Training in progress, step 900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbb88cd2ad49a28dfd1cc411e4818df1e3111793a50f870549a2cf9e7bc00e62
+oid sha256:bd3d3749c1bd6d89c5172acc406cbf998cb265de2f8a059883bd34374666967b
 size 18516456

trainer_log.jsonl

@@ -189,3 +189,14 @@
 {"current_steps": 845, "total_steps": 3400, "loss": 0.874, "lr": 8.960590861978265e-05, "epoch": 0.4352304918877157, "percentage": 24.85, "elapsed_time": "3:15:32", "remaining_time": "9:51:15", "throughput": 842.39, "total_tokens": 9883408}
 {"current_steps": 850, "total_steps": 3400, "loss": 0.9035, "lr": 8.945702546981969e-05, "epoch": 0.43780582024208087, "percentage": 25.0, "elapsed_time": "3:16:36", "remaining_time": "9:49:49", "throughput": 842.79, "total_tokens": 9941896}
 {"current_steps": 850, "total_steps": 3400, "eval_loss": 0.8779178261756897, "epoch": 0.43780582024208087, "percentage": 25.0, "elapsed_time": "3:16:52", "remaining_time": "9:50:37", "throughput": 841.64, "total_tokens": 9941896}
+{"current_steps": 855, "total_steps": 3400, "loss": 0.8516, "lr": 8.930720915538487e-05, "epoch": 0.44038114859644606, "percentage": 25.15, "elapsed_time": "3:18:00", "remaining_time": "9:49:23", "throughput": 841.75, "total_tokens": 10000336}
+{"current_steps": 860, "total_steps": 3400, "loss": 0.9206, "lr": 8.915646321965614e-05, "epoch": 0.44295647695081125, "percentage": 25.29, "elapsed_time": "3:19:03", "remaining_time": "9:47:54", "throughput": 842.2, "total_tokens": 10058816}
+{"current_steps": 865, "total_steps": 3400, "loss": 0.9028, "lr": 8.900479122779712e-05, "epoch": 0.4455318053051764, "percentage": 25.44, "elapsed_time": "3:20:06", "remaining_time": "9:46:26", "throughput": 842.66, "total_tokens": 10117320}
+{"current_steps": 870, "total_steps": 3400, "loss": 0.8991, "lr": 8.885219676687277e-05, "epoch": 0.4481071336595416, "percentage": 25.59, "elapsed_time": "3:21:09", "remaining_time": "9:45:00", "throughput": 843.07, "total_tokens": 10175824}
+{"current_steps": 875, "total_steps": 3400, "loss": 0.8934, "lr": 8.869868344576459e-05, "epoch": 0.45068246201390677, "percentage": 25.74, "elapsed_time": "3:22:12", "remaining_time": "9:43:32", "throughput": 843.51, "total_tokens": 10234288}
+{"current_steps": 880, "total_steps": 3400, "loss": 0.8908, "lr": 8.854425489508532e-05, "epoch": 0.45325779036827196, "percentage": 25.88, "elapsed_time": "3:23:15", "remaining_time": "9:42:04", "throughput": 843.95, "total_tokens": 10292736}
+{"current_steps": 885, "total_steps": 3400, "loss": 0.8988, "lr": 8.838891476709288e-05, "epoch": 0.45583311872263715, "percentage": 26.03, "elapsed_time": "3:24:18", "remaining_time": "9:40:36", "throughput": 844.4, "total_tokens": 10351224}
+{"current_steps": 890, "total_steps": 3400, "loss": 0.8965, "lr": 8.823266673560426e-05, "epoch": 0.4584084470770023, "percentage": 26.18, "elapsed_time": "3:25:21", "remaining_time": "9:39:10", "throughput": 844.81, "total_tokens": 10409736}
+{"current_steps": 895, "total_steps": 3400, "loss": 0.8989, "lr": 8.807551449590846e-05, "epoch": 0.4609837754313675, "percentage": 26.32, "elapsed_time": "3:26:25", "remaining_time": "9:37:44", "throughput": 845.22, "total_tokens": 10468240}
+{"current_steps": 900, "total_steps": 3400, "loss": 0.8961, "lr": 8.791746176467907e-05, "epoch": 0.4635591037857327, "percentage": 26.47, "elapsed_time": "3:27:28", "remaining_time": "9:36:18", "throughput": 845.63, "total_tokens": 10526712}
+{"current_steps": 900, "total_steps": 3400, "eval_loss": 0.891426146030426, "epoch": 0.4635591037857327, "percentage": 26.47, "elapsed_time": "3:27:44", "remaining_time": "9:37:03", "throughput": 844.54, "total_tokens": 10526712}