Training in progress, step 850

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88b2d36774d479a3fdb2ba7b4a9a7be10ecc3ca555eb032c5dfd44d3ef0afecd
+oid sha256:dadb1f7303a3c18d0bdc0b554c8e4c7d4969fdc3fe3f3ca3eb04301ec88cf002
 size 25200088

trainer_log.jsonl

@@ -94,3 +94,9 @@
 {"current_steps": 790, "total_steps": 1500, "loss": 0.2333, "accuracy": 0.949999988079071, "learning_rate": 2.290805391669212e-06, "epoch": 0.6377396569122099, "percentage": 52.67, "elapsed_time": "1:50:40", "remaining_time": "1:39:27", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 800, "total_steps": 1500, "loss": 0.2555, "accuracy": 0.887499988079071, "learning_rate": 2.238678841830867e-06, "epoch": 0.6458123107971746, "percentage": 53.33, "elapsed_time": "1:52:02", "remaining_time": "1:38:02", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 800, "total_steps": 1500, "eval_loss": 0.22401823103427887, "epoch": 0.6458123107971746, "percentage": 53.33, "elapsed_time": "1:52:32", "remaining_time": "1:38:28", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 810, "total_steps": 1500, "loss": 0.2228, "accuracy": 0.925000011920929, "learning_rate": 2.186666916089239e-06, "epoch": 0.6538849646821393, "percentage": 54.0, "elapsed_time": "1:53:50", "remaining_time": "1:36:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 820, "total_steps": 1500, "loss": 0.2156, "accuracy": 0.925000011920929, "learning_rate": 2.134792428593971e-06, "epoch": 0.6619576185671039, "percentage": 54.67, "elapsed_time": "1:55:07", "remaining_time": "1:35:28", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 830, "total_steps": 1500, "loss": 0.2229, "accuracy": 0.8999999761581421, "learning_rate": 2.0830781332097446e-06, "epoch": 0.6700302724520686, "percentage": 55.33, "elapsed_time": "1:56:25", "remaining_time": "1:33:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 840, "total_steps": 1500, "loss": 0.2255, "accuracy": 0.925000011920929, "learning_rate": 2.031546713535688e-06, "epoch": 0.6781029263370333, "percentage": 56.0, "elapsed_time": "1:57:39", "remaining_time": "1:32:26", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 850, "total_steps": 1500, "loss": 0.2116, "accuracy": 0.925000011920929, "learning_rate": 1.9802207729556023e-06, "epoch": 0.686175580221998, "percentage": 56.67, "elapsed_time": "1:58:53", "remaining_time": "1:30:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 850, "total_steps": 1500, "eval_loss": 0.21706117689609528, "epoch": 0.686175580221998, "percentage": 56.67, "elapsed_time": "1:59:23", "remaining_time": "1:31:18", "throughput": "0.00", "total_tokens": 0}