Training in progress, step 700

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae4ae60a26ee99e11a2e5ab6fb595036c6ed6a11a5c18815e41835fd861d1bc
+oid sha256:cb5f3724b5d59ea4e0a9371b33e20124137112f04ac962fd4bc5e834b083db05
 size 18516456

trainer_log.jsonl

@@ -145,3 +145,14 @@
 {"current_steps": 645, "total_steps": 3400, "loss": 0.8924, "lr": 9.475816456775313e-05, "epoch": 0.3322173577131084, "percentage": 18.97, "elapsed_time": "2:31:29", "remaining_time": "10:47:03", "throughput": 829.98, "total_tokens": 7544040}
 {"current_steps": 650, "total_steps": 3400, "loss": 0.904, "lr": 9.464925117963133e-05, "epoch": 0.3347926860674736, "percentage": 19.12, "elapsed_time": "2:32:34", "remaining_time": "10:45:29", "throughput": 830.49, "total_tokens": 7602512}
 {"current_steps": 650, "total_steps": 3400, "eval_loss": 0.90328449010849, "epoch": 0.3347926860674736, "percentage": 19.12, "elapsed_time": "2:32:50", "remaining_time": "10:46:37", "throughput": 829.03, "total_tokens": 7602512}
+{"current_steps": 655, "total_steps": 3400, "loss": 0.8929, "lr": 9.453928183013385e-05, "epoch": 0.3373680144218388, "percentage": 19.26, "elapsed_time": "2:33:59", "remaining_time": "10:45:22", "throughput": 829.14, "total_tokens": 7660968}
+{"current_steps": 660, "total_steps": 3400, "loss": 0.9078, "lr": 9.442825912005202e-05, "epoch": 0.33994334277620397, "percentage": 19.41, "elapsed_time": "2:35:03", "remaining_time": "10:43:45", "throughput": 829.7, "total_tokens": 7719448}
+{"current_steps": 665, "total_steps": 3400, "loss": 0.8963, "lr": 9.431618567508933e-05, "epoch": 0.34251867113056916, "percentage": 19.56, "elapsed_time": "2:36:07", "remaining_time": "10:42:07", "throughput": 830.29, "total_tokens": 7777928}
+{"current_steps": 670, "total_steps": 3400, "loss": 0.9134, "lr": 9.420306414579925e-05, "epoch": 0.34509399948493436, "percentage": 19.71, "elapsed_time": "2:37:11", "remaining_time": "10:40:30", "throughput": 830.86, "total_tokens": 7836424}
+{"current_steps": 675, "total_steps": 3400, "loss": 0.8984, "lr": 9.408889720752266e-05, "epoch": 0.3476693278392995, "percentage": 19.85, "elapsed_time": "2:38:16", "remaining_time": "10:38:56", "throughput": 831.38, "total_tokens": 7894904}
+{"current_steps": 680, "total_steps": 3400, "loss": 0.8997, "lr": 9.397368756032445e-05, "epoch": 0.3502446561936647, "percentage": 20.0, "elapsed_time": "2:39:20", "remaining_time": "10:37:20", "throughput": 831.93, "total_tokens": 7953432}
+{"current_steps": 685, "total_steps": 3400, "loss": 0.8926, "lr": 9.385743792892982e-05, "epoch": 0.3528199845480299, "percentage": 20.15, "elapsed_time": "2:40:24", "remaining_time": "10:35:46", "throughput": 832.45, "total_tokens": 8011888}
+{"current_steps": 690, "total_steps": 3400, "loss": 0.9008, "lr": 9.374015106265968e-05, "epoch": 0.35539531290239507, "percentage": 20.29, "elapsed_time": "2:41:28", "remaining_time": "10:34:11", "throughput": 832.99, "total_tokens": 8070344}
+{"current_steps": 695, "total_steps": 3400, "loss": 0.8986, "lr": 9.362182973536569e-05, "epoch": 0.35797064125676026, "percentage": 20.44, "elapsed_time": "2:42:32", "remaining_time": "10:32:38", "throughput": 833.49, "total_tokens": 8128816}
+{"current_steps": 700, "total_steps": 3400, "loss": 0.8972, "lr": 9.35024767453647e-05, "epoch": 0.3605459696111254, "percentage": 20.59, "elapsed_time": "2:43:36", "remaining_time": "10:31:04", "throughput": 834.03, "total_tokens": 8187320}
+{"current_steps": 700, "total_steps": 3400, "eval_loss": 0.9028835892677307, "epoch": 0.3605459696111254, "percentage": 20.59, "elapsed_time": "2:43:52", "remaining_time": "10:32:06", "throughput": 832.66, "total_tokens": 8187320}