Training in progress, step 2750

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b583b602b9e38c1b3b50b506d83107d06e11e7b44aab1de71c95fee8b4886d2
+oid sha256:0d165d56eef70a9fc2fbabc08f8c0eb0b8489e0f49da8222e1fc3acf534edf4b
 size 29034840

trainer_log.jsonl

@@ -595,3 +595,14 @@
 {"current_steps": 2695, "total_steps": 3400, "loss": 0.2881, "lr": 1.1301316554235397e-05, "epoch": 0.6940509915014165, "percentage": 79.26, "elapsed_time": "0:45:16", "remaining_time": "0:11:50", "throughput": 10416.26, "total_tokens": 28299864}
 {"current_steps": 2700, "total_steps": 3400, "loss": 0.3076, "lr": 1.114780323312724e-05, "epoch": 0.695338655678599, "percentage": 79.41, "elapsed_time": "0:46:42", "remaining_time": "0:12:06", "throughput": 10115.15, "total_tokens": 28352368}
 {"current_steps": 2700, "total_steps": 3400, "eval_loss": 0.4338160753250122, "epoch": 0.695338655678599, "percentage": 79.41, "elapsed_time": "0:47:21", "remaining_time": "0:12:16", "throughput": 9977.7, "total_tokens": 28352368}
+{"current_steps": 2705, "total_steps": 3400, "loss": 0.3024, "lr": 1.0995208772202897e-05, "epoch": 0.6966263198557816, "percentage": 79.56, "elapsed_time": "0:48:55", "remaining_time": "0:12:34", "throughput": 9675.61, "total_tokens": 28404360}
+{"current_steps": 2710, "total_steps": 3400, "loss": 0.2668, "lr": 1.0843536780343865e-05, "epoch": 0.6979139840329642, "percentage": 79.71, "elapsed_time": "0:50:21", "remaining_time": "0:12:49", "throughput": 9417.24, "total_tokens": 28456960}
+{"current_steps": 2715, "total_steps": 3400, "loss": 0.3344, "lr": 1.069279084461513e-05, "epoch": 0.6992016482101467, "percentage": 79.85, "elapsed_time": "0:51:49", "remaining_time": "0:13:04", "throughput": 9167.45, "total_tokens": 28509448}
+{"current_steps": 2720, "total_steps": 3400, "loss": 0.2942, "lr": 1.0542974530180327e-05, "epoch": 0.7004893123873294, "percentage": 80.0, "elapsed_time": "0:53:15", "remaining_time": "0:13:18", "throughput": 8937.08, "total_tokens": 28561496}
+{"current_steps": 2725, "total_steps": 3400, "loss": 0.3209, "lr": 1.0394091380217352e-05, "epoch": 0.701776976564512, "percentage": 80.15, "elapsed_time": "0:54:43", "remaining_time": "0:13:33", "throughput": 8714.68, "total_tokens": 28613224}
+{"current_steps": 2730, "total_steps": 3400, "loss": 0.3021, "lr": 1.0246144915834683e-05, "epoch": 0.7030646407416946, "percentage": 80.29, "elapsed_time": "0:56:08", "remaining_time": "0:13:46", "throughput": 8509.05, "total_tokens": 28665360}
+{"current_steps": 2735, "total_steps": 3400, "loss": 0.211, "lr": 1.0099138635988026e-05, "epoch": 0.7043523049188771, "percentage": 80.44, "elapsed_time": "0:57:35", "remaining_time": "0:14:00", "throughput": 8311.14, "total_tokens": 28719488}
+{"current_steps": 2740, "total_steps": 3400, "loss": 0.3017, "lr": 9.953076017397578e-06, "epoch": 0.7056399690960597, "percentage": 80.59, "elapsed_time": "0:59:02", "remaining_time": "0:14:13", "throughput": 8122.35, "total_tokens": 28771880}
+{"current_steps": 2745, "total_steps": 3400, "loss": 0.3022, "lr": 9.807960514465792e-06, "epoch": 0.7069276332732424, "percentage": 80.74, "elapsed_time": "1:00:29", "remaining_time": "0:14:25", "throughput": 7942.62, "total_tokens": 28825096}
+{"current_steps": 2750, "total_steps": 3400, "loss": 0.2817, "lr": 9.663795559195733e-06, "epoch": 0.7082152974504249, "percentage": 80.88, "elapsed_time": "1:01:54", "remaining_time": "0:14:38", "throughput": 7773.58, "total_tokens": 28877960}
+{"current_steps": 2750, "total_steps": 3400, "eval_loss": 0.4439634680747986, "epoch": 0.7082152974504249, "percentage": 80.88, "elapsed_time": "1:02:33", "remaining_time": "0:14:47", "throughput": 7693.75, "total_tokens": 28877960}