Training in progress, step 400

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:886e83225731329ec8fecf2885b7ea9c6656cc91593fafb84eb477c2dda182a4
+oid sha256:5682b2eafe76e843b3c252d9efdff6d8e222ea2c09fcb985ed44476c6c49d3c0
 size 29034840

trainer_log.jsonl

@@ -76,3 +76,14 @@
 {"current_steps": 345, "total_steps": 6770, "loss": 0.7252, "lr": 9.999978522440803e-05, "epoch": 0.1019202363367799, "percentage": 5.1, "elapsed_time": "1:44:08", "remaining_time": "1 day, 8:19:27", "throughput": 571.96, "total_tokens": 3573880}
 {"current_steps": 350, "total_steps": 6770, "loss": 0.6602, "lr": 9.999927811659165e-05, "epoch": 0.103397341211226, "percentage": 5.17, "elapsed_time": "1:45:35", "remaining_time": "1 day, 8:16:42", "throughput": 572.33, "total_tokens": 3625752}
 {"current_steps": 350, "total_steps": 6770, "eval_loss": 0.7663387656211853, "epoch": 0.103397341211226, "percentage": 5.17, "elapsed_time": "1:45:54", "remaining_time": "1 day, 8:22:34", "throughput": 570.6, "total_tokens": 3625752}
+{"current_steps": 355, "total_steps": 6770, "loss": 0.7222, "lr": 9.999847271358347e-05, "epoch": 0.10487444608567208, "percentage": 5.24, "elapsed_time": "1:47:27", "remaining_time": "1 day, 8:21:42", "throughput": 570.33, "total_tokens": 3676984}
+{"current_steps": 360, "total_steps": 6770, "loss": 0.6639, "lr": 9.99973690201885e-05, "epoch": 0.10635155096011817, "percentage": 5.32, "elapsed_time": "1:48:53", "remaining_time": "1 day, 8:18:51", "throughput": 570.78, "total_tokens": 3729168}
+{"current_steps": 365, "total_steps": 6770, "loss": 0.6501, "lr": 9.999596704299139e-05, "epoch": 0.10782865583456426, "percentage": 5.39, "elapsed_time": "1:50:20", "remaining_time": "1 day, 8:16:15", "throughput": 571.06, "total_tokens": 3780672}
+{"current_steps": 370, "total_steps": 6770, "loss": 0.6871, "lr": 9.999426679035628e-05, "epoch": 0.10930576070901034, "percentage": 5.47, "elapsed_time": "1:51:46", "remaining_time": "1 day, 8:13:25", "throughput": 571.43, "total_tokens": 3832328}
+{"current_steps": 375, "total_steps": 6770, "loss": 0.6621, "lr": 9.99922682724269e-05, "epoch": 0.11078286558345643, "percentage": 5.54, "elapsed_time": "1:53:12", "remaining_time": "1 day, 8:10:41", "throughput": 571.64, "total_tokens": 3883112}
+{"current_steps": 380, "total_steps": 6770, "loss": 0.7156, "lr": 9.998997150112635e-05, "epoch": 0.11225997045790251, "percentage": 5.61, "elapsed_time": "1:54:39", "remaining_time": "1 day, 8:08:06", "throughput": 571.98, "total_tokens": 3934976}
+{"current_steps": 385, "total_steps": 6770, "loss": 0.6662, "lr": 9.998737649015718e-05, "epoch": 0.1137370753323486, "percentage": 5.69, "elapsed_time": "1:56:05", "remaining_time": "1 day, 8:05:13", "throughput": 572.3, "total_tokens": 3986192}
+{"current_steps": 390, "total_steps": 6770, "loss": 0.682, "lr": 9.998448325500118e-05, "epoch": 0.11521418020679468, "percentage": 5.76, "elapsed_time": "1:57:32", "remaining_time": "1 day, 8:02:48", "throughput": 572.54, "total_tokens": 4037760}
+{"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}