Training in progress, step 2800

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c53cd6b7a9aaec48a0490b1f83024497fb7a940d74235cfb8f5dc2c2a530336
+oid sha256:5d8105e08b44734413954313ee3f59582f2323ad431f91a8d42d31e834f41c4c
 size 18516456

trainer_log.jsonl

@@ -607,3 +607,14 @@
 {"current_steps": 2745, "total_steps": 3400, "loss": 0.3019, "lr": 9.807960514465792e-06, "epoch": 1.4135977337110481, "percentage": 80.74, "elapsed_time": "10:10:18", "remaining_time": "2:25:37", "throughput": 876.6, "total_tokens": 32099656}
 {"current_steps": 2750, "total_steps": 3400, "loss": 0.164, "lr": 9.663795559195733e-06, "epoch": 1.4161730620654134, "percentage": 80.88, "elapsed_time": "10:11:22", "remaining_time": "2:24:30", "throughput": 876.65, "total_tokens": 32158144}
 {"current_steps": 2750, "total_steps": 3400, "eval_loss": 0.7807286381721497, "epoch": 1.4161730620654134, "percentage": 80.88, "elapsed_time": "10:11:39", "remaining_time": "2:24:34", "throughput": 876.27, "total_tokens": 32158144}
+{"current_steps": 2755, "total_steps": 3400, "loss": 0.3333, "lr": 9.520584561109864e-06, "epoch": 1.4187483904197786, "percentage": 81.03, "elapsed_time": "10:12:47", "remaining_time": "2:23:28", "throughput": 876.22, "total_tokens": 32216656}
+{"current_steps": 2760, "total_steps": 3400, "loss": 0.2993, "lr": 9.378330907169386e-06, "epoch": 1.4213237187741437, "percentage": 81.18, "elapsed_time": "10:13:51", "remaining_time": "2:22:20", "throughput": 876.28, "total_tokens": 32275168}
+{"current_steps": 2765, "total_steps": 3400, "loss": 0.2683, "lr": 9.237037961694223e-06, "epoch": 1.423899047128509, "percentage": 81.32, "elapsed_time": "10:14:56", "remaining_time": "2:21:13", "throughput": 876.34, "total_tokens": 32333664}
+{"current_steps": 2770, "total_steps": 3400, "loss": 0.3145, "lr": 9.096709066283354e-06, "epoch": 1.4264743754828741, "percentage": 81.47, "elapsed_time": "10:16:00", "remaining_time": "2:20:06", "throughput": 876.39, "total_tokens": 32392088}
+{"current_steps": 2775, "total_steps": 3400, "loss": 0.3092, "lr": 8.957347539735872e-06, "epoch": 1.4290497038372392, "percentage": 81.62, "elapsed_time": "10:17:05", "remaining_time": "2:18:58", "throughput": 876.45, "total_tokens": 32450584}
+{"current_steps": 2780, "total_steps": 3400, "loss": 0.2993, "lr": 8.818956677972406e-06, "epoch": 1.4316250321916044, "percentage": 81.76, "elapsed_time": "10:18:09", "remaining_time": "2:17:51", "throughput": 876.51, "total_tokens": 32509096}
+{"current_steps": 2785, "total_steps": 3400, "loss": 0.326, "lr": 8.681539753957269e-06, "epoch": 1.4342003605459697, "percentage": 81.91, "elapsed_time": "10:19:13", "remaining_time": "2:16:44", "throughput": 876.57, "total_tokens": 32567560}
+{"current_steps": 2790, "total_steps": 3400, "loss": 0.2494, "lr": 8.545100017620988e-06, "epoch": 1.436775688900335, "percentage": 82.06, "elapsed_time": "10:20:17", "remaining_time": "2:15:37", "throughput": 876.63, "total_tokens": 32626056}
+{"current_steps": 2795, "total_steps": 3400, "loss": 0.2691, "lr": 8.409640695783443e-06, "epoch": 1.4393510172547, "percentage": 82.21, "elapsed_time": "10:21:21", "remaining_time": "2:14:29", "throughput": 876.69, "total_tokens": 32684520}
+{"current_steps": 2800, "total_steps": 3400, "loss": 0.2939, "lr": 8.275164992077556e-06, "epoch": 1.4419263456090652, "percentage": 82.35, "elapsed_time": "10:22:25", "remaining_time": "2:13:22", "throughput": 876.75, "total_tokens": 32743032}
+{"current_steps": 2800, "total_steps": 3400, "eval_loss": 0.791334331035614, "epoch": 1.4419263456090652, "percentage": 82.35, "elapsed_time": "10:22:41", "remaining_time": "2:13:26", "throughput": 876.37, "total_tokens": 32743032}