tinyllama-codeHtml / trainer_log.jsonl
Tippawan's picture
Model save
9d8cc01 verified
{"current_steps": 5, "total_steps": 189, "loss": 1.6436, "lr": 1.0526315789473684e-05, "epoch": 0.08, "percentage": 2.65, "elapsed_time": "0:00:08", "remaining_time": "0:05:10"}
{"current_steps": 10, "total_steps": 189, "loss": 0.772, "lr": 2.368421052631579e-05, "epoch": 0.16, "percentage": 5.29, "elapsed_time": "0:00:13", "remaining_time": "0:04:00"}
{"current_steps": 15, "total_steps": 189, "loss": 0.1927, "lr": 3.6842105263157895e-05, "epoch": 0.24, "percentage": 7.94, "elapsed_time": "0:00:19", "remaining_time": "0:03:42"}
{"current_steps": 20, "total_steps": 189, "loss": 0.08, "lr": 5e-05, "epoch": 0.32, "percentage": 10.58, "elapsed_time": "0:00:24", "remaining_time": "0:03:24"}
{"current_steps": 25, "total_steps": 189, "loss": 0.0735, "lr": 4.989335440737586e-05, "epoch": 0.4, "percentage": 13.23, "elapsed_time": "0:00:29", "remaining_time": "0:03:14"}
{"current_steps": 30, "total_steps": 189, "loss": 0.0719, "lr": 4.957432749209755e-05, "epoch": 0.48, "percentage": 15.87, "elapsed_time": "0:00:34", "remaining_time": "0:03:05"}
{"current_steps": 35, "total_steps": 189, "loss": 0.0702, "lr": 4.9045641079320484e-05, "epoch": 0.56, "percentage": 18.52, "elapsed_time": "0:00:40", "remaining_time": "0:02:59"}
{"current_steps": 40, "total_steps": 189, "loss": 0.071, "lr": 4.8311805735108894e-05, "epoch": 0.64, "percentage": 21.16, "elapsed_time": "0:00:46", "remaining_time": "0:02:52"}
{"current_steps": 45, "total_steps": 189, "loss": 0.0677, "lr": 4.7379082283876566e-05, "epoch": 0.72, "percentage": 23.81, "elapsed_time": "0:00:51", "remaining_time": "0:02:44"}
{"current_steps": 50, "total_steps": 189, "loss": 0.0599, "lr": 4.625542839324036e-05, "epoch": 0.8, "percentage": 26.46, "elapsed_time": "0:00:57", "remaining_time": "0:02:39"}
{"current_steps": 55, "total_steps": 189, "loss": 0.0685, "lr": 4.4950430682006e-05, "epoch": 0.88, "percentage": 29.1, "elapsed_time": "0:01:02", "remaining_time": "0:02:31"}
{"current_steps": 60, "total_steps": 189, "loss": 0.0653, "lr": 4.347522293051648e-05, "epoch": 0.96, "percentage": 31.75, "elapsed_time": "0:01:07", "remaining_time": "0:02:25"}
{"current_steps": 65, "total_steps": 189, "loss": 0.0655, "lr": 4.184239109116393e-05, "epoch": 1.032, "percentage": 34.39, "elapsed_time": "0:01:12", "remaining_time": "0:02:18"}
{"current_steps": 70, "total_steps": 189, "loss": 0.0629, "lr": 4.0065865909481417e-05, "epoch": 1.112, "percentage": 37.04, "elapsed_time": "0:01:22", "remaining_time": "0:02:19"}
{"current_steps": 75, "total_steps": 189, "loss": 0.0594, "lr": 3.81608040719339e-05, "epoch": 1.192, "percentage": 39.68, "elapsed_time": "0:01:33", "remaining_time": "0:02:21"}
{"current_steps": 80, "total_steps": 189, "loss": 0.0594, "lr": 3.6143458894413465e-05, "epoch": 1.272, "percentage": 42.33, "elapsed_time": "0:01:43", "remaining_time": "0:02:20"}
{"current_steps": 85, "total_steps": 189, "loss": 0.058, "lr": 3.403104165467883e-05, "epoch": 1.3519999999999999, "percentage": 44.97, "elapsed_time": "0:01:52", "remaining_time": "0:02:17"}
{"current_steps": 90, "total_steps": 189, "loss": 0.0598, "lr": 3.1841574751802076e-05, "epoch": 1.432, "percentage": 47.62, "elapsed_time": "0:01:59", "remaining_time": "0:02:11"}
{"current_steps": 95, "total_steps": 189, "loss": 0.064, "lr": 2.9593737945414264e-05, "epoch": 1.512, "percentage": 50.26, "elapsed_time": "0:02:04", "remaining_time": "0:02:03"}
{"current_steps": 100, "total_steps": 189, "loss": 0.0629, "lr": 2.7306708986582553e-05, "epoch": 1.592, "percentage": 52.91, "elapsed_time": "0:02:10", "remaining_time": "0:01:56"}
{"current_steps": 105, "total_steps": 189, "loss": 0.0609, "lr": 2.5e-05, "epoch": 1.6720000000000002, "percentage": 55.56, "elapsed_time": "0:02:15", "remaining_time": "0:01:48"}
{"current_steps": 110, "total_steps": 189, "loss": 0.0641, "lr": 2.2693291013417453e-05, "epoch": 1.752, "percentage": 58.2, "elapsed_time": "0:02:20", "remaining_time": "0:01:41"}
{"current_steps": 115, "total_steps": 189, "loss": 0.0602, "lr": 2.0406262054585738e-05, "epoch": 1.8319999999999999, "percentage": 60.85, "elapsed_time": "0:02:26", "remaining_time": "0:01:34"}
{"current_steps": 120, "total_steps": 189, "loss": 0.0604, "lr": 1.815842524819793e-05, "epoch": 1.912, "percentage": 63.49, "elapsed_time": "0:02:33", "remaining_time": "0:01:28"}
{"current_steps": 125, "total_steps": 189, "loss": 0.0557, "lr": 1.5968958345321178e-05, "epoch": 1.992, "percentage": 66.14, "elapsed_time": "0:02:44", "remaining_time": "0:01:24"}
{"current_steps": 130, "total_steps": 189, "loss": 0.0545, "lr": 1.3856541105586545e-05, "epoch": 2.064, "percentage": 68.78, "elapsed_time": "0:02:54", "remaining_time": "0:01:19"}
{"current_steps": 135, "total_steps": 189, "loss": 0.0503, "lr": 1.1839195928066102e-05, "epoch": 2.144, "percentage": 71.43, "elapsed_time": "0:03:06", "remaining_time": "0:01:14"}
{"current_steps": 140, "total_steps": 189, "loss": 0.0543, "lr": 9.934134090518593e-06, "epoch": 2.224, "percentage": 74.07, "elapsed_time": "0:03:16", "remaining_time": "0:01:08"}
{"current_steps": 145, "total_steps": 189, "loss": 0.0538, "lr": 8.15760890883607e-06, "epoch": 2.304, "percentage": 76.72, "elapsed_time": "0:03:24", "remaining_time": "0:01:01"}
{"current_steps": 150, "total_steps": 189, "loss": 0.0521, "lr": 6.524777069483526e-06, "epoch": 2.384, "percentage": 79.37, "elapsed_time": "0:03:29", "remaining_time": "0:00:54"}
{"current_steps": 155, "total_steps": 189, "loss": 0.057, "lr": 5.049569317994013e-06, "epoch": 2.464, "percentage": 82.01, "elapsed_time": "0:03:37", "remaining_time": "0:00:47"}
{"current_steps": 160, "total_steps": 189, "loss": 0.0545, "lr": 3.7445716067596503e-06, "epoch": 2.544, "percentage": 84.66, "elapsed_time": "0:03:42", "remaining_time": "0:00:40"}
{"current_steps": 165, "total_steps": 189, "loss": 0.0544, "lr": 2.6209177161234445e-06, "epoch": 2.624, "percentage": 87.3, "elapsed_time": "0:03:50", "remaining_time": "0:00:33"}
{"current_steps": 170, "total_steps": 189, "loss": 0.0533, "lr": 1.6881942648911076e-06, "epoch": 2.7039999999999997, "percentage": 89.95, "elapsed_time": "0:03:56", "remaining_time": "0:00:26"}
{"current_steps": 175, "total_steps": 189, "loss": 0.054, "lr": 9.54358920679524e-07, "epoch": 2.784, "percentage": 92.59, "elapsed_time": "0:04:02", "remaining_time": "0:00:19"}
{"current_steps": 180, "total_steps": 189, "loss": 0.0549, "lr": 4.256725079024554e-07, "epoch": 2.864, "percentage": 95.24, "elapsed_time": "0:04:09", "remaining_time": "0:00:12"}
{"current_steps": 185, "total_steps": 189, "loss": 0.0532, "lr": 1.0664559262413831e-07, "epoch": 2.944, "percentage": 97.88, "elapsed_time": "0:04:14", "remaining_time": "0:00:05"}
{"current_steps": 189, "total_steps": 189, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:04:18", "remaining_time": "0:00:00"}
{"current_steps": 189, "total_steps": 189, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}