Training in progress, step 900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14710faa050ccd0b26aca822951abad2137e1b1b89898b43fac9eca824b78600
+oid sha256:caa180618f6c269e58295b781cc1250fd6faaa22c17ed568072318c6e4db345b
 size 1074144

trainer_log.jsonl

@@ -190,3 +190,12 @@
 {"current_steps": 855, "total_steps": 900, "eval_loss": 0.02903667651116848, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "0:02:24", "remaining_time": "0:00:07", "throughput": 1842.14, "total_tokens": 267040}
 {"current_steps": 860, "total_steps": 900, "loss": 0.0706, "lr": 3.1542206734221924e-07, "epoch": 9.555555555555555, "percentage": 95.56, "elapsed_time": "0:02:26", "remaining_time": "0:00:06", "throughput": 1833.61, "total_tokens": 268576}
 {"current_steps": 865, "total_steps": 900, "loss": 0.0009, "lr": 2.4329828146074095e-07, "epoch": 9.61111111111111, "percentage": 96.11, "elapsed_time": "0:02:27", "remaining_time": "0:00:05", "throughput": 1835.68, "total_tokens": 270144}
+{"current_steps": 870, "total_steps": 900, "loss": 0.0007, "lr": 1.8048447862070718e-07, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:02:27", "remaining_time": "0:00:05", "throughput": 1837.34, "total_tokens": 271648}
+{"current_steps": 875, "total_steps": 900, "loss": 0.0035, "lr": 1.2700428052447033e-07, "epoch": 9.722222222222221, "percentage": 97.22, "elapsed_time": "0:02:28", "remaining_time": "0:00:04", "throughput": 1839.87, "total_tokens": 273280}
+{"current_steps": 880, "total_steps": 900, "loss": 0.0642, "lr": 8.28777988873486e-08, "epoch": 9.777777777777779, "percentage": 97.78, "elapsed_time": "0:02:29", "remaining_time": "0:00:03", "throughput": 1842.09, "total_tokens": 274880}
+{"current_steps": 885, "total_steps": 900, "loss": 0.0019, "lr": 4.8121627874450625e-08, "epoch": 9.833333333333334, "percentage": 98.33, "elapsed_time": "0:02:29", "remaining_time": "0:00:02", "throughput": 1844.34, "total_tokens": 276480}
+{"current_steps": 890, "total_steps": 900, "loss": 0.0369, "lr": 2.2748837860270267e-08, "epoch": 9.88888888888889, "percentage": 98.89, "elapsed_time": "0:02:30", "remaining_time": "0:00:01", "throughput": 1846.55, "total_tokens": 278080}
+{"current_steps": 895, "total_steps": 900, "loss": 0.0096, "lr": 6.768970513457151e-09, "epoch": 9.944444444444445, "percentage": 99.44, "elapsed_time": "0:02:31", "remaining_time": "0:00:00", "throughput": 1848.92, "total_tokens": 279680}
+{"current_steps": 900, "total_steps": 900, "loss": 0.0802, "lr": 1.8803520859811406e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:32", "remaining_time": "0:00:00", "throughput": 1850.65, "total_tokens": 281312}
+{"current_steps": 900, "total_steps": 900, "eval_loss": 0.028846707195043564, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:32", "remaining_time": "0:00:00", "throughput": 1843.61, "total_tokens": 281312}
+{"current_steps": 900, "total_steps": 900, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:33", "remaining_time": "0:00:00", "throughput": 1834.51, "total_tokens": 281312}