Training in progress, step 1800

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95cb389d8c3bb8b023cd12cb33d7b6158b8a28b87779d6ac67f1897a141b861b
+oid sha256:520d9edd8a1a6f11a17fc4ae7016207030825c667ed2fdf06f05c31f73e229dc
 size 29034840

trainer_log.jsonl

@@ -387,3 +387,14 @@
 {"current_steps": 1745, "total_steps": 3400, "loss": 0.3763, "lr": 5.1944767918238624e-05, "epoch": 0.4493947978367242, "percentage": 51.32, "elapsed_time": "5:56:24", "remaining_time": "5:38:01", "throughput": 856.63, "total_tokens": 18318984}
 {"current_steps": 1750, "total_steps": 3400, "loss": 0.3767, "lr": 5.170177255257618e-05, "epoch": 0.45068246201390677, "percentage": 51.47, "elapsed_time": "5:57:52", "remaining_time": "5:37:25", "throughput": 855.59, "total_tokens": 18371928}
 {"current_steps": 1750, "total_steps": 3400, "eval_loss": 0.4234265685081482, "epoch": 0.45068246201390677, "percentage": 51.47, "elapsed_time": "5:58:31", "remaining_time": "5:38:01", "throughput": 854.07, "total_tokens": 18371928}
+{"current_steps": 1755, "total_steps": 3400, "loss": 0.4059, "lr": 5.145873693974188e-05, "epoch": 0.45197012619108934, "percentage": 51.62, "elapsed_time": "6:00:03", "remaining_time": "5:37:29", "throughput": 852.85, "total_tokens": 18424432}
+{"current_steps": 1760, "total_steps": 3400, "loss": 0.3709, "lr": 5.12156668275638e-05, "epoch": 0.45325779036827196, "percentage": 51.76, "elapsed_time": "6:01:31", "remaining_time": "5:36:52", "throughput": 851.8, "total_tokens": 18476736}
+{"current_steps": 1765, "total_steps": 3400, "loss": 0.4075, "lr": 5.097256796468598e-05, "epoch": 0.45454545454545453, "percentage": 51.91, "elapsed_time": "6:02:59", "remaining_time": "5:36:15", "throughput": 850.79, "total_tokens": 18529552}
+{"current_steps": 1770, "total_steps": 3400, "loss": 0.3101, "lr": 5.072944610043232e-05, "epoch": 0.45583311872263715, "percentage": 52.06, "elapsed_time": "6:04:28", "remaining_time": "5:35:38", "throughput": 849.77, "total_tokens": 18583232}
+{"current_steps": 1775, "total_steps": 3400, "loss": 0.33, "lr": 5.048630698467081e-05, "epoch": 0.4571207828998197, "percentage": 52.21, "elapsed_time": "6:05:55", "remaining_time": "5:35:00", "throughput": 848.8, "total_tokens": 18636296}
+{"current_steps": 1780, "total_steps": 3400, "loss": 0.4204, "lr": 5.024315636767738e-05, "epoch": 0.4584084470770023, "percentage": 52.35, "elapsed_time": "6:07:24", "remaining_time": "5:34:22", "throughput": 847.76, "total_tokens": 18688376}
+{"current_steps": 1785, "total_steps": 3400, "loss": 0.4855, "lr": 5e-05, "epoch": 0.4596961112541849, "percentage": 52.5, "elapsed_time": "6:08:51", "remaining_time": "5:33:43", "throughput": 846.83, "total_tokens": 18741192}
+{"current_steps": 1790, "total_steps": 3400, "loss": 0.3344, "lr": 4.9756843632322626e-05, "epoch": 0.4609837754313675, "percentage": 52.65, "elapsed_time": "6:10:19", "remaining_time": "5:33:05", "throughput": 845.85, "total_tokens": 18794320}
+{"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}