Training in progress, step 200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd098aebd62b556e77dbc64b42f3545d5c01ffbb7dacd2553b52d1d5fb304d18
+oid sha256:ea10d7c8d2fc92ef8f60cbc05bba685900d855bd384b17a315c7d54295f2cee0
 size 25200088

trainer_log.jsonl

@@ -16,3 +16,9 @@
 {"current_steps": 140, "total_steps": 1500, "loss": 0.904, "accuracy": 0.5625, "learning_rate": 4.893298743830168e-06, "epoch": 0.11655739410968884, "percentage": 9.33, "elapsed_time": "0:19:06", "remaining_time": "3:05:33", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 150, "total_steps": 1500, "loss": 0.8779, "accuracy": 0.6499999761581421, "learning_rate": 4.8776412907378845e-06, "epoch": 0.12488292226038089, "percentage": 10.0, "elapsed_time": "0:20:20", "remaining_time": "3:03:02", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.8768696784973145, "epoch": 0.12488292226038089, "percentage": 10.0, "elapsed_time": "0:20:49", "remaining_time": "3:07:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 160, "total_steps": 1500, "loss": 0.8756, "accuracy": 0.4749999940395355, "learning_rate": 4.860940925593703e-06, "epoch": 0.13320845041107296, "percentage": 10.67, "elapsed_time": "0:22:13", "remaining_time": "3:06:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 170, "total_steps": 1500, "loss": 0.8489, "accuracy": 0.699999988079071, "learning_rate": 4.84320497372973e-06, "epoch": 0.141533978561765, "percentage": 11.33, "elapsed_time": "0:23:32", "remaining_time": "3:04:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 180, "total_steps": 1500, "loss": 0.8715, "accuracy": 0.625, "learning_rate": 4.824441214720629e-06, "epoch": 0.14985950671245707, "percentage": 12.0, "elapsed_time": "0:24:49", "remaining_time": "3:02:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 190, "total_steps": 1500, "loss": 0.8582, "accuracy": 0.6499999761581421, "learning_rate": 4.804657878971252e-06, "epoch": 0.15818503486314914, "percentage": 12.67, "elapsed_time": "0:26:08", "remaining_time": "3:00:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 1500, "loss": 0.8196, "accuracy": 0.75, "learning_rate": 4.783863644106502e-06, "epoch": 0.16651056301384118, "percentage": 13.33, "elapsed_time": "0:27:24", "remaining_time": "2:58:11", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8032433986663818, "epoch": 0.16651056301384118, "percentage": 13.33, "elapsed_time": "0:27:53", "remaining_time": "3:01:20", "throughput": "0.00", "total_tokens": 0}