Training in progress, step 1150

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5dad64d30fcdb47a2e15bc593335933f84181ea038dde168b8ebbd434b58442
+oid sha256:9d7aab0cd9c4fe95e67375a76eb37d59d1f473e5a6c3091db1f696fc3d335f8c
 size 29034840

trainer_log.jsonl

@@ -240,3 +240,14 @@
 {"current_steps": 1095, "total_steps": 3882, "loss": 0.6087, "lr": 8.600445603256123e-05, "epoch": 0.5639969096059748, "percentage": 28.21, "elapsed_time": "5:36:14", "remaining_time": "14:15:47", "throughput": 634.84, "total_tokens": 12807504}
 {"current_steps": 1100, "total_steps": 3882, "loss": 0.5825, "lr": 8.585632030887658e-05, "epoch": 0.56657223796034, "percentage": 28.34, "elapsed_time": "5:37:42", "remaining_time": "14:14:05", "throughput": 634.96, "total_tokens": 12865992}
 {"current_steps": 1100, "total_steps": 3882, "eval_loss": 0.6431913375854492, "epoch": 0.56657223796034, "percentage": 28.34, "elapsed_time": "5:38:01", "remaining_time": "14:14:54", "throughput": 634.36, "total_tokens": 12865992}
+{"current_steps": 1105, "total_steps": 3882, "loss": 0.6113, "lr": 8.57075337687132e-05, "epoch": 0.5691475663147051, "percentage": 28.46, "elapsed_time": "5:39:34", "remaining_time": "14:13:24", "throughput": 634.34, "total_tokens": 12924448}
+{"current_steps": 1110, "total_steps": 3882, "loss": 0.562, "lr": 8.55580991126475e-05, "epoch": 0.5717228946690703, "percentage": 28.59, "elapsed_time": "5:41:02", "remaining_time": "14:11:41", "throughput": 634.47, "total_tokens": 12982912}
+{"current_steps": 1115, "total_steps": 3882, "loss": 0.6124, "lr": 8.540801905301963e-05, "epoch": 0.5742982230234355, "percentage": 28.72, "elapsed_time": "5:42:30", "remaining_time": "14:09:57", "throughput": 634.62, "total_tokens": 13041424}
+{"current_steps": 1120, "total_steps": 3882, "loss": 0.6788, "lr": 8.525729631388421e-05, "epoch": 0.5768735513778007, "percentage": 28.85, "elapsed_time": "5:43:59", "remaining_time": "14:08:17", "throughput": 634.71, "total_tokens": 13099888}
+{"current_steps": 1125, "total_steps": 3882, "loss": 0.5904, "lr": 8.510593363096097e-05, "epoch": 0.5794488797321659, "percentage": 28.98, "elapsed_time": "5:45:26", "remaining_time": "14:06:34", "throughput": 634.85, "total_tokens": 13158344}
+{"current_steps": 1130, "total_steps": 3882, "loss": 0.5433, "lr": 8.495393375158504e-05, "epoch": 0.582024208086531, "percentage": 29.11, "elapsed_time": "5:46:55", "remaining_time": "14:04:54", "throughput": 634.95, "total_tokens": 13216840}
+{"current_steps": 1135, "total_steps": 3882, "loss": 0.5937, "lr": 8.480129943465709e-05, "epoch": 0.5845995364408962, "percentage": 29.24, "elapsed_time": "5:48:22", "remaining_time": "14:03:09", "throughput": 635.11, "total_tokens": 13275328}
+{"current_steps": 1140, "total_steps": 3882, "loss": 0.5785, "lr": 8.464803345059324e-05, "epoch": 0.5871748647952614, "percentage": 29.37, "elapsed_time": "5:49:50", "remaining_time": "14:01:28", "throughput": 635.22, "total_tokens": 13333784}
+{"current_steps": 1145, "total_steps": 3882, "loss": 0.5472, "lr": 8.449413858127487e-05, "epoch": 0.5897501931496266, "percentage": 29.5, "elapsed_time": "5:51:17", "remaining_time": "13:59:44", "throughput": 635.37, "total_tokens": 13392280}
+{"current_steps": 1150, "total_steps": 3882, "loss": 0.5228, "lr": 8.433961761999796e-05, "epoch": 0.5923255215039918, "percentage": 29.62, "elapsed_time": "5:52:45", "remaining_time": "13:58:03", "throughput": 635.49, "total_tokens": 13450720}
+{"current_steps": 1150, "total_steps": 3882, "eval_loss": 0.6229755282402039, "epoch": 0.5923255215039918, "percentage": 29.62, "elapsed_time": "5:53:05", "remaining_time": "13:58:49", "throughput": 634.91, "total_tokens": 13450720}