Training in progress, step 350

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebc02da19989435043b7b50280b5e9e82d323b3ede799685ab53edfcf8cfad6a
+oid sha256:613cdc2baa395a9cb64ef1794cbc658fcd70f510e6627131b053d1c268735db7
 size 29034840

trainer_log.jsonl

@@ -64,3 +64,14 @@
 {"current_steps": 295, "total_steps": 3882, "loss": 0.9092, "lr": 9.981860274759173e-05, "epoch": 0.1519443729075457, "percentage": 7.6, "elapsed_time": "1:31:41", "remaining_time": "18:34:51", "throughput": 627.2, "total_tokens": 3450392}
 {"current_steps": 300, "total_steps": 3882, "loss": 0.8901, "lr": 9.980002193280342e-05, "epoch": 0.1545197012619109, "percentage": 7.73, "elapsed_time": "1:33:10", "remaining_time": "18:32:25", "throughput": 627.7, "total_tokens": 3508888}
 {"current_steps": 300, "total_steps": 3882, "eval_loss": 0.8932263255119324, "epoch": 0.1545197012619109, "percentage": 7.73, "elapsed_time": "1:33:29", "remaining_time": "18:36:21", "throughput": 625.48, "total_tokens": 3508888}
+{"current_steps": 305, "total_steps": 3882, "loss": 0.9042, "lr": 9.978053721391578e-05, "epoch": 0.15709502961627608, "percentage": 7.86, "elapsed_time": "1:35:05", "remaining_time": "18:35:12", "throughput": 625.26, "total_tokens": 3567368}
+{"current_steps": 310, "total_steps": 3882, "loss": 0.9007, "lr": 9.976014894458963e-05, "epoch": 0.15967035797064125, "percentage": 7.99, "elapsed_time": "1:36:33", "remaining_time": "18:32:40", "throughput": 625.81, "total_tokens": 3625848}
+{"current_steps": 315, "total_steps": 3882, "loss": 0.9036, "lr": 9.973885749488589e-05, "epoch": 0.16224568632500644, "percentage": 8.11, "elapsed_time": "1:38:03", "remaining_time": "18:30:22", "throughput": 626.22, "total_tokens": 3684336}
+{"current_steps": 320, "total_steps": 3882, "loss": 0.8936, "lr": 9.971666325125874e-05, "epoch": 0.16482101467937163, "percentage": 8.24, "elapsed_time": "1:39:30", "remaining_time": "18:27:44", "throughput": 626.83, "total_tokens": 3742800}
+{"current_steps": 325, "total_steps": 3882, "loss": 0.8989, "lr": 9.969356661654876e-05, "epoch": 0.1673963430337368, "percentage": 8.37, "elapsed_time": "1:41:00", "remaining_time": "18:25:29", "throughput": 627.23, "total_tokens": 3801280}
+{"current_steps": 330, "total_steps": 3882, "loss": 0.8983, "lr": 9.966956800997546e-05, "epoch": 0.16997167138810199, "percentage": 8.5, "elapsed_time": "1:42:28", "remaining_time": "18:22:55", "throughput": 627.81, "total_tokens": 3859792}
+{"current_steps": 335, "total_steps": 3882, "loss": 0.9038, "lr": 9.964466786712984e-05, "epoch": 0.17254699974246718, "percentage": 8.63, "elapsed_time": "1:43:57", "remaining_time": "18:20:45", "throughput": 628.16, "total_tokens": 3918272}
+{"current_steps": 340, "total_steps": 3882, "loss": 0.8947, "lr": 9.961886663996629e-05, "epoch": 0.17512232809683234, "percentage": 8.76, "elapsed_time": "1:45:26", "remaining_time": "18:18:25", "throughput": 628.61, "total_tokens": 3976760}
+{"current_steps": 345, "total_steps": 3882, "loss": 0.9179, "lr": 9.959216479679458e-05, "epoch": 0.17769765645119753, "percentage": 8.89, "elapsed_time": "1:46:56", "remaining_time": "18:16:25", "throughput": 628.86, "total_tokens": 4035240}
+{"current_steps": 350, "total_steps": 3882, "loss": 0.9059, "lr": 9.956456282227122e-05, "epoch": 0.1802729848055627, "percentage": 9.02, "elapsed_time": "1:48:25", "remaining_time": "18:14:06", "throughput": 629.29, "total_tokens": 4093688}
+{"current_steps": 350, "total_steps": 3882, "eval_loss": 0.8960411548614502, "epoch": 0.1802729848055627, "percentage": 9.02, "elapsed_time": "1:48:45", "remaining_time": "18:17:29", "throughput": 627.36, "total_tokens": 4093688}