Training in progress, step 1130

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5bfb933343c2989c47fce5993b03cb32e5a1a92027a024bf2ccff8f1c2903f2
+oid sha256:c17232986ac0f0f128abd049b04cf57a1aa84b296ae750594a2eb8b2fced77c7
 size 8388736

trainer_log.jsonl

@@ -237,3 +237,10 @@
 {"current_steps": 1090, "total_steps": 1130, "loss": 0.0002, "lr": 2.0024189799641435e-07, "epoch": 9.646017699115044, "percentage": 96.46, "elapsed_time": "0:02:25", "remaining_time": "0:00:05", "throughput": 2101.69, "total_tokens": 305784}
 {"current_steps": 1095, "total_steps": 1130, "loss": 0.0002, "lr": 1.5442771053230665e-07, "epoch": 9.690265486725664, "percentage": 96.9, "elapsed_time": "0:02:26", "remaining_time": "0:00:04", "throughput": 2106.56, "total_tokens": 307592}
 {"current_steps": 1100, "total_steps": 1130, "loss": 0.0013, "lr": 1.1454056799370672e-07, "epoch": 9.734513274336283, "percentage": 97.35, "elapsed_time": "0:02:26", "remaining_time": "0:00:03", "throughput": 2108.41, "total_tokens": 308760}
+{"current_steps": 1105, "total_steps": 1130, "loss": 0.0037, "lr": 8.058998567304633e-08, "epoch": 9.778761061946902, "percentage": 97.79, "elapsed_time": "0:02:26", "remaining_time": "0:00:03", "throughput": 2110.87, "total_tokens": 310040}
+{"current_steps": 1110, "total_steps": 1130, "loss": 0.0014, "lr": 5.2584062664368105e-08, "epoch": 9.823008849557523, "percentage": 98.23, "elapsed_time": "0:02:27", "remaining_time": "0:00:02", "throughput": 2115.58, "total_tokens": 311752}
+{"current_steps": 1115, "total_steps": 1130, "loss": 0.0041, "lr": 3.0529479931265535e-08, "epoch": 9.867256637168142, "percentage": 98.67, "elapsed_time": "0:02:27", "remaining_time": "0:00:01", "throughput": 2118.35, "total_tokens": 313128}
+{"current_steps": 1120, "total_steps": 1130, "loss": 0.0004, "lr": 1.443149871309113e-08, "epoch": 9.91150442477876, "percentage": 99.12, "elapsed_time": "0:02:28", "remaining_time": "0:00:01", "throughput": 2121.81, "total_tokens": 314568}
+{"current_steps": 1125, "total_steps": 1130, "loss": 0.0007, "lr": 4.293959269863201e-09, "epoch": 9.955752212389381, "percentage": 99.56, "elapsed_time": "0:02:28", "remaining_time": "0:00:00", "throughput": 2124.13, "total_tokens": 315800}
+{"current_steps": 1130, "total_steps": 1130, "loss": 0.2557, "lr": 1.192799661514643e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:29", "remaining_time": "0:00:00", "throughput": 2124.08, "total_tokens": 316840}
+{"current_steps": 1130, "total_steps": 1130, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:30", "remaining_time": "0:00:00", "throughput": 2102.7, "total_tokens": 316840}