Training in progress, step 600

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82e427cc7e624394004d64620be182b50bd10e2a67a34cf622de25a3f138b7e0
+oid sha256:168cc62ce0f9bc823e9f05cfca486c4f8b12cfdb3adf1b70687137fa417f7b65
 size 29034840

trainer_log.jsonl

@@ -119,3 +119,14 @@
 {"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}
+{"current_steps": 555, "total_steps": 3882, "loss": 0.8264, "lr": 9.7666055857936e-05, "epoch": 0.28586144733453517, "percentage": 14.3, "elapsed_time": "2:52:32", "remaining_time": "17:14:16", "throughput": 627.06, "total_tokens": 6491400}
+{"current_steps": 560, "total_steps": 3882, "loss": 0.8456, "lr": 9.760130083696595e-05, "epoch": 0.28843677568890036, "percentage": 14.43, "elapsed_time": "2:54:01", "remaining_time": "17:12:22", "throughput": 627.27, "total_tokens": 6549872}
+{"current_steps": 565, "total_steps": 3882, "loss": 0.8032, "lr": 9.75356818201724e-05, "epoch": 0.2910121040432655, "percentage": 14.55, "elapsed_time": "2:55:30", "remaining_time": "17:10:19", "throughput": 627.57, "total_tokens": 6608296}
+{"current_steps": 570, "total_steps": 3882, "loss": 0.8081, "lr": 9.746919999858492e-05, "epoch": 0.2935874323976307, "percentage": 14.68, "elapsed_time": "2:57:00", "remaining_time": "17:08:28", "throughput": 627.75, "total_tokens": 6666768}
+{"current_steps": 575, "total_steps": 3882, "loss": 0.8398, "lr": 9.740185657889357e-05, "epoch": 0.2961627607519959, "percentage": 14.81, "elapsed_time": "2:58:28", "remaining_time": "17:06:28", "throughput": 628.02, "total_tokens": 6725248}
+{"current_steps": 580, "total_steps": 3882, "loss": 0.8908, "lr": 9.733365278342696e-05, "epoch": 0.29873808910636107, "percentage": 14.94, "elapsed_time": "2:59:58", "remaining_time": "17:04:37", "throughput": 628.2, "total_tokens": 6783680}
+{"current_steps": 585, "total_steps": 3882, "loss": 0.8248, "lr": 9.726458985013017e-05, "epoch": 0.30131341746072626, "percentage": 15.07, "elapsed_time": "3:01:26", "remaining_time": "17:02:35", "throughput": 628.49, "total_tokens": 6842144}
+{"current_steps": 590, "total_steps": 3882, "loss": 0.829, "lr": 9.719466903254215e-05, "epoch": 0.3038887458150914, "percentage": 15.2, "elapsed_time": "3:02:56", "remaining_time": "17:00:43", "throughput": 628.69, "total_tokens": 6900656}
+{"current_steps": 595, "total_steps": 3882, "loss": 0.8269, "lr": 9.712389159977307e-05, "epoch": 0.3064640741694566, "percentage": 15.33, "elapsed_time": "3:04:24", "remaining_time": "16:58:45", "throughput": 628.95, "total_tokens": 6959128}
+{"current_steps": 600, "total_steps": 3882, "loss": 0.7997, "lr": 9.705225883648121e-05, "epoch": 0.3090394025238218, "percentage": 15.46, "elapsed_time": "3:05:54", "remaining_time": "16:56:56", "throughput": 629.11, "total_tokens": 7017576}
+{"current_steps": 600, "total_steps": 3882, "eval_loss": 0.787663459777832, "epoch": 0.3090394025238218, "percentage": 15.46, "elapsed_time": "3:06:14", "remaining_time": "16:58:44", "throughput": 628.0, "total_tokens": 7017576}