Training in progress, step 800

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acaedc144367149e2a92be2a9c0e75df4817558ae00e175c156fbc72ea2ce596
+oid sha256:f6287ca2ed8e9ca31735e5d987ece6f9b430689719f525a3a04c74ff709108ab
 size 29034840

trainer_log.jsonl

@@ -163,3 +163,14 @@
 {"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}
+{"current_steps": 755, "total_steps": 3400, "loss": 0.0426, "lr": 9.21223287233121e-05, "epoch": 0.3888745815091424, "percentage": 22.21, "elapsed_time": "3:44:33", "remaining_time": "13:06:41", "throughput": 559.46, "total_tokens": 7537920}
+{"current_steps": 760, "total_steps": 3400, "loss": 0.0094, "lr": 9.199082286279622e-05, "epoch": 0.3914499098635076, "percentage": 22.35, "elapsed_time": "3:45:59", "remaining_time": "13:05:02", "throughput": 559.58, "total_tokens": 7587840}
+{"current_steps": 765, "total_steps": 3400, "loss": 0.008, "lr": 9.185832391312644e-05, "epoch": 0.3940252382178728, "percentage": 22.5, "elapsed_time": "3:47:26", "remaining_time": "13:03:24", "throughput": 559.69, "total_tokens": 7637760}
+{"current_steps": 770, "total_steps": 3400, "loss": 0.0297, "lr": 9.172483500792244e-05, "epoch": 0.39660056657223797, "percentage": 22.65, "elapsed_time": "3:48:53", "remaining_time": "13:01:46", "throughput": 559.79, "total_tokens": 7687680}
+{"current_steps": 775, "total_steps": 3400, "loss": 0.0239, "lr": 9.159035930421658e-05, "epoch": 0.39917589492660316, "percentage": 22.79, "elapsed_time": "3:50:19", "remaining_time": "13:00:08", "throughput": 559.9, "total_tokens": 7737600}
+{"current_steps": 780, "total_steps": 3400, "loss": 0.0162, "lr": 9.145489998237902e-05, "epoch": 0.40175122328096835, "percentage": 22.94, "elapsed_time": "3:51:46", "remaining_time": "12:58:31", "throughput": 559.99, "total_tokens": 7787520}
+{"current_steps": 785, "total_steps": 3400, "loss": 0.0309, "lr": 9.131846024604274e-05, "epoch": 0.4043265516353335, "percentage": 23.09, "elapsed_time": "3:53:12", "remaining_time": "12:56:51", "throughput": 560.13, "total_tokens": 7837440}
+{"current_steps": 790, "total_steps": 3400, "loss": 0.0432, "lr": 9.11810433220276e-05, "epoch": 0.4069018799896987, "percentage": 23.24, "elapsed_time": "3:54:38", "remaining_time": "12:55:12", "throughput": 560.24, "total_tokens": 7887360}
+{"current_steps": 795, "total_steps": 3400, "loss": 0.0022, "lr": 9.104265246026415e-05, "epoch": 0.40947720834406387, "percentage": 23.38, "elapsed_time": "3:56:04", "remaining_time": "12:53:34", "throughput": 560.35, "total_tokens": 7937280}
+{"current_steps": 800, "total_steps": 3400, "loss": 0.0065, "lr": 9.090329093371666e-05, "epoch": 0.41205253669842906, "percentage": 23.53, "elapsed_time": "3:57:31", "remaining_time": "12:51:57", "throughput": 560.44, "total_tokens": 7987200}
+{"current_steps": 800, "total_steps": 3400, "eval_loss": 0.006797688081860542, "epoch": 0.41205253669842906, "percentage": 23.53, "elapsed_time": "3:57:50", "remaining_time": "12:53:00", "throughput": 559.68, "total_tokens": 7987200}