Training in progress, step 840

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e62e5f1d80b4c775220a0b4078d1261f2c590d62e84fee60abd766c3b6de6546
+oid sha256:19be0b97bb3ebd74830f87dc60ad3eb7736722b2fd56d93df4d82c1c7da2e3ea
 size 13107328

trainer_log.jsonl

@@ -178,3 +178,12 @@
 {"current_steps": 798, "total_steps": 840, "eval_loss": 0.35238173604011536, "epoch": 28.5, "percentage": 95.0, "elapsed_time": "0:04:51", "remaining_time": "0:00:15", "throughput": 4787.04, "total_tokens": 1394904}
 {"current_steps": 800, "total_steps": 840, "loss": 0.3513, "lr": 8.113961028402894e-07, "epoch": 28.571428571428573, "percentage": 95.24, "elapsed_time": "0:04:54", "remaining_time": "0:00:14", "throughput": 4746.34, "total_tokens": 1399256}
 {"current_steps": 805, "total_steps": 840, "loss": 0.35, "lr": 6.259506412906402e-07, "epoch": 28.75, "percentage": 95.83, "elapsed_time": "0:04:56", "remaining_time": "0:00:12", "throughput": 4755.48, "total_tokens": 1407896}
+{"current_steps": 810, "total_steps": 840, "loss": 0.338, "lr": 4.6440114404492363e-07, "epoch": 28.928571428571427, "percentage": 96.43, "elapsed_time": "0:04:57", "remaining_time": "0:00:11", "throughput": 4764.59, "total_tokens": 1416472}
+{"current_steps": 815, "total_steps": 840, "loss": 0.3438, "lr": 3.268257975405697e-07, "epoch": 29.107142857142858, "percentage": 97.02, "elapsed_time": "0:04:58", "remaining_time": "0:00:09", "throughput": 4766.77, "total_tokens": 1425120}
+{"current_steps": 820, "total_steps": 840, "loss": 0.3419, "lr": 2.1329118524827662e-07, "epoch": 29.285714285714285, "percentage": 97.62, "elapsed_time": "0:05:00", "remaining_time": "0:00:07", "throughput": 4774.8, "total_tokens": 1433248}
+{"current_steps": 825, "total_steps": 840, "loss": 0.3417, "lr": 1.238522554470989e-07, "epoch": 29.464285714285715, "percentage": 98.21, "elapsed_time": "0:05:01", "remaining_time": "0:00:05", "throughput": 4784.81, "total_tokens": 1442592}
+{"current_steps": 830, "total_steps": 840, "loss": 0.3451, "lr": 5.855229463068712e-08, "epoch": 29.642857142857142, "percentage": 98.81, "elapsed_time": "0:05:02", "remaining_time": "0:00:03", "throughput": 4793.77, "total_tokens": 1451360}
+{"current_steps": 835, "total_steps": 840, "loss": 0.3525, "lr": 1.742290655755707e-08, "epoch": 29.821428571428573, "percentage": 99.4, "elapsed_time": "0:05:03", "remaining_time": "0:00:01", "throughput": 4802.17, "total_tokens": 1459808}
+{"current_steps": 840, "total_steps": 840, "loss": 0.3344, "lr": 4.839969555581192e-10, "epoch": 30.0, "percentage": 100.0, "elapsed_time": "0:05:05", "remaining_time": "0:00:00", "throughput": 4807.86, "total_tokens": 1468632}
+{"current_steps": 840, "total_steps": 840, "eval_loss": 0.3523610234260559, "epoch": 30.0, "percentage": 100.0, "elapsed_time": "0:05:06", "remaining_time": "0:00:00", "throughput": 4788.61, "total_tokens": 1468632}
+{"current_steps": 840, "total_steps": 840, "epoch": 30.0, "percentage": 100.0, "elapsed_time": "0:05:09", "remaining_time": "0:00:00", "throughput": 4744.79, "total_tokens": 1468632}