Training in progress, step 3300

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:642c404d73293fddcd261352a6740967f2766dca25c2923d3502bb6f1bfc7e20
+oid sha256:edfec1beb3478ee41909b5ce24ea198317f07af35edd0e3dbe2802570cfa4c2f
 size 29034840

trainer_log.jsonl

@@ -716,3 +716,14 @@
 {"current_steps": 3245, "total_steps": 3400, "loss": 0.2519, "lr": 5.671205728947305e-07, "epoch": 0.8356940509915014, "percentage": 95.44, "elapsed_time": "3:30:53", "remaining_time": "0:10:04", "throughput": 2693.25, "total_tokens": 34077920}
 {"current_steps": 3250, "total_steps": 3400, "loss": 0.2836, "lr": 5.311861644696048e-07, "epoch": 0.836981715168684, "percentage": 95.59, "elapsed_time": "3:32:17", "remaining_time": "0:09:47", "throughput": 2679.43, "total_tokens": 34129832}
 {"current_steps": 3250, "total_steps": 3400, "eval_loss": 0.46573224663734436, "epoch": 0.836981715168684, "percentage": 95.59, "elapsed_time": "3:32:55", "remaining_time": "0:09:49", "throughput": 2671.58, "total_tokens": 34129832}
+{"current_steps": 3255, "total_steps": 3400, "loss": 0.3243, "lr": 4.964217007878081e-07, "epoch": 0.8382693793458666, "percentage": 95.74, "elapsed_time": "3:34:26", "remaining_time": "0:09:33", "throughput": 2656.65, "total_tokens": 34182360}
+{"current_steps": 3260, "total_steps": 3400, "loss": 0.295, "lr": 4.6282800403402715e-07, "epoch": 0.8395570435230492, "percentage": 95.88, "elapsed_time": "3:35:51", "remaining_time": "0:09:16", "throughput": 2643.19, "total_tokens": 34234176}
+{"current_steps": 3265, "total_steps": 3400, "loss": 0.3189, "lr": 4.3040586870415346e-07, "epoch": 0.8408447077002318, "percentage": 96.03, "elapsed_time": "3:37:18", "remaining_time": "0:08:59", "throughput": 2629.71, "total_tokens": 34287472}
+{"current_steps": 3270, "total_steps": 3400, "loss": 0.2927, "lr": 3.991560615864587e-07, "epoch": 0.8421323718774144, "percentage": 96.18, "elapsed_time": "3:38:43", "remaining_time": "0:08:41", "throughput": 2616.63, "total_tokens": 34339496}
+{"current_steps": 3275, "total_steps": 3400, "loss": 0.299, "lr": 3.6907932174349846e-07, "epoch": 0.8434200360545969, "percentage": 96.32, "elapsed_time": "3:40:10", "remaining_time": "0:08:24", "throughput": 2603.45, "total_tokens": 34391688}
+{"current_steps": 3280, "total_steps": 3400, "loss": 0.3218, "lr": 3.40176360494604e-07, "epoch": 0.8447077002317795, "percentage": 96.47, "elapsed_time": "3:41:34", "remaining_time": "0:08:06", "throughput": 2590.8, "total_tokens": 34443720}
+{"current_steps": 3285, "total_steps": 3400, "loss": 0.3295, "lr": 3.124478613990733e-07, "epoch": 0.8459953644089622, "percentage": 96.62, "elapsed_time": "3:43:01", "remaining_time": "0:07:48", "throughput": 2577.92, "total_tokens": 34495512}
+{"current_steps": 3290, "total_steps": 3400, "loss": 0.2889, "lr": 2.8589448023998987e-07, "epoch": 0.8472830285861447, "percentage": 96.76, "elapsed_time": "3:44:27", "remaining_time": "0:07:30", "throughput": 2565.24, "total_tokens": 34547936}
+{"current_steps": 3295, "total_steps": 3400, "loss": 0.2697, "lr": 2.605168450087514e-07, "epoch": 0.8485706927633273, "percentage": 96.91, "elapsed_time": "3:45:54", "remaining_time": "0:07:11", "throughput": 2552.74, "total_tokens": 34601320}
+{"current_steps": 3300, "total_steps": 3400, "loss": 0.3135, "lr": 2.363155558901542e-07, "epoch": 0.8498583569405099, "percentage": 97.06, "elapsed_time": "3:47:21", "remaining_time": "0:06:53", "throughput": 2540.34, "total_tokens": 34654480}
+{"current_steps": 3300, "total_steps": 3400, "eval_loss": 0.4714098274707794, "epoch": 0.8498583569405099, "percentage": 97.06, "elapsed_time": "3:47:59", "remaining_time": "0:06:54", "throughput": 2533.36, "total_tokens": 34654480}