Training in progress, step 600

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6281a33eda942518b50d9b920995d95366ff1b3af5aeaa5d4b68d339b7e7d21e
+oid sha256:d84455e90725f2f5b11961fcf62a8367ca670ec7a9bea66d6182404e884328a8
 size 40036488

trainer_log.jsonl

@@ -64,3 +64,9 @@
 {"current_steps": 540, "total_steps": 1500, "loss": 1.9159, "accuracy": 0.887499988079071, "learning_rate": 3.564448228912682e-06, "epoch": 0.4431678292983176, "percentage": 36.0, "elapsed_time": "1:10:38", "remaining_time": "2:05:34", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 550, "total_steps": 1500, "loss": 1.7838, "accuracy": 0.9624999761581421, "learning_rate": 3.516841607689501e-06, "epoch": 0.45137464095199015, "percentage": 36.67, "elapsed_time": "1:11:48", "remaining_time": "2:04:01", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.2348441481590271, "epoch": 0.45137464095199015, "percentage": 36.67, "elapsed_time": "1:12:14", "remaining_time": "2:04:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 560, "total_steps": 1500, "loss": 1.834, "accuracy": 0.925000011920929, "learning_rate": 3.4687889661302577e-06, "epoch": 0.4595814526056627, "percentage": 37.33, "elapsed_time": "1:13:40", "remaining_time": "2:03:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 570, "total_steps": 1500, "loss": 1.4036, "accuracy": 0.987500011920929, "learning_rate": 3.4203113817116955e-06, "epoch": 0.46778826425933523, "percentage": 38.0, "elapsed_time": "1:14:51", "remaining_time": "2:02:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 580, "total_steps": 1500, "loss": 1.7889, "accuracy": 0.987500011920929, "learning_rate": 3.3714301183045382e-06, "epoch": 0.47599507591300777, "percentage": 38.67, "elapsed_time": "1:16:02", "remaining_time": "2:00:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 590, "total_steps": 1500, "loss": 1.4502, "accuracy": 0.987500011920929, "learning_rate": 3.3221666168464584e-06, "epoch": 0.48420188756668037, "percentage": 39.33, "elapsed_time": "1:17:14", "remaining_time": "1:59:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 600, "total_steps": 1500, "loss": 1.338, "accuracy": 0.9750000238418579, "learning_rate": 3.272542485937369e-06, "epoch": 0.4924086992203529, "percentage": 40.0, "elapsed_time": "1:18:23", "remaining_time": "1:57:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 600, "total_steps": 1500, "eval_loss": 0.21987247467041016, "epoch": 0.4924086992203529, "percentage": 40.0, "elapsed_time": "1:18:50", "remaining_time": "1:58:15", "throughput": "0.00", "total_tokens": 0}