Training in progress, step 550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2e0c6663f9caf4c82edd2f2f443e68581b38e6694c5546fceac68ca4ca82104
+oid sha256:add143543c39f322e4d3f1cbbfc33056da1d86262daa3a59f99362191c70de30
 size 25200088

trainer_log.jsonl

@@ -58,3 +58,9 @@
 {"current_steps": 490, "total_steps": 1500, "loss": 0.322, "accuracy": 0.9375, "learning_rate": 3.795067523432826e-06, "epoch": 0.4351687388987567, "percentage": 32.67, "elapsed_time": "1:06:22", "remaining_time": "2:16:49", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "loss": 0.3075, "accuracy": 0.875, "learning_rate": 3.7500000000000005e-06, "epoch": 0.44404973357015987, "percentage": 33.33, "elapsed_time": "1:07:41", "remaining_time": "2:15:22", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.3319137990474701, "epoch": 0.44404973357015987, "percentage": 33.33, "elapsed_time": "1:08:06", "remaining_time": "2:16:12", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 510, "total_steps": 1500, "loss": 0.3116, "accuracy": 0.862500011920929, "learning_rate": 3.7043841852542884e-06, "epoch": 0.45293072824156305, "percentage": 34.0, "elapsed_time": "1:09:28", "remaining_time": "2:14:51", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 520, "total_steps": 1500, "loss": 0.3015, "accuracy": 0.8999999761581421, "learning_rate": 3.658240087799655e-06, "epoch": 0.46181172291296624, "percentage": 34.67, "elapsed_time": "1:10:42", "remaining_time": "2:13:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 530, "total_steps": 1500, "loss": 0.3006, "accuracy": 0.925000011920929, "learning_rate": 3.611587947962319e-06, "epoch": 0.4706927175843694, "percentage": 35.33, "elapsed_time": "1:11:58", "remaining_time": "2:11:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 540, "total_steps": 1500, "loss": 0.2684, "accuracy": 0.9125000238418579, "learning_rate": 3.564448228912682e-06, "epoch": 0.47957371225577267, "percentage": 36.0, "elapsed_time": "1:13:11", "remaining_time": "2:10:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "loss": 0.3159, "accuracy": 0.9375, "learning_rate": 3.516841607689501e-06, "epoch": 0.48845470692717585, "percentage": 36.67, "elapsed_time": "1:14:27", "remaining_time": "2:08:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "eval_loss": 0.30747923254966736, "epoch": 0.48845470692717585, "percentage": 36.67, "elapsed_time": "1:14:52", "remaining_time": "2:09:19", "throughput": "0.00", "total_tokens": 0}