_log.jsonl

{"current_steps": 10, "total_steps": 230, "loss": 1.2798, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.5e-05, "epoch": 0.08695652173913043, "percentage": 4.35, "elapsed_time": "0:01:21", "remaining_time": "0:29:51"}
{"current_steps": 20, "total_steps": 230, "loss": 0.9826, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 5e-05, "epoch": 0.17391304347826086, "percentage": 8.7, "elapsed_time": "0:02:32", "remaining_time": "0:26:36"}
{"current_steps": 30, "total_steps": 230, "loss": 0.7455, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.972077065562821e-05, "epoch": 0.2608695652173913, "percentage": 13.04, "elapsed_time": "0:03:43", "remaining_time": "0:24:48"}
{"current_steps": 40, "total_steps": 230, "loss": 0.7768, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.888932014465352e-05, "epoch": 0.34782608695652173, "percentage": 17.39, "elapsed_time": "0:04:53", "remaining_time": "0:23:14"}
{"current_steps": 50, "total_steps": 230, "loss": 0.651, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.752422169756048e-05, "epoch": 0.43478260869565216, "percentage": 21.74, "elapsed_time": "0:06:03", "remaining_time": "0:21:49"}
{"current_steps": 60, "total_steps": 230, "loss": 0.6196, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.5655969357899874e-05, "epoch": 0.5217391304347826, "percentage": 26.09, "elapsed_time": "0:07:14", "remaining_time": "0:20:30"}
{"current_steps": 70, "total_steps": 230, "loss": 0.6283, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.332629679574566e-05, "epoch": 0.6086956521739131, "percentage": 30.43, "elapsed_time": "0:08:24", "remaining_time": "0:19:13"}
{"current_steps": 80, "total_steps": 230, "loss": 0.6584, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.058724504646834e-05, "epoch": 0.6956521739130435, "percentage": 34.78, "elapsed_time": "0:09:34", "remaining_time": "0:17:57"}
{"current_steps": 90, "total_steps": 230, "loss": 0.7047, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.7500000000000003e-05, "epoch": 0.782608695652174, "percentage": 39.13, "elapsed_time": "0:10:44", "remaining_time": "0:16:43"}
{"current_steps": 100, "total_steps": 230, "loss": 0.6153, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.413352560915988e-05, "epoch": 0.8695652173913043, "percentage": 43.48, "elapsed_time": "0:11:54", "remaining_time": "0:15:29"}
{"current_steps": 100, "total_steps": 230, "loss": null, "eval_loss": 0.6939123868942261, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.8695652173913043, "percentage": 43.48, "elapsed_time": "0:11:54", "remaining_time": "0:15:29"}
{"current_steps": 110, "total_steps": 230, "loss": 0.6807, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.056302334890786e-05, "epoch": 0.9565217391304348, "percentage": 47.83, "elapsed_time": "0:14:58", "remaining_time": "0:16:19"}
{"current_steps": 120, "total_steps": 230, "loss": 0.6801, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.686825233966061e-05, "epoch": 1.0434782608695652, "percentage": 52.17, "elapsed_time": "0:16:08", "remaining_time": "0:14:47"}
{"current_steps": 130, "total_steps": 230, "loss": 0.6434, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.3131747660339394e-05, "epoch": 1.1304347826086956, "percentage": 56.52, "elapsed_time": "0:17:19", "remaining_time": "0:13:19"}
{"current_steps": 140, "total_steps": 230, "loss": 0.5609, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.9436976651092144e-05, "epoch": 1.2173913043478262, "percentage": 60.87, "elapsed_time": "0:18:29", "remaining_time": "0:11:53"}
{"current_steps": 150, "total_steps": 230, "loss": 0.6344, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.5866474390840125e-05, "epoch": 1.3043478260869565, "percentage": 65.22, "elapsed_time": "0:19:40", "remaining_time": "0:10:29"}
{"current_steps": 160, "total_steps": 230, "loss": 0.5988, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.2500000000000006e-05, "epoch": 1.391304347826087, "percentage": 69.57, "elapsed_time": "0:20:50", "remaining_time": "0:09:07"}
{"current_steps": 170, "total_steps": 230, "loss": 0.6445, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 9.412754953531663e-06, "epoch": 1.4782608695652173, "percentage": 73.91, "elapsed_time": "0:22:00", "remaining_time": "0:07:46"}
{"current_steps": 180, "total_steps": 230, "loss": 0.6121, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 6.673703204254347e-06, "epoch": 1.5652173913043477, "percentage": 78.26, "elapsed_time": "0:23:11", "remaining_time": "0:06:26"}
{"current_steps": 190, "total_steps": 230, "loss": 0.6374, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.344030642100133e-06, "epoch": 1.6521739130434783, "percentage": 82.61, "elapsed_time": "0:24:21", "remaining_time": "0:05:07"}
{"current_steps": 200, "total_steps": 230, "loss": 0.5431, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.475778302439524e-06, "epoch": 1.7391304347826086, "percentage": 86.96, "elapsed_time": "0:25:30", "remaining_time": "0:03:49"}
{"current_steps": 200, "total_steps": 230, "loss": null, "eval_loss": 0.6907033324241638, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 1.7391304347826086, "percentage": 86.96, "elapsed_time": "0:25:30", "remaining_time": "0:03:49"}
{"current_steps": 210, "total_steps": 230, "loss": 0.601, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.1106798553464804e-06, "epoch": 1.8260869565217392, "percentage": 91.3, "elapsed_time": "0:28:30", "remaining_time": "0:02:42"}
{"current_steps": 220, "total_steps": 230, "loss": 0.6266, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.7922934437178695e-07, "epoch": 1.9130434782608696, "percentage": 95.65, "elapsed_time": "0:29:39", "remaining_time": "0:01:20"}
{"current_steps": 230, "total_steps": 230, "loss": 0.5671, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:30:50", "remaining_time": "0:00:00"}
{"current_steps": 230, "total_steps": 230, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:30:50", "remaining_time": "0:00:00"}
{"current_steps": 26, "total_steps": 26, "loss": null, "eval_loss": 0.6907033324241638, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:32:39", "remaining_time": "0:00:00"}