Training in progress, step 91

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcf3e605bc7d333ae21f920a05a4b729b77b1c1c0e22bf5fb7dbf1fb85439a51
+oid sha256:0cb2096de7884069d354cc1cddde97bf3910a9a5f82ac71ce0d6c3e1f9f8dfda
 size 335717200

trainer_log.jsonl

@@ -22,3 +22,10 @@
 {"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}
+{"current_steps": 91, "total_steps": 249, "eval_loss": 0.36092114448547363, "epoch": 0.3654618473895582, "percentage": 36.55, "elapsed_time": "0:00:27", "remaining_time": "0:00:47", "throughput": 585.62, "total_tokens": 16048}
+{"current_steps": 95, "total_steps": 249, "loss": 0.3395, "lr": 3.9179413635373897e-05, "epoch": 0.3815261044176707, "percentage": 38.15, "elapsed_time": "0:00:30", "remaining_time": "0:00:50", "throughput": 539.73, "total_tokens": 16688}
+{"current_steps": 100, "total_steps": 249, "loss": 0.2898, "lr": 3.770188363116324e-05, "epoch": 0.40160642570281124, "percentage": 40.16, "elapsed_time": "0:00:31", "remaining_time": "0:00:46", "throughput": 561.52, "total_tokens": 17552}
+{"current_steps": 104, "total_steps": 249, "eval_loss": 0.37226182222366333, "epoch": 0.41767068273092367, "percentage": 41.77, "elapsed_time": "0:00:32", "remaining_time": "0:00:44", "throughput": 568.78, "total_tokens": 18272}
+{"current_steps": 105, "total_steps": 249, "loss": 0.3169, "lr": 3.616191779978907e-05, "epoch": 0.42168674698795183, "percentage": 42.17, "elapsed_time": "0:00:33", "remaining_time": "0:00:45", "throughput": 549.13, "total_tokens": 18400}
+{"current_steps": 110, "total_steps": 249, "loss": 0.3631, "lr": 3.456708580912725e-05, "epoch": 0.44176706827309237, "percentage": 44.18, "elapsed_time": "0:00:33", "remaining_time": "0:00:42", "throughput": 574.97, "total_tokens": 19456}
+{"current_steps": 115, "total_steps": 249, "loss": 0.4246, "lr": 3.292522702044221e-05, "epoch": 0.46184738955823296, "percentage": 46.18, "elapsed_time": "0:00:34", "remaining_time": "0:00:39", "throughput": 593.75, "total_tokens": 20288}