Training in progress, step 900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:225f72ff9b7f9c853fb09c800c12132526a5daf835bf208974c3ab84a3d509ea
+oid sha256:2218b044a084d407654e159e8bd2f281745eb1fcc7181c35351d205ef1013095
 size 798032

trainer_log.jsonl

@@ -190,3 +190,12 @@
 {"current_steps": 855, "total_steps": 900, "eval_loss": 0.03170046582818031, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "0:02:33", "remaining_time": "0:00:08", "throughput": 1736.37, "total_tokens": 267040}
 {"current_steps": 860, "total_steps": 900, "loss": 0.1207, "lr": 3.1542206734221924e-07, "epoch": 9.555555555555555, "percentage": 95.56, "elapsed_time": "0:02:35", "remaining_time": "0:00:07", "throughput": 1729.88, "total_tokens": 268576}
 {"current_steps": 865, "total_steps": 900, "loss": 0.0059, "lr": 2.4329828146074095e-07, "epoch": 9.61111111111111, "percentage": 96.11, "elapsed_time": "0:02:35", "remaining_time": "0:00:06", "throughput": 1731.75, "total_tokens": 270144}
+{"current_steps": 870, "total_steps": 900, "loss": 0.0237, "lr": 1.8048447862070718e-07, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:02:36", "remaining_time": "0:00:05", "throughput": 1733.24, "total_tokens": 271648}
+{"current_steps": 875, "total_steps": 900, "loss": 0.0611, "lr": 1.2700428052447033e-07, "epoch": 9.722222222222221, "percentage": 97.22, "elapsed_time": "0:02:37", "remaining_time": "0:00:04", "throughput": 1735.52, "total_tokens": 273280}
+{"current_steps": 880, "total_steps": 900, "loss": 0.1409, "lr": 8.28777988873486e-08, "epoch": 9.777777777777779, "percentage": 97.78, "elapsed_time": "0:02:38", "remaining_time": "0:00:03", "throughput": 1737.59, "total_tokens": 274880}
+{"current_steps": 885, "total_steps": 900, "loss": 0.022, "lr": 4.8121627874450625e-08, "epoch": 9.833333333333334, "percentage": 98.33, "elapsed_time": "0:02:38", "remaining_time": "0:00:02", "throughput": 1739.62, "total_tokens": 276480}
+{"current_steps": 890, "total_steps": 900, "loss": 0.0872, "lr": 2.2748837860270267e-08, "epoch": 9.88888888888889, "percentage": 98.89, "elapsed_time": "0:02:39", "remaining_time": "0:00:01", "throughput": 1741.64, "total_tokens": 278080}
+{"current_steps": 895, "total_steps": 900, "loss": 0.0503, "lr": 6.768970513457151e-09, "epoch": 9.944444444444445, "percentage": 99.44, "elapsed_time": "0:02:40", "remaining_time": "0:00:00", "throughput": 1743.77, "total_tokens": 279680}
+{"current_steps": 900, "total_steps": 900, "loss": 0.1442, "lr": 1.8803520859811406e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:41", "remaining_time": "0:00:00", "throughput": 1745.2, "total_tokens": 281312}
+{"current_steps": 900, "total_steps": 900, "eval_loss": 0.0329829640686512, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:41", "remaining_time": "0:00:00", "throughput": 1738.68, "total_tokens": 281312}
+{"current_steps": 900, "total_steps": 900, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:42", "remaining_time": "0:00:00", "throughput": 1730.02, "total_tokens": 281312}