Training in progress, step 900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d91d551790a48037a1eaa6ea5c4fba821ef4a27ccf0d500eacddc0a22b236a4
+oid sha256:9ffb7f56a20372b0dac18e1372bceb77f577498d45f1fd9f38dc6f44473bc6b9
 size 1638528

trainer_log.jsonl

@@ -189,3 +189,13 @@
 {"current_steps": 855, "total_steps": 900, "loss": 0.0001, "lr": 3.9682871345891883e-07, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "0:03:13", "remaining_time": "0:00:10", "throughput": 1385.54, "total_tokens": 267840}
 {"current_steps": 855, "total_steps": 900, "eval_loss": 0.24860987067222595, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "0:03:14", "remaining_time": "0:00:10", "throughput": 1379.05, "total_tokens": 267840}
 {"current_steps": 860, "total_steps": 900, "loss": 0.0001, "lr": 3.1542206734221924e-07, "epoch": 9.555555555555555, "percentage": 95.56, "elapsed_time": "0:03:16", "remaining_time": "0:00:09", "throughput": 1371.02, "total_tokens": 269376}
+{"current_steps": 865, "total_steps": 900, "loss": 0.0005, "lr": 2.4329828146074095e-07, "epoch": 9.61111111111111, "percentage": 96.11, "elapsed_time": "0:03:17", "remaining_time": "0:00:07", "throughput": 1373.04, "total_tokens": 270944}
+{"current_steps": 870, "total_steps": 900, "loss": 0.0001, "lr": 1.8048447862070718e-07, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:03:18", "remaining_time": "0:00:06", "throughput": 1374.79, "total_tokens": 272448}
+{"current_steps": 875, "total_steps": 900, "loss": 0.0001, "lr": 1.2700428052447033e-07, "epoch": 9.722222222222221, "percentage": 97.22, "elapsed_time": "0:03:19", "remaining_time": "0:00:05", "throughput": 1376.63, "total_tokens": 273984}
+{"current_steps": 880, "total_steps": 900, "loss": 0.0001, "lr": 8.28777988873486e-08, "epoch": 9.777777777777779, "percentage": 97.78, "elapsed_time": "0:03:19", "remaining_time": "0:00:04", "throughput": 1378.47, "total_tokens": 275520}
+{"current_steps": 885, "total_steps": 900, "loss": 0.0001, "lr": 4.8121627874450625e-08, "epoch": 9.833333333333334, "percentage": 98.33, "elapsed_time": "0:03:20", "remaining_time": "0:00:03", "throughput": 1380.67, "total_tokens": 277152}
+{"current_steps": 890, "total_steps": 900, "loss": 0.0001, "lr": 2.2748837860270267e-08, "epoch": 9.88888888888889, "percentage": 98.89, "elapsed_time": "0:03:21", "remaining_time": "0:00:02", "throughput": 1382.5, "total_tokens": 278688}
+{"current_steps": 895, "total_steps": 900, "loss": 0.0001, "lr": 6.768970513457151e-09, "epoch": 9.944444444444445, "percentage": 99.44, "elapsed_time": "0:03:22", "remaining_time": "0:00:01", "throughput": 1384.45, "total_tokens": 280256}
+{"current_steps": 900, "total_steps": 900, "loss": 0.0001, "lr": 1.8803520859811406e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:03:23", "remaining_time": "0:00:00", "throughput": 1386.08, "total_tokens": 281856}
+{"current_steps": 900, "total_steps": 900, "eval_loss": 0.24965079128742218, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:03:24", "remaining_time": "0:00:00", "throughput": 1379.92, "total_tokens": 281856}
+{"current_steps": 900, "total_steps": 900, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:03:25", "remaining_time": "0:00:00", "throughput": 1370.03, "total_tokens": 281856}