llama3-1_8b_dolphin / trainer_log.jsonl
gsmyrnis's picture
Training in progress, epoch 1
56ff6b1 verified
{"current_steps": 10, "total_steps": 192, "loss": 0.7255, "lr": 5e-06, "epoch": 0.15625, "percentage": 5.21, "elapsed_time": "0:00:59", "remaining_time": "0:18:06"}
{"current_steps": 20, "total_steps": 192, "loss": 0.6224, "lr": 5e-06, "epoch": 0.3125, "percentage": 10.42, "elapsed_time": "0:01:57", "remaining_time": "0:16:53"}
{"current_steps": 30, "total_steps": 192, "loss": 0.5848, "lr": 5e-06, "epoch": 0.46875, "percentage": 15.62, "elapsed_time": "0:02:55", "remaining_time": "0:15:48"}
{"current_steps": 40, "total_steps": 192, "loss": 0.5638, "lr": 5e-06, "epoch": 0.625, "percentage": 20.83, "elapsed_time": "0:03:53", "remaining_time": "0:14:47"}
{"current_steps": 50, "total_steps": 192, "loss": 0.5486, "lr": 5e-06, "epoch": 0.78125, "percentage": 26.04, "elapsed_time": "0:04:51", "remaining_time": "0:13:48"}
{"current_steps": 60, "total_steps": 192, "loss": 0.5351, "lr": 5e-06, "epoch": 0.9375, "percentage": 31.25, "elapsed_time": "0:05:50", "remaining_time": "0:12:50"}
{"current_steps": 64, "total_steps": 192, "eval_loss": 0.5265702605247498, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:06:19", "remaining_time": "0:12:39"}
{"current_steps": 70, "total_steps": 192, "loss": 0.5117, "lr": 5e-06, "epoch": 1.09375, "percentage": 36.46, "elapsed_time": "0:08:17", "remaining_time": "0:14:27"}
{"current_steps": 80, "total_steps": 192, "loss": 0.4927, "lr": 5e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "0:09:15", "remaining_time": "0:12:58"}
{"current_steps": 90, "total_steps": 192, "loss": 0.488, "lr": 5e-06, "epoch": 1.40625, "percentage": 46.88, "elapsed_time": "0:10:13", "remaining_time": "0:11:35"}
{"current_steps": 100, "total_steps": 192, "loss": 0.4873, "lr": 5e-06, "epoch": 1.5625, "percentage": 52.08, "elapsed_time": "0:11:12", "remaining_time": "0:10:18"}
{"current_steps": 110, "total_steps": 192, "loss": 0.4868, "lr": 5e-06, "epoch": 1.71875, "percentage": 57.29, "elapsed_time": "0:12:10", "remaining_time": "0:09:04"}
{"current_steps": 120, "total_steps": 192, "loss": 0.483, "lr": 5e-06, "epoch": 1.875, "percentage": 62.5, "elapsed_time": "0:13:08", "remaining_time": "0:07:52"}
{"current_steps": 128, "total_steps": 192, "eval_loss": 0.5022982358932495, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:14:00", "remaining_time": "0:07:00"}
{"current_steps": 130, "total_steps": 192, "loss": 0.4743, "lr": 5e-06, "epoch": 2.03125, "percentage": 67.71, "elapsed_time": "0:15:37", "remaining_time": "0:07:27"}
{"current_steps": 140, "total_steps": 192, "loss": 0.4464, "lr": 5e-06, "epoch": 2.1875, "percentage": 72.92, "elapsed_time": "0:16:35", "remaining_time": "0:06:09"}
{"current_steps": 150, "total_steps": 192, "loss": 0.4484, "lr": 5e-06, "epoch": 2.34375, "percentage": 78.12, "elapsed_time": "0:17:33", "remaining_time": "0:04:55"}
{"current_steps": 160, "total_steps": 192, "loss": 0.4458, "lr": 5e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:18:32", "remaining_time": "0:03:42"}
{"current_steps": 170, "total_steps": 192, "loss": 0.4485, "lr": 5e-06, "epoch": 2.65625, "percentage": 88.54, "elapsed_time": "0:19:30", "remaining_time": "0:02:31"}
{"current_steps": 180, "total_steps": 192, "loss": 0.4471, "lr": 5e-06, "epoch": 2.8125, "percentage": 93.75, "elapsed_time": "0:20:28", "remaining_time": "0:01:21"}
{"current_steps": 190, "total_steps": 192, "loss": 0.4461, "lr": 5e-06, "epoch": 2.96875, "percentage": 98.96, "elapsed_time": "0:21:27", "remaining_time": "0:00:13"}
{"current_steps": 192, "total_steps": 192, "eval_loss": 0.5014501214027405, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:23:06", "remaining_time": "0:00:00"}
{"current_steps": 192, "total_steps": 192, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:24:33", "remaining_time": "0:00:00"}