Training in progress, step 550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55382d84797424bf555d465074d1d58ecfa91cc23250d3509fdb9cd78d1cbeff
+oid sha256:82e427cc7e624394004d64620be182b50bd10e2a67a34cf622de25a3f138b7e0
 size 29034840

trainer_log.jsonl

@@ -108,3 +108,14 @@
 {"current_steps": 495, "total_steps": 3882, "loss": 0.8818, "lr": 9.837531236929726e-05, "epoch": 0.254957507082153, "percentage": 12.75, "elapsed_time": "2:33:31", "remaining_time": "17:30:30", "throughput": 628.5, "total_tokens": 5789544}
 {"current_steps": 500, "total_steps": 3882, "loss": 0.8576, "lr": 9.832101246944439e-05, "epoch": 0.25753283543651817, "percentage": 12.88, "elapsed_time": "2:35:02", "remaining_time": "17:28:38", "throughput": 628.68, "total_tokens": 5848048}
 {"current_steps": 500, "total_steps": 3882, "eval_loss": 0.8268976211547852, "epoch": 0.25753283543651817, "percentage": 12.88, "elapsed_time": "2:35:21", "remaining_time": "17:30:51", "throughput": 627.36, "total_tokens": 5848048}
+{"current_steps": 505, "total_steps": 3882, "loss": 0.8566, "lr": 9.826583551051483e-05, "epoch": 0.26010816379088336, "percentage": 13.01, "elapsed_time": "2:36:58", "remaining_time": "17:29:43", "throughput": 627.12, "total_tokens": 5906512}
+{"current_steps": 510, "total_steps": 3882, "loss": 0.8365, "lr": 9.820978249400773e-05, "epoch": 0.2626834921452485, "percentage": 13.14, "elapsed_time": "2:38:27", "remaining_time": "17:27:38", "throughput": 627.43, "total_tokens": 5965024}
+{"current_steps": 515, "total_steps": 3882, "loss": 0.8882, "lr": 9.81528544373233e-05, "epoch": 0.2652588204996137, "percentage": 13.27, "elapsed_time": "2:39:56", "remaining_time": "17:25:40", "throughput": 627.67, "total_tokens": 6023496}
+{"current_steps": 520, "total_steps": 3882, "loss": 0.8799, "lr": 9.809505237374426e-05, "epoch": 0.2678341488539789, "percentage": 13.4, "elapsed_time": "2:41:25", "remaining_time": "17:23:40", "throughput": 627.94, "total_tokens": 6082000}
+{"current_steps": 525, "total_steps": 3882, "loss": 0.8758, "lr": 9.80363773524172e-05, "epoch": 0.2704094772083441, "percentage": 13.52, "elapsed_time": "2:42:59", "remaining_time": "17:22:15", "throughput": 627.87, "total_tokens": 6140480}
+{"current_steps": 530, "total_steps": 3882, "loss": 0.8644, "lr": 9.797683043833345e-05, "epoch": 0.27298480556270927, "percentage": 13.65, "elapsed_time": "2:44:32", "remaining_time": "17:20:39", "throughput": 627.89, "total_tokens": 6198968}
+{"current_steps": 535, "total_steps": 3882, "loss": 0.8453, "lr": 9.791641271230982e-05, "epoch": 0.2755601339170744, "percentage": 13.78, "elapsed_time": "2:46:06", "remaining_time": "17:19:13", "throughput": 627.82, "total_tokens": 6257464}
+{"current_steps": 540, "total_steps": 3882, "loss": 0.8533, "lr": 9.78551252709689e-05, "epoch": 0.2781354622714396, "percentage": 13.91, "elapsed_time": "2:47:37", "remaining_time": "17:17:24", "throughput": 627.98, "total_tokens": 6315944}
+{"current_steps": 545, "total_steps": 3882, "loss": 0.8575, "lr": 9.779296922671923e-05, "epoch": 0.2807107906258048, "percentage": 14.04, "elapsed_time": "2:49:07", "remaining_time": "17:15:32", "throughput": 628.18, "total_tokens": 6374408}
+{"current_steps": 550, "total_steps": 3882, "loss": 0.8666, "lr": 9.77299457077351e-05, "epoch": 0.28328611898017, "percentage": 14.17, "elapsed_time": "2:50:37", "remaining_time": "17:13:38", "throughput": 628.39, "total_tokens": 6432936}
+{"current_steps": 550, "total_steps": 3882, "eval_loss": 0.7909801602363586, "epoch": 0.28328611898017, "percentage": 14.17, "elapsed_time": "2:50:57", "remaining_time": "17:15:38", "throughput": 627.17, "total_tokens": 6432936}