Training in progress, step 1500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:140829d96675f8a17bdb0fa18b56b080defbfc9f26441176908846cb9afcc2fb
+oid sha256:5c9a15524ca69ba3d1a171c59eaf574e64f0642e13435155688ec32a8d7af040
 size 29034840

trainer_log.jsonl

@@ -317,3 +317,14 @@
 {"current_steps": 1445, "total_steps": 3882, "loss": 0.4457, "lr": 7.422122663783187e-05, "epoch": 0.7442698944115375, "percentage": 37.22, "elapsed_time": "7:22:18", "remaining_time": "12:25:56", "throughput": 636.87, "total_tokens": 16901176}
 {"current_steps": 1450, "total_steps": 3882, "loss": 0.4353, "lr": 7.403465200908883e-05, "epoch": 0.7468452227659027, "percentage": 37.35, "elapsed_time": "7:23:45", "remaining_time": "12:24:17", "throughput": 636.97, "total_tokens": 16959632}
 {"current_steps": 1450, "total_steps": 3882, "eval_loss": 0.43503889441490173, "epoch": 0.7468452227659027, "percentage": 37.35, "elapsed_time": "7:24:05", "remaining_time": "12:24:50", "throughput": 636.5, "total_tokens": 16959632}
+{"current_steps": 1455, "total_steps": 3882, "loss": 0.4183, "lr": 7.38476411351468e-05, "epoch": 0.7494205511202678, "percentage": 37.48, "elapsed_time": "7:25:39", "remaining_time": "12:23:23", "throughput": 636.43, "total_tokens": 17018072}
+{"current_steps": 1460, "total_steps": 3882, "loss": 0.4632, "lr": 7.366019741037973e-05, "epoch": 0.751995879474633, "percentage": 37.61, "elapsed_time": "7:27:09", "remaining_time": "12:21:47", "throughput": 636.49, "total_tokens": 17076560}
+{"current_steps": 1465, "total_steps": 3882, "loss": 0.4512, "lr": 7.347232423701804e-05, "epoch": 0.7545712078289982, "percentage": 37.74, "elapsed_time": "7:28:37", "remaining_time": "12:20:09", "throughput": 636.57, "total_tokens": 17135016}
+{"current_steps": 1470, "total_steps": 3882, "loss": 0.4121, "lr": 7.328402502508701e-05, "epoch": 0.7571465361833634, "percentage": 37.87, "elapsed_time": "7:30:06", "remaining_time": "12:18:33", "throughput": 636.64, "total_tokens": 17193496}
+{"current_steps": 1475, "total_steps": 3882, "loss": 0.5234, "lr": 7.309530319234472e-05, "epoch": 0.7597218645377286, "percentage": 38.0, "elapsed_time": "7:31:35", "remaining_time": "12:16:55", "throughput": 636.72, "total_tokens": 17251944}
+{"current_steps": 1480, "total_steps": 3882, "loss": 0.3895, "lr": 7.290616216422017e-05, "epoch": 0.7622971928920937, "percentage": 38.12, "elapsed_time": "7:33:03", "remaining_time": "12:15:18", "throughput": 636.79, "total_tokens": 17310456}
+{"current_steps": 1485, "total_steps": 3882, "loss": 0.3641, "lr": 7.271660537375102e-05, "epoch": 0.7648725212464589, "percentage": 38.25, "elapsed_time": "7:34:32", "remaining_time": "12:13:42", "throughput": 636.86, "total_tokens": 17368968}
+{"current_steps": 1490, "total_steps": 3882, "loss": 0.3867, "lr": 7.25266362615213e-05, "epoch": 0.7674478496008241, "percentage": 38.38, "elapsed_time": "7:36:01", "remaining_time": "12:12:05", "throughput": 636.92, "total_tokens": 17427424}
+{"current_steps": 1495, "total_steps": 3882, "loss": 0.3214, "lr": 7.233625827559893e-05, "epoch": 0.7700231779551893, "percentage": 38.51, "elapsed_time": "7:37:30", "remaining_time": "12:10:28", "throughput": 637.01, "total_tokens": 17485936}
+{"current_steps": 1500, "total_steps": 3882, "loss": 0.3369, "lr": 7.21454748714732e-05, "epoch": 0.7725985063095545, "percentage": 38.64, "elapsed_time": "7:38:59", "remaining_time": "12:08:52", "throughput": 637.07, "total_tokens": 17544440}
+{"current_steps": 1500, "total_steps": 3882, "eval_loss": 0.3963810205459595, "epoch": 0.7725985063095545, "percentage": 38.64, "elapsed_time": "7:39:18", "remaining_time": "12:09:22", "throughput": 636.62, "total_tokens": 17544440}