Training in progress, step 350

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b99b8b6736c9551b7572fb855984029765a2e7449d447f3321e71447af523fc8
+oid sha256:77c3ac7da08d446d1e9f20eb9182580b5c74675d4321465f97ce8b96cb262f6a
 size 18516456

trainer_log.jsonl

@@ -68,3 +68,14 @@
 {"current_steps": 295, "total_steps": 3400, "loss": 0.9091, "lr": 9.96309206782565e-05, "epoch": 0.1519443729075457, "percentage": 8.68, "elapsed_time": "1:09:42", "remaining_time": "12:13:46", "throughput": 824.88, "total_tokens": 3450392}
 {"current_steps": 300, "total_steps": 3400, "loss": 0.8893, "lr": 9.960084393841355e-05, "epoch": 0.1545197012619109, "percentage": 8.82, "elapsed_time": "1:10:49", "remaining_time": "12:11:54", "throughput": 825.67, "total_tokens": 3508888}
 {"current_steps": 300, "total_steps": 3400, "eval_loss": 0.8908902406692505, "epoch": 0.1545197012619109, "percentage": 8.82, "elapsed_time": "1:11:06", "remaining_time": "12:14:49", "throughput": 822.39, "total_tokens": 3508888}
+{"current_steps": 305, "total_steps": 3400, "loss": 0.9056, "lr": 9.956959413129585e-05, "epoch": 0.15709502961627608, "percentage": 8.97, "elapsed_time": "1:12:19", "remaining_time": "12:13:52", "throughput": 822.12, "total_tokens": 3567368}
+{"current_steps": 310, "total_steps": 3400, "loss": 0.8982, "lr": 9.953717199596598e-05, "epoch": 0.15967035797064125, "percentage": 9.12, "elapsed_time": "1:13:26", "remaining_time": "12:12:05", "throughput": 822.79, "total_tokens": 3625848}
+{"current_steps": 315, "total_steps": 3400, "loss": 0.8968, "lr": 9.95035782992122e-05, "epoch": 0.16224568632500644, "percentage": 9.26, "elapsed_time": "1:14:34", "remaining_time": "12:10:19", "throughput": 823.44, "total_tokens": 3684336}
+{"current_steps": 320, "total_steps": 3400, "loss": 0.8975, "lr": 9.94688138355304e-05, "epoch": 0.16482101467937163, "percentage": 9.41, "elapsed_time": "1:15:42", "remaining_time": "12:08:37", "throughput": 824.02, "total_tokens": 3742800}
+{"current_steps": 325, "total_steps": 3400, "loss": 0.9061, "lr": 9.943287942710527e-05, "epoch": 0.1673963430337368, "percentage": 9.56, "elapsed_time": "1:16:50", "remaining_time": "12:07:00", "throughput": 824.51, "total_tokens": 3801280}
+{"current_steps": 330, "total_steps": 3400, "loss": 0.8948, "lr": 9.939577592379088e-05, "epoch": 0.16997167138810199, "percentage": 9.71, "elapsed_time": "1:17:58", "remaining_time": "12:05:19", "throughput": 825.09, "total_tokens": 3859792}
+{"current_steps": 335, "total_steps": 3400, "loss": 0.9063, "lr": 9.935750420309055e-05, "epoch": 0.17254699974246718, "percentage": 9.85, "elapsed_time": "1:19:05", "remaining_time": "12:03:41", "throughput": 825.61, "total_tokens": 3918272}
+{"current_steps": 340, "total_steps": 3400, "loss": 0.8952, "lr": 9.931806517013612e-05, "epoch": 0.17512232809683234, "percentage": 10.0, "elapsed_time": "1:20:14", "remaining_time": "12:02:06", "throughput": 826.07, "total_tokens": 3976760}
+{"current_steps": 345, "total_steps": 3400, "loss": 0.9136, "lr": 9.927745975766654e-05, "epoch": 0.17769765645119753, "percentage": 10.15, "elapsed_time": "1:21:22", "remaining_time": "12:00:30", "throughput": 826.55, "total_tokens": 4035240}
+{"current_steps": 350, "total_steps": 3400, "loss": 0.9075, "lr": 9.923568892600578e-05, "epoch": 0.1802729848055627, "percentage": 10.29, "elapsed_time": "1:22:30", "remaining_time": "11:59:02", "throughput": 826.88, "total_tokens": 4093688}
+{"current_steps": 350, "total_steps": 3400, "eval_loss": 0.89204341173172, "epoch": 0.1802729848055627, "percentage": 10.29, "elapsed_time": "1:22:47", "remaining_time": "12:01:26", "throughput": 824.12, "total_tokens": 4093688}