Training in progress, step 900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:259bd141846908f3276873ee38879bd4e1a51aed36a5298ea93b74989e834a19
+oid sha256:877724dae737e663fbb5d560f65510f56c511469d419085e4b452c60a1656a2d
 size 26214528

trainer_log.jsonl

@@ -189,3 +189,13 @@
 {"current_steps": 855, "total_steps": 900, "loss": 0.2546, "lr": 3.9682871345891883e-07, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "0:03:03", "remaining_time": "0:00:09", "throughput": 1457.9, "total_tokens": 267840}
 {"current_steps": 855, "total_steps": 900, "eval_loss": 0.27361875772476196, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "0:03:04", "remaining_time": "0:00:09", "throughput": 1451.37, "total_tokens": 267840}
 {"current_steps": 860, "total_steps": 900, "loss": 0.2583, "lr": 3.1542206734221924e-07, "epoch": 9.555555555555555, "percentage": 95.56, "elapsed_time": "0:03:06", "remaining_time": "0:00:08", "throughput": 1442.01, "total_tokens": 269376}
+{"current_steps": 865, "total_steps": 900, "loss": 0.2518, "lr": 2.4329828146074095e-07, "epoch": 9.61111111111111, "percentage": 96.11, "elapsed_time": "0:03:07", "remaining_time": "0:00:07", "throughput": 1443.65, "total_tokens": 270944}
+{"current_steps": 870, "total_steps": 900, "loss": 0.2647, "lr": 1.8048447862070718e-07, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:03:08", "remaining_time": "0:00:06", "throughput": 1445.34, "total_tokens": 272448}
+{"current_steps": 875, "total_steps": 900, "loss": 0.2578, "lr": 1.2700428052447033e-07, "epoch": 9.722222222222221, "percentage": 97.22, "elapsed_time": "0:03:09", "remaining_time": "0:00:05", "throughput": 1447.13, "total_tokens": 273984}
+{"current_steps": 880, "total_steps": 900, "loss": 0.2975, "lr": 8.28777988873486e-08, "epoch": 9.777777777777779, "percentage": 97.78, "elapsed_time": "0:03:10", "remaining_time": "0:00:04", "throughput": 1448.92, "total_tokens": 275520}
+{"current_steps": 885, "total_steps": 900, "loss": 0.2991, "lr": 4.8121627874450625e-08, "epoch": 9.833333333333334, "percentage": 98.33, "elapsed_time": "0:03:10", "remaining_time": "0:00:03", "throughput": 1451.12, "total_tokens": 277152}
+{"current_steps": 890, "total_steps": 900, "loss": 0.2624, "lr": 2.2748837860270267e-08, "epoch": 9.88888888888889, "percentage": 98.89, "elapsed_time": "0:03:11", "remaining_time": "0:00:02", "throughput": 1452.96, "total_tokens": 278688}
+{"current_steps": 895, "total_steps": 900, "loss": 0.2444, "lr": 6.768970513457151e-09, "epoch": 9.944444444444445, "percentage": 99.44, "elapsed_time": "0:03:12", "remaining_time": "0:00:01", "throughput": 1454.92, "total_tokens": 280256}
+{"current_steps": 900, "total_steps": 900, "loss": 0.2711, "lr": 1.8803520859811406e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:03:13", "remaining_time": "0:00:00", "throughput": 1456.39, "total_tokens": 281856}
+{"current_steps": 900, "total_steps": 900, "eval_loss": 0.26932746171951294, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:03:14", "remaining_time": "0:00:00", "throughput": 1450.14, "total_tokens": 281856}
+{"current_steps": 900, "total_steps": 900, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:03:15", "remaining_time": "0:00:00", "throughput": 1440.52, "total_tokens": 281856}