Training in progress, step 570

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5e739b9c499dbf7e3e1289db5a5cb30d28691450615719f4fde88153d50c446
+oid sha256:4acb01157e27b4852e4e68be003b38e0b21b69d35c45e5a53db42b1e50e66091
 size 1638528

trainer_log.jsonl

@@ -128,3 +128,7 @@
 {"current_steps": 550, "total_steps": 570, "loss": 0.072, "lr": 2.064500424599436e-07, "epoch": 9.649122807017545, "percentage": 96.49, "elapsed_time": "0:02:53", "remaining_time": "0:00:06", "throughput": 2049.15, "total_tokens": 355432}
 {"current_steps": 551, "total_steps": 570, "eval_loss": 0.2247486412525177, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:02:54", "remaining_time": "0:00:06", "throughput": 2041.41, "total_tokens": 356456}
 {"current_steps": 555, "total_steps": 570, "loss": 0.0824, "lr": 1.1991334092484318e-07, "epoch": 9.736842105263158, "percentage": 97.37, "elapsed_time": "0:02:56", "remaining_time": "0:00:04", "throughput": 2027.87, "total_tokens": 358760}
+{"current_steps": 560, "total_steps": 570, "loss": 0.141, "lr": 5.6701710711626334e-08, "epoch": 9.824561403508772, "percentage": 98.25, "elapsed_time": "0:02:58", "remaining_time": "0:00:03", "throughput": 2032.82, "total_tokens": 362088}
+{"current_steps": 565, "total_steps": 570, "loss": 0.0604, "lr": 1.6874412698408836e-08, "epoch": 9.912280701754385, "percentage": 99.12, "elapsed_time": "0:02:59", "remaining_time": "0:00:01", "throughput": 2038.23, "total_tokens": 365544}
+{"current_steps": 570, "total_steps": 570, "loss": 0.3128, "lr": 4.687849611939576e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:03:00", "remaining_time": "0:00:00", "throughput": 2038.95, "total_tokens": 367864}
+{"current_steps": 570, "total_steps": 570, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:03:01", "remaining_time": "0:00:00", "throughput": 2022.82, "total_tokens": 367864}