Training in progress, step 2550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cd56f5dfc9655c1cce72c58e7171b43d809ae6db173fb5bf3e8fc8c8fe2e604
+oid sha256:171dfcb8bb8ac5a7df90ac9ee419e7a8a301f24e9f99f3e8664ab7c1ada5f55f
 size 29034840

trainer_log.jsonl

@@ -552,3 +552,14 @@
 {"current_steps": 2495, "total_steps": 3400, "loss": 0.3576, "lr": 1.8151288651144893e-05, "epoch": 0.6425444244141127, "percentage": 73.38, "elapsed_time": "9:45:57", "remaining_time": "3:32:32", "throughput": 745.24, "total_tokens": 26200744}
 {"current_steps": 2500, "total_steps": 3400, "loss": 0.363, "lr": 1.796421964420285e-05, "epoch": 0.6438320885912954, "percentage": 73.53, "elapsed_time": "9:47:25", "remaining_time": "3:31:28", "throughput": 744.86, "total_tokens": 26252584}
 {"current_steps": 2500, "total_steps": 3400, "eval_loss": 0.44705262780189514, "epoch": 0.6438320885912954, "percentage": 73.53, "elapsed_time": "9:48:03", "remaining_time": "3:31:42", "throughput": 744.05, "total_tokens": 26252584}
+{"current_steps": 2505, "total_steps": 3400, "loss": 0.3113, "lr": 1.7777908288191176e-05, "epoch": 0.645119752768478, "percentage": 73.68, "elapsed_time": "9:49:35", "remaining_time": "3:30:39", "throughput": 743.58, "total_tokens": 26304800}
+{"current_steps": 2510, "total_steps": 3400, "loss": 0.3581, "lr": 1.7592358989400883e-05, "epoch": 0.6464074169456606, "percentage": 73.82, "elapsed_time": "9:51:03", "remaining_time": "3:29:34", "throughput": 743.23, "total_tokens": 26357680}
+{"current_steps": 2515, "total_steps": 3400, "loss": 0.3353, "lr": 1.740757613610028e-05, "epoch": 0.6476950811228431, "percentage": 73.97, "elapsed_time": "9:52:31", "remaining_time": "3:28:30", "throughput": 742.89, "total_tokens": 26410432}
+{"current_steps": 2520, "total_steps": 3400, "loss": 0.2796, "lr": 1.7223564098431067e-05, "epoch": 0.6489827453000258, "percentage": 74.12, "elapsed_time": "9:54:00", "remaining_time": "3:27:26", "throughput": 742.49, "total_tokens": 26463016}
+{"current_steps": 2525, "total_steps": 3400, "loss": 0.3197, "lr": 1.704032722830512e-05, "epoch": 0.6502704094772084, "percentage": 74.26, "elapsed_time": "9:55:31", "remaining_time": "3:26:22", "throughput": 742.07, "total_tokens": 26515408}
+{"current_steps": 2530, "total_steps": 3400, "loss": 0.3182, "lr": 1.68578698593014e-05, "epoch": 0.6515580736543909, "percentage": 74.41, "elapsed_time": "9:57:00", "remaining_time": "3:25:17", "throughput": 741.67, "total_tokens": 26567024}
+{"current_steps": 2535, "total_steps": 3400, "loss": 0.3822, "lr": 1.6676196306563613e-05, "epoch": 0.6528457378315735, "percentage": 74.56, "elapsed_time": "9:58:28", "remaining_time": "3:24:12", "throughput": 741.31, "total_tokens": 26619744}
+{"current_steps": 2540, "total_steps": 3400, "loss": 0.2853, "lr": 1.6495310866698093e-05, "epoch": 0.6541334020087561, "percentage": 74.71, "elapsed_time": "9:59:57", "remaining_time": "3:23:08", "throughput": 740.94, "total_tokens": 26672408}
+{"current_steps": 2545, "total_steps": 3400, "loss": 0.3622, "lr": 1.631521781767214e-05, "epoch": 0.6554210661859388, "percentage": 74.85, "elapsed_time": "10:01:25", "remaining_time": "3:22:03", "throughput": 740.58, "total_tokens": 26724488}
+{"current_steps": 2550, "total_steps": 3400, "loss": 0.3195, "lr": 1.6135921418712956e-05, "epoch": 0.6567087303631213, "percentage": 75.0, "elapsed_time": "10:02:54", "remaining_time": "3:20:58", "throughput": 740.22, "total_tokens": 26776816}
+{"current_steps": 2550, "total_steps": 3400, "eval_loss": 0.43731561303138733, "epoch": 0.6567087303631213, "percentage": 75.0, "elapsed_time": "10:03:32", "remaining_time": "3:21:10", "throughput": 739.43, "total_tokens": 26776816}