Training in progress, step 114

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:459ad9538f7f03af8d5d226ab8ed12a5d25cd63247154296682f7c4805414ea3
+oid sha256:9fcf8e252a6d74f3bc1c6af88abc6124819a3ba197eeebc54057053f6ba19dd9
 size 798032

trainer_log.jsonl

@@ -16,3 +16,12 @@
 {"current_steps": 75, "total_steps": 1140, "loss": 1.1615, "lr": 3.24561403508772e-05, "epoch": 1.3157894736842106, "percentage": 6.58, "elapsed_time": "0:00:17", "remaining_time": "0:04:09", "throughput": 2624.29, "total_tokens": 46112}
 {"current_steps": 80, "total_steps": 1140, "loss": 1.1548, "lr": 3.4649122807017546e-05, "epoch": 1.4035087719298245, "percentage": 7.02, "elapsed_time": "0:00:18", "remaining_time": "0:04:08", "throughput": 2651.59, "total_tokens": 49632}
 {"current_steps": 85, "total_steps": 1140, "loss": 1.0904, "lr": 3.6842105263157895e-05, "epoch": 1.4912280701754386, "percentage": 7.46, "elapsed_time": "0:00:19", "remaining_time": "0:04:06", "throughput": 2672.14, "total_tokens": 53024}
+{"current_steps": 90, "total_steps": 1140, "loss": 1.0917, "lr": 3.9035087719298244e-05, "epoch": 1.5789473684210527, "percentage": 7.89, "elapsed_time": "0:00:21", "remaining_time": "0:04:05", "throughput": 2696.78, "total_tokens": 56672}
+{"current_steps": 95, "total_steps": 1140, "loss": 1.1794, "lr": 4.12280701754386e-05, "epoch": 1.6666666666666665, "percentage": 8.33, "elapsed_time": "0:00:21", "remaining_time": "0:04:01", "throughput": 2705.05, "total_tokens": 59296}
+{"current_steps": 100, "total_steps": 1140, "loss": 1.098, "lr": 4.342105263157895e-05, "epoch": 1.7543859649122808, "percentage": 8.77, "elapsed_time": "0:00:23", "remaining_time": "0:03:59", "throughput": 2715.98, "total_tokens": 62528}
+{"current_steps": 105, "total_steps": 1140, "loss": 0.6296, "lr": 4.56140350877193e-05, "epoch": 1.8421052631578947, "percentage": 9.21, "elapsed_time": "0:00:24", "remaining_time": "0:03:57", "throughput": 2731.14, "total_tokens": 65856}
+{"current_steps": 110, "total_steps": 1140, "loss": 0.7728, "lr": 4.780701754385965e-05, "epoch": 1.9298245614035088, "percentage": 9.65, "elapsed_time": "0:00:25", "remaining_time": "0:03:57", "throughput": 2747.93, "total_tokens": 69664}
+{"current_steps": 114, "total_steps": 1140, "eval_loss": 0.47614240646362305, "epoch": 2.0, "percentage": 10.0, "elapsed_time": "0:00:26", "remaining_time": "0:04:01", "throughput": 2684.58, "total_tokens": 72112}
+{"current_steps": 115, "total_steps": 1140, "loss": 0.7205, "lr": 5e-05, "epoch": 2.017543859649123, "percentage": 10.09, "elapsed_time": "0:00:28", "remaining_time": "0:04:09", "throughput": 2599.59, "total_tokens": 72848}
+{"current_steps": 120, "total_steps": 1140, "loss": 0.4737, "lr": 4.999707014206475e-05, "epoch": 2.1052631578947367, "percentage": 10.53, "elapsed_time": "0:00:29", "remaining_time": "0:04:06", "throughput": 2613.07, "total_tokens": 75888}
+{"current_steps": 125, "total_steps": 1140, "loss": 0.2419, "lr": 4.9988281254984414e-05, "epoch": 2.192982456140351, "percentage": 10.96, "elapsed_time": "0:00:30", "remaining_time": "0:04:04", "throughput": 2624.32, "total_tokens": 78896}