Training in progress, step 49

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca6cdcb092133bd2a1bcc28eb7a243a07d1d99b253ad46a0ca6f4bf40cc937d6
+oid sha256:ca2595eb71261e63df9d3ab90bcbb69e81929e5c93b160c872f8c1da5d377666
 size 2818586248

trainer_log.jsonl

@@ -14,3 +14,9 @@
 {"current_steps": 42, "total_steps": 125, "eval_loss": 0.41257768869400024, "epoch": 0.336, "percentage": 33.6, "elapsed_time": "0:02:26", "remaining_time": "0:04:48", "throughput": 114.07, "total_tokens": 16672}
 {"current_steps": 45, "total_steps": 125, "loss": 0.4533, "lr": 4.1129299588552193e-05, "epoch": 0.36, "percentage": 36.0, "elapsed_time": "0:02:51", "remaining_time": "0:05:04", "throughput": 104.78, "total_tokens": 17920}
 {"current_steps": 49, "total_steps": 125, "eval_loss": 1.1762187480926514, "epoch": 0.392, "percentage": 39.2, "elapsed_time": "0:02:52", "remaining_time": "0:04:27", "throughput": 111.92, "total_tokens": 19296}
+{"current_steps": 50, "total_steps": 125, "loss": 0.1866, "lr": 3.830080191288342e-05, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:03:21", "remaining_time": "0:05:01", "throughput": 98.04, "total_tokens": 19712}
+{"current_steps": 55, "total_steps": 125, "loss": 1.3512, "lr": 3.521110642339991e-05, "epoch": 0.44, "percentage": 44.0, "elapsed_time": "0:03:22", "remaining_time": "0:04:17", "throughput": 108.65, "total_tokens": 21952}
+{"current_steps": 56, "total_steps": 125, "eval_loss": 0.806473433971405, "epoch": 0.448, "percentage": 44.8, "elapsed_time": "0:03:22", "remaining_time": "0:04:09", "throughput": 110.56, "total_tokens": 22432}
+{"current_steps": 60, "total_steps": 125, "loss": 0.7948, "lr": 3.1920887785621235e-05, "epoch": 0.48, "percentage": 48.0, "elapsed_time": "0:03:41", "remaining_time": "0:03:59", "throughput": 109.23, "total_tokens": 24160}
+{"current_steps": 63, "total_steps": 125, "eval_loss": 1.0268325805664062, "epoch": 0.504, "percentage": 50.4, "elapsed_time": "0:03:42", "remaining_time": "0:03:38", "throughput": 114.67, "total_tokens": 25504}
+{"current_steps": 65, "total_steps": 125, "loss": 0.6941, "lr": 2.849475848838749e-05, "epoch": 0.52, "percentage": 52.0, "elapsed_time": "0:04:04", "remaining_time": "0:03:45", "throughput": 106.72, "total_tokens": 26112}