Training in progress, step 600

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ea0b12291caef0384f7fd3bc0b1e4fc7815f7b867e0e565a267ef13238fd6a9
+oid sha256:69777f5aa25eff25d556b3b21e25927428c8db95972e0d7a65589f133ec91630
 size 29034840

trainer_log.jsonl

@@ -120,3 +120,14 @@
 {"current_steps": 545, "total_steps": 6770, "loss": 0.5845, "lr": 9.974704070662254e-05, "epoch": 0.16100443131462333, "percentage": 8.05, "elapsed_time": "2:43:27", "remaining_time": "1 day, 7:06:58", "throughput": 576.19, "total_tokens": 5650816}
 {"current_steps": 550, "total_steps": 6770, "loss": 0.5957, "lr": 9.973462311090336e-05, "epoch": 0.16248153618906944, "percentage": 8.12, "elapsed_time": "2:44:53", "remaining_time": "1 day, 7:04:48", "throughput": 576.43, "total_tokens": 5703016}
 {"current_steps": 550, "total_steps": 6770, "eval_loss": 0.6883422136306763, "epoch": 0.16248153618906944, "percentage": 8.12, "elapsed_time": "2:45:12", "remaining_time": "1 day, 7:08:25", "throughput": 575.31, "total_tokens": 5703016}
+{"current_steps": 555, "total_steps": 6770, "loss": 0.6076, "lr": 9.972190879892147e-05, "epoch": 0.16395864106351551, "percentage": 8.2, "elapsed_time": "2:46:46", "remaining_time": "1 day, 7:07:29", "throughput": 575.07, "total_tokens": 5754192}
+{"current_steps": 560, "total_steps": 6770, "loss": 0.6136, "lr": 9.970889784653033e-05, "epoch": 0.1654357459379616, "percentage": 8.27, "elapsed_time": "2:48:12", "remaining_time": "1 day, 7:05:15", "throughput": 575.32, "total_tokens": 5806272}
+{"current_steps": 565, "total_steps": 6770, "loss": 0.5554, "lr": 9.969559033135318e-05, "epoch": 0.16691285081240767, "percentage": 8.35, "elapsed_time": "2:49:38", "remaining_time": "1 day, 7:03:03", "throughput": 575.59, "total_tokens": 5858632}
+{"current_steps": 570, "total_steps": 6770, "loss": 0.5847, "lr": 9.96819863327825e-05, "epoch": 0.16838995568685378, "percentage": 8.42, "elapsed_time": "2:51:05", "remaining_time": "1 day, 7:01:01", "throughput": 575.7, "total_tokens": 5909936}
+{"current_steps": 575, "total_steps": 6770, "loss": 0.6217, "lr": 9.966808593197959e-05, "epoch": 0.16986706056129985, "percentage": 8.49, "elapsed_time": "2:52:32", "remaining_time": "1 day, 6:58:52", "throughput": 575.87, "total_tokens": 5961464}
+{"current_steps": 580, "total_steps": 6770, "loss": 0.5569, "lr": 9.965388921187413e-05, "epoch": 0.17134416543574593, "percentage": 8.57, "elapsed_time": "2:53:58", "remaining_time": "1 day, 6:56:48", "throughput": 576.08, "total_tokens": 6013696}
+{"current_steps": 585, "total_steps": 6770, "loss": 0.5894, "lr": 9.963939625716361e-05, "epoch": 0.172821270310192, "percentage": 8.64, "elapsed_time": "2:55:24", "remaining_time": "1 day, 6:54:36", "throughput": 576.32, "total_tokens": 6065736}
+{"current_steps": 590, "total_steps": 6770, "loss": 0.5783, "lr": 9.962460715431284e-05, "epoch": 0.17429837518463812, "percentage": 8.71, "elapsed_time": "2:56:52", "remaining_time": "1 day, 6:52:40", "throughput": 576.53, "total_tokens": 6118400}
+{"current_steps": 595, "total_steps": 6770, "loss": 0.5657, "lr": 9.960952199155347e-05, "epoch": 0.1757754800590842, "percentage": 8.79, "elapsed_time": "2:58:18", "remaining_time": "1 day, 6:50:27", "throughput": 576.84, "total_tokens": 6171120}
+{"current_steps": 600, "total_steps": 6770, "loss": 0.6331, "lr": 9.959414085888342e-05, "epoch": 0.17725258493353027, "percentage": 8.86, "elapsed_time": "2:59:45", "remaining_time": "1 day, 6:48:30", "throughput": 576.95, "total_tokens": 6222736}
+{"current_steps": 600, "total_steps": 6770, "eval_loss": 0.5883122682571411, "epoch": 0.17725258493353027, "percentage": 8.86, "elapsed_time": "3:00:04", "remaining_time": "1 day, 6:51:46", "throughput": 575.94, "total_tokens": 6222736}