Training in progress, step 550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8ecc5a648518cc4ff97dfa90a4631d1a0f8688970bf31a18bc590cd6c3f344e
+oid sha256:2a8ee895f0237d28e6f095234083ae6bd256106964cfd522d74fb91565c79332
 size 25200088

trainer_log.jsonl

@@ -58,3 +58,9 @@
 {"current_steps": 490, "total_steps": 1500, "loss": 0.3097, "accuracy": 0.887499988079071, "learning_rate": 3.795067523432826e-06, "epoch": 0.4211431027073485, "percentage": 32.67, "elapsed_time": "1:05:43", "remaining_time": "2:15:29", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "loss": 0.3031, "accuracy": 0.875, "learning_rate": 3.7500000000000005e-06, "epoch": 0.42973785990545765, "percentage": 33.33, "elapsed_time": "1:06:56", "remaining_time": "2:13:52", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.33660775423049927, "epoch": 0.42973785990545765, "percentage": 33.33, "elapsed_time": "1:07:21", "remaining_time": "2:14:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 510, "total_steps": 1500, "loss": 0.318, "accuracy": 0.9125000238418579, "learning_rate": 3.7043841852542884e-06, "epoch": 0.4383326171035668, "percentage": 34.0, "elapsed_time": "1:08:44", "remaining_time": "2:13:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 520, "total_steps": 1500, "loss": 0.3053, "accuracy": 0.8999999761581421, "learning_rate": 3.658240087799655e-06, "epoch": 0.44692737430167595, "percentage": 34.67, "elapsed_time": "1:10:01", "remaining_time": "2:11:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 530, "total_steps": 1500, "loss": 0.3255, "accuracy": 0.887499988079071, "learning_rate": 3.611587947962319e-06, "epoch": 0.45552213149978515, "percentage": 35.33, "elapsed_time": "1:11:18", "remaining_time": "2:10:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 540, "total_steps": 1500, "loss": 0.3361, "accuracy": 0.8999999761581421, "learning_rate": 3.564448228912682e-06, "epoch": 0.4641168886978943, "percentage": 36.0, "elapsed_time": "1:12:32", "remaining_time": "2:08:57", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "loss": 0.2928, "accuracy": 0.862500011920929, "learning_rate": 3.516841607689501e-06, "epoch": 0.47271164589600345, "percentage": 36.67, "elapsed_time": "1:13:47", "remaining_time": "2:07:26", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "eval_loss": 0.3121817409992218, "epoch": 0.47271164589600345, "percentage": 36.67, "elapsed_time": "1:14:12", "remaining_time": "2:08:10", "throughput": "0.00", "total_tokens": 0}