Training in progress, step 3150

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:006fbddb28ccd3f24fce77178564cf32b9a0d6002aa0e149d2a632f6bc384cad
+oid sha256:d53665e5e9c8528df47b7ef76a4152d56ed4d96010a44cb39a4f16dca91d64bb
 size 29034840

trainer_log.jsonl

@@ -683,3 +683,14 @@
 {"current_steps": 3095, "total_steps": 3400, "loss": 0.3132, "lr": 2.183972356965125e-06, "epoch": 0.7970641256760237, "percentage": 91.03, "elapsed_time": "2:45:57", "remaining_time": "0:16:21", "throughput": 3264.09, "total_tokens": 32500664}
 {"current_steps": 3100, "total_steps": 3400, "loss": 0.2856, "lr": 2.113458308225458e-06, "epoch": 0.7983517898532063, "percentage": 91.18, "elapsed_time": "2:47:21", "remaining_time": "0:16:11", "throughput": 3241.74, "total_tokens": 32553288}
 {"current_steps": 3100, "total_steps": 3400, "eval_loss": 0.4740166962146759, "epoch": 0.7983517898532063, "percentage": 91.18, "elapsed_time": "2:47:59", "remaining_time": "0:16:15", "throughput": 3229.66, "total_tokens": 32553288}
+{"current_steps": 3105, "total_steps": 3400, "loss": 0.3052, "lr": 2.0440767832595574e-06, "epoch": 0.7996394540303888, "percentage": 91.32, "elapsed_time": "2:49:30", "remaining_time": "0:16:06", "throughput": 3205.89, "total_tokens": 32606096}
+{"current_steps": 3110, "total_steps": 3400, "loss": 0.2125, "lr": 1.975829422950709e-06, "epoch": 0.8009271182075715, "percentage": 91.47, "elapsed_time": "2:50:55", "remaining_time": "0:15:56", "throughput": 3184.46, "total_tokens": 32659376}
+{"current_steps": 3115, "total_steps": 3400, "loss": 0.3122, "lr": 1.908717841359048e-06, "epoch": 0.8022147823847541, "percentage": 91.62, "elapsed_time": "2:52:21", "remaining_time": "0:15:46", "throughput": 3163.29, "total_tokens": 32712168}
+{"current_steps": 3120, "total_steps": 3400, "loss": 0.3006, "lr": 1.8427436256833852e-06, "epoch": 0.8035024465619367, "percentage": 91.76, "elapsed_time": "2:53:46", "remaining_time": "0:15:35", "throughput": 3142.38, "total_tokens": 32764296}
+{"current_steps": 3125, "total_steps": 3400, "loss": 0.3077, "lr": 1.7779083362236547e-06, "epoch": 0.8047901107391192, "percentage": 91.91, "elapsed_time": "2:55:11", "remaining_time": "0:15:25", "throughput": 3121.71, "total_tokens": 32815296}
+{"current_steps": 3130, "total_steps": 3400, "loss": 0.29, "lr": 1.7142135063440035e-06, "epoch": 0.8060777749163018, "percentage": 92.06, "elapsed_time": "2:56:37", "remaining_time": "0:15:14", "throughput": 3101.47, "total_tokens": 32867288}
+{"current_steps": 3135, "total_steps": 3400, "loss": 0.3574, "lr": 1.6516606424365643e-06, "epoch": 0.8073654390934845, "percentage": 92.21, "elapsed_time": "2:58:02", "remaining_time": "0:15:02", "throughput": 3081.68, "total_tokens": 32919584}
+{"current_steps": 3140, "total_steps": 3400, "loss": 0.2414, "lr": 1.5902512238857858e-06, "epoch": 0.808653103270667, "percentage": 92.35, "elapsed_time": "2:59:28", "remaining_time": "0:14:51", "throughput": 3062.07, "total_tokens": 32972736}
+{"current_steps": 3145, "total_steps": 3400, "loss": 0.2521, "lr": 1.5299867030334814e-06, "epoch": 0.8099407674478496, "percentage": 92.5, "elapsed_time": "3:00:53", "remaining_time": "0:14:39", "throughput": 3043.05, "total_tokens": 33026320}
+{"current_steps": 3150, "total_steps": 3400, "loss": 0.2669, "lr": 1.4708685051444515e-06, "epoch": 0.8112284316250322, "percentage": 92.65, "elapsed_time": "3:02:18", "remaining_time": "0:14:28", "throughput": 3023.98, "total_tokens": 33078960}
+{"current_steps": 3150, "total_steps": 3400, "eval_loss": 0.4687062203884125, "epoch": 0.8112284316250322, "percentage": 92.65, "elapsed_time": "3:02:56", "remaining_time": "0:14:31", "throughput": 3013.66, "total_tokens": 33078960}