Training in progress, step 1100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ec2597cb66cc8bf7c12cf0511653b2a0fba5900300120225835d32ef88d42ca
+oid sha256:a5dad64d30fcdb47a2e15bc593335933f84181ea038dde168b8ebbd434b58442
 size 29034840

trainer_log.jsonl

@@ -229,3 +229,14 @@
 {"current_steps": 1045, "total_steps": 3882, "loss": 0.7189, "lr": 8.744943274483376e-05, "epoch": 0.5382436260623229, "percentage": 26.92, "elapsed_time": "5:21:11", "remaining_time": "14:32:00", "throughput": 634.22, "total_tokens": 12222672}
 {"current_steps": 1050, "total_steps": 3882, "loss": 0.6914, "lr": 8.730795109484461e-05, "epoch": 0.5408189544166881, "percentage": 27.05, "elapsed_time": "5:22:39", "remaining_time": "14:30:14", "throughput": 634.37, "total_tokens": 12281072}
 {"current_steps": 1050, "total_steps": 3882, "eval_loss": 0.6824291348457336, "epoch": 0.5408189544166881, "percentage": 27.05, "elapsed_time": "5:22:59", "remaining_time": "14:31:08", "throughput": 633.73, "total_tokens": 12281072}
+{"current_steps": 1055, "total_steps": 3882, "loss": 0.6567, "lr": 8.716579228029562e-05, "epoch": 0.5433942827710533, "percentage": 27.18, "elapsed_time": "5:24:32", "remaining_time": "14:29:39", "throughput": 633.68, "total_tokens": 12339544}
+{"current_steps": 1060, "total_steps": 3882, "loss": 0.6155, "lr": 8.702295888146548e-05, "epoch": 0.5459696111254185, "percentage": 27.31, "elapsed_time": "5:26:00", "remaining_time": "14:27:56", "throughput": 633.81, "total_tokens": 12397992}
+{"current_steps": 1065, "total_steps": 3882, "loss": 0.6029, "lr": 8.687945349087703e-05, "epoch": 0.5485449394797837, "percentage": 27.43, "elapsed_time": "5:27:29", "remaining_time": "14:26:13", "throughput": 633.94, "total_tokens": 12456480}
+{"current_steps": 1070, "total_steps": 3882, "loss": 0.6129, "lr": 8.673527871325022e-05, "epoch": 0.5511202678341488, "percentage": 27.56, "elapsed_time": "5:28:56", "remaining_time": "14:24:28", "throughput": 634.1, "total_tokens": 12515000}
+{"current_steps": 1075, "total_steps": 3882, "loss": 0.6825, "lr": 8.659043716545485e-05, "epoch": 0.553695596188514, "percentage": 27.69, "elapsed_time": "5:30:24", "remaining_time": "14:22:45", "throughput": 634.24, "total_tokens": 12573504}
+{"current_steps": 1080, "total_steps": 3882, "loss": 0.6828, "lr": 8.644493147646302e-05, "epoch": 0.5562709245428792, "percentage": 27.82, "elapsed_time": "5:31:52", "remaining_time": "14:21:00", "throughput": 634.39, "total_tokens": 12632008}
+{"current_steps": 1085, "total_steps": 3882, "loss": 0.6286, "lr": 8.629876428730145e-05, "epoch": 0.5588462528972444, "percentage": 27.95, "elapsed_time": "5:33:19", "remaining_time": "14:19:16", "throughput": 634.54, "total_tokens": 12690520}
+{"current_steps": 1090, "total_steps": 3882, "loss": 0.6361, "lr": 8.615193825100355e-05, "epoch": 0.5614215812516096, "percentage": 28.08, "elapsed_time": "5:34:47", "remaining_time": "14:17:32", "throughput": 634.69, "total_tokens": 12749032}
+{"current_steps": 1095, "total_steps": 3882, "loss": 0.6087, "lr": 8.600445603256123e-05, "epoch": 0.5639969096059748, "percentage": 28.21, "elapsed_time": "5:36:14", "remaining_time": "14:15:47", "throughput": 634.84, "total_tokens": 12807504}
+{"current_steps": 1100, "total_steps": 3882, "loss": 0.5825, "lr": 8.585632030887658e-05, "epoch": 0.56657223796034, "percentage": 28.34, "elapsed_time": "5:37:42", "remaining_time": "14:14:05", "throughput": 634.96, "total_tokens": 12865992}
+{"current_steps": 1100, "total_steps": 3882, "eval_loss": 0.6431913375854492, "epoch": 0.56657223796034, "percentage": 28.34, "elapsed_time": "5:38:01", "remaining_time": "14:14:54", "throughput": 634.36, "total_tokens": 12865992}