Training in progress, step 1140

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14178f1e88151c4b2244cf2a2b2bb1d384e0b39c8fd2470adb03d7285fb53d21
+oid sha256:ad45acf3051a1d5eb066faf0e4eaf9f80f8f0cbf9263424df46770082f4c5d4c
 size 819328

trainer_log.jsonl

@@ -235,3 +235,15 @@
 {"current_steps": 1083, "total_steps": 1140, "eval_loss": 0.17038847506046295, "epoch": 19.0, "percentage": 95.0, "elapsed_time": "0:04:36", "remaining_time": "0:00:14", "throughput": 2496.65, "total_tokens": 689856}
 {"current_steps": 1085, "total_steps": 1140, "loss": 0.0351, "lr": 0.00021997735521649408, "epoch": 19.035087719298247, "percentage": 95.18, "elapsed_time": "0:04:37", "remaining_time": "0:00:14", "throughput": 2490.06, "total_tokens": 691200}
 {"current_steps": 1090, "total_steps": 1140, "loss": 0.0203, "lr": 0.00018252564485670973, "epoch": 19.12280701754386, "percentage": 95.61, "elapsed_time": "0:04:38", "remaining_time": "0:00:12", "throughput": 2490.87, "total_tokens": 694240}
+{"current_steps": 1095, "total_steps": 1140, "loss": 0.0152, "lr": 0.00014854698208250638, "epoch": 19.210526315789473, "percentage": 96.05, "elapsed_time": "0:04:39", "remaining_time": "0:00:11", "throughput": 2492.27, "total_tokens": 697472}
+{"current_steps": 1100, "total_steps": 1140, "loss": 0.0162, "lr": 0.00011804933110626359, "epoch": 19.29824561403509, "percentage": 96.49, "elapsed_time": "0:04:40", "remaining_time": "0:00:10", "throughput": 2491.83, "total_tokens": 699872}
+{"current_steps": 1105, "total_steps": 1140, "loss": 0.0398, "lr": 9.103984023075773e-05, "epoch": 19.385964912280702, "percentage": 96.93, "elapsed_time": "0:04:42", "remaining_time": "0:00:08", "throughput": 2496.56, "total_tokens": 704736}
+{"current_steps": 1110, "total_steps": 1140, "loss": 0.0059, "lr": 6.752484017368553e-05, "epoch": 19.473684210526315, "percentage": 97.37, "elapsed_time": "0:04:43", "remaining_time": "0:00:07", "throughput": 2497.91, "total_tokens": 707968}
+{"current_steps": 1115, "total_steps": 1140, "loss": 0.0162, "lr": 4.750984258380608e-05, "epoch": 19.56140350877193, "percentage": 97.81, "elapsed_time": "0:04:44", "remaining_time": "0:00:06", "throughput": 2499.2, "total_tokens": 711136}
+{"current_steps": 1120, "total_steps": 1140, "loss": 0.0065, "lr": 3.099953874908079e-05, "epoch": 19.649122807017545, "percentage": 98.25, "elapsed_time": "0:04:45", "remaining_time": "0:00:05", "throughput": 2500.74, "total_tokens": 714432}
+{"current_steps": 1125, "total_steps": 1140, "loss": 0.0208, "lr": 1.7997798497084714e-05, "epoch": 19.736842105263158, "percentage": 98.68, "elapsed_time": "0:04:46", "remaining_time": "0:00:03", "throughput": 2501.62, "total_tokens": 717440}
+{"current_steps": 1130, "total_steps": 1140, "loss": 0.035, "lr": 8.50766928796709e-06, "epoch": 19.82456140350877, "percentage": 99.12, "elapsed_time": "0:04:47", "remaining_time": "0:00:02", "throughput": 2502.67, "total_tokens": 720480}
+{"current_steps": 1135, "total_steps": 1140, "loss": 0.0293, "lr": 2.5313755001593604e-06, "epoch": 19.912280701754387, "percentage": 99.56, "elapsed_time": "0:04:48", "remaining_time": "0:00:01", "throughput": 2503.82, "total_tokens": 723552}
+{"current_steps": 1140, "total_steps": 1140, "loss": 0.0121, "lr": 7.03179089989181e-08, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:04:49", "remaining_time": "0:00:00", "throughput": 2503.65, "total_tokens": 725992}
+{"current_steps": 1140, "total_steps": 1140, "eval_loss": 0.16927888989448547, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:04:50", "remaining_time": "0:00:00", "throughput": 2496.65, "total_tokens": 725992}
+{"current_steps": 1140, "total_steps": 1140, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:04:51", "remaining_time": "0:00:00", "throughput": 2490.33, "total_tokens": 725992}