Training in progress, step 551

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad22163279126e421bebd0a627e8cf953827f0abaf332fc21b0cb03c8165a39c
+oid sha256:a5e739b9c499dbf7e3e1289db5a5cb30d28691450615719f4fde88153d50c446
 size 1638528

trainer_log.jsonl

@@ -121,3 +121,10 @@
 {"current_steps": 520, "total_steps": 570, "loss": 0.1549, "lr": 1.2094341632602064e-06, "epoch": 9.12280701754386, "percentage": 91.23, "elapsed_time": "0:02:44", "remaining_time": "0:00:15", "throughput": 2050.06, "total_tokens": 336296}
 {"current_steps": 522, "total_steps": 570, "eval_loss": 0.19831164181232452, "epoch": 9.157894736842104, "percentage": 91.58, "elapsed_time": "0:02:45", "remaining_time": "0:00:15", "throughput": 2040.93, "total_tokens": 337480}
 {"current_steps": 525, "total_steps": 570, "loss": 0.1365, "lr": 9.85409612575411e-07, "epoch": 9.210526315789474, "percentage": 92.11, "elapsed_time": "0:02:47", "remaining_time": "0:00:14", "throughput": 2024.53, "total_tokens": 339080}
+{"current_steps": 530, "total_steps": 570, "loss": 0.0859, "lr": 7.838987308029427e-07, "epoch": 9.298245614035087, "percentage": 92.98, "elapsed_time": "0:02:48", "remaining_time": "0:00:12", "throughput": 2030.44, "total_tokens": 342568}
+{"current_steps": 535, "total_steps": 570, "loss": 0.067, "lr": 6.050904343141095e-07, "epoch": 9.385964912280702, "percentage": 93.86, "elapsed_time": "0:02:49", "remaining_time": "0:00:11", "throughput": 2034.36, "total_tokens": 345576}
+{"current_steps": 540, "total_steps": 570, "loss": 0.1141, "lr": 4.491523558155714e-07, "epoch": 9.473684210526315, "percentage": 94.74, "elapsed_time": "0:02:51", "remaining_time": "0:00:09", "throughput": 2037.36, "total_tokens": 348392}
+{"current_steps": 545, "total_steps": 570, "loss": 0.0688, "lr": 3.162306871937387e-07, "epoch": 9.56140350877193, "percentage": 95.61, "elapsed_time": "0:02:52", "remaining_time": "0:00:07", "throughput": 2043.28, "total_tokens": 351912}
+{"current_steps": 550, "total_steps": 570, "loss": 0.072, "lr": 2.064500424599436e-07, "epoch": 9.649122807017545, "percentage": 96.49, "elapsed_time": "0:02:53", "remaining_time": "0:00:06", "throughput": 2049.15, "total_tokens": 355432}
+{"current_steps": 551, "total_steps": 570, "eval_loss": 0.2247486412525177, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:02:54", "remaining_time": "0:00:06", "throughput": 2041.41, "total_tokens": 356456}
+{"current_steps": 555, "total_steps": 570, "loss": 0.0824, "lr": 1.1991334092484318e-07, "epoch": 9.736842105263158, "percentage": 97.37, "elapsed_time": "0:02:56", "remaining_time": "0:00:04", "throughput": 2027.87, "total_tokens": 358760}