Training in progress, step 1650

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36f722668f1a0618c0a9e43f223d905e82d0c1068f32211684745e00d5aaa272
+oid sha256:a98d193ab7c674712e3c18a30e49e6fde0bcc59efee6c60450baf3a08afe8f78
 size 29034840

trainer_log.jsonl

@@ -350,3 +350,14 @@
 {"current_steps": 1595, "total_steps": 3882, "loss": 0.3956, "lr": 6.84482086985991e-05, "epoch": 0.8215297450424929, "percentage": 41.09, "elapsed_time": "8:08:00", "remaining_time": "11:39:44", "throughput": 637.13, "total_tokens": 18655584}
 {"current_steps": 1600, "total_steps": 3882, "loss": 0.3834, "lr": 6.825005345225019e-05, "epoch": 0.8241050733968581, "percentage": 41.22, "elapsed_time": "8:09:29", "remaining_time": "11:38:07", "throughput": 637.2, "total_tokens": 18714072}
 {"current_steps": 1600, "total_steps": 3882, "eval_loss": 0.44774264097213745, "epoch": 0.8241050733968581, "percentage": 41.22, "elapsed_time": "8:09:48", "remaining_time": "11:38:35", "throughput": 636.78, "total_tokens": 18714072}
+{"current_steps": 1605, "total_steps": 3882, "loss": 0.4136, "lr": 6.805156695508075e-05, "epoch": 0.8266804017512233, "percentage": 41.34, "elapsed_time": "8:11:23", "remaining_time": "11:37:08", "throughput": 636.71, "total_tokens": 18772552}
+{"current_steps": 1610, "total_steps": 3882, "loss": 0.3523, "lr": 6.7852752809755e-05, "epoch": 0.8292557301055885, "percentage": 41.47, "elapsed_time": "8:12:52", "remaining_time": "11:35:31", "throughput": 636.78, "total_tokens": 18830992}
+{"current_steps": 1615, "total_steps": 3882, "loss": 0.2983, "lr": 6.765361462488424e-05, "epoch": 0.8318310584599536, "percentage": 41.6, "elapsed_time": "8:14:21", "remaining_time": "11:33:56", "throughput": 636.83, "total_tokens": 18889480}
+{"current_steps": 1620, "total_steps": 3882, "loss": 0.3987, "lr": 6.745415601496127e-05, "epoch": 0.8344063868143188, "percentage": 41.73, "elapsed_time": "8:15:49", "remaining_time": "11:32:19", "throughput": 636.91, "total_tokens": 18947936}
+{"current_steps": 1625, "total_steps": 3882, "loss": 0.5012, "lr": 6.725438060029485e-05, "epoch": 0.836981715168684, "percentage": 41.86, "elapsed_time": "8:17:19", "remaining_time": "11:30:45", "throughput": 636.95, "total_tokens": 19006432}
+{"current_steps": 1630, "total_steps": 3882, "loss": 0.36, "lr": 6.705429200694396e-05, "epoch": 0.8395570435230492, "percentage": 41.99, "elapsed_time": "8:18:48", "remaining_time": "11:29:08", "throughput": 637.02, "total_tokens": 19064920}
+{"current_steps": 1635, "total_steps": 3882, "loss": 0.3816, "lr": 6.685389386665197e-05, "epoch": 0.8421323718774144, "percentage": 42.12, "elapsed_time": "8:20:17", "remaining_time": "11:27:33", "throughput": 637.07, "total_tokens": 19123376}
+{"current_steps": 1640, "total_steps": 3882, "loss": 0.3503, "lr": 6.665318981678072e-05, "epoch": 0.8447077002317795, "percentage": 42.25, "elapsed_time": "8:21:46", "remaining_time": "11:25:57", "throughput": 637.13, "total_tokens": 19181864}
+{"current_steps": 1645, "total_steps": 3882, "loss": 0.3644, "lr": 6.645218350024456e-05, "epoch": 0.8472830285861447, "percentage": 42.38, "elapsed_time": "8:23:14", "remaining_time": "11:24:20", "throughput": 637.21, "total_tokens": 19240352}
+{"current_steps": 1650, "total_steps": 3882, "loss": 0.475, "lr": 6.625087856544416e-05, "epoch": 0.8498583569405099, "percentage": 42.5, "elapsed_time": "8:24:42", "remaining_time": "11:22:43", "throughput": 637.3, "total_tokens": 19298848}
+{"current_steps": 1650, "total_steps": 3882, "eval_loss": 0.35129043459892273, "epoch": 0.8498583569405099, "percentage": 42.5, "elapsed_time": "8:25:01", "remaining_time": "11:23:09", "throughput": 636.9, "total_tokens": 19298848}