Training in progress, step 1500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e596c26d2df35b77cc480d957016d295b5f3cce78d8ca6896a2874423ecc836
+oid sha256:d1639ec927af20e1a663f0cdfd7ec32c776e84d2a82c242a6f7be38270dfcd30
 size 40036488

trainer_log.jsonl

@@ -172,3 +172,10 @@
 {"current_steps": 1440, "total_steps": 1500, "loss": 0.5759, "accuracy": 0.987500011920929, "learning_rate": 1.9713246713805588e-08, "epoch": 1.1813705375461634, "percentage": 96.0, "elapsed_time": "3:10:58", "remaining_time": "0:07:57", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1450, "total_steps": 1500, "loss": 0.7314, "accuracy": 0.987500011920929, "learning_rate": 1.3695261579316776e-08, "epoch": 1.1895773491998358, "percentage": 96.67, "elapsed_time": "3:12:08", "remaining_time": "0:06:37", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1450, "total_steps": 1500, "eval_loss": 0.07983284443616867, "epoch": 1.1895773491998358, "percentage": 96.67, "elapsed_time": "3:12:34", "remaining_time": "0:06:38", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1460, "total_steps": 1500, "loss": 0.5282, "accuracy": 0.949999988079071, "learning_rate": 8.767851876239075e-09, "epoch": 1.1977841608535085, "percentage": 97.33, "elapsed_time": "3:14:00", "remaining_time": "0:05:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1470, "total_steps": 1500, "loss": 0.5102, "accuracy": 0.9624999761581421, "learning_rate": 4.933178929321103e-09, "epoch": 1.205990972507181, "percentage": 98.0, "elapsed_time": "3:15:11", "remaining_time": "0:03:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1480, "total_steps": 1500, "loss": 0.4382, "accuracy": 0.987500011920929, "learning_rate": 2.192924752854042e-09, "epoch": 1.2141977841608536, "percentage": 98.67, "elapsed_time": "3:16:25", "remaining_time": "0:02:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1490, "total_steps": 1500, "loss": 0.4595, "accuracy": 0.9750000238418579, "learning_rate": 5.48291312886251e-10, "epoch": 1.222404595814526, "percentage": 99.33, "elapsed_time": "3:17:37", "remaining_time": "0:01:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1500, "total_steps": 1500, "loss": 0.4756, "accuracy": 0.9624999761581421, "learning_rate": 0.0, "epoch": 1.2306114074681986, "percentage": 100.0, "elapsed_time": "3:18:50", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1500, "total_steps": 1500, "eval_loss": 0.08085642755031586, "epoch": 1.2306114074681986, "percentage": 100.0, "elapsed_time": "3:19:16", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1500, "total_steps": 1500, "epoch": 1.2306114074681986, "percentage": 100.0, "elapsed_time": "3:19:28", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}