Training in progress, step 1850

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:520d9edd8a1a6f11a17fc4ae7016207030825c667ed2fdf06f05c31f73e229dc
+oid sha256:83d482b0521ba55cbd644a8b0adfd6f4e4037fa30dd12a4a9ba58c4d63a8e631
 size 29034840

trainer_log.jsonl

@@ -398,3 +398,14 @@
 {"current_steps": 1795, "total_steps": 3400, "loss": 0.3836, "lr": 4.9513693015329197e-05, "epoch": 0.4622714396085501, "percentage": 52.79, "elapsed_time": "6:11:45", "remaining_time": "5:32:24", "throughput": 844.9, "total_tokens": 18846368}
 {"current_steps": 1800, "total_steps": 3400, "loss": 0.4484, "lr": 4.9270553899567686e-05, "epoch": 0.4635591037857327, "percentage": 52.94, "elapsed_time": "6:13:14", "remaining_time": "5:31:46", "throughput": 843.91, "total_tokens": 18898888}
 {"current_steps": 1800, "total_steps": 3400, "eval_loss": 0.4194311797618866, "epoch": 0.4635591037857327, "percentage": 52.94, "elapsed_time": "6:13:52", "remaining_time": "5:32:20", "throughput": 842.48, "total_tokens": 18898888}
+{"current_steps": 1805, "total_steps": 3400, "loss": 0.3301, "lr": 4.902743203531405e-05, "epoch": 0.4648467679629153, "percentage": 53.09, "elapsed_time": "6:15:24", "remaining_time": "5:31:43", "throughput": 841.39, "total_tokens": 18951672}
+{"current_steps": 1810, "total_steps": 3400, "loss": 0.3861, "lr": 4.8784333172436206e-05, "epoch": 0.46613443214009787, "percentage": 53.24, "elapsed_time": "6:16:51", "remaining_time": "5:31:03", "throughput": 840.48, "total_tokens": 19005008}
+{"current_steps": 1815, "total_steps": 3400, "loss": 0.459, "lr": 4.854126306025812e-05, "epoch": 0.46742209631728043, "percentage": 53.38, "elapsed_time": "6:18:18", "remaining_time": "5:30:22", "throughput": 839.6, "total_tokens": 19057856}
+{"current_steps": 1820, "total_steps": 3400, "loss": 0.3944, "lr": 4.829822744742383e-05, "epoch": 0.46870976049446306, "percentage": 53.53, "elapsed_time": "6:19:46", "remaining_time": "5:29:41", "throughput": 838.71, "total_tokens": 19110992}
+{"current_steps": 1825, "total_steps": 3400, "loss": 0.3447, "lr": 4.8055232081761395e-05, "epoch": 0.4699974246716456, "percentage": 53.68, "elapsed_time": "6:21:13", "remaining_time": "5:29:00", "throughput": 837.78, "total_tokens": 19162816}
+{"current_steps": 1830, "total_steps": 3400, "loss": 0.3954, "lr": 4.781228271014704e-05, "epoch": 0.47128508884882825, "percentage": 53.82, "elapsed_time": "6:22:40", "remaining_time": "5:28:18", "throughput": 836.9, "total_tokens": 19215752}
+{"current_steps": 1835, "total_steps": 3400, "loss": 0.415, "lr": 4.756938507836929e-05, "epoch": 0.4725727530260108, "percentage": 53.97, "elapsed_time": "6:24:07", "remaining_time": "5:27:36", "throughput": 836.02, "total_tokens": 19268392}
+{"current_steps": 1840, "total_steps": 3400, "loss": 0.2794, "lr": 4.732654493099291e-05, "epoch": 0.4738604172031934, "percentage": 54.12, "elapsed_time": "6:25:34", "remaining_time": "5:26:54", "throughput": 835.18, "total_tokens": 19321696}
+{"current_steps": 1845, "total_steps": 3400, "loss": 0.3699, "lr": 4.708376801122321e-05, "epoch": 0.475148081380376, "percentage": 54.26, "elapsed_time": "6:27:02", "remaining_time": "5:26:12", "throughput": 834.27, "total_tokens": 19373584}
+{"current_steps": 1850, "total_steps": 3400, "loss": 0.3941, "lr": 4.6841060060770154e-05, "epoch": 0.4764357455575586, "percentage": 54.41, "elapsed_time": "6:28:29", "remaining_time": "5:25:29", "throughput": 833.35, "total_tokens": 19424688}
+{"current_steps": 1850, "total_steps": 3400, "eval_loss": 0.45103010535240173, "epoch": 0.4764357455575586, "percentage": 54.41, "elapsed_time": "6:29:07", "remaining_time": "5:26:01", "throughput": 831.99, "total_tokens": 19424688}