Training in progress, step 1450

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1cfac0e8b9dcb659e1e1aecd6c6484a664c1bc40a9c86d4a35709450060ad76
+oid sha256:140829d96675f8a17bdb0fa18b56b080defbfc9f26441176908846cb9afcc2fb
 size 29034840

trainer_log.jsonl

@@ -306,3 +306,14 @@
 {"current_steps": 1395, "total_steps": 3882, "loss": 0.4899, "lr": 7.606223841738775e-05, "epoch": 0.7185166108678857, "percentage": 35.94, "elapsed_time": "7:07:11", "remaining_time": "12:41:35", "throughput": 636.57, "total_tokens": 16316264}
 {"current_steps": 1400, "total_steps": 3882, "loss": 0.4294, "lr": 7.588021115889777e-05, "epoch": 0.7210919392222508, "percentage": 36.06, "elapsed_time": "7:08:40", "remaining_time": "12:39:57", "throughput": 636.66, "total_tokens": 16374784}
 {"current_steps": 1400, "total_steps": 3882, "eval_loss": 0.47318556904792786, "epoch": 0.7210919392222508, "percentage": 36.06, "elapsed_time": "7:08:59", "remaining_time": "12:40:32", "throughput": 636.18, "total_tokens": 16374784}
+{"current_steps": 1405, "total_steps": 3882, "loss": 0.444, "lr": 7.569771415706126e-05, "epoch": 0.723667267576616, "percentage": 36.19, "elapsed_time": "7:10:32", "remaining_time": "12:39:02", "throughput": 636.14, "total_tokens": 16433288}
+{"current_steps": 1410, "total_steps": 3882, "loss": 0.4971, "lr": 7.551475072432237e-05, "epoch": 0.7262425959309812, "percentage": 36.32, "elapsed_time": "7:12:00", "remaining_time": "12:37:24", "throughput": 636.24, "total_tokens": 16491784}
+{"current_steps": 1415, "total_steps": 3882, "loss": 0.4284, "lr": 7.533132418159119e-05, "epoch": 0.7288179242853464, "percentage": 36.45, "elapsed_time": "7:13:28", "remaining_time": "12:35:45", "throughput": 636.34, "total_tokens": 16550272}
+{"current_steps": 1420, "total_steps": 3882, "loss": 0.414, "lr": 7.514743785818361e-05, "epoch": 0.7313932526397116, "percentage": 36.58, "elapsed_time": "7:14:56", "remaining_time": "12:34:06", "throughput": 636.43, "total_tokens": 16608704}
+{"current_steps": 1425, "total_steps": 3882, "loss": 0.3715, "lr": 7.496309509176082e-05, "epoch": 0.7339685809940767, "percentage": 36.71, "elapsed_time": "7:16:25", "remaining_time": "12:32:29", "throughput": 636.51, "total_tokens": 16667200}
+{"current_steps": 1430, "total_steps": 3882, "loss": 0.4723, "lr": 7.477829922826883e-05, "epoch": 0.7365439093484419, "percentage": 36.84, "elapsed_time": "7:17:53", "remaining_time": "12:30:50", "throughput": 636.61, "total_tokens": 16725704}
+{"current_steps": 1435, "total_steps": 3882, "loss": 0.4357, "lr": 7.459305362187756e-05, "epoch": 0.7391192377028071, "percentage": 36.97, "elapsed_time": "7:19:21", "remaining_time": "12:29:12", "throughput": 636.69, "total_tokens": 16784192}
+{"current_steps": 1440, "total_steps": 3882, "loss": 0.4402, "lr": 7.440736163492016e-05, "epoch": 0.7416945660571723, "percentage": 37.09, "elapsed_time": "7:20:49", "remaining_time": "12:27:33", "throughput": 636.79, "total_tokens": 16842704}
+{"current_steps": 1445, "total_steps": 3882, "loss": 0.4457, "lr": 7.422122663783187e-05, "epoch": 0.7442698944115375, "percentage": 37.22, "elapsed_time": "7:22:18", "remaining_time": "12:25:56", "throughput": 636.87, "total_tokens": 16901176}
+{"current_steps": 1450, "total_steps": 3882, "loss": 0.4353, "lr": 7.403465200908883e-05, "epoch": 0.7468452227659027, "percentage": 37.35, "elapsed_time": "7:23:45", "remaining_time": "12:24:17", "throughput": 636.97, "total_tokens": 16959632}
+{"current_steps": 1450, "total_steps": 3882, "eval_loss": 0.43503889441490173, "epoch": 0.7468452227659027, "percentage": 37.35, "elapsed_time": "7:24:05", "remaining_time": "12:24:50", "throughput": 636.5, "total_tokens": 16959632}