Training in progress, step 650

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69777f5aa25eff25d556b3b21e25927428c8db95972e0d7a65589f133ec91630
+oid sha256:ecbf7b990542d94deda7efbddabf6a00086c684dd76c82c04c38e95dfe58bb1c
 size 29034840

trainer_log.jsonl

@@ -131,3 +131,14 @@
 {"current_steps": 595, "total_steps": 6770, "loss": 0.5657, "lr": 9.960952199155347e-05, "epoch": 0.1757754800590842, "percentage": 8.79, "elapsed_time": "2:58:18", "remaining_time": "1 day, 6:50:27", "throughput": 576.84, "total_tokens": 6171120}
 {"current_steps": 600, "total_steps": 6770, "loss": 0.6331, "lr": 9.959414085888342e-05, "epoch": 0.17725258493353027, "percentage": 8.86, "elapsed_time": "2:59:45", "remaining_time": "1 day, 6:48:30", "throughput": 576.95, "total_tokens": 6222736}
 {"current_steps": 600, "total_steps": 6770, "eval_loss": 0.5883122682571411, "epoch": 0.17725258493353027, "percentage": 8.86, "elapsed_time": "3:00:04", "remaining_time": "1 day, 6:51:46", "throughput": 575.94, "total_tokens": 6222736}
+{"current_steps": 605, "total_steps": 6770, "loss": 0.5678, "lr": 9.957846384806636e-05, "epoch": 0.17872968980797638, "percentage": 8.94, "elapsed_time": "3:01:35", "remaining_time": "1 day, 6:50:24", "throughput": 575.87, "total_tokens": 6274328}
+{"current_steps": 610, "total_steps": 6770, "loss": 0.5609, "lr": 9.956249105263121e-05, "epoch": 0.18020679468242246, "percentage": 9.01, "elapsed_time": "3:03:02", "remaining_time": "1 day, 6:48:22", "throughput": 576.12, "total_tokens": 6327088}
+{"current_steps": 615, "total_steps": 6770, "loss": 0.5177, "lr": 9.95462225678715e-05, "epoch": 0.18168389955686853, "percentage": 9.08, "elapsed_time": "3:04:28", "remaining_time": "1 day, 6:46:14", "throughput": 576.3, "total_tokens": 6378824}
+{"current_steps": 620, "total_steps": 6770, "loss": 0.5839, "lr": 9.952965849084483e-05, "epoch": 0.1831610044313146, "percentage": 9.16, "elapsed_time": "3:05:55", "remaining_time": "1 day, 6:44:15", "throughput": 576.49, "total_tokens": 6431024}
+{"current_steps": 625, "total_steps": 6770, "loss": 0.5069, "lr": 9.951279892037233e-05, "epoch": 0.18463810930576072, "percentage": 9.23, "elapsed_time": "3:07:21", "remaining_time": "1 day, 6:42:09", "throughput": 576.69, "total_tokens": 6483072}
+{"current_steps": 630, "total_steps": 6770, "loss": 0.495, "lr": 9.949564395703803e-05, "epoch": 0.1861152141802068, "percentage": 9.31, "elapsed_time": "3:08:48", "remaining_time": "1 day, 6:40:08", "throughput": 576.84, "total_tokens": 6534768}
+{"current_steps": 635, "total_steps": 6770, "loss": 0.6435, "lr": 9.947819370318825e-05, "epoch": 0.18759231905465287, "percentage": 9.38, "elapsed_time": "3:10:14", "remaining_time": "1 day, 6:38:02", "throughput": 577.01, "total_tokens": 6586416}
+{"current_steps": 640, "total_steps": 6770, "loss": 0.5014, "lr": 9.946044826293106e-05, "epoch": 0.18906942392909898, "percentage": 9.45, "elapsed_time": "3:11:41", "remaining_time": "1 day, 6:35:58", "throughput": 577.21, "total_tokens": 6638592}
+{"current_steps": 645, "total_steps": 6770, "loss": 0.529, "lr": 9.944240774213556e-05, "epoch": 0.19054652880354506, "percentage": 9.53, "elapsed_time": "3:13:07", "remaining_time": "1 day, 6:33:54", "throughput": 577.35, "total_tokens": 6689920}
+{"current_steps": 650, "total_steps": 6770, "loss": 0.5483, "lr": 9.942407224843132e-05, "epoch": 0.19202363367799113, "percentage": 9.6, "elapsed_time": "3:14:33", "remaining_time": "1 day, 6:31:54", "throughput": 577.62, "total_tokens": 6743120}
+{"current_steps": 650, "total_steps": 6770, "eval_loss": 0.6100574135780334, "epoch": 0.19202363367799113, "percentage": 9.6, "elapsed_time": "3:14:52", "remaining_time": "1 day, 6:34:53", "throughput": 576.68, "total_tokens": 6743120}