Training in progress, step 2500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76ea3377531bb34d473bfe1ac7fb7435074a39aec464fce193b5f47faf92de11
+oid sha256:0cd56f5dfc9655c1cce72c58e7171b43d809ae6db173fb5bf3e8fc8c8fe2e604
 size 29034840

trainer_log.jsonl

@@ -541,3 +541,14 @@
 {"current_steps": 2445, "total_steps": 3400, "loss": 0.2833, "lr": 2.0062667461317426e-05, "epoch": 0.6296677826422868, "percentage": 71.91, "elapsed_time": "9:30:34", "remaining_time": "3:42:51", "throughput": 750.1, "total_tokens": 25679208}
 {"current_steps": 2450, "total_steps": 3400, "loss": 0.3413, "lr": 1.9868268181037185e-05, "epoch": 0.6309554468194695, "percentage": 72.06, "elapsed_time": "9:32:01", "remaining_time": "3:41:48", "throughput": 749.68, "total_tokens": 25730432}
 {"current_steps": 2450, "total_steps": 3400, "eval_loss": 0.46914541721343994, "epoch": 0.6309554468194695, "percentage": 72.06, "elapsed_time": "9:32:40", "remaining_time": "3:42:03", "throughput": 748.85, "total_tokens": 25730432}
+{"current_steps": 2455, "total_steps": 3400, "loss": 0.3132, "lr": 1.967458152065857e-05, "epoch": 0.6322431109966521, "percentage": 72.21, "elapsed_time": "9:34:13", "remaining_time": "3:41:02", "throughput": 748.34, "total_tokens": 25782992}
+{"current_steps": 2460, "total_steps": 3400, "loss": 0.2995, "lr": 1.9481612060899646e-05, "epoch": 0.6335307751738347, "percentage": 72.35, "elapsed_time": "9:35:41", "remaining_time": "3:39:58", "throughput": 747.96, "total_tokens": 25835576}
+{"current_steps": 2465, "total_steps": 3400, "loss": 0.3104, "lr": 1.928936436551661e-05, "epoch": 0.6348184393510172, "percentage": 72.5, "elapsed_time": "9:37:09", "remaining_time": "3:38:55", "throughput": 747.54, "total_tokens": 25886784}
+{"current_steps": 2470, "total_steps": 3400, "loss": 0.2866, "lr": 1.9097842981195834e-05, "epoch": 0.6361061035281999, "percentage": 72.65, "elapsed_time": "9:38:37", "remaining_time": "3:37:51", "throughput": 747.16, "total_tokens": 25939408}
+{"current_steps": 2475, "total_steps": 3400, "loss": 0.2886, "lr": 1.8907052437446272e-05, "epoch": 0.6373937677053825, "percentage": 72.79, "elapsed_time": "9:40:05", "remaining_time": "3:36:48", "throughput": 746.78, "total_tokens": 25992048}
+{"current_steps": 2480, "total_steps": 3400, "loss": 0.3752, "lr": 1.871699724649244e-05, "epoch": 0.638681431882565, "percentage": 72.94, "elapsed_time": "9:41:33", "remaining_time": "3:35:44", "throughput": 746.42, "total_tokens": 26045216}
+{"current_steps": 2485, "total_steps": 3400, "loss": 0.3039, "lr": 1.8527681903167644e-05, "epoch": 0.6399690960597476, "percentage": 73.09, "elapsed_time": "9:43:01", "remaining_time": "3:34:40", "throughput": 746.04, "total_tokens": 26097424}
+{"current_steps": 2490, "total_steps": 3400, "loss": 0.3142, "lr": 1.833911088480767e-05, "epoch": 0.6412567602369302, "percentage": 73.24, "elapsed_time": "9:44:29", "remaining_time": "3:33:36", "throughput": 745.65, "total_tokens": 26149616}
+{"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}