Training in progress, step 1150

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:096ceb3aa916d4d6902ff8e257744f81a5081e748a27dc3a2d5249eefe4172c7
+oid sha256:2ba1a684cb0c9d39be76c9920c1189d211e013ed9e9e25243edff961b8c41477
 size 25200088

trainer_log.jsonl

@@ -118,3 +118,21 @@
 {"current_steps": 990, "total_steps": 1500, "loss": 0.1902, "accuracy": 0.9624999761581421, "learning_rate": 1.2956158147457116e-06, "epoch": 0.8792184724689165, "percentage": 66.0, "elapsed_time": "2:14:20", "remaining_time": "1:09:12", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1000, "total_steps": 1500, "loss": 0.1807, "accuracy": 0.925000011920929, "learning_rate": 1.2500000000000007e-06, "epoch": 0.8880994671403197, "percentage": 66.67, "elapsed_time": "2:15:33", "remaining_time": "1:07:46", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1000, "total_steps": 1500, "eval_loss": 0.22103577852249146, "epoch": 0.8880994671403197, "percentage": 66.67, "elapsed_time": "2:15:58", "remaining_time": "1:07:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1010, "total_steps": 1500, "loss": 0.2276, "accuracy": 0.925000011920929, "learning_rate": 1.204932476567175e-06, "epoch": 0.8969804618117229, "percentage": 67.33, "elapsed_time": "2:17:21", "remaining_time": "1:06:38", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1020, "total_steps": 1500, "loss": 0.1907, "accuracy": 0.9375, "learning_rate": 1.160433012552508e-06, "epoch": 0.9058614564831261, "percentage": 68.0, "elapsed_time": "2:18:35", "remaining_time": "1:05:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1030, "total_steps": 1500, "loss": 0.2483, "accuracy": 0.9624999761581421, "learning_rate": 1.11652112689164e-06, "epoch": 0.9147424511545293, "percentage": 68.67, "elapsed_time": "2:19:49", "remaining_time": "1:03:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1040, "total_steps": 1500, "loss": 0.1995, "accuracy": 0.9624999761581421, "learning_rate": 1.073216080788921e-06, "epoch": 0.9236234458259325, "percentage": 69.33, "elapsed_time": "2:20:58", "remaining_time": "1:02:21", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1050, "total_steps": 1500, "loss": 0.2275, "accuracy": 0.9375, "learning_rate": 1.0305368692688175e-06, "epoch": 0.9325044404973357, "percentage": 70.0, "elapsed_time": "2:22:18", "remaining_time": "1:00:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1050, "total_steps": 1500, "eval_loss": 0.2168363630771637, "epoch": 0.9325044404973357, "percentage": 70.0, "elapsed_time": "2:22:43", "remaining_time": "1:01:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1060, "total_steps": 1500, "loss": 0.214, "accuracy": 0.987500011920929, "learning_rate": 9.88502212844063e-07, "epoch": 0.9413854351687388, "percentage": 70.67, "elapsed_time": "2:24:06", "remaining_time": "0:59:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1070, "total_steps": 1500, "loss": 0.2135, "accuracy": 0.8999999761581421, "learning_rate": 9.471305493042243e-07, "epoch": 0.9502664298401421, "percentage": 71.33, "elapsed_time": "2:25:22", "remaining_time": "0:58:25", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1080, "total_steps": 1500, "loss": 0.2002, "accuracy": 0.9125000238418579, "learning_rate": 9.064400256282757e-07, "epoch": 0.9591474245115453, "percentage": 72.0, "elapsed_time": "2:26:35", "remaining_time": "0:57:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1090, "total_steps": 1500, "loss": 0.2498, "accuracy": 0.9624999761581421, "learning_rate": 8.664484900247363e-07, "epoch": 0.9680284191829485, "percentage": 72.67, "elapsed_time": "2:27:50", "remaining_time": "0:55:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1100, "total_steps": 1500, "loss": 0.1854, "accuracy": 0.949999988079071, "learning_rate": 8.271734841028553e-07, "epoch": 0.9769094138543517, "percentage": 73.33, "elapsed_time": "2:29:07", "remaining_time": "0:54:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1100, "total_steps": 1500, "eval_loss": 0.2113826721906662, "epoch": 0.9769094138543517, "percentage": 73.33, "elapsed_time": "2:29:32", "remaining_time": "0:54:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1110, "total_steps": 1500, "loss": 0.1986, "accuracy": 0.9125000238418579, "learning_rate": 7.886322351782782e-07, "epoch": 0.9857904085257548, "percentage": 74.0, "elapsed_time": "2:30:55", "remaining_time": "0:53:01", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1120, "total_steps": 1500, "loss": 0.1663, "accuracy": 0.949999988079071, "learning_rate": 7.508416487165862e-07, "epoch": 0.9946714031971581, "percentage": 74.67, "elapsed_time": "2:32:12", "remaining_time": "0:51:38", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1130, "total_steps": 1500, "loss": 0.1985, "accuracy": 0.9125000238418579, "learning_rate": 7.138183009179922e-07, "epoch": 1.0035523978685612, "percentage": 75.33, "elapsed_time": "2:33:30", "remaining_time": "0:50:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1140, "total_steps": 1500, "loss": 0.2141, "accuracy": 0.987500011920929, "learning_rate": 6.775784314464717e-07, "epoch": 1.0124333925399644, "percentage": 76.0, "elapsed_time": "2:34:44", "remaining_time": "0:48:51", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1150, "total_steps": 1500, "loss": 0.2069, "accuracy": 0.949999988079071, "learning_rate": 6.421379363065142e-07, "epoch": 1.0213143872113677, "percentage": 76.67, "elapsed_time": "2:36:01", "remaining_time": "0:47:29", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1150, "total_steps": 1500, "eval_loss": 0.20922726392745972, "epoch": 1.0213143872113677, "percentage": 76.67, "elapsed_time": "2:36:26", "remaining_time": "0:47:36", "throughput": "0.00", "total_tokens": 0}