Training in progress, step 1450

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1c7ec080c49b4ded7d9add721716bdf06187fb00c39ff223f5982466d466c72
+oid sha256:63bdf97cbdcbe4d5216e9c0ce613d425d968ff354386ba05cd27adff5ef1275e
 size 29034840

trainer_log.jsonl

@@ -310,3 +310,14 @@
 {"current_steps": 1395, "total_steps": 3400, "loss": 0.4341, "lr": 6.851469673071143e-05, "epoch": 0.3592583054339428, "percentage": 41.03, "elapsed_time": "4:08:35", "remaining_time": "5:57:17", "throughput": 981.81, "total_tokens": 14643920}
 {"current_steps": 1400, "total_steps": 3400, "loss": 0.437, "lr": 6.828860628415253e-05, "epoch": 0.3605459696111254, "percentage": 41.18, "elapsed_time": "4:10:03", "remaining_time": "5:57:13", "throughput": 979.58, "total_tokens": 14697136}
 {"current_steps": 1400, "total_steps": 3400, "eval_loss": 0.46620962023735046, "epoch": 0.3605459696111254, "percentage": 41.18, "elapsed_time": "4:10:41", "remaining_time": "5:58:08", "throughput": 977.08, "total_tokens": 14697136}
+{"current_steps": 1405, "total_steps": 3400, "loss": 0.4377, "lr": 6.806208330935766e-05, "epoch": 0.361833633788308, "percentage": 41.32, "elapsed_time": "4:12:14", "remaining_time": "5:58:09", "throughput": 974.56, "total_tokens": 14749168}
+{"current_steps": 1410, "total_steps": 3400, "loss": 0.412, "lr": 6.783513316362855e-05, "epoch": 0.3631212979654906, "percentage": 41.47, "elapsed_time": "4:13:42", "remaining_time": "5:58:04", "throughput": 972.35, "total_tokens": 14801568}
+{"current_steps": 1415, "total_steps": 3400, "loss": 0.4441, "lr": 6.760776121436962e-05, "epoch": 0.3644089621426732, "percentage": 41.62, "elapsed_time": "4:15:09", "remaining_time": "5:57:56", "throughput": 970.22, "total_tokens": 14853384}
+{"current_steps": 1420, "total_steps": 3400, "loss": 0.4576, "lr": 6.737997283896103e-05, "epoch": 0.3656966263198558, "percentage": 41.76, "elapsed_time": "4:16:37", "remaining_time": "5:57:50", "throughput": 968.1, "total_tokens": 14906632}
+{"current_steps": 1425, "total_steps": 3400, "loss": 0.3853, "lr": 6.715177342463145e-05, "epoch": 0.36698429049703835, "percentage": 41.91, "elapsed_time": "4:18:04", "remaining_time": "5:57:41", "throughput": 966.07, "total_tokens": 14959240}
+{"current_steps": 1430, "total_steps": 3400, "loss": 0.3755, "lr": 6.692316836833065e-05, "epoch": 0.36827195467422097, "percentage": 42.06, "elapsed_time": "4:19:32", "remaining_time": "5:57:33", "throughput": 964.01, "total_tokens": 15012256}
+{"current_steps": 1435, "total_steps": 3400, "loss": 0.5384, "lr": 6.6694163076602e-05, "epoch": 0.36955961885140354, "percentage": 42.21, "elapsed_time": "4:21:00", "remaining_time": "5:57:24", "throughput": 961.97, "total_tokens": 15064664}
+{"current_steps": 1440, "total_steps": 3400, "loss": 0.4377, "lr": 6.646476296545434e-05, "epoch": 0.37084728302858616, "percentage": 42.35, "elapsed_time": "4:22:28", "remaining_time": "5:57:15", "throughput": 959.94, "total_tokens": 15117384}
+{"current_steps": 1445, "total_steps": 3400, "loss": 0.3876, "lr": 6.623497346023418e-05, "epoch": 0.37213494720576873, "percentage": 42.5, "elapsed_time": "4:23:55", "remaining_time": "5:57:05", "throughput": 957.94, "total_tokens": 15169880}
+{"current_steps": 1450, "total_steps": 3400, "loss": 0.4065, "lr": 6.60047999954972e-05, "epoch": 0.37342261138295135, "percentage": 42.65, "elapsed_time": "4:25:23", "remaining_time": "5:56:54", "throughput": 955.96, "total_tokens": 15222568}
+{"current_steps": 1450, "total_steps": 3400, "eval_loss": 0.4395444095134735, "epoch": 0.37342261138295135, "percentage": 42.65, "elapsed_time": "4:26:02", "remaining_time": "5:57:46", "throughput": 953.66, "total_tokens": 15222568}