Training in progress, step 950

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ab1b54ce042c169c01101e1c005c36e39e3afd27d938891c20b92f985d53f5
+oid sha256:dfd440e7fad2202aa5aadeb518f98ac0d3f292864f45e1beccd3794320180905
 size 29034840

trainer_log.jsonl

@@ -197,3 +197,14 @@
 {"current_steps": 895, "total_steps": 6770, "loss": 0.4476, "lr": 9.81670071435415e-05, "epoch": 0.26440177252584934, "percentage": 13.22, "elapsed_time": "4:27:37", "remaining_time": "1 day, 5:16:42", "throughput": 578.77, "total_tokens": 9293328}
 {"current_steps": 900, "total_steps": 6770, "loss": 0.4852, "lr": 9.813409891992988e-05, "epoch": 0.2658788774002954, "percentage": 13.29, "elapsed_time": "4:29:04", "remaining_time": "1 day, 5:14:54", "throughput": 578.86, "total_tokens": 9345160}
 {"current_steps": 900, "total_steps": 6770, "eval_loss": 0.5605542063713074, "epoch": 0.2658788774002954, "percentage": 13.29, "elapsed_time": "4:29:23", "remaining_time": "1 day, 5:16:59", "throughput": 578.18, "total_tokens": 9345160}
+{"current_steps": 905, "total_steps": 6770, "loss": 0.4973, "lr": 9.810090352876685e-05, "epoch": 0.2673559822747415, "percentage": 13.37, "elapsed_time": "4:30:55", "remaining_time": "1 day, 5:15:48", "throughput": 578.04, "total_tokens": 9396608}
+{"current_steps": 910, "total_steps": 6770, "loss": 0.4845, "lr": 9.806742116809575e-05, "epoch": 0.2688330871491876, "percentage": 13.44, "elapsed_time": "4:32:23", "remaining_time": "1 day, 5:14:02", "throughput": 578.12, "total_tokens": 9448264}
+{"current_steps": 915, "total_steps": 6770, "loss": 0.4405, "lr": 9.803365203767201e-05, "epoch": 0.27031019202363366, "percentage": 13.52, "elapsed_time": "4:33:50", "remaining_time": "1 day, 5:12:19", "throughput": 578.26, "total_tokens": 9501288}
+{"current_steps": 920, "total_steps": 6770, "loss": 0.5228, "lr": 9.799959633896194e-05, "epoch": 0.2717872968980798, "percentage": 13.59, "elapsed_time": "4:35:18", "remaining_time": "1 day, 5:10:38", "throughput": 578.29, "total_tokens": 9552680}
+{"current_steps": 925, "total_steps": 6770, "loss": 0.4189, "lr": 9.79652542751415e-05, "epoch": 0.27326440177252587, "percentage": 13.66, "elapsed_time": "4:36:46", "remaining_time": "1 day, 5:08:57", "throughput": 578.34, "total_tokens": 9604432}
+{"current_steps": 930, "total_steps": 6770, "loss": 0.4449, "lr": 9.793062605109509e-05, "epoch": 0.27474150664697194, "percentage": 13.74, "elapsed_time": "4:38:14", "remaining_time": "1 day, 5:07:15", "throughput": 578.45, "total_tokens": 9656992}
+{"current_steps": 935, "total_steps": 6770, "loss": 0.4678, "lr": 9.789571187341433e-05, "epoch": 0.276218611521418, "percentage": 13.81, "elapsed_time": "4:39:42", "remaining_time": "1 day, 5:05:32", "throughput": 578.52, "total_tokens": 9709016}
+{"current_steps": 940, "total_steps": 6770, "loss": 0.5359, "lr": 9.786051195039689e-05, "epoch": 0.2776957163958641, "percentage": 13.88, "elapsed_time": "4:41:10", "remaining_time": "1 day, 5:03:51", "throughput": 578.53, "total_tokens": 9759936}
+{"current_steps": 945, "total_steps": 6770, "loss": 0.5507, "lr": 9.782502649204512e-05, "epoch": 0.2791728212703102, "percentage": 13.96, "elapsed_time": "4:42:37", "remaining_time": "1 day, 5:02:07", "throughput": 578.61, "total_tokens": 9811880}
+{"current_steps": 950, "total_steps": 6770, "loss": 0.4737, "lr": 9.778925571006495e-05, "epoch": 0.28064992614475626, "percentage": 14.03, "elapsed_time": "4:44:05", "remaining_time": "1 day, 5:00:27", "throughput": 578.63, "total_tokens": 9863168}
+{"current_steps": 950, "total_steps": 6770, "eval_loss": 0.479105681180954, "epoch": 0.28064992614475626, "percentage": 14.03, "elapsed_time": "4:44:24", "remaining_time": "1 day, 5:02:25", "throughput": 577.98, "total_tokens": 9863168}