Training in progress, step 1450

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2ea934ab728b1244cad904f211efc8dbea34bf120d0aaee69bc85b174ce604c
+oid sha256:c22365f9f1922257bce2b624ba131f902a872d3af6a64b3fc1e949516f00f5ac
 size 18516456

trainer_log.jsonl

@@ -310,3 +310,14 @@
 {"current_steps": 1395, "total_steps": 3400, "loss": 0.7862, "lr": 6.851469673071143e-05, "epoch": 0.7185166108678857, "percentage": 41.03, "elapsed_time": "5:15:27", "remaining_time": "7:33:23", "throughput": 862.05, "total_tokens": 16316264}
 {"current_steps": 1400, "total_steps": 3400, "loss": 0.7359, "lr": 6.828860628415253e-05, "epoch": 0.7210919392222508, "percentage": 41.18, "elapsed_time": "5:16:30", "remaining_time": "7:32:09", "throughput": 862.24, "total_tokens": 16374784}
 {"current_steps": 1400, "total_steps": 3400, "eval_loss": 0.6643603444099426, "epoch": 0.7210919392222508, "percentage": 41.18, "elapsed_time": "5:16:47", "remaining_time": "7:32:32", "throughput": 861.51, "total_tokens": 16374784}
+{"current_steps": 1405, "total_steps": 3400, "loss": 0.706, "lr": 6.806208330935766e-05, "epoch": 0.723667267576616, "percentage": 41.32, "elapsed_time": "5:17:55", "remaining_time": "7:31:25", "throughput": 861.49, "total_tokens": 16433288}
+{"current_steps": 1410, "total_steps": 3400, "loss": 0.6714, "lr": 6.783513316362855e-05, "epoch": 0.7262425959309812, "percentage": 41.47, "elapsed_time": "5:18:58", "remaining_time": "7:30:11", "throughput": 861.7, "total_tokens": 16491784}
+{"current_steps": 1415, "total_steps": 3400, "loss": 0.693, "lr": 6.760776121436962e-05, "epoch": 0.7288179242853464, "percentage": 41.62, "elapsed_time": "5:20:02", "remaining_time": "7:28:57", "throughput": 861.9, "total_tokens": 16550272}
+{"current_steps": 1420, "total_steps": 3400, "loss": 0.7005, "lr": 6.737997283896103e-05, "epoch": 0.7313932526397116, "percentage": 41.76, "elapsed_time": "5:21:04", "remaining_time": "7:27:42", "throughput": 862.12, "total_tokens": 16608704}
+{"current_steps": 1425, "total_steps": 3400, "loss": 0.6573, "lr": 6.715177342463145e-05, "epoch": 0.7339685809940767, "percentage": 41.91, "elapsed_time": "5:22:08", "remaining_time": "7:26:28", "throughput": 862.32, "total_tokens": 16667200}
+{"current_steps": 1430, "total_steps": 3400, "loss": 0.6751, "lr": 6.692316836833065e-05, "epoch": 0.7365439093484419, "percentage": 42.06, "elapsed_time": "5:23:11", "remaining_time": "7:25:13", "throughput": 862.54, "total_tokens": 16725704}
+{"current_steps": 1435, "total_steps": 3400, "loss": 0.6173, "lr": 6.6694163076602e-05, "epoch": 0.7391192377028071, "percentage": 42.21, "elapsed_time": "5:24:14", "remaining_time": "7:23:59", "throughput": 862.74, "total_tokens": 16784192}
+{"current_steps": 1440, "total_steps": 3400, "loss": 0.728, "lr": 6.646476296545434e-05, "epoch": 0.7416945660571723, "percentage": 42.35, "elapsed_time": "5:25:17", "remaining_time": "7:22:45", "throughput": 862.95, "total_tokens": 16842704}
+{"current_steps": 1445, "total_steps": 3400, "loss": 0.743, "lr": 6.623497346023418e-05, "epoch": 0.7442698944115375, "percentage": 42.5, "elapsed_time": "5:26:20", "remaining_time": "7:21:31", "throughput": 863.15, "total_tokens": 16901176}
+{"current_steps": 1450, "total_steps": 3400, "loss": 0.6291, "lr": 6.60047999954972e-05, "epoch": 0.7468452227659027, "percentage": 42.65, "elapsed_time": "5:27:23", "remaining_time": "7:20:17", "throughput": 863.37, "total_tokens": 16959632}
+{"current_steps": 1450, "total_steps": 3400, "eval_loss": 0.753077507019043, "epoch": 0.7468452227659027, "percentage": 42.65, "elapsed_time": "5:27:39", "remaining_time": "7:20:38", "throughput": 862.66, "total_tokens": 16959632}