Training in progress, step 750

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e8b8b0d35e964892c4538367f208dcb82426a1165c1fe8d9ec6ab99f0299952
+oid sha256:87a05b954f6ad396e106053a5bf73274eb4671d1ca4b7518421076c40296fc81
 size 29034840

trainer_log.jsonl

@@ -153,3 +153,14 @@
 {"current_steps": 695, "total_steps": 6770, "loss": 0.4764, "lr": 9.924579765365536e-05, "epoch": 0.20531757754800592, "percentage": 10.27, "elapsed_time": "3:27:55", "remaining_time": "1 day, 6:17:29", "throughput": 577.97, "total_tokens": 7210552}
 {"current_steps": 700, "total_steps": 6770, "loss": 0.477, "lr": 9.922451873731569e-05, "epoch": 0.206794682422452, "percentage": 10.34, "elapsed_time": "3:29:21", "remaining_time": "1 day, 6:15:27", "throughput": 578.17, "total_tokens": 7262832}
 {"current_steps": 700, "total_steps": 6770, "eval_loss": 0.5883837938308716, "epoch": 0.206794682422452, "percentage": 10.34, "elapsed_time": "3:29:40", "remaining_time": "1 day, 6:18:13", "throughput": 577.3, "total_tokens": 7262832}
+{"current_steps": 705, "total_steps": 6770, "loss": 0.5151, "lr": 9.92029461479909e-05, "epoch": 0.20827178729689808, "percentage": 10.41, "elapsed_time": "3:31:13", "remaining_time": "1 day, 6:17:07", "throughput": 577.15, "total_tokens": 7314520}
+{"current_steps": 710, "total_steps": 6770, "loss": 0.6158, "lr": 9.918108001438283e-05, "epoch": 0.20974889217134415, "percentage": 10.49, "elapsed_time": "3:32:39", "remaining_time": "1 day, 6:15:03", "throughput": 577.25, "total_tokens": 7365368}
+{"current_steps": 715, "total_steps": 6770, "loss": 0.5164, "lr": 9.915892046694464e-05, "epoch": 0.21122599704579026, "percentage": 10.56, "elapsed_time": "3:34:05", "remaining_time": "1 day, 6:13:05", "throughput": 577.41, "total_tokens": 7417296}
+{"current_steps": 720, "total_steps": 6770, "loss": 0.5823, "lr": 9.913646763787992e-05, "epoch": 0.21270310192023634, "percentage": 10.64, "elapsed_time": "3:35:32", "remaining_time": "1 day, 6:11:07", "throughput": 577.59, "total_tokens": 7469640}
+{"current_steps": 725, "total_steps": 6770, "loss": 0.5145, "lr": 9.911372166114208e-05, "epoch": 0.21418020679468242, "percentage": 10.71, "elapsed_time": "3:36:58", "remaining_time": "1 day, 6:09:09", "throughput": 577.75, "total_tokens": 7521520}
+{"current_steps": 730, "total_steps": 6770, "loss": 0.571, "lr": 9.909068267243336e-05, "epoch": 0.21565731166912852, "percentage": 10.78, "elapsed_time": "3:38:24", "remaining_time": "1 day, 6:07:08", "throughput": 577.95, "total_tokens": 7573880}
+{"current_steps": 735, "total_steps": 6770, "loss": 0.4638, "lr": 9.906735080920413e-05, "epoch": 0.2171344165435746, "percentage": 10.86, "elapsed_time": "3:39:51", "remaining_time": "1 day, 6:05:10", "throughput": 578.11, "total_tokens": 7625896}
+{"current_steps": 740, "total_steps": 6770, "loss": 0.5449, "lr": 9.904372621065206e-05, "epoch": 0.21861152141802068, "percentage": 10.93, "elapsed_time": "3:41:17", "remaining_time": "1 day, 6:03:13", "throughput": 578.16, "total_tokens": 7676528}
+{"current_steps": 745, "total_steps": 6770, "loss": 0.5505, "lr": 9.901980901772126e-05, "epoch": 0.22008862629246675, "percentage": 11.0, "elapsed_time": "3:42:43", "remaining_time": "1 day, 6:01:16", "throughput": 578.3, "total_tokens": 7728240}
+{"current_steps": 750, "total_steps": 6770, "loss": 0.514, "lr": 9.899559937310148e-05, "epoch": 0.22156573116691286, "percentage": 11.08, "elapsed_time": "3:44:09", "remaining_time": "1 day, 5:59:17", "throughput": 578.44, "total_tokens": 7779872}
+{"current_steps": 750, "total_steps": 6770, "eval_loss": 0.4665524661540985, "epoch": 0.22156573116691286, "percentage": 11.08, "elapsed_time": "3:44:29", "remaining_time": "1 day, 6:01:51", "throughput": 577.61, "total_tokens": 7779872}