Training in progress, step 700

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:426151b36cec917b14a15214973ed502f8ea33ed6fcfede1e67ed989a36bb672
+oid sha256:8020df4428a4bb0226fcdb433566eee61a8744cb0a01975a9edb530f8d10891f
 size 25200088

trainer_log.jsonl

@@ -76,3 +76,9 @@
 {"current_steps": 640, "total_steps": 1500, "loss": 0.2505, "accuracy": 0.8999999761581421, "learning_rate": 3.0708771752766397e-06, "epoch": 0.5166498486377397, "percentage": 42.67, "elapsed_time": "1:29:43", "remaining_time": "2:00:33", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 650, "total_steps": 1500, "loss": 0.2889, "accuracy": 0.9125000238418579, "learning_rate": 3.019779227044398e-06, "epoch": 0.5247225025227044, "percentage": 43.33, "elapsed_time": "1:30:57", "remaining_time": "1:58:56", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 650, "total_steps": 1500, "eval_loss": 0.2533933222293854, "epoch": 0.5247225025227044, "percentage": 43.33, "elapsed_time": "1:31:27", "remaining_time": "1:59:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 660, "total_steps": 1500, "loss": 0.2228, "accuracy": 0.9624999761581421, "learning_rate": 2.9684532864643123e-06, "epoch": 0.5327951564076691, "percentage": 44.0, "elapsed_time": "1:32:53", "remaining_time": "1:58:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 670, "total_steps": 1500, "loss": 0.2443, "accuracy": 0.9624999761581421, "learning_rate": 2.9169218667902562e-06, "epoch": 0.5408678102926338, "percentage": 44.67, "elapsed_time": "1:34:10", "remaining_time": "1:56:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 680, "total_steps": 1500, "loss": 0.2413, "accuracy": 0.887499988079071, "learning_rate": 2.8652075714060296e-06, "epoch": 0.5489404641775983, "percentage": 45.33, "elapsed_time": "1:35:22", "remaining_time": "1:55:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 690, "total_steps": 1500, "loss": 0.2356, "accuracy": 0.949999988079071, "learning_rate": 2.813333083910761e-06, "epoch": 0.557013118062563, "percentage": 46.0, "elapsed_time": "1:36:42", "remaining_time": "1:53:31", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 700, "total_steps": 1500, "loss": 0.212, "accuracy": 0.949999988079071, "learning_rate": 2.761321158169134e-06, "epoch": 0.5650857719475277, "percentage": 46.67, "elapsed_time": "1:37:56", "remaining_time": "1:51:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 700, "total_steps": 1500, "eval_loss": 0.24302434921264648, "epoch": 0.5650857719475277, "percentage": 46.67, "elapsed_time": "1:38:26", "remaining_time": "1:52:29", "throughput": "0.00", "total_tokens": 0}