Training in progress, step 550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26b71f0067960532c2814f1e4642d5cb656eaf3eec65f685946328cacd674237
+oid sha256:db8ac4c6cf4d1fc5ec15ae4264c8ffff32276db9138e7e7cdfcdc691a90802d7
 size 25200088

trainer_log.jsonl

@@ -58,3 +58,9 @@
 {"current_steps": 490, "total_steps": 1500, "loss": 0.3555, "accuracy": 0.875, "learning_rate": 3.795067523432826e-06, "epoch": 0.4211431027073485, "percentage": 32.67, "elapsed_time": "1:04:26", "remaining_time": "2:12:50", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "loss": 0.3211, "accuracy": 0.824999988079071, "learning_rate": 3.7500000000000005e-06, "epoch": 0.42973785990545765, "percentage": 33.33, "elapsed_time": "1:05:37", "remaining_time": "2:11:15", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.37026864290237427, "epoch": 0.42973785990545765, "percentage": 33.33, "elapsed_time": "1:06:03", "remaining_time": "2:12:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 510, "total_steps": 1500, "loss": 0.3375, "accuracy": 0.887499988079071, "learning_rate": 3.7043841852542884e-06, "epoch": 0.4383326171035668, "percentage": 34.0, "elapsed_time": "1:07:25", "remaining_time": "2:10:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 520, "total_steps": 1500, "loss": 0.3388, "accuracy": 0.887499988079071, "learning_rate": 3.658240087799655e-06, "epoch": 0.44692737430167595, "percentage": 34.67, "elapsed_time": "1:08:37", "remaining_time": "2:09:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 530, "total_steps": 1500, "loss": 0.3281, "accuracy": 0.8500000238418579, "learning_rate": 3.611587947962319e-06, "epoch": 0.45552213149978515, "percentage": 35.33, "elapsed_time": "1:09:52", "remaining_time": "2:07:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 540, "total_steps": 1500, "loss": 0.3565, "accuracy": 0.9125000238418579, "learning_rate": 3.564448228912682e-06, "epoch": 0.4641168886978943, "percentage": 36.0, "elapsed_time": "1:11:05", "remaining_time": "2:06:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "loss": 0.3103, "accuracy": 0.887499988079071, "learning_rate": 3.516841607689501e-06, "epoch": 0.47271164589600345, "percentage": 36.67, "elapsed_time": "1:12:23", "remaining_time": "2:05:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "eval_loss": 0.32732319831848145, "epoch": 0.47271164589600345, "percentage": 36.67, "elapsed_time": "1:12:49", "remaining_time": "2:05:47", "throughput": "0.00", "total_tokens": 0}