Training in progress, step 1800

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f5524c21ac56e84ccecb502446bff34953758b37c78418ab304558e0c9b9e9d
+oid sha256:8cace4c2e251729651557bb7344dfb818b42606007c842e9ccfc0f1931be1cac
 size 58745928

trainer_log.jsonl

@@ -370,3 +370,12 @@
 {"current_steps": 1755, "total_steps": 1800, "loss": 0.0, "lr": 9.940480466855417e-08, "epoch": 19.5, "percentage": 97.5, "elapsed_time": "0:06:42", "remaining_time": "0:00:10", "throughput": 1365.05, "total_tokens": 550016}
 {"current_steps": 1760, "total_steps": 1800, "loss": 0.0, "lr": 7.898027451078982e-08, "epoch": 19.555555555555557, "percentage": 97.78, "elapsed_time": "0:06:43", "remaining_time": "0:00:09", "throughput": 1365.6, "total_tokens": 551584}
 {"current_steps": 1765, "total_steps": 1800, "loss": 0.0, "lr": 6.089874350439506e-08, "epoch": 19.61111111111111, "percentage": 98.06, "elapsed_time": "0:06:44", "remaining_time": "0:00:08", "throughput": 1366.12, "total_tokens": 553152}
+{"current_steps": 1770, "total_steps": 1800, "loss": 0.0, "lr": 4.516191162040051e-08, "epoch": 19.666666666666668, "percentage": 98.33, "elapsed_time": "0:06:45", "remaining_time": "0:00:06", "throughput": 1366.71, "total_tokens": 554752}
+{"current_steps": 1775, "total_steps": 1800, "loss": 0.0, "lr": 3.177125838830786e-08, "epoch": 19.72222222222222, "percentage": 98.61, "elapsed_time": "0:06:46", "remaining_time": "0:00:05", "throughput": 1367.18, "total_tokens": 556288}
+{"current_steps": 1780, "total_steps": 1800, "loss": 0.0, "lr": 2.0728042756967824e-08, "epoch": 19.77777777777778, "percentage": 98.89, "elapsed_time": "0:06:47", "remaining_time": "0:00:04", "throughput": 1367.8, "total_tokens": 557888}
+{"current_steps": 1785, "total_steps": 1800, "loss": 0.0, "lr": 1.2033302976222071e-08, "epoch": 19.833333333333332, "percentage": 99.17, "elapsed_time": "0:06:48", "remaining_time": "0:00:03", "throughput": 1368.26, "total_tokens": 559424}
+{"current_steps": 1790, "total_steps": 1800, "loss": 0.0, "lr": 5.687856499297928e-09, "epoch": 19.88888888888889, "percentage": 99.44, "elapsed_time": "0:06:49", "remaining_time": "0:00:02", "throughput": 1368.71, "total_tokens": 560960}
+{"current_steps": 1795, "total_steps": 1800, "loss": 0.0, "lr": 1.692299905944883e-09, "epoch": 19.944444444444443, "percentage": 99.72, "elapsed_time": "0:06:50", "remaining_time": "0:00:01", "throughput": 1369.4, "total_tokens": 562592}
+{"current_steps": 1800, "total_steps": 1800, "loss": 0.0, "lr": 4.700884634611935e-11, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:06:51", "remaining_time": "0:00:00", "throughput": 1369.65, "total_tokens": 564096}
+{"current_steps": 1800, "total_steps": 1800, "eval_loss": 0.10150279104709625, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:06:52", "remaining_time": "0:00:00", "throughput": 1367.66, "total_tokens": 564096}
+{"current_steps": 1800, "total_steps": 1800, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:06:53", "remaining_time": "0:00:00", "throughput": 1363.39, "total_tokens": 564096}