Training in progress, step 200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1db5746fd65250f2bf6817d2de9266703177b7d0c3decef80aefa9773e3ca7a
+oid sha256:381d89dd7c1135d0334349b9f49a436d03516c244b2ccee7000cd0fdc6d88805
 size 29034840

trainer_log.jsonl

@@ -31,3 +31,14 @@
 {"current_steps": 145, "total_steps": 3400, "loss": 0.0334, "lr": 8.529411764705883e-05, "epoch": 0.07468452227659027, "percentage": 4.26, "elapsed_time": "0:44:28", "remaining_time": "16:38:14", "throughput": 542.59, "total_tokens": 1447680}
 {"current_steps": 150, "total_steps": 3400, "loss": 0.0667, "lr": 8.823529411764706e-05, "epoch": 0.07725985063095545, "percentage": 4.41, "elapsed_time": "0:45:53", "remaining_time": "16:34:25", "throughput": 543.83, "total_tokens": 1497600}
 {"current_steps": 150, "total_steps": 3400, "eval_loss": 0.09665286540985107, "epoch": 0.07725985063095545, "percentage": 4.41, "elapsed_time": "0:46:13", "remaining_time": "16:41:23", "throughput": 540.05, "total_tokens": 1497600}
+{"current_steps": 155, "total_steps": 3400, "loss": 0.06, "lr": 9.11764705882353e-05, "epoch": 0.07983517898532062, "percentage": 4.56, "elapsed_time": "0:47:46", "remaining_time": "16:40:10", "throughput": 539.88, "total_tokens": 1547520}
+{"current_steps": 160, "total_steps": 3400, "loss": 0.0265, "lr": 9.411764705882353e-05, "epoch": 0.08241050733968582, "percentage": 4.71, "elapsed_time": "0:49:12", "remaining_time": "16:36:21", "throughput": 541.11, "total_tokens": 1597440}
+{"current_steps": 165, "total_steps": 3400, "loss": 0.1743, "lr": 9.705882352941177e-05, "epoch": 0.08498583569405099, "percentage": 4.85, "elapsed_time": "0:50:39", "remaining_time": "16:33:07", "throughput": 542.03, "total_tokens": 1647360}
+{"current_steps": 170, "total_steps": 3400, "loss": 0.051, "lr": 0.0001, "epoch": 0.08756116404841617, "percentage": 5.0, "elapsed_time": "0:52:04", "remaining_time": "16:29:34", "throughput": 543.14, "total_tokens": 1697280}
+{"current_steps": 175, "total_steps": 3400, "loss": 0.0584, "lr": 9.999940874631277e-05, "epoch": 0.09013649240278135, "percentage": 5.15, "elapsed_time": "0:53:31", "remaining_time": "16:26:31", "throughput": 543.97, "total_tokens": 1747200}
+{"current_steps": 180, "total_steps": 3400, "loss": 0.0704, "lr": 9.999763499923432e-05, "epoch": 0.09271182075714654, "percentage": 5.29, "elapsed_time": "0:54:57", "remaining_time": "16:23:09", "throughput": 544.99, "total_tokens": 1797120}
+{"current_steps": 185, "total_steps": 3400, "loss": 0.0278, "lr": 9.999467880071402e-05, "epoch": 0.09528714911151172, "percentage": 5.44, "elapsed_time": "0:56:23", "remaining_time": "16:20:03", "throughput": 545.86, "total_tokens": 1847040}
+{"current_steps": 190, "total_steps": 3400, "loss": 0.0862, "lr": 9.999054022066641e-05, "epoch": 0.0978624774658769, "percentage": 5.59, "elapsed_time": "0:57:49", "remaining_time": "16:16:57", "throughput": 546.74, "total_tokens": 1896960}
+{"current_steps": 195, "total_steps": 3400, "loss": 0.0565, "lr": 9.998521935696953e-05, "epoch": 0.10043780582024209, "percentage": 5.74, "elapsed_time": "0:59:16", "remaining_time": "16:14:07", "throughput": 547.48, "total_tokens": 1946880}
+{"current_steps": 200, "total_steps": 3400, "loss": 0.0459, "lr": 9.997871633546257e-05, "epoch": 0.10301313417460727, "percentage": 5.88, "elapsed_time": "1:00:42", "remaining_time": "16:11:15", "throughput": 548.24, "total_tokens": 1996800}
+{"current_steps": 200, "total_steps": 3400, "eval_loss": 0.09957947582006454, "epoch": 0.10301313417460727, "percentage": 5.88, "elapsed_time": "1:01:01", "remaining_time": "16:16:23", "throughput": 545.35, "total_tokens": 1996800}