Training in progress, step 720

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b0443b9b135f0a9747f74e9ff6f5b14c6630b525f4dd33bf72233c83c38e3d8
+oid sha256:5e922a7fc08a17653fe762a1597a8c91569f5f4cdbbe90e572739282753962f0
 size 58745928

trainer_log.jsonl

@@ -139,3 +139,22 @@
 {"current_steps": 660, "total_steps": 1800, "loss": 0.0, "lr": 3.996782472623705e-05, "epoch": 7.333333333333333, "percentage": 36.67, "elapsed_time": "0:02:31", "remaining_time": "0:04:21", "throughput": 1370.5, "total_tokens": 207264}
 {"current_steps": 665, "total_steps": 1800, "loss": 0.0, "lr": 3.977296508774278e-05, "epoch": 7.388888888888889, "percentage": 36.94, "elapsed_time": "0:02:32", "remaining_time": "0:04:19", "throughput": 1371.91, "total_tokens": 208832}
 {"current_steps": 670, "total_steps": 1800, "loss": 0.0, "lr": 3.957671653960337e-05, "epoch": 7.444444444444445, "percentage": 37.22, "elapsed_time": "0:02:33", "remaining_time": "0:04:18", "throughput": 1373.09, "total_tokens": 210368}
+{"current_steps": 675, "total_steps": 1800, "loss": 0.0, "lr": 3.9379097532515725e-05, "epoch": 7.5, "percentage": 37.5, "elapsed_time": "0:02:34", "remaining_time": "0:04:16", "throughput": 1374.44, "total_tokens": 211936}
+{"current_steps": 680, "total_steps": 1800, "loss": 0.0, "lr": 3.918012664602317e-05, "epoch": 7.555555555555555, "percentage": 37.78, "elapsed_time": "0:02:35", "remaining_time": "0:04:15", "throughput": 1376.04, "total_tokens": 213536}
+{"current_steps": 685, "total_steps": 1800, "loss": 0.0, "lr": 3.897982258676867e-05, "epoch": 7.611111111111111, "percentage": 38.06, "elapsed_time": "0:02:36", "remaining_time": "0:04:14", "throughput": 1377.6, "total_tokens": 215136}
+{"current_steps": 690, "total_steps": 1800, "loss": 0.0, "lr": 3.8778204186736076e-05, "epoch": 7.666666666666667, "percentage": 38.33, "elapsed_time": "0:02:37", "remaining_time": "0:04:12", "throughput": 1379.15, "total_tokens": 216736}
+{"current_steps": 695, "total_steps": 1800, "loss": 0.0, "lr": 3.8575290401479586e-05, "epoch": 7.722222222222222, "percentage": 38.61, "elapsed_time": "0:02:38", "remaining_time": "0:04:11", "throughput": 1380.24, "total_tokens": 218272}
+{"current_steps": 700, "total_steps": 1800, "loss": 0.0, "lr": 3.837110030834161e-05, "epoch": 7.777777777777778, "percentage": 38.89, "elapsed_time": "0:02:39", "remaining_time": "0:04:10", "throughput": 1381.29, "total_tokens": 219808}
+{"current_steps": 705, "total_steps": 1800, "loss": 0.0, "lr": 3.8165653104659185e-05, "epoch": 7.833333333333333, "percentage": 39.17, "elapsed_time": "0:02:40", "remaining_time": "0:04:08", "throughput": 1382.13, "total_tokens": 221312}
+{"current_steps": 710, "total_steps": 1800, "loss": 0.0, "lr": 3.79589681059591e-05, "epoch": 7.888888888888889, "percentage": 39.44, "elapsed_time": "0:02:41", "remaining_time": "0:04:07", "throughput": 1383.39, "total_tokens": 222880}
+{"current_steps": 715, "total_steps": 1800, "loss": 0.0, "lr": 3.775106474414188e-05, "epoch": 7.944444444444445, "percentage": 39.72, "elapsed_time": "0:02:42", "remaining_time": "0:04:05", "throughput": 1384.43, "total_tokens": 224416}
+{"current_steps": 720, "total_steps": 1800, "loss": 0.0, "lr": 3.75419625656549e-05, "epoch": 8.0, "percentage": 40.0, "elapsed_time": "0:02:43", "remaining_time": "0:04:04", "throughput": 1385.39, "total_tokens": 225984}
+{"current_steps": 720, "total_steps": 1800, "eval_loss": 0.09462722390890121, "epoch": 8.0, "percentage": 40.0, "elapsed_time": "0:02:43", "remaining_time": "0:04:05", "throughput": 1380.31, "total_tokens": 225984}
+{"current_steps": 725, "total_steps": 1800, "loss": 0.0, "lr": 3.7331681229654635e-05, "epoch": 8.055555555555555, "percentage": 40.28, "elapsed_time": "0:02:46", "remaining_time": "0:04:07", "throughput": 1363.69, "total_tokens": 227552}
+{"current_steps": 730, "total_steps": 1800, "loss": 0.0, "lr": 3.712024050615843e-05, "epoch": 8.11111111111111, "percentage": 40.56, "elapsed_time": "0:02:47", "remaining_time": "0:04:06", "throughput": 1364.74, "total_tokens": 229088}
+{"current_steps": 735, "total_steps": 1800, "loss": 0.0, "lr": 3.690766027418573e-05, "epoch": 8.166666666666666, "percentage": 40.83, "elapsed_time": "0:02:48", "remaining_time": "0:04:04", "throughput": 1365.96, "total_tokens": 230656}
+{"current_steps": 740, "total_steps": 1800, "loss": 0.0, "lr": 3.6693960519889106e-05, "epoch": 8.222222222222221, "percentage": 41.11, "elapsed_time": "0:02:50", "remaining_time": "0:04:03", "throughput": 1364.38, "total_tokens": 232224}
+{"current_steps": 745, "total_steps": 1800, "loss": 0.0, "lr": 3.6479161334675296e-05, "epoch": 8.277777777777779, "percentage": 41.39, "elapsed_time": "0:02:51", "remaining_time": "0:04:02", "throughput": 1365.45, "total_tokens": 233792}
+{"current_steps": 750, "total_steps": 1800, "loss": 0.0, "lr": 3.626328291331618e-05, "epoch": 8.333333333333334, "percentage": 41.67, "elapsed_time": "0:02:52", "remaining_time": "0:04:01", "throughput": 1366.43, "total_tokens": 235328}
+{"current_steps": 755, "total_steps": 1800, "loss": 0.0, "lr": 3.60463455520502e-05, "epoch": 8.38888888888889, "percentage": 41.94, "elapsed_time": "0:02:53", "remaining_time": "0:03:59", "throughput": 1367.34, "total_tokens": 236864}
+{"current_steps": 760, "total_steps": 1800, "loss": 0.0, "lr": 3.582836964667408e-05, "epoch": 8.444444444444445, "percentage": 42.22, "elapsed_time": "0:02:54", "remaining_time": "0:03:58", "throughput": 1368.19, "total_tokens": 238368}