Training in progress, step 1050

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6e45eb274c1273932226b11445e2fd07b7c7ebefc12bc54da671bc0cebf939d
+oid sha256:58fee999d861c33a13a1ad6ddc5c198927b03d1f1f7a88f80cd0e47458a79905
 size 29034840

trainer_log.jsonl

@@ -222,3 +222,14 @@
 {"current_steps": 995, "total_steps": 3400, "loss": 0.5399, "lr": 8.474846307659658e-05, "epoch": 0.25624517125933555, "percentage": 29.26, "elapsed_time": "2:05:01", "remaining_time": "5:02:11", "throughput": 1392.18, "total_tokens": 10443080}
 {"current_steps": 1000, "total_steps": 3400, "loss": 0.483, "lr": 8.457321315344694e-05, "epoch": 0.25753283543651817, "percentage": 29.41, "elapsed_time": "2:06:30", "remaining_time": "5:03:37", "throughput": 1382.7, "total_tokens": 10495592}
 {"current_steps": 1000, "total_steps": 3400, "eval_loss": 0.5305114388465881, "epoch": 0.25753283543651817, "percentage": 29.41, "elapsed_time": "2:07:09", "remaining_time": "5:05:10", "throughput": 1375.65, "total_tokens": 10495592}
+{"current_steps": 1005, "total_steps": 3400, "loss": 0.568, "lr": 8.439714556870704e-05, "epoch": 0.25882049961370074, "percentage": 29.56, "elapsed_time": "2:08:43", "remaining_time": "5:06:44", "throughput": 1365.8, "total_tokens": 10548136}
+{"current_steps": 1010, "total_steps": 3400, "loss": 0.4335, "lr": 8.422026448640124e-05, "epoch": 0.26010816379088336, "percentage": 29.71, "elapsed_time": "2:10:12", "remaining_time": "5:08:07", "throughput": 1356.78, "total_tokens": 10600048}
+{"current_steps": 1015, "total_steps": 3400, "loss": 0.5385, "lr": 8.40425740897932e-05, "epoch": 0.26139582796806593, "percentage": 29.85, "elapsed_time": "2:11:40", "remaining_time": "5:09:25", "throughput": 1348.21, "total_tokens": 10652160}
+{"current_steps": 1020, "total_steps": 3400, "loss": 0.5171, "lr": 8.386407858128706e-05, "epoch": 0.2626834921452485, "percentage": 30.0, "elapsed_time": "2:13:11", "remaining_time": "5:10:46", "throughput": 1339.57, "total_tokens": 10705208}
+{"current_steps": 1025, "total_steps": 3400, "loss": 0.5201, "lr": 8.368478218232787e-05, "epoch": 0.2639711563224311, "percentage": 30.15, "elapsed_time": "2:14:39", "remaining_time": "5:12:00", "throughput": 1331.61, "total_tokens": 10758688}
+{"current_steps": 1030, "total_steps": 3400, "loss": 0.5521, "lr": 8.350468913330192e-05, "epoch": 0.2652588204996137, "percentage": 30.29, "elapsed_time": "2:16:08", "remaining_time": "5:13:16", "throughput": 1323.48, "total_tokens": 10811408}
+{"current_steps": 1035, "total_steps": 3400, "loss": 0.4938, "lr": 8.33238036934364e-05, "epoch": 0.2665464846767963, "percentage": 30.44, "elapsed_time": "2:17:37", "remaining_time": "5:14:28", "throughput": 1315.65, "total_tokens": 10864144}
+{"current_steps": 1040, "total_steps": 3400, "loss": 0.4828, "lr": 8.31421301406986e-05, "epoch": 0.2678341488539789, "percentage": 30.59, "elapsed_time": "2:19:08", "remaining_time": "5:15:44", "throughput": 1307.65, "total_tokens": 10916952}
+{"current_steps": 1045, "total_steps": 3400, "loss": 0.5491, "lr": 8.29596727716949e-05, "epoch": 0.26912181303116145, "percentage": 30.74, "elapsed_time": "2:20:37", "remaining_time": "5:16:53", "throughput": 1300.06, "total_tokens": 10968824}
+{"current_steps": 1050, "total_steps": 3400, "loss": 0.4628, "lr": 8.277643590156894e-05, "epoch": 0.2704094772083441, "percentage": 30.88, "elapsed_time": "2:22:08", "remaining_time": "5:18:07", "throughput": 1292.35, "total_tokens": 11021656}
+{"current_steps": 1050, "total_steps": 3400, "eval_loss": 0.5039986371994019, "epoch": 0.2704094772083441, "percentage": 30.88, "elapsed_time": "2:22:48", "remaining_time": "5:19:37", "throughput": 1286.28, "total_tokens": 11021656}