Training in progress, step 450

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08b87c533591cf43be22c8b89220b2967d41fed152c79aaa9842299ccd408331
+oid sha256:a24a7751d933c419ff20a88671474ce5f1c87cc1568eaae7c47539cec49a0328
 size 83945296

trainer_log.jsonl

@@ -22,3 +22,33 @@
 {"current_steps": 190, "total_steps": 500, "loss": 0.0873, "learning_rate": 3.912417508562345e-06, "epoch": 3.753086419753086, "percentage": 38.0, "elapsed_time": "0:04:20", "remaining_time": "0:07:04"}
 {"current_steps": 200, "total_steps": 500, "loss": 0.0743, "learning_rate": 3.7650844103029093e-06, "epoch": 3.950617283950617, "percentage": 40.0, "elapsed_time": "0:04:33", "remaining_time": "0:06:49"}
 {"current_steps": 200, "total_steps": 500, "eval_loss": 0.10680027306079865, "epoch": 3.950617283950617, "percentage": 40.0, "elapsed_time": "0:04:35", "remaining_time": "0:06:53"}
+{"current_steps": 210, "total_steps": 500, "loss": 0.0622, "learning_rate": 3.611587947962319e-06, "epoch": 4.148148148148148, "percentage": 42.0, "elapsed_time": "0:04:50", "remaining_time": "0:06:41"}
+{"current_steps": 220, "total_steps": 500, "loss": 0.0883, "learning_rate": 3.452675940875686e-06, "epoch": 4.345679012345679, "percentage": 44.0, "elapsed_time": "0:05:04", "remaining_time": "0:06:27"}
+{"current_steps": 230, "total_steps": 500, "loss": 0.0546, "learning_rate": 3.2891225923677565e-06, "epoch": 4.54320987654321, "percentage": 46.0, "elapsed_time": "0:05:16", "remaining_time": "0:06:11"}
+{"current_steps": 240, "total_steps": 500, "loss": 0.052, "learning_rate": 3.121724717912138e-06, "epoch": 4.7407407407407405, "percentage": 48.0, "elapsed_time": "0:05:29", "remaining_time": "0:05:56"}
+{"current_steps": 250, "total_steps": 500, "loss": 0.0855, "learning_rate": 2.9512978631264006e-06, "epoch": 4.938271604938271, "percentage": 50.0, "elapsed_time": "0:05:42", "remaining_time": "0:05:42"}
+{"current_steps": 250, "total_steps": 500, "eval_loss": 0.10621543228626251, "epoch": 4.938271604938271, "percentage": 50.0, "elapsed_time": "0:05:44", "remaining_time": "0:05:44"}
+{"current_steps": 260, "total_steps": 500, "loss": 0.0887, "learning_rate": 2.778672330515814e-06, "epoch": 5.135802469135802, "percentage": 52.0, "elapsed_time": "0:06:00", "remaining_time": "0:05:32"}
+{"current_steps": 270, "total_steps": 500, "loss": 0.058, "learning_rate": 2.604689134322999e-06, "epoch": 5.333333333333333, "percentage": 54.0, "elapsed_time": "0:06:13", "remaining_time": "0:05:18"}
+{"current_steps": 280, "total_steps": 500, "loss": 0.0671, "learning_rate": 2.4301959031910785e-06, "epoch": 5.530864197530864, "percentage": 56.0, "elapsed_time": "0:06:26", "remaining_time": "0:05:04"}
+{"current_steps": 290, "total_steps": 500, "loss": 0.0563, "learning_rate": 2.256042750602127e-06, "epoch": 5.728395061728395, "percentage": 58.0, "elapsed_time": "0:06:39", "remaining_time": "0:04:49"}
+{"current_steps": 300, "total_steps": 500, "loss": 0.0571, "learning_rate": 2.0830781332097446e-06, "epoch": 5.925925925925926, "percentage": 60.0, "elapsed_time": "0:06:52", "remaining_time": "0:04:34"}
+{"current_steps": 300, "total_steps": 500, "eval_loss": 0.10575470328330994, "epoch": 5.925925925925926, "percentage": 60.0, "elapsed_time": "0:06:54", "remaining_time": "0:04:36"}
+{"current_steps": 310, "total_steps": 500, "loss": 0.0644, "learning_rate": 1.912144717243525e-06, "epoch": 6.1234567901234565, "percentage": 62.0, "elapsed_time": "0:07:10", "remaining_time": "0:04:23"}
+{"current_steps": 320, "total_steps": 500, "loss": 0.0574, "learning_rate": 1.744075273123889e-06, "epoch": 6.320987654320987, "percentage": 64.0, "elapsed_time": "0:07:23", "remaining_time": "0:04:09"}
+{"current_steps": 330, "total_steps": 500, "loss": 0.0642, "learning_rate": 1.5796886182883053e-06, "epoch": 6.518518518518518, "percentage": 66.0, "elapsed_time": "0:07:36", "remaining_time": "0:03:55"}
+{"current_steps": 340, "total_steps": 500, "loss": 0.0584, "learning_rate": 1.419785627995044e-06, "epoch": 6.716049382716049, "percentage": 68.0, "elapsed_time": "0:07:49", "remaining_time": "0:03:40"}
+{"current_steps": 350, "total_steps": 500, "loss": 0.063, "learning_rate": 1.2651453335394232e-06, "epoch": 6.91358024691358, "percentage": 70.0, "elapsed_time": "0:08:02", "remaining_time": "0:03:26"}
+{"current_steps": 350, "total_steps": 500, "eval_loss": 0.10544978082180023, "epoch": 6.91358024691358, "percentage": 70.0, "elapsed_time": "0:08:04", "remaining_time": "0:03:27"}
+{"current_steps": 360, "total_steps": 500, "loss": 0.0585, "learning_rate": 1.11652112689164e-06, "epoch": 7.111111111111111, "percentage": 72.0, "elapsed_time": "0:08:21", "remaining_time": "0:03:14"}
+{"current_steps": 370, "total_steps": 500, "loss": 0.0556, "learning_rate": 9.746370902468311e-07, "epoch": 7.308641975308642, "percentage": 74.0, "elapsed_time": "0:08:33", "remaining_time": "0:03:00"}
+{"current_steps": 380, "total_steps": 500, "loss": 0.0665, "learning_rate": 8.40184468369396e-07, "epoch": 7.506172839506172, "percentage": 76.0, "elapsed_time": "0:08:47", "remaining_time": "0:02:46"}
+{"current_steps": 390, "total_steps": 500, "loss": 0.0513, "learning_rate": 7.138183009179922e-07, "epoch": 7.703703703703704, "percentage": 78.0, "elapsed_time": "0:09:00", "remaining_time": "0:02:32"}
+{"current_steps": 400, "total_steps": 500, "loss": 0.0597, "learning_rate": 5.961542311581586e-07, "epoch": 7.901234567901234, "percentage": 80.0, "elapsed_time": "0:09:13", "remaining_time": "0:02:18"}
+{"current_steps": 400, "total_steps": 500, "eval_loss": 0.10566332191228867, "epoch": 7.901234567901234, "percentage": 80.0, "elapsed_time": "0:09:15", "remaining_time": "0:02:18"}
+{"current_steps": 410, "total_steps": 500, "loss": 0.0481, "learning_rate": 4.87765506610215e-07, "epoch": 8.098765432098766, "percentage": 82.0, "elapsed_time": "0:09:30", "remaining_time": "0:02:05"}
+{"current_steps": 420, "total_steps": 500, "loss": 0.0474, "learning_rate": 3.891801862449629e-07, "epoch": 8.296296296296296, "percentage": 84.0, "elapsed_time": "0:09:43", "remaining_time": "0:01:51"}
+{"current_steps": 430, "total_steps": 500, "loss": 0.0455, "learning_rate": 3.0087856783345916e-07, "epoch": 8.493827160493828, "percentage": 86.0, "elapsed_time": "0:09:57", "remaining_time": "0:01:37"}
+{"current_steps": 440, "total_steps": 500, "loss": 0.0609, "learning_rate": 2.2329084798455747e-07, "epoch": 8.691358024691358, "percentage": 88.0, "elapsed_time": "0:10:09", "remaining_time": "0:01:23"}
+{"current_steps": 450, "total_steps": 500, "loss": 0.0694, "learning_rate": 1.567950262702714e-07, "epoch": 8.88888888888889, "percentage": 90.0, "elapsed_time": "0:10:23", "remaining_time": "0:01:09"}
+{"current_steps": 450, "total_steps": 500, "eval_loss": 0.10525013506412506, "epoch": 8.88888888888889, "percentage": 90.0, "elapsed_time": "0:10:25", "remaining_time": "0:01:09"}