Training in progress, step 2150

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b39895ee437656d2822d9ef3e148e364db825b03d8467830b69e5610c256e5a
+oid sha256:ff2cc1f16a485d3e450e8a2a866e3d76b5149212ac068f60cacb581a8329cec2
 size 18516456

trainer_log.jsonl

@@ -464,3 +464,14 @@
 {"current_steps": 2095, "total_steps": 3400, "loss": 0.3654, "lr": 3.515163588305735e-05, "epoch": 1.0788050476435747, "percentage": 61.62, "elapsed_time": "7:48:09", "remaining_time": "4:51:37", "throughput": 872.12, "total_tokens": 24497448}
 {"current_steps": 2100, "total_steps": 3400, "loss": 0.3351, "lr": 3.491962445238569e-05, "epoch": 1.0813803759979397, "percentage": 61.76, "elapsed_time": "7:49:14", "remaining_time": "4:50:28", "throughput": 872.19, "total_tokens": 24555904}
 {"current_steps": 2100, "total_steps": 3400, "eval_loss": 0.8075026869773865, "epoch": 1.0813803759979397, "percentage": 61.76, "elapsed_time": "7:49:30", "remaining_time": "4:50:38", "throughput": 871.69, "total_tokens": 24555904}
+{"current_steps": 2105, "total_steps": 3400, "loss": 0.3827, "lr": 3.4687969674819906e-05, "epoch": 1.083955704352305, "percentage": 61.91, "elapsed_time": "7:50:39", "remaining_time": "4:49:32", "throughput": 871.63, "total_tokens": 24614392}
+{"current_steps": 2110, "total_steps": 3400, "loss": 0.3676, "lr": 3.445667702902969e-05, "epoch": 1.0865310327066702, "percentage": 62.06, "elapsed_time": "7:51:43", "remaining_time": "4:48:24", "throughput": 871.72, "total_tokens": 24672848}
+{"current_steps": 2115, "total_steps": 3400, "loss": 0.3253, "lr": 3.4225751985120215e-05, "epoch": 1.0891063610610352, "percentage": 62.21, "elapsed_time": "7:52:47", "remaining_time": "4:47:15", "throughput": 871.81, "total_tokens": 24731344}
+{"current_steps": 2120, "total_steps": 3400, "loss": 0.4297, "lr": 3.3995200004502816e-05, "epoch": 1.0916816894154004, "percentage": 62.35, "elapsed_time": "7:53:52", "remaining_time": "4:46:06", "throughput": 871.89, "total_tokens": 24789832}
+{"current_steps": 2125, "total_steps": 3400, "loss": 0.3536, "lr": 3.3765026539765834e-05, "epoch": 1.0942570177697657, "percentage": 62.5, "elapsed_time": "7:54:56", "remaining_time": "4:44:57", "throughput": 871.98, "total_tokens": 24848264}
+{"current_steps": 2130, "total_steps": 3400, "loss": 0.3588, "lr": 3.3535237034545675e-05, "epoch": 1.0968323461241307, "percentage": 62.65, "elapsed_time": "7:56:00", "remaining_time": "4:43:49", "throughput": 872.06, "total_tokens": 24906744}
+{"current_steps": 2135, "total_steps": 3400, "loss": 0.3666, "lr": 3.330583692339802e-05, "epoch": 1.099407674478496, "percentage": 62.79, "elapsed_time": "7:57:05", "remaining_time": "4:42:40", "throughput": 872.15, "total_tokens": 24965256}
+{"current_steps": 2140, "total_steps": 3400, "loss": 0.3334, "lr": 3.307683163166934e-05, "epoch": 1.1019830028328612, "percentage": 62.94, "elapsed_time": "7:58:08", "remaining_time": "4:41:31", "throughput": 872.25, "total_tokens": 25023768}
+{"current_steps": 2145, "total_steps": 3400, "loss": 0.3848, "lr": 3.284822657536856e-05, "epoch": 1.1045583311872265, "percentage": 63.09, "elapsed_time": "7:59:11", "remaining_time": "4:40:22", "throughput": 872.37, "total_tokens": 25082248}
+{"current_steps": 2150, "total_steps": 3400, "loss": 0.3699, "lr": 3.262002716103897e-05, "epoch": 1.1071336595415915, "percentage": 63.24, "elapsed_time": "8:00:15", "remaining_time": "4:39:12", "throughput": 872.49, "total_tokens": 25140752}
+{"current_steps": 2150, "total_steps": 3400, "eval_loss": 0.8523861169815063, "epoch": 1.1071336595415915, "percentage": 63.24, "elapsed_time": "8:00:31", "remaining_time": "4:39:22", "throughput": 872.0, "total_tokens": 25140752}