Training in progress, step 1100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da53d237a43e76b6b6ecf9bc93363994b337aa5f251d99299031ee1f2c39842a
+oid sha256:be6a452ea262292ea28f67eb353d402a3d23cb22335c8edcc56c90298ec6e395
 size 25200088

trainer_log.jsonl

@@ -124,3 +124,9 @@
 {"current_steps": 1040, "total_steps": 1500, "loss": 0.2158, "accuracy": 0.9375, "learning_rate": 1.073216080788921e-06, "epoch": 0.9555530033306535, "percentage": 69.33, "elapsed_time": "2:23:57", "remaining_time": "1:03:40", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1050, "total_steps": 1500, "loss": 0.1967, "accuracy": 0.9125000238418579, "learning_rate": 1.0305368692688175e-06, "epoch": 0.9647410129780636, "percentage": 70.0, "elapsed_time": "2:25:13", "remaining_time": "1:02:14", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1050, "total_steps": 1500, "eval_loss": 0.20923514664173126, "epoch": 0.9647410129780636, "percentage": 70.0, "elapsed_time": "2:25:37", "remaining_time": "1:02:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1060, "total_steps": 1500, "loss": 0.2182, "accuracy": 0.949999988079071, "learning_rate": 9.88502212844063e-07, "epoch": 0.9739290226254738, "percentage": 70.67, "elapsed_time": "2:27:03", "remaining_time": "1:01:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1070, "total_steps": 1500, "loss": 0.2056, "accuracy": 0.925000011920929, "learning_rate": 9.471305493042243e-07, "epoch": 0.9831170322728839, "percentage": 71.33, "elapsed_time": "2:28:22", "remaining_time": "0:59:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1080, "total_steps": 1500, "loss": 0.1974, "accuracy": 0.949999988079071, "learning_rate": 9.064400256282757e-07, "epoch": 0.992305041920294, "percentage": 72.0, "elapsed_time": "2:29:35", "remaining_time": "0:58:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1090, "total_steps": 1500, "loss": 0.1982, "accuracy": 0.9333333373069763, "learning_rate": 8.664484900247363e-07, "epoch": 1.000918800964741, "percentage": 72.67, "elapsed_time": "2:30:53", "remaining_time": "0:56:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1100, "total_steps": 1500, "loss": 0.2476, "accuracy": 0.925000011920929, "learning_rate": 8.271734841028553e-07, "epoch": 1.0101068106121511, "percentage": 73.33, "elapsed_time": "2:32:09", "remaining_time": "0:55:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1100, "total_steps": 1500, "eval_loss": 0.2056656777858734, "epoch": 1.0101068106121511, "percentage": 73.33, "elapsed_time": "2:32:33", "remaining_time": "0:55:28", "throughput": "0.00", "total_tokens": 0}