Training in progress, step 169

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:024543e6a3320fa2965e7dbc1e152a1d144bdf5f42099dba3322f8a53c8a5fa5
+oid sha256:f8841ff326a77fba8d99cf67aab47c1ca0327657161986dd49e15ae8b043928f
 size 335717200

trainer_log.jsonl

@@ -43,3 +43,11 @@
 {"current_steps": 156, "total_steps": 249, "eval_loss": 0.3516700565814972, "epoch": 0.6265060240963856, "percentage": 62.65, "elapsed_time": "0:00:47", "remaining_time": "0:00:28", "throughput": 584.93, "total_tokens": 27552}
 {"current_steps": 160, "total_steps": 249, "loss": 0.3667, "lr": 1.7408081372259632e-05, "epoch": 0.642570281124498, "percentage": 64.26, "elapsed_time": "0:00:48", "remaining_time": "0:00:27", "throughput": 580.26, "total_tokens": 28272}
 {"current_steps": 165, "total_steps": 249, "loss": 0.3198, "lr": 1.5757778980982626e-05, "epoch": 0.6626506024096386, "percentage": 66.27, "elapsed_time": "0:00:49", "remaining_time": "0:00:24", "throughput": 594.93, "total_tokens": 29184}
+{"current_steps": 169, "total_steps": 249, "eval_loss": 0.354565292596817, "epoch": 0.678714859437751, "percentage": 67.87, "elapsed_time": "0:00:49", "remaining_time": "0:00:23", "throughput": 600.92, "total_tokens": 29984}
+{"current_steps": 170, "total_steps": 249, "loss": 0.3366, "lr": 1.4152906522061048e-05, "epoch": 0.6827309236947792, "percentage": 68.27, "elapsed_time": "0:00:52", "remaining_time": "0:00:24", "throughput": 568.69, "total_tokens": 30128}
+{"current_steps": 175, "total_steps": 249, "loss": 0.3291, "lr": 1.2601352710458313e-05, "epoch": 0.7028112449799196, "percentage": 70.28, "elapsed_time": "0:00:53", "remaining_time": "0:00:22", "throughput": 581.0, "total_tokens": 30976}
+{"current_steps": 180, "total_steps": 249, "loss": 0.369, "lr": 1.1110744174509952e-05, "epoch": 0.7228915662650602, "percentage": 72.29, "elapsed_time": "0:00:53", "remaining_time": "0:00:20", "throughput": 592.22, "total_tokens": 31776}
+{"current_steps": 182, "total_steps": 249, "eval_loss": 0.34907668828964233, "epoch": 0.7309236947791165, "percentage": 73.09, "elapsed_time": "0:00:54", "remaining_time": "0:00:20", "throughput": 590.05, "total_tokens": 32080}
+{"current_steps": 185, "total_steps": 249, "loss": 0.3852, "lr": 9.688407967401248e-06, "epoch": 0.7429718875502008, "percentage": 74.3, "elapsed_time": "0:00:55", "remaining_time": "0:00:19", "throughput": 583.93, "total_tokens": 32608}
+{"current_steps": 190, "total_steps": 249, "loss": 0.4115, "lr": 8.341335551199902e-06, "epoch": 0.7630522088353414, "percentage": 76.31, "elapsed_time": "0:00:56", "remaining_time": "0:00:17", "throughput": 593.85, "total_tokens": 33360}
+{"current_steps": 195, "total_steps": 249, "loss": 0.3673, "lr": 7.076148430479321e-06, "epoch": 0.7831325301204819, "percentage": 78.31, "elapsed_time": "0:00:56", "remaining_time": "0:00:15", "throughput": 604.8, "total_tokens": 34176}