Training in progress, step 500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3838f6fa412378b6f36b3f773cede659c9f0fc77d473841346746580eb5780f5
+oid sha256:e2e0c6663f9caf4c82edd2f2f443e68581b38e6694c5546fceac68ca4ca82104
 size 25200088

trainer_log.jsonl

@@ -52,3 +52,9 @@
 {"current_steps": 440, "total_steps": 1500, "loss": 0.3611, "accuracy": 0.925000011920929, "learning_rate": 4.011497787155938e-06, "epoch": 0.3907637655417407, "percentage": 29.33, "elapsed_time": "0:59:33", "remaining_time": "2:23:28", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 450, "total_steps": 1500, "loss": 0.354, "accuracy": 0.8500000238418579, "learning_rate": 3.969463130731183e-06, "epoch": 0.3996447602131439, "percentage": 30.0, "elapsed_time": "1:00:48", "remaining_time": "2:21:53", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.36211252212524414, "epoch": 0.3996447602131439, "percentage": 30.0, "elapsed_time": "1:01:14", "remaining_time": "2:22:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 460, "total_steps": 1500, "loss": 0.3266, "accuracy": 0.887499988079071, "learning_rate": 3.92678391921108e-06, "epoch": 0.40852575488454707, "percentage": 30.67, "elapsed_time": "1:02:33", "remaining_time": "2:21:26", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 470, "total_steps": 1500, "loss": 0.3339, "accuracy": 0.925000011920929, "learning_rate": 3.88347887310836e-06, "epoch": 0.41740674955595025, "percentage": 31.33, "elapsed_time": "1:03:53", "remaining_time": "2:20:01", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 480, "total_steps": 1500, "loss": 0.3226, "accuracy": 0.875, "learning_rate": 3.839566987447492e-06, "epoch": 0.42628774422735344, "percentage": 32.0, "elapsed_time": "1:05:06", "remaining_time": "2:18:21", "throughput": "0.00", "total_tokens": 0}
+{"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}