Training in progress, step 900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:094f8e95f21de855ead8399600cbdaf77bfb87240f5f5aec4d851138c9de6e41
+oid sha256:db8cdf228da4eaa470f91326a484381bcf5a581427b95d357299e9bdd01813ae
 size 819328

trainer_log.jsonl

@@ -189,3 +189,13 @@
 {"current_steps": 855, "total_steps": 900, "loss": 0.0012, "lr": 3.9682871345891883e-07, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "0:02:47", "remaining_time": "0:00:08", "throughput": 1600.99, "total_tokens": 268256}
 {"current_steps": 855, "total_steps": 900, "eval_loss": 0.04785161092877388, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "0:02:48", "remaining_time": "0:00:08", "throughput": 1592.56, "total_tokens": 268256}
 {"current_steps": 860, "total_steps": 900, "loss": 0.0007, "lr": 3.1542206734221924e-07, "epoch": 9.555555555555555, "percentage": 95.56, "elapsed_time": "0:02:50", "remaining_time": "0:00:07", "throughput": 1587.11, "total_tokens": 269824}
+{"current_steps": 865, "total_steps": 900, "loss": 0.0014, "lr": 2.4329828146074095e-07, "epoch": 9.61111111111111, "percentage": 96.11, "elapsed_time": "0:02:50", "remaining_time": "0:00:06", "throughput": 1589.13, "total_tokens": 271424}
+{"current_steps": 870, "total_steps": 900, "loss": 0.0005, "lr": 1.8048447862070718e-07, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:02:51", "remaining_time": "0:00:05", "throughput": 1590.82, "total_tokens": 272960}
+{"current_steps": 875, "total_steps": 900, "loss": 0.0535, "lr": 1.2700428052447033e-07, "epoch": 9.722222222222221, "percentage": 97.22, "elapsed_time": "0:02:52", "remaining_time": "0:00:04", "throughput": 1592.63, "total_tokens": 274528}
+{"current_steps": 880, "total_steps": 900, "loss": 0.0017, "lr": 8.28777988873486e-08, "epoch": 9.777777777777779, "percentage": 97.78, "elapsed_time": "0:02:53", "remaining_time": "0:00:03", "throughput": 1594.61, "total_tokens": 276128}
+{"current_steps": 885, "total_steps": 900, "loss": 0.0181, "lr": 4.8121627874450625e-08, "epoch": 9.833333333333334, "percentage": 98.33, "elapsed_time": "0:02:53", "remaining_time": "0:00:02", "throughput": 1596.22, "total_tokens": 277664}
+{"current_steps": 890, "total_steps": 900, "loss": 0.0149, "lr": 2.2748837860270267e-08, "epoch": 9.88888888888889, "percentage": 98.89, "elapsed_time": "0:02:54", "remaining_time": "0:00:01", "throughput": 1597.99, "total_tokens": 279232}
+{"current_steps": 895, "total_steps": 900, "loss": 0.2401, "lr": 6.768970513457151e-09, "epoch": 9.944444444444445, "percentage": 99.44, "elapsed_time": "0:02:55", "remaining_time": "0:00:00", "throughput": 1599.59, "total_tokens": 280768}
+{"current_steps": 900, "total_steps": 900, "loss": 0.0003, "lr": 1.8803520859811406e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:56", "remaining_time": "0:00:00", "throughput": 1600.83, "total_tokens": 282368}
+{"current_steps": 900, "total_steps": 900, "eval_loss": 0.045247167348861694, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:57", "remaining_time": "0:00:00", "throughput": 1592.84, "total_tokens": 282368}
+{"current_steps": 900, "total_steps": 900, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:58", "remaining_time": "0:00:00", "throughput": 1585.22, "total_tokens": 282368}