Llama-3.1-8B-Instruct_resist_30 / trainer_log.jsonl
Incomple's picture
Training in progress, epoch 0
9c9731f verified
{"current_steps": 101, "total_steps": 2015, "loss": 0.6923, "accuracy": 0.48514851927757263, "lr": 5e-07, "epoch": 0.05011163483006698, "percentage": 5.01, "elapsed_time": "0:23:46", "remaining_time": "7:30:41"}
{"current_steps": 202, "total_steps": 2015, "loss": 0.6541, "accuracy": 0.8923267126083374, "lr": 1e-06, "epoch": 0.10022326966013397, "percentage": 10.02, "elapsed_time": "0:48:11", "remaining_time": "7:12:29"}
{"current_steps": 303, "total_steps": 2015, "loss": 0.4367, "accuracy": 0.978960394859314, "lr": 9.442912300055157e-07, "epoch": 0.15033490449020095, "percentage": 15.04, "elapsed_time": "1:12:50", "remaining_time": "6:51:33"}
{"current_steps": 404, "total_steps": 2015, "loss": 0.2188, "accuracy": 0.978960394859314, "lr": 8.885824600110314e-07, "epoch": 0.20044653932026793, "percentage": 20.05, "elapsed_time": "1:36:38", "remaining_time": "6:25:23"}
{"current_steps": 505, "total_steps": 2015, "loss": 0.1223, "accuracy": 0.9764851331710815, "lr": 8.328736900165472e-07, "epoch": 0.2505581741503349, "percentage": 25.06, "elapsed_time": "2:00:47", "remaining_time": "6:01:09"}
{"current_steps": 606, "total_steps": 2015, "loss": 0.0623, "accuracy": 0.9826732277870178, "lr": 7.771649200220628e-07, "epoch": 0.3006698089804019, "percentage": 30.07, "elapsed_time": "2:24:40", "remaining_time": "5:36:23"}
{"current_steps": 707, "total_steps": 2015, "loss": 0.0399, "accuracy": 0.983910858631134, "lr": 7.214561500275785e-07, "epoch": 0.3507814438104689, "percentage": 35.09, "elapsed_time": "2:48:26", "remaining_time": "5:11:38"}
{"current_steps": 808, "total_steps": 2015, "loss": 0.0344, "accuracy": 0.9863861203193665, "lr": 6.657473800330943e-07, "epoch": 0.40089307864053586, "percentage": 40.1, "elapsed_time": "3:12:37", "remaining_time": "4:47:44"}
{"current_steps": 909, "total_steps": 2015, "loss": 0.037, "accuracy": 0.9826732277870178, "lr": 6.100386100386101e-07, "epoch": 0.45100471347060284, "percentage": 45.11, "elapsed_time": "3:36:38", "remaining_time": "4:23:35"}
{"current_steps": 1010, "total_steps": 2015, "loss": 0.0331, "accuracy": 0.9876237511634827, "lr": 5.543298400441257e-07, "epoch": 0.5011163483006698, "percentage": 50.12, "elapsed_time": "4:01:43", "remaining_time": "4:00:31"}
{"current_steps": 1111, "total_steps": 2015, "loss": 0.025, "accuracy": 0.9876237511634827, "lr": 4.986210700496414e-07, "epoch": 0.5512279831307368, "percentage": 55.14, "elapsed_time": "4:26:22", "remaining_time": "3:36:44"}
{"current_steps": 1212, "total_steps": 2015, "loss": 0.0212, "accuracy": 0.9863861203193665, "lr": 4.4291230005515716e-07, "epoch": 0.6013396179608038, "percentage": 60.15, "elapsed_time": "4:50:25", "remaining_time": "3:12:25"}
{"current_steps": 1313, "total_steps": 2015, "loss": 0.024, "accuracy": 0.9888613820075989, "lr": 3.8720353006067294e-07, "epoch": 0.6514512527908708, "percentage": 65.16, "elapsed_time": "5:14:16", "remaining_time": "2:48:01"}
{"current_steps": 1414, "total_steps": 2015, "loss": 0.025, "accuracy": 0.983910858631134, "lr": 3.3149476006618866e-07, "epoch": 0.7015628876209378, "percentage": 70.17, "elapsed_time": "5:37:35", "remaining_time": "2:23:29"}
{"current_steps": 1515, "total_steps": 2015, "loss": 0.024, "accuracy": 0.9900990128517151, "lr": 2.757859900717043e-07, "epoch": 0.7516745224510047, "percentage": 75.19, "elapsed_time": "6:01:52", "remaining_time": "1:59:25"}
{"current_steps": 1616, "total_steps": 2015, "loss": 0.0325, "accuracy": 0.9851484894752502, "lr": 2.2007722007722007e-07, "epoch": 0.8017861572810717, "percentage": 80.2, "elapsed_time": "6:25:36", "remaining_time": "1:35:12"}
{"current_steps": 1717, "total_steps": 2015, "loss": 0.0266, "accuracy": 0.9888613820075989, "lr": 1.643684500827358e-07, "epoch": 0.8518977921111387, "percentage": 85.21, "elapsed_time": "6:49:36", "remaining_time": "1:11:05"}
{"current_steps": 1818, "total_steps": 2015, "loss": 0.0283, "accuracy": 0.9876237511634827, "lr": 1.086596800882515e-07, "epoch": 0.9020094269412057, "percentage": 90.22, "elapsed_time": "7:13:55", "remaining_time": "0:47:01"}
{"current_steps": 1919, "total_steps": 2015, "loss": 0.0178, "accuracy": 0.9925742149353027, "lr": 5.295091009376723e-08, "epoch": 0.9521210617712726, "percentage": 95.24, "elapsed_time": "7:37:09", "remaining_time": "0:22:52"}
{"current_steps": 2015, "total_steps": 2015, "epoch": 0.9997519225998511, "percentage": 100.0, "elapsed_time": "7:59:29", "remaining_time": "0:00:00"}