Training in progress, step 65

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16afb188e887538ca3cdcdd45ce22fc17234562dc5f31e5a76ee9273276ea8fa
+oid sha256:fcf3e605bc7d333ae21f920a05a4b729b77b1c1c0e22bf5fb7dbf1fb85439a51
 size 335717200

trainer_log.jsonl

@@ -12,3 +12,13 @@
 {"current_steps": 45, "total_steps": 249, "loss": 0.3929, "lr": 4.91176324775594e-05, "epoch": 0.18072289156626506, "percentage": 18.07, "elapsed_time": "0:00:15", "remaining_time": "0:01:11", "throughput": 498.33, "total_tokens": 7856}
 {"current_steps": 50, "total_steps": 249, "loss": 0.3565, "lr": 4.8597083257709194e-05, "epoch": 0.20080321285140562, "percentage": 20.08, "elapsed_time": "0:00:16", "remaining_time": "0:01:04", "throughput": 551.64, "total_tokens": 8880}
 {"current_steps": 52, "total_steps": 249, "eval_loss": 0.3768366277217865, "epoch": 0.20883534136546184, "percentage": 20.88, "elapsed_time": "0:00:16", "remaining_time": "0:01:03", "throughput": 548.86, "total_tokens": 9232}
+{"current_steps": 55, "total_steps": 249, "loss": 0.4015, "lr": 4.796054309867053e-05, "epoch": 0.22088353413654618, "percentage": 22.09, "elapsed_time": "0:00:18", "remaining_time": "0:01:04", "throughput": 526.83, "total_tokens": 9680}
+{"current_steps": 60, "total_steps": 249, "loss": 0.3437, "lr": 4.721114089947181e-05, "epoch": 0.24096385542168675, "percentage": 24.1, "elapsed_time": "0:00:18", "remaining_time": "0:00:58", "throughput": 565.33, "total_tokens": 10576}
+{"current_steps": 65, "total_steps": 249, "loss": 0.3087, "lr": 4.6352560329995686e-05, "epoch": 0.26104417670682734, "percentage": 26.1, "elapsed_time": "0:00:19", "remaining_time": "0:00:53", "throughput": 599.97, "total_tokens": 11424}
+{"current_steps": 65, "total_steps": 249, "eval_loss": 0.3713006377220154, "epoch": 0.26104417670682734, "percentage": 26.1, "elapsed_time": "0:00:19", "remaining_time": "0:00:55", "throughput": 582.24, "total_tokens": 11424}
+{"current_steps": 70, "total_steps": 249, "loss": 0.3702, "lr": 4.538902172398151e-05, "epoch": 0.28112449799196787, "percentage": 28.11, "elapsed_time": "0:00:23", "remaining_time": "0:00:59", "throughput": 523.92, "total_tokens": 12224}
+{"current_steps": 75, "total_steps": 249, "loss": 0.3607, "lr": 4.4325261334068426e-05, "epoch": 0.30120481927710846, "percentage": 30.12, "elapsed_time": "0:00:23", "remaining_time": "0:00:54", "throughput": 556.31, "total_tokens": 13168}
+{"current_steps": 78, "total_steps": 249, "eval_loss": 0.3614208996295929, "epoch": 0.3132530120481928, "percentage": 31.33, "elapsed_time": "0:00:24", "remaining_time": "0:00:53", "throughput": 562.07, "total_tokens": 13760}
+{"current_steps": 80, "total_steps": 249, "loss": 0.3766, "lr": 4.316650805085068e-05, "epoch": 0.321285140562249, "percentage": 32.13, "elapsed_time": "0:00:26", "remaining_time": "0:00:55", "throughput": 539.63, "total_tokens": 14080}
+{"current_steps": 85, "total_steps": 249, "loss": 0.3639, "lr": 4.1918457700381855e-05, "epoch": 0.3413654618473896, "percentage": 34.14, "elapsed_time": "0:00:26", "remaining_time": "0:00:50", "throughput": 569.82, "total_tokens": 15056}
+{"current_steps": 90, "total_steps": 249, "loss": 0.3589, "lr": 4.058724504646834e-05, "epoch": 0.3614457831325301, "percentage": 36.14, "elapsed_time": "0:00:26", "remaining_time": "0:00:47", "throughput": 594.48, "total_tokens": 15904}