Training in progress, step 182

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2d5b595f47cacb4719f8b6331630e3ef29556ccac245bc2b9e9f5c17d12aac
+oid sha256:8b88be18cb72b9882ca5f661464f62b04dc167734f9f990c1a045cc611c21e55
 size 335717200

trainer_log.jsonl

@@ -45,3 +45,10 @@
 {"current_steps": 165, "total_steps": 249, "loss": 0.3281, "lr": 1.5757778980982626e-05, "epoch": 0.6626506024096386, "percentage": 66.27, "elapsed_time": "0:00:38", "remaining_time": "0:00:19", "throughput": 766.77, "total_tokens": 29184}
 {"current_steps": 169, "total_steps": 249, "eval_loss": 0.35279974341392517, "epoch": 0.678714859437751, "percentage": 67.87, "elapsed_time": "0:00:39", "remaining_time": "0:00:18", "throughput": 766.99, "total_tokens": 29984}
 {"current_steps": 170, "total_steps": 249, "loss": 0.333, "lr": 1.4152906522061048e-05, "epoch": 0.6827309236947792, "percentage": 68.27, "elapsed_time": "0:00:40", "remaining_time": "0:00:18", "throughput": 746.8, "total_tokens": 30128}
+{"current_steps": 175, "total_steps": 249, "loss": 0.3335, "lr": 1.2601352710458313e-05, "epoch": 0.7028112449799196, "percentage": 70.28, "elapsed_time": "0:00:40", "remaining_time": "0:00:17", "throughput": 760.02, "total_tokens": 30976}
+{"current_steps": 180, "total_steps": 249, "loss": 0.3654, "lr": 1.1110744174509952e-05, "epoch": 0.7228915662650602, "percentage": 72.29, "elapsed_time": "0:00:41", "remaining_time": "0:00:15", "throughput": 773.33, "total_tokens": 31776}
+{"current_steps": 182, "total_steps": 249, "eval_loss": 0.3537220358848572, "epoch": 0.7309236947791165, "percentage": 73.09, "elapsed_time": "0:00:41", "remaining_time": "0:00:15", "throughput": 765.23, "total_tokens": 32080}
+{"current_steps": 185, "total_steps": 249, "loss": 0.3846, "lr": 9.688407967401248e-06, "epoch": 0.7429718875502008, "percentage": 74.3, "elapsed_time": "0:00:43", "remaining_time": "0:00:15", "throughput": 744.94, "total_tokens": 32608}
+{"current_steps": 190, "total_steps": 249, "loss": 0.4085, "lr": 8.341335551199902e-06, "epoch": 0.7630522088353414, "percentage": 76.31, "elapsed_time": "0:00:44", "remaining_time": "0:00:13", "throughput": 756.08, "total_tokens": 33360}
+{"current_steps": 195, "total_steps": 249, "loss": 0.3745, "lr": 7.076148430479321e-06, "epoch": 0.7831325301204819, "percentage": 78.31, "elapsed_time": "0:00:44", "remaining_time": "0:00:12", "throughput": 768.47, "total_tokens": 34176}
+{"current_steps": 195, "total_steps": 249, "eval_loss": 0.3510403037071228, "epoch": 0.7831325301204819, "percentage": 78.31, "elapsed_time": "0:00:45", "remaining_time": "0:00:12", "throughput": 756.02, "total_tokens": 34176}