test / trainer_log.jsonl
rbelanec's picture
Training in progress, step 49
200408c verified
raw
history blame
5.22 kB
{"current_steps": 5, "total_steps": 125, "loss": 10.9709, "lr": 1.5384615384615387e-05, "epoch": 0.04, "percentage": 4.0, "elapsed_time": "0:00:02", "remaining_time": "0:01:09", "throughput": 735.72, "total_tokens": 2144}
{"current_steps": 7, "total_steps": 125, "eval_loss": 6.5227251052856445, "epoch": 0.056, "percentage": 5.6, "elapsed_time": "0:00:03", "remaining_time": "0:01:06", "throughput": 732.42, "total_tokens": 2880}
{"current_steps": 10, "total_steps": 125, "loss": 6.4075, "lr": 3.461538461538462e-05, "epoch": 0.08, "percentage": 8.0, "elapsed_time": "0:00:20", "remaining_time": "0:03:52", "throughput": 203.87, "total_tokens": 4128}
{"current_steps": 14, "total_steps": 125, "eval_loss": 1.382468581199646, "epoch": 0.112, "percentage": 11.2, "elapsed_time": "0:00:21", "remaining_time": "0:02:51", "throughput": 273.75, "total_tokens": 5920}
{"current_steps": 15, "total_steps": 125, "loss": 2.5338, "lr": 4.999016565957633e-05, "epoch": 0.12, "percentage": 12.0, "elapsed_time": "0:00:30", "remaining_time": "0:03:43", "throughput": 204.83, "total_tokens": 6240}
{"current_steps": 20, "total_steps": 125, "loss": 0.5326, "lr": 4.96467754629559e-05, "epoch": 0.16, "percentage": 16.0, "elapsed_time": "0:00:31", "remaining_time": "0:02:44", "throughput": 259.14, "total_tokens": 8096}
{"current_steps": 21, "total_steps": 125, "eval_loss": 0.4987373352050781, "epoch": 0.168, "percentage": 16.8, "elapsed_time": "0:00:31", "remaining_time": "0:02:38", "throughput": 263.74, "total_tokens": 8416}
{"current_steps": 25, "total_steps": 125, "loss": 0.4144, "lr": 4.881937806807241e-05, "epoch": 0.2, "percentage": 20.0, "elapsed_time": "0:00:39", "remaining_time": "0:02:37", "throughput": 256.96, "total_tokens": 10112}
{"current_steps": 28, "total_steps": 125, "eval_loss": 0.4531269073486328, "epoch": 0.224, "percentage": 22.4, "elapsed_time": "0:00:40", "remaining_time": "0:02:19", "throughput": 279.63, "total_tokens": 11264}
{"current_steps": 30, "total_steps": 125, "loss": 0.4563, "lr": 4.752422169756048e-05, "epoch": 0.24, "percentage": 24.0, "elapsed_time": "0:00:47", "remaining_time": "0:02:30", "throughput": 253.43, "total_tokens": 12032}
{"current_steps": 35, "total_steps": 125, "loss": 0.4802, "lr": 4.5786740307563636e-05, "epoch": 0.28, "percentage": 28.0, "elapsed_time": "0:00:48", "remaining_time": "0:02:04", "throughput": 286.57, "total_tokens": 13824}
{"current_steps": 35, "total_steps": 125, "eval_loss": 0.36931881308555603, "epoch": 0.28, "percentage": 28.0, "elapsed_time": "0:00:48", "remaining_time": "0:02:05", "throughput": 282.37, "total_tokens": 13824}
{"current_steps": 40, "total_steps": 125, "loss": 0.3809, "lr": 4.364105412207914e-05, "epoch": 0.32, "percentage": 32.0, "elapsed_time": "0:00:58", "remaining_time": "0:02:05", "throughput": 268.48, "total_tokens": 15840}
{"current_steps": 42, "total_steps": 125, "eval_loss": 0.3872639238834381, "epoch": 0.336, "percentage": 33.6, "elapsed_time": "0:01:00", "remaining_time": "0:01:58", "throughput": 277.51, "total_tokens": 16672}
{"current_steps": 45, "total_steps": 125, "loss": 0.3844, "lr": 4.1129299588552193e-05, "epoch": 0.36, "percentage": 36.0, "elapsed_time": "0:01:09", "remaining_time": "0:02:03", "throughput": 257.82, "total_tokens": 17920}
{"current_steps": 49, "total_steps": 125, "eval_loss": 0.3777945637702942, "epoch": 0.392, "percentage": 39.2, "elapsed_time": "0:01:10", "remaining_time": "0:01:50", "throughput": 272.03, "total_tokens": 19296}
{"current_steps": 50, "total_steps": 125, "loss": 0.2817, "lr": 3.830080191288342e-05, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:01:26", "remaining_time": "0:02:09", "throughput": 227.54, "total_tokens": 19712}
{"current_steps": 55, "total_steps": 125, "loss": 0.3831, "lr": 3.521110642339991e-05, "epoch": 0.44, "percentage": 44.0, "elapsed_time": "0:01:27", "remaining_time": "0:01:51", "throughput": 250.88, "total_tokens": 21952}
{"current_steps": 56, "total_steps": 125, "eval_loss": 0.4436803460121155, "epoch": 0.448, "percentage": 44.8, "elapsed_time": "0:01:28", "remaining_time": "0:01:48", "throughput": 253.75, "total_tokens": 22432}
{"current_steps": 60, "total_steps": 125, "loss": 0.5576, "lr": 3.1920887785621235e-05, "epoch": 0.48, "percentage": 48.0, "elapsed_time": "0:01:37", "remaining_time": "0:01:46", "throughput": 246.65, "total_tokens": 24160}
{"current_steps": 63, "total_steps": 125, "eval_loss": 0.35032057762145996, "epoch": 0.504, "percentage": 50.4, "elapsed_time": "0:01:39", "remaining_time": "0:01:37", "throughput": 257.13, "total_tokens": 25504}
{"current_steps": 65, "total_steps": 125, "loss": 0.4013, "lr": 2.849475848838749e-05, "epoch": 0.52, "percentage": 52.0, "elapsed_time": "0:01:48", "remaining_time": "0:01:40", "throughput": 240.47, "total_tokens": 26112}
{"current_steps": 70, "total_steps": 125, "loss": 0.3242, "lr": 2.5e-05, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:01:49", "remaining_time": "0:01:25", "throughput": 256.58, "total_tokens": 28064}
{"current_steps": 70, "total_steps": 125, "eval_loss": 0.37164703011512756, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:01:50", "remaining_time": "0:01:26", "throughput": 254.81, "total_tokens": 28064}