Training in progress, step 900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43157ea427c1a589b407f164b78ce7fef23c956fd051bb9195c65f1fec80b987
+oid sha256:c19d9a83a42d0c73cc5cd76a0514775a70992086be98433bad07b09606a857b2
 size 798032

trainer_log.jsonl

@@ -190,3 +190,12 @@
 {"current_steps": 855, "total_steps": 900, "eval_loss": 0.11859162151813507, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "0:02:35", "remaining_time": "0:00:08", "throughput": 1716.93, "total_tokens": 267840}
 {"current_steps": 860, "total_steps": 900, "loss": 0.0237, "lr": 3.1542206734221924e-07, "epoch": 9.555555555555555, "percentage": 95.56, "elapsed_time": "0:02:37", "remaining_time": "0:00:07", "throughput": 1708.74, "total_tokens": 269376}
 {"current_steps": 865, "total_steps": 900, "loss": 0.1186, "lr": 2.4329828146074095e-07, "epoch": 9.61111111111111, "percentage": 96.11, "elapsed_time": "0:02:38", "remaining_time": "0:00:06", "throughput": 1710.82, "total_tokens": 270944}
+{"current_steps": 870, "total_steps": 900, "loss": 0.1139, "lr": 1.8048447862070718e-07, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:02:39", "remaining_time": "0:00:05", "throughput": 1712.49, "total_tokens": 272448}
+{"current_steps": 875, "total_steps": 900, "loss": 0.1073, "lr": 1.2700428052447033e-07, "epoch": 9.722222222222221, "percentage": 97.22, "elapsed_time": "0:02:39", "remaining_time": "0:00:04", "throughput": 1714.31, "total_tokens": 273984}
+{"current_steps": 880, "total_steps": 900, "loss": 0.0366, "lr": 8.28777988873486e-08, "epoch": 9.777777777777779, "percentage": 97.78, "elapsed_time": "0:02:40", "remaining_time": "0:00:03", "throughput": 1716.17, "total_tokens": 275520}
+{"current_steps": 885, "total_steps": 900, "loss": 0.0188, "lr": 4.8121627874450625e-08, "epoch": 9.833333333333334, "percentage": 98.33, "elapsed_time": "0:02:41", "remaining_time": "0:00:02", "throughput": 1718.65, "total_tokens": 277152}
+{"current_steps": 890, "total_steps": 900, "loss": 0.0931, "lr": 2.2748837860270267e-08, "epoch": 9.88888888888889, "percentage": 98.89, "elapsed_time": "0:02:41", "remaining_time": "0:00:01", "throughput": 1720.49, "total_tokens": 278688}
+{"current_steps": 895, "total_steps": 900, "loss": 0.0155, "lr": 6.768970513457151e-09, "epoch": 9.944444444444445, "percentage": 99.44, "elapsed_time": "0:02:42", "remaining_time": "0:00:00", "throughput": 1722.62, "total_tokens": 280256}
+{"current_steps": 900, "total_steps": 900, "loss": 0.0783, "lr": 1.8803520859811406e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:43", "remaining_time": "0:00:00", "throughput": 1724.23, "total_tokens": 281856}
+{"current_steps": 900, "total_steps": 900, "eval_loss": 0.1192222386598587, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:44", "remaining_time": "0:00:00", "throughput": 1718.2, "total_tokens": 281856}
+{"current_steps": 900, "total_steps": 900, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:44", "remaining_time": "0:00:00", "throughput": 1708.93, "total_tokens": 281856}