Training in progress, step 100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e0965d85d2059e66711cfd602d8653fa3ff9df2502c33a50c785432d3a510f8
+oid sha256:10b20a6cbc63060eb8f30979d458631a6f5b8f1b12ebf77d9c03e30bcf274bec
 size 29034840

trainer_log.jsonl

@@ -10,3 +10,14 @@
 {"current_steps": 45, "total_steps": 6770, "loss": 1.4552, "lr": 1.3274336283185843e-05, "epoch": 0.013293943870014771, "percentage": 0.66, "elapsed_time": "0:14:30", "remaining_time": "1 day, 12:07:14", "throughput": 534.0, "total_tokens": 464640}
 {"current_steps": 50, "total_steps": 6770, "loss": 1.3918, "lr": 1.4749262536873157e-05, "epoch": 0.014771048744460856, "percentage": 0.74, "elapsed_time": "0:15:58", "remaining_time": "1 day, 11:47:49", "throughput": 538.4, "total_tokens": 516240}
 {"current_steps": 50, "total_steps": 6770, "eval_loss": 1.042170763015747, "epoch": 0.014771048744460856, "percentage": 0.74, "elapsed_time": "0:16:47", "remaining_time": "1 day, 13:37:05", "throughput": 512.33, "total_tokens": 516240}
+{"current_steps": 55, "total_steps": 6770, "loss": 1.2308, "lr": 1.6224188790560475e-05, "epoch": 0.01624815361890694, "percentage": 0.81, "elapsed_time": "0:18:22", "remaining_time": "1 day, 13:24:07", "throughput": 514.61, "total_tokens": 567536}
+{"current_steps": 60, "total_steps": 6770, "loss": 1.0922, "lr": 1.7699115044247787e-05, "epoch": 0.01772525849335303, "percentage": 0.89, "elapsed_time": "0:19:50", "remaining_time": "1 day, 12:58:38", "throughput": 520.35, "total_tokens": 619392}
+{"current_steps": 65, "total_steps": 6770, "loss": 0.9517, "lr": 1.9174041297935107e-05, "epoch": 0.019202363367799114, "percentage": 0.96, "elapsed_time": "0:21:16", "remaining_time": "1 day, 12:34:14", "throughput": 525.87, "total_tokens": 671168}
+{"current_steps": 70, "total_steps": 6770, "loss": 0.9277, "lr": 2.064896755162242e-05, "epoch": 0.0206794682422452, "percentage": 1.03, "elapsed_time": "0:22:43", "remaining_time": "1 day, 12:15:52", "throughput": 529.67, "total_tokens": 722464}
+{"current_steps": 75, "total_steps": 6770, "loss": 0.8741, "lr": 2.2123893805309738e-05, "epoch": 0.022156573116691284, "percentage": 1.11, "elapsed_time": "0:24:09", "remaining_time": "1 day, 11:57:07", "throughput": 533.91, "total_tokens": 774120}
+{"current_steps": 80, "total_steps": 6770, "loss": 0.8837, "lr": 2.359882005899705e-05, "epoch": 0.023633677991137372, "percentage": 1.18, "elapsed_time": "0:25:37", "remaining_time": "1 day, 11:42:56", "throughput": 537.19, "total_tokens": 825944}
+{"current_steps": 85, "total_steps": 6770, "loss": 0.8658, "lr": 2.5073746312684367e-05, "epoch": 0.025110782865583457, "percentage": 1.26, "elapsed_time": "0:27:03", "remaining_time": "1 day, 11:28:18", "throughput": 540.52, "total_tokens": 877632}
+{"current_steps": 90, "total_steps": 6770, "loss": 0.8626, "lr": 2.6548672566371686e-05, "epoch": 0.026587887740029542, "percentage": 1.33, "elapsed_time": "0:28:32", "remaining_time": "1 day, 11:18:12", "throughput": 542.34, "total_tokens": 928664}
+{"current_steps": 95, "total_steps": 6770, "loss": 0.828, "lr": 2.8023598820059e-05, "epoch": 0.028064992614475627, "percentage": 1.4, "elapsed_time": "0:29:59", "remaining_time": "1 day, 11:07:21", "throughput": 544.65, "total_tokens": 980120}
+{"current_steps": 100, "total_steps": 6770, "loss": 0.8208, "lr": 2.9498525073746314e-05, "epoch": 0.029542097488921712, "percentage": 1.48, "elapsed_time": "0:31:27", "remaining_time": "1 day, 10:58:11", "throughput": 546.08, "total_tokens": 1030696}
+{"current_steps": 100, "total_steps": 6770, "eval_loss": 0.8917127847671509, "epoch": 0.029542097488921712, "percentage": 1.48, "elapsed_time": "0:31:46", "remaining_time": "1 day, 11:19:33", "throughput": 540.58, "total_tokens": 1030696}