Training in progress, step 1250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c1933263a4147535e3edcd506e0269c5b74a0e48619e4b7de41e058b06d730b
+oid sha256:3bb18bc55e51868d1cfa188776cb8ea35d99e69f7889e54da75d1f08cd00c5fb
 size 29034840

trainer_log.jsonl

@@ -266,3 +266,14 @@
 {"current_steps": 1195, "total_steps": 3400, "loss": 0.407, "lr": 7.714352216101055e-05, "epoch": 0.3077517383466392, "percentage": 35.15, "elapsed_time": "3:07:07", "remaining_time": "5:45:17", "throughput": 1117.27, "total_tokens": 12544264}
 {"current_steps": 1200, "total_steps": 3400, "loss": 0.454, "lr": 7.693899446759727e-05, "epoch": 0.3090394025238218, "percentage": 35.29, "elapsed_time": "3:08:36", "remaining_time": "5:45:47", "throughput": 1113.05, "total_tokens": 12596208}
 {"current_steps": 1200, "total_steps": 3400, "eval_loss": 0.49250805377960205, "epoch": 0.3090394025238218, "percentage": 35.29, "elapsed_time": "3:09:15", "remaining_time": "5:46:58", "throughput": 1109.25, "total_tokens": 12596208}
+{"current_steps": 1205, "total_steps": 3400, "loss": 0.5226, "lr": 7.673382966299163e-05, "epoch": 0.31032706670100435, "percentage": 35.44, "elapsed_time": "3:10:48", "remaining_time": "5:47:33", "throughput": 1104.87, "total_tokens": 12648936}
+{"current_steps": 1210, "total_steps": 3400, "loss": 0.4757, "lr": 7.65280325993715e-05, "epoch": 0.311614730878187, "percentage": 35.59, "elapsed_time": "3:12:16", "remaining_time": "5:48:00", "throughput": 1101.05, "total_tokens": 12702432}
+{"current_steps": 1215, "total_steps": 3400, "loss": 0.451, "lr": 7.63216081438678e-05, "epoch": 0.31290239505536954, "percentage": 35.74, "elapsed_time": "3:13:43", "remaining_time": "5:48:23", "throughput": 1097.34, "total_tokens": 12755128}
+{"current_steps": 1220, "total_steps": 3400, "loss": 0.4155, "lr": 7.611456117844934e-05, "epoch": 0.31419005923255217, "percentage": 35.88, "elapsed_time": "3:15:12", "remaining_time": "5:48:49", "throughput": 1093.54, "total_tokens": 12808152}
+{"current_steps": 1225, "total_steps": 3400, "loss": 0.4094, "lr": 7.59068965998074e-05, "epoch": 0.31547772340973473, "percentage": 36.03, "elapsed_time": "3:16:39", "remaining_time": "5:49:10", "throughput": 1090.0, "total_tokens": 12861592}
+{"current_steps": 1230, "total_steps": 3400, "loss": 0.4663, "lr": 7.569861931923989e-05, "epoch": 0.31676538758691736, "percentage": 36.18, "elapsed_time": "3:18:08", "remaining_time": "5:49:33", "throughput": 1086.31, "total_tokens": 12914240}
+{"current_steps": 1235, "total_steps": 3400, "loss": 0.468, "lr": 7.548973426253521e-05, "epoch": 0.3180530517640999, "percentage": 36.32, "elapsed_time": "3:19:35", "remaining_time": "5:49:52", "throughput": 1082.86, "total_tokens": 12967472}
+{"current_steps": 1240, "total_steps": 3400, "loss": 0.4744, "lr": 7.528024636985575e-05, "epoch": 0.3193407159412825, "percentage": 36.47, "elapsed_time": "3:21:04", "remaining_time": "5:50:15", "throughput": 1079.25, "total_tokens": 13020232}
+{"current_steps": 1245, "total_steps": 3400, "loss": 0.4269, "lr": 7.507016059562107e-05, "epoch": 0.3206283801184651, "percentage": 36.62, "elapsed_time": "3:22:31", "remaining_time": "5:50:33", "throughput": 1075.84, "total_tokens": 13073032}
+{"current_steps": 1250, "total_steps": 3400, "loss": 0.4725, "lr": 7.485948190839077e-05, "epoch": 0.3219160442956477, "percentage": 36.76, "elapsed_time": "3:24:00", "remaining_time": "5:50:52", "throughput": 1072.35, "total_tokens": 13125624}
+{"current_steps": 1250, "total_steps": 3400, "eval_loss": 0.4339977502822876, "epoch": 0.3219160442956477, "percentage": 36.76, "elapsed_time": "3:24:39", "remaining_time": "5:52:00", "throughput": 1068.93, "total_tokens": 13125624}