Training in progress, step 200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bd67c3fadd8938aedbcb981125cb64ddd2ee672724df68f939199ca89ccfbcb
+oid sha256:b429eff2d94a39ff0cd74e96b721b051c369979584f0853ccb5c79966083fe52
 size 25200088

trainer_log.jsonl

@@ -16,3 +16,9 @@
 {"current_steps": 140, "total_steps": 1500, "loss": 0.8915, "accuracy": 0.6499999761581421, "learning_rate": 4.893298743830168e-06, "epoch": 0.11301715438950555, "percentage": 9.33, "elapsed_time": "0:19:05", "remaining_time": "3:05:26", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 150, "total_steps": 1500, "loss": 0.8954, "accuracy": 0.4375, "learning_rate": 4.8776412907378845e-06, "epoch": 0.12108980827447023, "percentage": 10.0, "elapsed_time": "0:20:24", "remaining_time": "3:03:39", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.8780961036682129, "epoch": 0.12108980827447023, "percentage": 10.0, "elapsed_time": "0:20:54", "remaining_time": "3:08:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 160, "total_steps": 1500, "loss": 0.8814, "accuracy": 0.5874999761581421, "learning_rate": 4.860940925593703e-06, "epoch": 0.12916246215943492, "percentage": 10.67, "elapsed_time": "0:22:19", "remaining_time": "3:06:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 170, "total_steps": 1500, "loss": 0.8739, "accuracy": 0.7124999761581421, "learning_rate": 4.84320497372973e-06, "epoch": 0.13723511604439959, "percentage": 11.33, "elapsed_time": "0:23:33", "remaining_time": "3:04:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 180, "total_steps": 1500, "loss": 0.8732, "accuracy": 0.6499999761581421, "learning_rate": 4.824441214720629e-06, "epoch": 0.14530776992936428, "percentage": 12.0, "elapsed_time": "0:24:49", "remaining_time": "3:02:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 190, "total_steps": 1500, "loss": 0.8425, "accuracy": 0.6875, "learning_rate": 4.804657878971252e-06, "epoch": 0.15338042381432895, "percentage": 12.67, "elapsed_time": "0:26:08", "remaining_time": "3:00:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 1500, "loss": 0.8327, "accuracy": 0.612500011920929, "learning_rate": 4.783863644106502e-06, "epoch": 0.16145307769929365, "percentage": 13.33, "elapsed_time": "0:27:31", "remaining_time": "2:58:56", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8103437423706055, "epoch": 0.16145307769929365, "percentage": 13.33, "elapsed_time": "0:28:01", "remaining_time": "3:02:10", "throughput": "0.00", "total_tokens": 0}