Training in progress, step 1150

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38c92d201c343dd983a22c7fe6d61ce77cf92ee8cd85263b720e40f9ba6a14e5
+oid sha256:ad37ecfc8f56cfb958ea72a1146b5dd079374376e542f0312701bdbcbb5deae5
 size 29034840

trainer_log.jsonl

@@ -244,3 +244,14 @@
 {"current_steps": 1095, "total_steps": 3400, "loss": 0.4895, "lr": 8.109294756255375e-05, "epoch": 0.2819984548029874, "percentage": 32.21, "elapsed_time": "2:36:17", "remaining_time": "5:28:59", "throughput": 1225.81, "total_tokens": 11494880}
 {"current_steps": 1100, "total_steps": 3400, "loss": 0.4825, "lr": 8.090215701880419e-05, "epoch": 0.28328611898017, "percentage": 32.35, "elapsed_time": "2:37:45", "remaining_time": "5:29:51", "throughput": 1219.93, "total_tokens": 11547008}
 {"current_steps": 1100, "total_steps": 3400, "eval_loss": 0.4798590838909149, "epoch": 0.28328611898017, "percentage": 32.35, "elapsed_time": "2:38:25", "remaining_time": "5:31:16", "throughput": 1214.71, "total_tokens": 11547008}
+{"current_steps": 1105, "total_steps": 3400, "loss": 0.4927, "lr": 8.07106356344834e-05, "epoch": 0.28457378315735254, "percentage": 32.5, "elapsed_time": "2:40:02", "remaining_time": "5:32:23", "throughput": 1208.03, "total_tokens": 11600032}
+{"current_steps": 1110, "total_steps": 3400, "loss": 0.4353, "lr": 8.051838793910038e-05, "epoch": 0.28586144733453517, "percentage": 32.65, "elapsed_time": "2:41:30", "remaining_time": "5:33:11", "throughput": 1202.47, "total_tokens": 11652120}
+{"current_steps": 1115, "total_steps": 3400, "loss": 0.4891, "lr": 8.032541847934146e-05, "epoch": 0.28714911151171774, "percentage": 32.79, "elapsed_time": "2:42:59", "remaining_time": "5:34:01", "throughput": 1196.88, "total_tokens": 11705184}
+{"current_steps": 1120, "total_steps": 3400, "loss": 0.4497, "lr": 8.013173181896283e-05, "epoch": 0.28843677568890036, "percentage": 32.94, "elapsed_time": "2:44:27", "remaining_time": "5:34:48", "throughput": 1191.54, "total_tokens": 11758032}
+{"current_steps": 1125, "total_steps": 3400, "loss": 0.4927, "lr": 7.993733253868256e-05, "epoch": 0.28972443986608293, "percentage": 33.09, "elapsed_time": "2:45:57", "remaining_time": "5:35:36", "throughput": 1186.11, "total_tokens": 11810736}
+{"current_steps": 1130, "total_steps": 3400, "loss": 0.4853, "lr": 7.974222523607236e-05, "epoch": 0.2910121040432655, "percentage": 33.24, "elapsed_time": "2:47:24", "remaining_time": "5:36:17", "throughput": 1181.07, "total_tokens": 11863152}
+{"current_steps": 1135, "total_steps": 3400, "loss": 0.4458, "lr": 7.954641452544865e-05, "epoch": 0.2922997682204481, "percentage": 33.38, "elapsed_time": "2:48:52", "remaining_time": "5:37:00", "throughput": 1175.84, "total_tokens": 11914536}
+{"current_steps": 1140, "total_steps": 3400, "loss": 0.3976, "lr": 7.934990503776363e-05, "epoch": 0.2935874323976307, "percentage": 33.53, "elapsed_time": "2:50:19", "remaining_time": "5:37:40", "throughput": 1170.89, "total_tokens": 11966064}
+{"current_steps": 1145, "total_steps": 3400, "loss": 0.508, "lr": 7.915270142049566e-05, "epoch": 0.2948750965748133, "percentage": 33.68, "elapsed_time": "2:51:47", "remaining_time": "5:38:20", "throughput": 1166.0, "total_tokens": 12018928}
+{"current_steps": 1150, "total_steps": 3400, "loss": 0.4553, "lr": 7.89548083375394e-05, "epoch": 0.2961627607519959, "percentage": 33.82, "elapsed_time": "2:53:14", "remaining_time": "5:38:57", "throughput": 1161.26, "total_tokens": 12071088}
+{"current_steps": 1150, "total_steps": 3400, "eval_loss": 0.45381438732147217, "epoch": 0.2961627607519959, "percentage": 33.82, "elapsed_time": "2:53:53", "remaining_time": "5:40:12", "throughput": 1156.99, "total_tokens": 12071088}