Training in progress, step 550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2e33ab4487c1a06c567516ea6e07b84e961c6141c94d9e716655afade3dc9bb
+oid sha256:a2e5abf38eb0fdc317c249ba7ccab44d888ceb90c33c41ddd7fc4c0eef213371
 size 25200088

trainer_log.jsonl

@@ -58,3 +58,9 @@
 {"current_steps": 490, "total_steps": 1500, "loss": 0.3086, "accuracy": 0.9375, "learning_rate": 3.795067523432826e-06, "epoch": 0.45021247272309634, "percentage": 32.67, "elapsed_time": "1:07:36", "remaining_time": "2:19:22", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "loss": 0.3128, "accuracy": 0.9125000238418579, "learning_rate": 3.7500000000000005e-06, "epoch": 0.4594004823705065, "percentage": 33.33, "elapsed_time": "1:08:51", "remaining_time": "2:17:42", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.32884541153907776, "epoch": 0.4594004823705065, "percentage": 33.33, "elapsed_time": "1:09:15", "remaining_time": "2:18:31", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 510, "total_steps": 1500, "loss": 0.335, "accuracy": 0.925000011920929, "learning_rate": 3.7043841852542884e-06, "epoch": 0.46858849201791664, "percentage": 34.0, "elapsed_time": "1:10:38", "remaining_time": "2:17:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 520, "total_steps": 1500, "loss": 0.3306, "accuracy": 0.887499988079071, "learning_rate": 3.658240087799655e-06, "epoch": 0.47777650166532676, "percentage": 34.67, "elapsed_time": "1:11:56", "remaining_time": "2:15:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 530, "total_steps": 1500, "loss": 0.3151, "accuracy": 0.9375, "learning_rate": 3.611587947962319e-06, "epoch": 0.4869645113127369, "percentage": 35.33, "elapsed_time": "1:13:14", "remaining_time": "2:14:03", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 540, "total_steps": 1500, "loss": 0.2995, "accuracy": 0.9375, "learning_rate": 3.564448228912682e-06, "epoch": 0.496152520960147, "percentage": 36.0, "elapsed_time": "1:14:34", "remaining_time": "2:12:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "loss": 0.3203, "accuracy": 0.887499988079071, "learning_rate": 3.516841607689501e-06, "epoch": 0.5053405306075571, "percentage": 36.67, "elapsed_time": "1:15:53", "remaining_time": "2:11:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "eval_loss": 0.304200142621994, "epoch": 0.5053405306075571, "percentage": 36.67, "elapsed_time": "1:16:17", "remaining_time": "2:11:47", "throughput": "0.00", "total_tokens": 0}