Training in progress, step 2850

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f209712b49d72a0a61d59f7b8f5e51be948aa2ecb02420dc257c2b1ba5b38a8
+oid sha256:73c7f2377d2df91cf17de2733b3a5bbe82d66442455824ef9aa239771fcb5c26
 size 29034840

trainer_log.jsonl

@@ -596,3 +596,14 @@
 {"current_steps": 2795, "total_steps": 3882, "loss": 0.23, "lr": 1.9956337350170446e-05, "epoch": 1.4393510172547, "percentage": 72.0, "elapsed_time": "14:14:14", "remaining_time": "5:32:13", "throughput": 637.7, "total_tokens": 32684520}
 {"current_steps": 2800, "total_steps": 3882, "loss": 0.2162, "lr": 1.978633562151875e-05, "epoch": 1.4419263456090652, "percentage": 72.13, "elapsed_time": "14:15:42", "remaining_time": "5:30:40", "throughput": 637.74, "total_tokens": 32743032}
 {"current_steps": 2800, "total_steps": 3882, "eval_loss": 0.2771253287792206, "epoch": 1.4419263456090652, "percentage": 72.13, "elapsed_time": "14:16:01", "remaining_time": "5:30:47", "throughput": 637.5, "total_tokens": 32743032}
+{"current_steps": 2805, "total_steps": 3882, "loss": 0.2128, "lr": 1.9616882291322043e-05, "epoch": 1.4445016739634302, "percentage": 72.26, "elapsed_time": "14:17:35", "remaining_time": "5:29:16", "throughput": 637.48, "total_tokens": 32801504}
+{"current_steps": 2810, "total_steps": 3882, "loss": 0.226, "lr": 1.9447980435272982e-05, "epoch": 1.4470770023177955, "percentage": 72.39, "elapsed_time": "14:19:03", "remaining_time": "5:27:43", "throughput": 637.52, "total_tokens": 32860032}
+{"current_steps": 2815, "total_steps": 3882, "loss": 0.1945, "lr": 1.9279633119054524e-05, "epoch": 1.4496523306721607, "percentage": 72.51, "elapsed_time": "14:20:31", "remaining_time": "5:26:10", "throughput": 637.57, "total_tokens": 32918472}
+{"current_steps": 2820, "total_steps": 3882, "loss": 0.1593, "lr": 1.9111843398284412e-05, "epoch": 1.452227659026526, "percentage": 72.64, "elapsed_time": "14:22:00", "remaining_time": "5:24:37", "throughput": 637.6, "total_tokens": 32976944}
+{"current_steps": 2825, "total_steps": 3882, "loss": 0.2154, "lr": 1.8944614318459604e-05, "epoch": 1.4548029873808912, "percentage": 72.77, "elapsed_time": "14:23:28", "remaining_time": "5:23:04", "throughput": 637.64, "total_tokens": 33035424}
+{"current_steps": 2830, "total_steps": 3882, "loss": 0.2266, "lr": 1.8777948914901066e-05, "epoch": 1.4573783157352562, "percentage": 72.9, "elapsed_time": "14:24:56", "remaining_time": "5:21:31", "throughput": 637.69, "total_tokens": 33093880}
+{"current_steps": 2835, "total_steps": 3882, "loss": 0.1948, "lr": 1.8611850212698678e-05, "epoch": 1.4599536440896215, "percentage": 73.03, "elapsed_time": "14:26:25", "remaining_time": "5:19:58", "throughput": 637.72, "total_tokens": 33152328}
+{"current_steps": 2840, "total_steps": 3882, "loss": 0.2159, "lr": 1.84463212266563e-05, "epoch": 1.4625289724439865, "percentage": 73.16, "elapsed_time": "14:27:53", "remaining_time": "5:18:25", "throughput": 637.76, "total_tokens": 33210816}
+{"current_steps": 2845, "total_steps": 3882, "loss": 0.2326, "lr": 1.8281364961237013e-05, "epoch": 1.4651043007983517, "percentage": 73.29, "elapsed_time": "14:29:22", "remaining_time": "5:16:53", "throughput": 637.81, "total_tokens": 33269320}
+{"current_steps": 2850, "total_steps": 3882, "loss": 0.1912, "lr": 1.8116984410508696e-05, "epoch": 1.467679629152717, "percentage": 73.42, "elapsed_time": "14:30:50", "remaining_time": "5:15:20", "throughput": 637.85, "total_tokens": 33327720}
+{"current_steps": 2850, "total_steps": 3882, "eval_loss": 0.2647402584552765, "epoch": 1.467679629152717, "percentage": 73.42, "elapsed_time": "14:31:10", "remaining_time": "5:15:27", "throughput": 637.61, "total_tokens": 33327720}