Llama-3.1-8B-Instruct_resist / trainer_log.jsonl
Incomple's picture
Training in progress, epoch 0
c0c12bd verified
{"current_steps": 44, "total_steps": 867, "loss": 0.6943, "accuracy": 0.4375, "lr": 5.057471264367817e-07, "epoch": 0.050720461095100866, "percentage": 5.07, "elapsed_time": "0:11:42", "remaining_time": "3:38:52"}
{"current_steps": 88, "total_steps": 867, "loss": 0.6841, "accuracy": 0.65625, "lr": 9.987179487179487e-07, "epoch": 0.10144092219020173, "percentage": 10.15, "elapsed_time": "0:23:24", "remaining_time": "3:27:15"}
{"current_steps": 132, "total_steps": 867, "loss": 0.6512, "accuracy": 0.917613685131073, "lr": 9.423076923076923e-07, "epoch": 0.1521613832853026, "percentage": 15.22, "elapsed_time": "0:34:28", "remaining_time": "3:11:57"}
{"current_steps": 176, "total_steps": 867, "loss": 0.5764, "accuracy": 0.9630681872367859, "lr": 8.858974358974358e-07, "epoch": 0.20288184438040346, "percentage": 20.3, "elapsed_time": "0:46:08", "remaining_time": "3:01:08"}
{"current_steps": 220, "total_steps": 867, "loss": 0.4526, "accuracy": 0.9715909361839294, "lr": 8.294871794871795e-07, "epoch": 0.25360230547550433, "percentage": 25.37, "elapsed_time": "0:57:35", "remaining_time": "2:49:23"}
{"current_steps": 264, "total_steps": 867, "loss": 0.3581, "accuracy": 0.96875, "lr": 7.730769230769231e-07, "epoch": 0.3043227665706052, "percentage": 30.45, "elapsed_time": "1:09:11", "remaining_time": "2:38:02"}
{"current_steps": 308, "total_steps": 867, "loss": 0.2842, "accuracy": 0.9744318723678589, "lr": 7.166666666666667e-07, "epoch": 0.35504322766570606, "percentage": 35.52, "elapsed_time": "1:20:17", "remaining_time": "2:25:43"}
{"current_steps": 352, "total_steps": 867, "loss": 0.2386, "accuracy": 0.9659091234207153, "lr": 6.602564102564102e-07, "epoch": 0.40576368876080693, "percentage": 40.6, "elapsed_time": "1:31:41", "remaining_time": "2:14:09"}
{"current_steps": 396, "total_steps": 867, "loss": 0.1872, "accuracy": 0.980113685131073, "lr": 6.038461538461538e-07, "epoch": 0.4564841498559078, "percentage": 45.67, "elapsed_time": "1:43:19", "remaining_time": "2:02:53"}
{"current_steps": 440, "total_steps": 867, "loss": 0.1813, "accuracy": 0.9772727489471436, "lr": 5.474358974358975e-07, "epoch": 0.5072046109510087, "percentage": 50.75, "elapsed_time": "1:55:02", "remaining_time": "1:51:38"}
{"current_steps": 484, "total_steps": 867, "loss": 0.1446, "accuracy": 0.9829545617103577, "lr": 4.910256410256409e-07, "epoch": 0.5579250720461095, "percentage": 55.82, "elapsed_time": "2:07:12", "remaining_time": "1:40:39"}
{"current_steps": 528, "total_steps": 867, "loss": 0.1132, "accuracy": 0.9886363744735718, "lr": 4.346153846153846e-07, "epoch": 0.6086455331412104, "percentage": 60.9, "elapsed_time": "2:18:28", "remaining_time": "1:28:54"}
{"current_steps": 572, "total_steps": 867, "loss": 0.1041, "accuracy": 0.9886363744735718, "lr": 3.782051282051282e-07, "epoch": 0.6593659942363113, "percentage": 65.97, "elapsed_time": "2:29:49", "remaining_time": "1:17:15"}
{"current_steps": 616, "total_steps": 867, "loss": 0.095, "accuracy": 0.9857954978942871, "lr": 3.217948717948718e-07, "epoch": 0.7100864553314121, "percentage": 71.05, "elapsed_time": "2:40:55", "remaining_time": "1:05:34"}
{"current_steps": 660, "total_steps": 867, "loss": 0.0878, "accuracy": 0.9857954978942871, "lr": 2.653846153846154e-07, "epoch": 0.760806916426513, "percentage": 76.12, "elapsed_time": "2:52:16", "remaining_time": "0:54:01"}
{"current_steps": 704, "total_steps": 867, "loss": 0.0715, "accuracy": 0.9857954978942871, "lr": 2.0897435897435897e-07, "epoch": 0.8115273775216139, "percentage": 81.2, "elapsed_time": "3:03:22", "remaining_time": "0:42:27"}
{"current_steps": 748, "total_steps": 867, "loss": 0.0837, "accuracy": 0.9715909361839294, "lr": 1.5256410256410257e-07, "epoch": 0.8622478386167147, "percentage": 86.27, "elapsed_time": "3:14:35", "remaining_time": "0:30:57"}
{"current_steps": 792, "total_steps": 867, "loss": 0.0751, "accuracy": 0.96875, "lr": 9.615384615384616e-08, "epoch": 0.9129682997118156, "percentage": 91.35, "elapsed_time": "3:25:42", "remaining_time": "0:19:28"}
{"current_steps": 836, "total_steps": 867, "loss": 0.0653, "accuracy": 0.980113685131073, "lr": 3.9743589743589737e-08, "epoch": 0.9636887608069165, "percentage": 96.42, "elapsed_time": "3:37:19", "remaining_time": "0:08:03"}
{"current_steps": 867, "total_steps": 867, "epoch": 0.9994236311239193, "percentage": 100.0, "elapsed_time": "3:45:41", "remaining_time": "0:00:00"}