Training in progress, step 200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f816513921eead20be38083633ae03c13535bc9218320e2ce541a573d481a335
+oid sha256:9b46650585d549db15a88ae31d90e6a5753076a356c350d134669e8e5cfea84e
 size 25200088

trainer_log.jsonl

@@ -16,3 +16,9 @@
 {"current_steps": 140, "total_steps": 1500, "loss": 0.8957, "accuracy": 0.612500011920929, "learning_rate": 4.893298743830168e-06, "epoch": 0.11301715438950555, "percentage": 9.33, "elapsed_time": "0:19:03", "remaining_time": "3:05:11", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 150, "total_steps": 1500, "loss": 0.892, "accuracy": 0.4375, "learning_rate": 4.8776412907378845e-06, "epoch": 0.12108980827447023, "percentage": 10.0, "elapsed_time": "0:20:21", "remaining_time": "3:03:17", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.8789658546447754, "epoch": 0.12108980827447023, "percentage": 10.0, "elapsed_time": "0:20:51", "remaining_time": "3:07:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 160, "total_steps": 1500, "loss": 0.8789, "accuracy": 0.574999988079071, "learning_rate": 4.860940925593703e-06, "epoch": 0.12916246215943492, "percentage": 10.67, "elapsed_time": "0:22:22", "remaining_time": "3:07:21", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 170, "total_steps": 1500, "loss": 0.8857, "accuracy": 0.675000011920929, "learning_rate": 4.84320497372973e-06, "epoch": 0.13723511604439959, "percentage": 11.33, "elapsed_time": "0:23:39", "remaining_time": "3:05:08", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 180, "total_steps": 1500, "loss": 0.8699, "accuracy": 0.6625000238418579, "learning_rate": 4.824441214720629e-06, "epoch": 0.14530776992936428, "percentage": 12.0, "elapsed_time": "0:24:54", "remaining_time": "3:02:38", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 190, "total_steps": 1500, "loss": 0.8565, "accuracy": 0.675000011920929, "learning_rate": 4.804657878971252e-06, "epoch": 0.15338042381432895, "percentage": 12.67, "elapsed_time": "0:26:10", "remaining_time": "3:00:29", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 1500, "loss": 0.8482, "accuracy": 0.5874999761581421, "learning_rate": 4.783863644106502e-06, "epoch": 0.16145307769929365, "percentage": 13.33, "elapsed_time": "0:27:26", "remaining_time": "2:58:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8243693113327026, "epoch": 0.16145307769929365, "percentage": 13.33, "elapsed_time": "0:27:55", "remaining_time": "3:01:32", "throughput": "0.00", "total_tokens": 0}