Training in progress, step 200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3099a0a9a0911ee7ab48e2dbd2ea794d4749b6166b1908e46f7872bf7517e84
+oid sha256:79387fe1fa1a86683dcaeefe38022b992b6089822c0fad02214bc28a04683b06
 size 40036488

trainer_log.jsonl

@@ -16,3 +16,9 @@
 {"current_steps": 140, "total_steps": 1500, "loss": 7.1196, "accuracy": 0.625, "learning_rate": 4.893298743830168e-06, "epoch": 0.10147685059345837, "percentage": 9.33, "elapsed_time": "0:18:55", "remaining_time": "3:03:47", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 150, "total_steps": 1500, "loss": 7.1227, "accuracy": 0.6499999761581421, "learning_rate": 4.8776412907378845e-06, "epoch": 0.10872519706441967, "percentage": 10.0, "elapsed_time": "0:20:07", "remaining_time": "3:01:08", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.8760393261909485, "epoch": 0.10872519706441967, "percentage": 10.0, "elapsed_time": "0:20:37", "remaining_time": "3:05:41", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 160, "total_steps": 1500, "loss": 7.0272, "accuracy": 0.5375000238418579, "learning_rate": 4.860940925593703e-06, "epoch": 0.11597354353538099, "percentage": 10.67, "elapsed_time": "0:22:04", "remaining_time": "3:04:56", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 170, "total_steps": 1500, "loss": 7.1603, "accuracy": 0.637499988079071, "learning_rate": 4.84320497372973e-06, "epoch": 0.1232218900063423, "percentage": 11.33, "elapsed_time": "0:23:15", "remaining_time": "3:01:56", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 180, "total_steps": 1500, "loss": 6.995, "accuracy": 0.637499988079071, "learning_rate": 4.824441214720629e-06, "epoch": 0.1304702364773036, "percentage": 12.0, "elapsed_time": "0:24:31", "remaining_time": "2:59:49", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 190, "total_steps": 1500, "loss": 6.9941, "accuracy": 0.5874999761581421, "learning_rate": 4.804657878971252e-06, "epoch": 0.13771858294826492, "percentage": 12.67, "elapsed_time": "0:25:45", "remaining_time": "2:57:32", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 1500, "loss": 7.0413, "accuracy": 0.6499999761581421, "learning_rate": 4.783863644106502e-06, "epoch": 0.14496692941922623, "percentage": 13.33, "elapsed_time": "0:26:59", "remaining_time": "2:55:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8543878793716431, "epoch": 0.14496692941922623, "percentage": 13.33, "elapsed_time": "0:27:29", "remaining_time": "2:58:41", "throughput": "0.00", "total_tokens": 0}