Training in progress, step 900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2604e713adfd5ff8fff3e76524b74b5484d4e4df2c3ddf9459067c342c4d295
+oid sha256:dca569a5bee748c34c51ac0d5b0f16a410ab4a71a296a7c172247ce0d6801519
 size 29034840

trainer_log.jsonl

@@ -185,3 +185,14 @@
 {"current_steps": 845, "total_steps": 3882, "loss": 0.7273, "lr": 9.252536251332813e-05, "epoch": 0.4352304918877157, "percentage": 21.77, "elapsed_time": "4:20:36", "remaining_time": "15:36:40", "throughput": 632.05, "total_tokens": 9883408}
 {"current_steps": 850, "total_steps": 3882, "loss": 0.7455, "lr": 9.24129371512962e-05, "epoch": 0.43780582024208087, "percentage": 21.9, "elapsed_time": "4:22:04", "remaining_time": "15:34:49", "throughput": 632.26, "total_tokens": 9941896}
 {"current_steps": 850, "total_steps": 3882, "eval_loss": 0.7039459347724915, "epoch": 0.43780582024208087, "percentage": 21.9, "elapsed_time": "4:22:24", "remaining_time": "15:36:00", "throughput": 631.47, "total_tokens": 9941896}
+{"current_steps": 855, "total_steps": 3882, "loss": 0.6829, "lr": 9.22997419657528e-05, "epoch": 0.44038114859644606, "percentage": 22.02, "elapsed_time": "4:23:58", "remaining_time": "15:34:34", "throughput": 631.38, "total_tokens": 10000336}
+{"current_steps": 860, "total_steps": 3882, "loss": 0.6971, "lr": 9.218577901126713e-05, "epoch": 0.44295647695081125, "percentage": 22.15, "elapsed_time": "4:25:26", "remaining_time": "15:32:45", "throughput": 631.58, "total_tokens": 10058816}
+{"current_steps": 865, "total_steps": 3882, "loss": 0.7239, "lr": 9.207105035634397e-05, "epoch": 0.4455318053051764, "percentage": 22.28, "elapsed_time": "4:26:56", "remaining_time": "15:31:02", "throughput": 631.69, "total_tokens": 10117320}
+{"current_steps": 870, "total_steps": 3882, "loss": 0.7113, "lr": 9.195555808338603e-05, "epoch": 0.4481071336595416, "percentage": 22.41, "elapsed_time": "4:28:23", "remaining_time": "15:29:12", "throughput": 631.89, "total_tokens": 10175824}
+{"current_steps": 875, "total_steps": 3882, "loss": 0.685, "lr": 9.183930428865622e-05, "epoch": 0.45068246201390677, "percentage": 22.54, "elapsed_time": "4:29:53", "remaining_time": "15:27:28", "throughput": 632.02, "total_tokens": 10234288}
+{"current_steps": 880, "total_steps": 3882, "loss": 0.6804, "lr": 9.17222910822396e-05, "epoch": 0.45325779036827196, "percentage": 22.67, "elapsed_time": "4:31:20", "remaining_time": "15:25:40", "throughput": 632.2, "total_tokens": 10292736}
+{"current_steps": 885, "total_steps": 3882, "loss": 0.7056, "lr": 9.160452058800504e-05, "epoch": 0.45583311872263715, "percentage": 22.8, "elapsed_time": "4:32:50", "remaining_time": "15:23:57", "throughput": 632.31, "total_tokens": 10351224}
+{"current_steps": 890, "total_steps": 3882, "loss": 0.7234, "lr": 9.148599494356671e-05, "epoch": 0.4584084470770023, "percentage": 22.93, "elapsed_time": "4:34:17", "remaining_time": "15:22:08", "throughput": 632.51, "total_tokens": 10409736}
+{"current_steps": 895, "total_steps": 3882, "loss": 0.7505, "lr": 9.136671630024527e-05, "epoch": 0.4609837754313675, "percentage": 23.06, "elapsed_time": "4:35:46", "remaining_time": "15:20:22", "throughput": 632.66, "total_tokens": 10468240}
+{"current_steps": 900, "total_steps": 3882, "loss": 0.7378, "lr": 9.124668682302882e-05, "epoch": 0.4635591037857327, "percentage": 23.18, "elapsed_time": "4:37:14", "remaining_time": "15:18:35", "throughput": 632.82, "total_tokens": 10526712}
+{"current_steps": 900, "total_steps": 3882, "eval_loss": 0.7197856903076172, "epoch": 0.4635591037857327, "percentage": 23.18, "elapsed_time": "4:37:34", "remaining_time": "15:19:40", "throughput": 632.07, "total_tokens": 10526712}