Training in progress, step 2400

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d159d3ba185322d9f83c53738ceab5e5c90742b79ccfaf680796d68d03ad7724
+oid sha256:e9d5ec3c39553916ddeed05ebc73c5ecc3358eb275ee803834c3cbefd37b2102
 size 29034840

trainer_log.jsonl

@@ -515,3 +515,11 @@
 {"current_steps": 2345, "total_steps": 3882, "loss": 0.2293, "lr": 3.708991435474151e-05, "epoch": 1.2075714653618337, "percentage": 60.41, "elapsed_time": "11:56:43", "remaining_time": "7:49:45", "throughput": 637.66, "total_tokens": 27421360}
 {"current_steps": 2350, "total_steps": 3882, "loss": 0.2757, "lr": 3.688423715303082e-05, "epoch": 1.210146793716199, "percentage": 60.54, "elapsed_time": "11:58:14", "remaining_time": "7:48:14", "throughput": 637.66, "total_tokens": 27479840}
 {"current_steps": 2350, "total_steps": 3882, "eval_loss": 0.26213815808296204, "epoch": 1.210146793716199, "percentage": 60.54, "elapsed_time": "11:58:34", "remaining_time": "7:48:26", "throughput": 637.37, "total_tokens": 27479840}
+{"current_steps": 2355, "total_steps": 3882, "loss": 0.242, "lr": 3.6678798011291674e-05, "epoch": 1.212722122070564, "percentage": 60.66, "elapsed_time": "12:00:11", "remaining_time": "7:46:58", "throughput": 637.29, "total_tokens": 27538344}
+{"current_steps": 2360, "total_steps": 3882, "loss": 0.2451, "lr": 3.647360065838348e-05, "epoch": 1.2152974504249292, "percentage": 60.79, "elapsed_time": "12:01:42", "remaining_time": "7:45:26", "throughput": 637.3, "total_tokens": 27596808}
+{"current_steps": 2365, "total_steps": 3882, "loss": 0.2237, "lr": 3.6268648818777105e-05, "epoch": 1.2178727787792945, "percentage": 60.92, "elapsed_time": "12:03:13", "remaining_time": "7:43:54", "throughput": 637.32, "total_tokens": 27655272}
+{"current_steps": 2370, "total_steps": 3882, "loss": 0.2033, "lr": 3.606394621248709e-05, "epoch": 1.2204481071336595, "percentage": 61.05, "elapsed_time": "12:04:45", "remaining_time": "7:42:22", "throughput": 637.31, "total_tokens": 27713784}
+{"current_steps": 2375, "total_steps": 3882, "loss": 0.2741, "lr": 3.585949655500429e-05, "epoch": 1.2230234354880247, "percentage": 61.18, "elapsed_time": "12:06:16", "remaining_time": "7:40:50", "throughput": 637.32, "total_tokens": 27772248}
+{"current_steps": 2380, "total_steps": 3882, "loss": 0.2677, "lr": 3.5655303557228335e-05, "epoch": 1.22559876384239, "percentage": 61.31, "elapsed_time": "12:07:47", "remaining_time": "7:39:18", "throughput": 637.33, "total_tokens": 27830704}
+{"current_steps": 2400, "total_steps": 3882, "loss": 0.2766, "lr": 3.484117221672465e-05, "epoch": 1.2359000772598505, "percentage": 61.82, "elapsed_time": "12:13:57", "remaining_time": "7:33:12", "throughput": 637.29, "total_tokens": 28064552}
+{"current_steps": 2400, "total_steps": 3882, "eval_loss": 0.2361450344324112, "epoch": 1.2359000772598505, "percentage": 61.82, "elapsed_time": "12:14:17", "remaining_time": "7:33:25", "throughput": 637.01, "total_tokens": 28064552}