Training in progress, step 1140

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cd62d60a08641467e05df30cdf17251d3252dc90a408e61ba8b43783b2cb77f
+oid sha256:1739c463b12234ce9dfa73bd7f494606e0aa6303980c38ecb34a51b6955c3b84
 size 541712

trainer_log.jsonl

@@ -235,3 +235,15 @@
 {"current_steps": 1083, "total_steps": 1140, "eval_loss": 0.9556061029434204, "epoch": 19.0, "percentage": 95.0, "elapsed_time": "0:04:14", "remaining_time": "0:00:13", "throughput": 2764.43, "total_tokens": 704816}
 {"current_steps": 1085, "total_steps": 1140, "loss": 0.983, "lr": 3.666289253608235e-07, "epoch": 19.035087719298247, "percentage": 95.18, "elapsed_time": "0:04:16", "remaining_time": "0:00:12", "throughput": 2756.32, "total_tokens": 706192}
 {"current_steps": 1090, "total_steps": 1140, "loss": 0.9368, "lr": 3.0420940809451624e-07, "epoch": 19.12280701754386, "percentage": 95.61, "elapsed_time": "0:04:17", "remaining_time": "0:00:11", "throughput": 2757.36, "total_tokens": 709072}
+{"current_steps": 1095, "total_steps": 1140, "loss": 0.8551, "lr": 2.47578303470844e-07, "epoch": 19.210526315789473, "percentage": 96.05, "elapsed_time": "0:04:18", "remaining_time": "0:00:10", "throughput": 2759.08, "total_tokens": 712496}
+{"current_steps": 1100, "total_steps": 1140, "loss": 1.1214, "lr": 1.96748885177106e-07, "epoch": 19.29824561403509, "percentage": 96.49, "elapsed_time": "0:04:19", "remaining_time": "0:00:09", "throughput": 2759.72, "total_tokens": 715056}
+{"current_steps": 1105, "total_steps": 1140, "loss": 0.9253, "lr": 1.517330670512629e-07, "epoch": 19.385964912280702, "percentage": 96.93, "elapsed_time": "0:04:20", "remaining_time": "0:00:08", "throughput": 2761.15, "total_tokens": 718416}
+{"current_steps": 1110, "total_steps": 1140, "loss": 0.9045, "lr": 1.125414002894759e-07, "epoch": 19.473684210526315, "percentage": 97.37, "elapsed_time": "0:04:21", "remaining_time": "0:00:07", "throughput": 2763.13, "total_tokens": 721744}
+{"current_steps": 1115, "total_steps": 1140, "loss": 0.992, "lr": 7.918307097301014e-08, "epoch": 19.56140350877193, "percentage": 97.81, "elapsed_time": "0:04:22", "remaining_time": "0:00:05", "throughput": 2764.95, "total_tokens": 725328}
+{"current_steps": 1120, "total_steps": 1140, "loss": 1.0666, "lr": 5.166589791513465e-08, "epoch": 19.649122807017545, "percentage": 98.25, "elapsed_time": "0:04:23", "remaining_time": "0:00:04", "throughput": 2766.75, "total_tokens": 728976}
+{"current_steps": 1125, "total_steps": 1140, "loss": 1.0409, "lr": 2.999633082847453e-08, "epoch": 19.736842105263158, "percentage": 98.68, "elapsed_time": "0:04:24", "remaining_time": "0:00:03", "throughput": 2768.56, "total_tokens": 732368}
+{"current_steps": 1130, "total_steps": 1140, "loss": 0.9188, "lr": 1.4179448813278484e-08, "epoch": 19.82456140350877, "percentage": 99.12, "elapsed_time": "0:04:25", "remaining_time": "0:00:02", "throughput": 2769.66, "total_tokens": 735440}
+{"current_steps": 1135, "total_steps": 1140, "loss": 1.0218, "lr": 4.218959166932268e-09, "epoch": 19.912280701754387, "percentage": 99.56, "elapsed_time": "0:04:26", "remaining_time": "0:00:01", "throughput": 2771.39, "total_tokens": 739120}
+{"current_steps": 1140, "total_steps": 1140, "loss": 0.7929, "lr": 1.1719651499819683e-10, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:04:27", "remaining_time": "0:00:00", "throughput": 2771.76, "total_tokens": 742296}
+{"current_steps": 1140, "total_steps": 1140, "eval_loss": 0.9411159157752991, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:04:28", "remaining_time": "0:00:00", "throughput": 2766.21, "total_tokens": 742296}
+{"current_steps": 1140, "total_steps": 1140, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:04:29", "remaining_time": "0:00:00", "throughput": 2758.61, "total_tokens": 742296}