Training in progress, step 1140

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf1d65144a3cac27494bf9e443af33cc4cb536c6a23a1c74706674469ae35c5e
+oid sha256:ff5590a69c8f0e6e9bb0f4198fb14da3d76efb386c29cea83a33ca6de77125f1
 size 58745928

trainer_log.jsonl

@@ -238,3 +238,12 @@
 {"current_steps": 1095, "total_steps": 1140, "loss": 0.0, "lr": 2.47578303470844e-07, "epoch": 19.210526315789473, "percentage": 96.05, "elapsed_time": "0:05:18", "remaining_time": "0:00:13", "throughput": 2175.83, "total_tokens": 692784}
 {"current_steps": 1100, "total_steps": 1140, "loss": 0.0, "lr": 1.96748885177106e-07, "epoch": 19.29824561403509, "percentage": 96.49, "elapsed_time": "0:05:19", "remaining_time": "0:00:11", "throughput": 2177.6, "total_tokens": 696176}
 {"current_steps": 1105, "total_steps": 1140, "loss": 0.0, "lr": 1.517330670512629e-07, "epoch": 19.385964912280702, "percentage": 96.93, "elapsed_time": "0:05:20", "remaining_time": "0:00:10", "throughput": 2178.95, "total_tokens": 699184}
+{"current_steps": 1110, "total_steps": 1140, "loss": 0.0, "lr": 1.125414002894759e-07, "epoch": 19.473684210526315, "percentage": 97.37, "elapsed_time": "0:05:22", "remaining_time": "0:00:08", "throughput": 2180.46, "total_tokens": 702448}
+{"current_steps": 1115, "total_steps": 1140, "loss": 0.0, "lr": 7.918307097301014e-08, "epoch": 19.56140350877193, "percentage": 97.81, "elapsed_time": "0:05:23", "remaining_time": "0:00:07", "throughput": 2181.37, "total_tokens": 705232}
+{"current_steps": 1120, "total_steps": 1140, "loss": 0.0, "lr": 5.166589791513465e-08, "epoch": 19.649122807017545, "percentage": 98.25, "elapsed_time": "0:05:24", "remaining_time": "0:00:05", "throughput": 2183.35, "total_tokens": 708624}
+{"current_steps": 1125, "total_steps": 1140, "loss": 0.0, "lr": 2.999633082847453e-08, "epoch": 19.736842105263158, "percentage": 98.68, "elapsed_time": "0:05:25", "remaining_time": "0:00:04", "throughput": 2184.37, "total_tokens": 711568}
+{"current_steps": 1130, "total_steps": 1140, "loss": 0.0, "lr": 1.4179448813278484e-08, "epoch": 19.82456140350877, "percentage": 99.12, "elapsed_time": "0:05:27", "remaining_time": "0:00:02", "throughput": 2186.08, "total_tokens": 715216}
+{"current_steps": 1135, "total_steps": 1140, "loss": 0.0, "lr": 4.218959166932268e-09, "epoch": 19.912280701754387, "percentage": 99.56, "elapsed_time": "0:05:28", "remaining_time": "0:00:01", "throughput": 2187.4, "total_tokens": 718288}
+{"current_steps": 1140, "total_steps": 1140, "loss": 0.0, "lr": 1.1719651499819683e-10, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:05:29", "remaining_time": "0:00:00", "throughput": 2188.28, "total_tokens": 721856}
+{"current_steps": 1140, "total_steps": 1140, "eval_loss": 0.31993791460990906, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:05:30", "remaining_time": "0:00:00", "throughput": 2183.87, "total_tokens": 721856}
+{"current_steps": 1140, "total_steps": 1140, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:05:31", "remaining_time": "0:00:00", "throughput": 2176.22, "total_tokens": 721856}