Training in progress, step 450

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5682b2eafe76e843b3c252d9efdff6d8e222ea2c09fcb985ed44476c6c49d3c0
+oid sha256:3e3aaf9e6c8d830995b2a237a6a326491ecc141ce2f9713c7cafa4ab230f17cb
 size 29034840

trainer_log.jsonl

@@ -87,3 +87,14 @@
 {"current_steps": 395, "total_steps": 6770, "loss": 0.6137, "lr": 9.998129181291936e-05, "epoch": 0.11669128508124077, "percentage": 5.83, "elapsed_time": "1:58:57", "remaining_time": "1 day, 7:59:58", "throughput": 573.13, "total_tokens": 4090872}
 {"current_steps": 400, "total_steps": 6770, "loss": 0.6739, "lr": 9.997780218295185e-05, "epoch": 0.11816838995568685, "percentage": 5.91, "elapsed_time": "2:00:25", "remaining_time": "1 day, 7:57:39", "throughput": 573.36, "total_tokens": 4142592}
 {"current_steps": 400, "total_steps": 6770, "eval_loss": 0.7038857936859131, "epoch": 0.11816838995568685, "percentage": 5.91, "elapsed_time": "2:00:44", "remaining_time": "1 day, 8:02:42", "throughput": 571.85, "total_tokens": 4142592}
+{"current_steps": 405, "total_steps": 6770, "loss": 0.6209, "lr": 9.997401438591772e-05, "epoch": 0.11964549483013294, "percentage": 5.98, "elapsed_time": "2:02:16", "remaining_time": "1 day, 8:01:36", "throughput": 571.81, "total_tokens": 4194920}
+{"current_steps": 410, "total_steps": 6770, "loss": 0.6576, "lr": 9.996992844441495e-05, "epoch": 0.12112259970457903, "percentage": 6.06, "elapsed_time": "2:03:44", "remaining_time": "1 day, 7:59:30", "throughput": 572.03, "total_tokens": 4247048}
+{"current_steps": 415, "total_steps": 6770, "loss": 0.6851, "lr": 9.996554438282022e-05, "epoch": 0.12259970457902511, "percentage": 6.13, "elapsed_time": "2:05:11", "remaining_time": "1 day, 7:57:04", "throughput": 572.42, "total_tokens": 4299728}
+{"current_steps": 420, "total_steps": 6770, "loss": 0.6288, "lr": 9.996086222728879e-05, "epoch": 0.1240768094534712, "percentage": 6.2, "elapsed_time": "2:06:39", "remaining_time": "1 day, 7:55:03", "throughput": 572.52, "total_tokens": 4351088}
+{"current_steps": 425, "total_steps": 6770, "loss": 0.667, "lr": 9.995588200575439e-05, "epoch": 0.1255539143279173, "percentage": 6.28, "elapsed_time": "2:08:05", "remaining_time": "1 day, 7:52:16", "throughput": 572.92, "total_tokens": 4403016}
+{"current_steps": 430, "total_steps": 6770, "loss": 0.6747, "lr": 9.995060374792892e-05, "epoch": 0.12703101920236337, "percentage": 6.35, "elapsed_time": "2:09:31", "remaining_time": "1 day, 7:49:50", "throughput": 573.07, "total_tokens": 4453880}
+{"current_steps": 435, "total_steps": 6770, "loss": 0.6594, "lr": 9.994502748530244e-05, "epoch": 0.12850812407680945, "percentage": 6.43, "elapsed_time": "2:10:57", "remaining_time": "1 day, 7:47:14", "throughput": 573.4, "total_tokens": 4505616}
+{"current_steps": 440, "total_steps": 6770, "loss": 0.6727, "lr": 9.993915325114288e-05, "epoch": 0.12998522895125553, "percentage": 6.5, "elapsed_time": "2:12:24", "remaining_time": "1 day, 7:44:55", "throughput": 573.77, "total_tokens": 4558384}
+{"current_steps": 445, "total_steps": 6770, "loss": 0.6526, "lr": 9.993298108049582e-05, "epoch": 0.13146233382570163, "percentage": 6.57, "elapsed_time": "2:13:50", "remaining_time": "1 day, 7:42:20", "throughput": 574.21, "total_tokens": 4611184}
+{"current_steps": 450, "total_steps": 6770, "loss": 0.5661, "lr": 9.992651101018445e-05, "epoch": 0.1329394387001477, "percentage": 6.65, "elapsed_time": "2:15:17", "remaining_time": "1 day, 7:40:00", "throughput": 574.5, "total_tokens": 4663320}
+{"current_steps": 450, "total_steps": 6770, "eval_loss": 0.7132604718208313, "epoch": 0.1329394387001477, "percentage": 6.65, "elapsed_time": "2:15:36", "remaining_time": "1 day, 7:44:27", "throughput": 573.16, "total_tokens": 4663320}