Training in progress, step 2800

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d165d56eef70a9fc2fbabc08f8c0eb0b8489e0f49da8222e1fc3acf534edf4b
+oid sha256:656b339f848f4a5e39a2f325df5573bc98a1ce1de9df8113a07cd8eeae54367e
 size 29034840

trainer_log.jsonl

@@ -606,3 +606,14 @@
 {"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}
+{"current_steps": 2755, "total_steps": 3400, "loss": 0.2854, "lr": 9.520584561109864e-06, "epoch": 0.7095029616276075, "percentage": 81.03, "elapsed_time": "1:04:05", "remaining_time": "0:15:00", "throughput": 7523.08, "total_tokens": 28930512}
+{"current_steps": 2760, "total_steps": 3400, "loss": 0.3635, "lr": 9.378330907169386e-06, "epoch": 0.7107906258047901, "percentage": 81.18, "elapsed_time": "1:05:32", "remaining_time": "0:15:11", "throughput": 7369.7, "total_tokens": 28984048}
+{"current_steps": 2765, "total_steps": 3400, "loss": 0.3276, "lr": 9.237037961694223e-06, "epoch": 0.7120782899819728, "percentage": 81.32, "elapsed_time": "1:06:59", "remaining_time": "0:15:23", "throughput": 7223.95, "total_tokens": 29034368}
+{"current_steps": 2770, "total_steps": 3400, "loss": 0.2939, "lr": 9.096709066283354e-06, "epoch": 0.7133659541591553, "percentage": 81.47, "elapsed_time": "1:08:26", "remaining_time": "0:15:33", "throughput": 7082.87, "total_tokens": 29086720}
+{"current_steps": 2775, "total_steps": 3400, "loss": 0.2814, "lr": 8.957347539735872e-06, "epoch": 0.7146536183363379, "percentage": 81.62, "elapsed_time": "1:09:52", "remaining_time": "0:15:44", "throughput": 6950.08, "total_tokens": 29139744}
+{"current_steps": 2780, "total_steps": 3400, "loss": 0.3773, "lr": 8.818956677972406e-06, "epoch": 0.7159412825135205, "percentage": 81.76, "elapsed_time": "1:11:20", "remaining_time": "0:15:54", "throughput": 6819.86, "total_tokens": 29192168}
+{"current_steps": 2785, "total_steps": 3400, "loss": 0.3126, "lr": 8.681539753957269e-06, "epoch": 0.717228946690703, "percentage": 81.91, "elapsed_time": "1:12:46", "remaining_time": "0:16:04", "throughput": 6697.07, "total_tokens": 29244896}
+{"current_steps": 2790, "total_steps": 3400, "loss": 0.3038, "lr": 8.545100017620988e-06, "epoch": 0.7185166108678857, "percentage": 82.06, "elapsed_time": "1:14:14", "remaining_time": "0:16:13", "throughput": 6577.22, "total_tokens": 29297424}
+{"current_steps": 2795, "total_steps": 3400, "loss": 0.308, "lr": 8.409640695783443e-06, "epoch": 0.7198042750450683, "percentage": 82.21, "elapsed_time": "1:15:40", "remaining_time": "0:16:22", "throughput": 6464.36, "total_tokens": 29349664}
+{"current_steps": 2800, "total_steps": 3400, "loss": 0.3567, "lr": 8.275164992077556e-06, "epoch": 0.7210919392222508, "percentage": 82.35, "elapsed_time": "1:17:08", "remaining_time": "0:16:31", "throughput": 6353.06, "total_tokens": 29402040}
+{"current_steps": 2800, "total_steps": 3400, "eval_loss": 0.4282406270503998, "epoch": 0.7210919392222508, "percentage": 82.35, "elapsed_time": "1:17:46", "remaining_time": "0:16:39", "throughput": 6301.28, "total_tokens": 29402040}