Training in progress, step 750

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42550e6e1d7736cbdce18e29b8623c64df817502dd31846b4342331ecc33a1e0
+oid sha256:acaedc144367149e2a92be2a9c0e75df4817558ae00e175c156fbc72ea2ce596
 size 29034840

trainer_log.jsonl

@@ -152,3 +152,14 @@
 {"current_steps": 695, "total_steps": 3400, "loss": 0.0171, "lr": 9.362182973536569e-05, "epoch": 0.35797064125676026, "percentage": 20.44, "elapsed_time": "3:26:32", "remaining_time": "13:23:51", "throughput": 559.94, "total_tokens": 6938880}
 {"current_steps": 700, "total_steps": 3400, "loss": 0.0267, "lr": 9.35024767453647e-05, "epoch": 0.3605459696111254, "percentage": 20.59, "elapsed_time": "3:27:56", "remaining_time": "13:22:04", "throughput": 560.15, "total_tokens": 6988800}
 {"current_steps": 700, "total_steps": 3400, "eval_loss": 0.005286735948175192, "epoch": 0.3605459696111254, "percentage": 20.59, "elapsed_time": "3:28:16", "remaining_time": "13:23:18", "throughput": 559.28, "total_tokens": 6988800}
+{"current_steps": 705, "total_steps": 3400, "loss": 0.0335, "lr": 9.338209491537257e-05, "epoch": 0.3631212979654906, "percentage": 20.74, "elapsed_time": "3:29:47", "remaining_time": "13:21:58", "throughput": 559.17, "total_tokens": 7038720}
+{"current_steps": 710, "total_steps": 3400, "loss": 0.0108, "lr": 9.326068709243727e-05, "epoch": 0.3656966263198558, "percentage": 20.88, "elapsed_time": "3:31:13", "remaining_time": "13:20:14", "throughput": 559.35, "total_tokens": 7088640}
+{"current_steps": 715, "total_steps": 3400, "loss": 0.0296, "lr": 9.313825614787177e-05, "epoch": 0.36827195467422097, "percentage": 21.03, "elapsed_time": "3:32:39", "remaining_time": "13:18:34", "throughput": 559.48, "total_tokens": 7138560}
+{"current_steps": 720, "total_steps": 3400, "loss": 0.042, "lr": 9.301480497718593e-05, "epoch": 0.37084728302858616, "percentage": 21.18, "elapsed_time": "3:34:04", "remaining_time": "13:16:51", "throughput": 559.64, "total_tokens": 7188480}
+{"current_steps": 725, "total_steps": 3400, "loss": 0.0083, "lr": 9.289033650001817e-05, "epoch": 0.37342261138295135, "percentage": 21.32, "elapsed_time": "3:35:31", "remaining_time": "13:15:11", "throughput": 559.76, "total_tokens": 7238400}
+{"current_steps": 730, "total_steps": 3400, "loss": 0.0109, "lr": 9.276485366006634e-05, "epoch": 0.3759979397373165, "percentage": 21.47, "elapsed_time": "3:36:56", "remaining_time": "13:13:29", "throughput": 559.92, "total_tokens": 7288320}
+{"current_steps": 735, "total_steps": 3400, "loss": 0.0122, "lr": 9.263835942501807e-05, "epoch": 0.3785732680916817, "percentage": 21.62, "elapsed_time": "3:38:23", "remaining_time": "13:11:49", "throughput": 560.04, "total_tokens": 7338240}
+{"current_steps": 740, "total_steps": 3400, "loss": 0.017, "lr": 9.251085678648072e-05, "epoch": 0.3811485964460469, "percentage": 21.76, "elapsed_time": "3:39:49", "remaining_time": "13:10:10", "throughput": 560.16, "total_tokens": 7388160}
+{"current_steps": 745, "total_steps": 3400, "loss": 0.0236, "lr": 9.238234875991046e-05, "epoch": 0.38372392480041206, "percentage": 21.91, "elapsed_time": "3:41:16", "remaining_time": "13:08:33", "throughput": 560.25, "total_tokens": 7438080}
+{"current_steps": 750, "total_steps": 3400, "loss": 0.014, "lr": 9.225283838454111e-05, "epoch": 0.38629925315477726, "percentage": 22.06, "elapsed_time": "3:42:42", "remaining_time": "13:06:53", "throughput": 560.39, "total_tokens": 7488000}
+{"current_steps": 750, "total_steps": 3400, "eval_loss": 0.005334165878593922, "epoch": 0.38629925315477726, "percentage": 22.06, "elapsed_time": "3:43:01", "remaining_time": "13:08:01", "throughput": 559.58, "total_tokens": 7488000}