Training in progress, step 551

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2425854de943c5fcf3bab24cf0e857e18bc341c329e687e81c2b3b13b983d65a
+oid sha256:750eb8a9299167e816154006b95edc792878be3155f2d2ce52716534ef8875b9
 size 1074144

trainer_log.jsonl

@@ -121,3 +121,10 @@
 {"current_steps": 520, "total_steps": 570, "loss": 0.0318, "lr": 1.2094341632602064e-06, "epoch": 9.12280701754386, "percentage": 91.23, "elapsed_time": "0:02:17", "remaining_time": "0:00:13", "throughput": 2336.65, "total_tokens": 321888}
 {"current_steps": 522, "total_steps": 570, "eval_loss": 0.19350025057792664, "epoch": 9.157894736842104, "percentage": 91.58, "elapsed_time": "0:02:18", "remaining_time": "0:00:12", "throughput": 2326.35, "total_tokens": 323296}
 {"current_steps": 525, "total_steps": 570, "loss": 0.0575, "lr": 9.85409612575411e-07, "epoch": 9.210526315789474, "percentage": 92.11, "elapsed_time": "0:02:20", "remaining_time": "0:00:12", "throughput": 2317.23, "total_tokens": 325248}
+{"current_steps": 530, "total_steps": 570, "loss": 0.0182, "lr": 7.838987308029427e-07, "epoch": 9.298245614035087, "percentage": 92.98, "elapsed_time": "0:02:21", "remaining_time": "0:00:10", "throughput": 2321.79, "total_tokens": 328224}
+{"current_steps": 535, "total_steps": 570, "loss": 0.0079, "lr": 6.050904343141095e-07, "epoch": 9.385964912280702, "percentage": 93.86, "elapsed_time": "0:02:22", "remaining_time": "0:00:09", "throughput": 2325.87, "total_tokens": 330880}
+{"current_steps": 540, "total_steps": 570, "loss": 0.241, "lr": 4.491523558155714e-07, "epoch": 9.473684210526315, "percentage": 94.74, "elapsed_time": "0:02:23", "remaining_time": "0:00:07", "throughput": 2331.2, "total_tokens": 334176}
+{"current_steps": 545, "total_steps": 570, "loss": 0.018, "lr": 3.162306871937387e-07, "epoch": 9.56140350877193, "percentage": 95.61, "elapsed_time": "0:02:24", "remaining_time": "0:00:06", "throughput": 2335.78, "total_tokens": 337280}
+{"current_steps": 550, "total_steps": 570, "loss": 0.0381, "lr": 2.064500424599436e-07, "epoch": 9.649122807017545, "percentage": 96.49, "elapsed_time": "0:02:25", "remaining_time": "0:00:05", "throughput": 2340.78, "total_tokens": 340480}
+{"current_steps": 551, "total_steps": 570, "eval_loss": 0.19899024069309235, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:02:26", "remaining_time": "0:00:05", "throughput": 2329.58, "total_tokens": 340960}
+{"current_steps": 555, "total_steps": 570, "loss": 0.1419, "lr": 1.1991334092484318e-07, "epoch": 9.736842105263158, "percentage": 97.37, "elapsed_time": "0:02:27", "remaining_time": "0:00:03", "throughput": 2320.91, "total_tokens": 343328}